Plant diseases pose a serious threat to agriculture, causing yield losses of 20 to 40 percent each year, resulting in more than 220,000 million dollars in economic damage and significantly affecting the global food supply. Traditional plant health monitoring practices involve visual inspection of plant tissue and can only detect the presence of disease once visual symptoms are already evident. This article presents AgriIDIA, an early-detection plant disease recognition system trained on datasets of 24-channel multispectral images derived from six optical filters (BlueIR, Hotmirror, K590, K665, K720, and K850) and six vegetation indices (NDVI, GNDVI, NDRE, EVI, REI, and SAVI). First, an exploratory data analysis is conducted on the diagnostic capability of the described 24-channel data representation, using 1,266 image stacks labeled with six classes (diseased/healthy papaya, diseased/healthy potato, diseased/healthy tomato). Next, using the results of the exploratory data analysis, the manuscript describes the training and cross-validation performance of AgriIDIA, with a macro-F1 score of 83.91 ± 3.42% and an accuracy of 84.00 ± 3.17% on the validation set. Finally, the performance of the trained model is evaluated on the reserved test set (N=190), demonstrating an accuracy of 81.05%, a macro-F1 score of 0.7398, and a weighted ROC-AUC of 0.9383. The results of this study suggest that the 24-channel multispectral representation has significant diagnostic potential for the early detection of plant diseases and can be used to design accessible phytosanitary methods for small-scale farmers.
Why it matches plant phenotyping methods多チャネルマルチスペクトル画像から植物病害状態を推定する認識システムの開発・検証が研究の中心であり、植物表現型として病害状態を直接評価している。
abstractThis article presents AgriIDIA, an early-detection plant disease recognition system trained on datasets of 24-channel multispectral images
Accurate plant disease detection remains challenging when using single-modality data, which fails to capture comprehensive disease-related features. However, many existing studies rely on pixel-level classification or prior plant segmentation and lack explicit modeling of cross-modal interactions, limiting their ability to distinguish between healthy and diseased plants. This study presents a spatial–spectral fusion deep learning framework (S2-PDD) that fuses uncrewed aerial vehicles (UAV)-based RGB imagery and hyperspectral-derived feature representations for plant-level detection of potato diseases (blackleg and Potato virus Y (PVY)), employing early fusion (modalities combined at the input stage) and middle fusion (features integrated at intermediate stages within the model backbone) strategies. The multimodal fusion models were compared against single-modal models and an existing S2ADet model. Model performance, assessed through five-fold cross-validation, demonstrated that multimodal models integrating RGB and vegetation index features achieved the highest mAPs of 86.65 ± 1.71 (%; E-RV model) and 85.74 ± 1.96 (M-RV), respectively. These mAPs were higher than those of all single-modal models, including the RGB-only (83.21 ± 1.46) and hyperspectral-only models (PCA features: 79.71 ± 1.45; vegetation index features: 85.31 ± 2.36). They also exceeded mAPs of multimodal models combining RGB with PCA features (early fusion: 83.00 ± 2.81; middle fusion: 83.11 ± 2.46; S2ADet: 84.04 ± 2.73), regardless of the fusion strategy. The superior performance highlights that vegetation index features provide strong class separability compared to other hyperspectral representations. The proposed models achieved strong plant-level detection performance, with AP of 78.65 ± 4.14 (E-RV) and 77.40 ± 3.46 (M-RV) for blackleg disease, as well as 84.82 ± 3.59 (E-RV) and 83.28 ± 3.86 (M-RV) for PVY. These results demonstrate the potential of UAV-based multimodal sensing for disease monitoring in cropping systems. A potato plant disease detection dataset was constructed and made publicly available, containing paired RGB and hyperspectral image tiles with bounding box annotations. The code is available at https://github.com/Tim-Agro/S2-PDD.
Why it matches plant phenotyping methodsUAV RGB・ハイパースペクトル画像からジャガイモ個体の病害状態を推定する融合モデルを開発・比較検証し、公開データセットも構築しており、病害表現型の取得・抽出手法が中心である。
abstractThis study presents a spatial–spectral fusion deep learning framework (S2-PDD) that fuses uncrewed aerial vehicles (UAV)-based RGB imagery and hyperspectral-derived feature representations for plant-level detection of potato diseases (blackleg and Potato virus Y (PVY))
Problem: Agriculture plays a pivotal role in the Indian economy, where crop production quality and quantity directly impact the livelihoods of millions. Climate variability, emerging plant diseases, and improper pesticide application contribute significantly to agricultural losses. Early and accurate disease detection is crucial for mitigating crop damage and ensuring food security. Methodology: This study presents a novel deep learning framework based on EfficientNet architecture, enhanced with Progressive Fine-Tuning Strategy for automated plant disease detection. The proposed methodology was evaluated on two benchmark datasets: the Plant Village dataset comprising 20,639 images of tomato, potato, and bell pepper with 15 disease varieties; and a drone-captured rice plant dataset containing 4432 samples from public repositories. The model’s performance was assessed using multiple metrics, including classification accuracy, precision, recall, and F1-score. To strengthen the validation of high accuracy results, additional statistical analyses like class imbalance ratio, Entropy, Chi-Square test, convergence curve, ANOVA test, Tukey’s post hoc HSD test, confidence interval, Cohen’s Kappa result, fold-wise dispersion analysis, mean, std deviation are included in the manuscript. Result: Experimental results demonstrate that the fine-tuned EfficientNetV2-B1 architecture achieved exceptional performance with 99.7% classification accuracy on the PlantVillage dataset and 99.03% accuracy on the drone-based rice disease dataset, significantly outperforming existing state-of-the-art transfer learning models. Model explainability techniques further validated the reliability and interpretability of the predictions, confirming the model’s focus on disease-relevant features.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習手法を開発し、複数データセットで性能検証しており、植物フェノタイピング手法が中心である。
abstractThis study presents a novel deep learning framework based on EfficientNet architecture, enhanced with Progressive Fine-Tuning Strategy for automated plant disease detection.
Abstract In Bangladesh, the potato (Solanum tuberosum L.) stands as an indispensable food and cash crop, deeply intertwined with national food security, rural livelihoods, and the broader agricultural economy. However, foliar diseases such as early blight and late blight frequently precipitate substantial yield losses and quality degradation when not identified and mitigated during the nascent stages of infection. Contemporary diagnostic paradigms remain predominantly manual and visual, relying heavily on agricultural professionals, which is often inefficient and inaccessible for remote farmers. While deep learning has demonstrated remarkable efficacy in automated plant disease recognition, existing methodologies frequently lack interpretability, disease severity quantification, and real-world field applicability. This paper introduces a comprehensive, interpretable deep learning-based framework utilizing EfficientNetV2-B0 for classifying potato leaf images into healthy, early blight, and late blight categories. By integrating Gradient-Weighted Class Activation Mapping (Grad-CAM), the model achieves high transparency, highlighting critical prediction regions. Furthermore, a severity assessment module estimates infection percentages, providing actionable treatment recommendations, ultimately enhancing agricultural decision-making.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病害の種類と感染割合（重症度）を推定する深層学習手法が研究の中心であり、植物病害状態の表現型取得・定量化に該当する。
abstractThis paper introduces a comprehensive, interpretable deep learning-based framework utilizing EfficientNetV2-B0 for classifying potato leaf images into healthy, early blight, and late blight categories.
Pepper / chilliPotatoTomatoLeafClassificationVisualization / data managementDisease symptoms / severity
Early detection of plant leaf diseases is critical for minimizing crop losses and supporting precision agriculture. While Convolutional Neural Networks (CNNs) have demonstrated high accuracy in image-based diagnosis, conventional architectures may not optimally balance spatial localization and channel-wise feature refinement, particularly in multi-crop classification settings. This study proposes a redundancy-aware dual-attention architecture, termed ATSA-DenseNet, which integrates the spatial branch of the Convolutional Block Attention Module (CBAM-Spatial) with Efficient Channel Attention (ECA) within a DenseNet121 backbone. Unlike prior dual-attention frameworks that retain full CBAM and introduce channel-level redundancy, the proposed design isolates complementary spatial and channel mechanisms to improve representational efficiency without increasing computational complexity. The framework is evaluated on controlled multi-crop PlantVillage-derived datasets comprising tomato, potato, pepper, and maize. Across both 3-crop and 4-crop configuration, ATSA-DenseNet consistently outperforms baseline DenseNet121 and single-attention variants, achieving 99.94% accuracy and 0.9994 macro-F1 on the 4-crop setting while maintaining a lightweight footprint (6.96M parameters, 2.87G FLOPs). Grad-CAM visualizations indicate improved localization of disease-relevant regions compared to the baseline. While results are obtained under controlled imaging conditions, the findings demonstrate that redundancy-aware dual-attention enhances feature discrimination efficiency in multi-class agricultural classification tasks. Future work will extend validation to real-field datasets with natural variability.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定するCNN手法を提案・評価しており、病害表現型の取得・分類手法が研究の中心である。
abstractThis study proposes a redundancy-aware dual-attention architecture, termed ATSA-DenseNet, which integrates the spatial branch of the Convolutional Block Attention Module (CBAM-Spatial) with Efficient Channel Attention (ECA) within a DenseNet121 backbone.
Abstract Purpose : The system for diagnosing diseases in Solanaceae crops (SolanAPP), including tomatoes, potatoes, peppers, and eggplants, represents a promising tool for supporting decision-making in agricultural fields using AI. This system reconciles the computational intensity of multitasking models with the infrastructural limitations of rural environments, thereby increasing digital literacy. Its architecture is based on two fundamental pillars: (i) autonomous, offline operation for the detection and classification of diseases in Solanaceae crops; (ii) a georeferenced epidemiological surveillance network with agricultural recommendations for crop monitoring. Methods : The core diagnostic process combines crop-specific semantic segmentation and disease classification models exported to TensorFlow Lite, enabling on-device visual inference and pixel-level severity estimation. An optional online layer integrates Groq’s large language model (LLM)-based reasoning and Firebase services to generate structured agronomic explanations and facilitate the creation of georeferenced community reports when a connection is available. Preprocessing and management of the dataset were performed using the Roboflow platform. The mobile app was developed natively in Kotlin. Model performance was rigorously evaluated using accuracy, recall, F1 score, mean IoU, mPA, inference latency, model size, and decision matrix. The optimal model for the crop was selected using Simple Additive Weighting (SAW). Finally, the overall framework quality and usability were evaluated in Cuba through a user validation survey using a 5-point Likert scale and aligned with the ISO/IEC 25010 software quality model. Results : The model that yielded the best results for most crops was DeepLabV3+ with MobileNetV2, which achieved a classification accuracy of over 97\% while operating with lower inference latency. Beyond individual diagnoses, the system incorporates a collaborative georeferencing feature that allows users to share observations and precise geographic coordinates of detected pathologies to facilitate regional epidemiological monitoring. The user satisfaction survey yielded a satisfaction rating of 4.5/5, with users highlighting the importance of offline diagnosis. Conclusion : Plant disease diagnosis using computer vision can support earlier intervention in resource-constrained agricultural settings, but practical deployment requires models that are accurate, lightweight, interpretable, and usable under limited connectivity. SolanAPP, an offline-first Android framework for detecting foliar pathologies in Solanaceae crops, not only establishes a framework for disease identification in complex natural environments but also provides a theoretical and practical foundation for automated agronomic treatment recommendations and community-based crop surveillance. Impact SolanAPP is a free framework that supports the synergy between multitask deep learning for offline disease diagnosis and LLM-driven reasoning for decision-making in the field. Beyond the quantitative metrics obtained from the selected models, the deployment of SolanAPP in rural contexts serves a fundamental socio-technical purpose: it acts as a catalyst for open access, digital literacy, and agronomic decision-making under unfavorable development conditions. It also represents a strong effort to foster a collaborative epidemiological surveillance network in the agricultural sector. Although it faces challenges, such as the use of field images for model training, this framework marks a promising step in the deployment of edge AI, balancing technical accuracy with practical utility.
Why it matches plant phenotyping methods植物病害を画像からセグメンテーションし、病害のピクセル単位の重症度を推定する手法と、オフライン実装・性能評価を中心とした研究であり、植物状態の計測方法が中核です。
abstractThe core diagnostic process combines crop-specific semantic segmentation and disease classification models exported to TensorFlow Lite, enabling on-device visual inference and pixel-level severity estimation.
Plant disease and plant stress early warning systems have advanced through deep learning, remote sensing, digital phenotyping, disease forecasting, and sensor networks. Detection accuracy, precision, recall, F1-score, and area under the curve remain indispensable, but they are insufficient for judging whether a warning can support timely and proportionate phytoprotection under field variability. This Mini Review argues that intelligent plant health warning systems should be evaluated not only as prediction models, but also as safety-relevant decision-support systems embedded in biological, agronomic, and operational contexts. We first relate AI-based detection to established plant disease forecasting and decision-support traditions, including weather-based models, epidemiological forecasting, and integrated disease management. We then adapt selected safety-assurance concepts, including risk assessment, failure mode and effects analysis, Bow-tie reasoning, warning-threshold governance, reliability analysis, resilience thinking, and response closure, to host-pathogen-environment warning chains. The proposed framework links AI or sensor outputs with pathogen biology, host susceptibility, environmental conduciveness, inoculum pressure, uncertainty assessment, risk classification, threshold decisions, human or automated verification, intervention, and feedback learning. Illustrative crop-pathogen scenarios, including wheat rust, rice blast, potato late blight, grapevine downy mildew, and citrus greening, show how safety assurance can complement existing forecasting and decision-support systems rather than replace them. The framework remains conceptual, and whether these added assurance functions improve existing warning systems requires comparative evaluation under field conditions. Future systems should be evaluated through detection performance and response-oriented indicators such as lead time, calibration, false-alert burden, missed-warning rate, response completion, disease suppression, economic value, and learning after field action.
Why it matches plant phenotyping methods植物病害・ストレスの検出を含む知的警戒システムについて、AI・リモートセンシング・デジタルフェノタイピング・センサーネットワークの評価枠組みを体系的に論じる方法論レビューであり、方法論が中心です。
abstractPlant disease and plant stress early warning systems have advanced through deep learning, remote sensing, digital phenotyping, disease forecasting, and sensor networks.
Potato, one of the world's most important staple food crops, is highly susceptible to various foliar diseases that significantly affect its productivity and pose a serious threat to food security, thereby contributing to economic losses and impacting farmers’ income. Therefore, early and accurate detection is essential. Conventional detection methods rely primarily on manual observation, which is time-consuming and requires specialized personnel. In this study, five convolutional neural network (CNN) architectures were evaluated for the automatic classification of potato leaf diseases, including pretrained models (ResNet50, MobileNet, and VGG16) and models trained from scratch (AlexNet and LeNet-5). The dataset was constructed by integrating and selecting images from publicly available Kaggle repositories, resulting in a total of 6,691 images distributed across five classes: early blight, late blight, potato leafroll virus (PLRV), mosaic virus (PVY), and healthy leaves. Multiple experiments were conducted by varying hyperparameters such as batch size, optimizers, and the number of training epochs. The results show that VGG16 achieved the best performance, with an accuracy of 99.87%, outperforming the other architectures. Additionally, a mobile application based on the optimal model was developed for real-time detection. These findings demonstrate the potential of deep learning for intelligent and scalable agricultural diagnostic systems.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から自動分類するCNN手法を比較・評価し、最適モデルと実時間アプリを開発しており、植物表現型取得が中心である。
abstractfive convolutional neural network (CNN) architectures were evaluated for the automatic classification of potato leaf diseases
Photosynthesis is among the most consequential yet genetically complex traits in crop plants, and translating its natural variation into actionable genomic targets remains a central challenge for breeding climate-resilient varieties. To start addressing this, researchers are generating increasingly large, multi-environment field photosynthesis datasets. Yet, these data have been structurally under-analysed since their inception. Here we report the outcomes of the first dedicated hackathon focused on computational mining of such field data held in Accra, Ghana, in March 2026. Bringing together data scientists, plant physiologists, geneticists, and breeders from Europe and Africa, these interdisciplinary teams used photosynthetic data collected with hand-held fluorometers to genome-wide marker data across four crop species: cowpea (Vigna unguiculata), barley (Hordeum vulgare), common bean (Phaseolus vulgaris), and potato (Solanum tuberosum). Despite using different species and methods, independent teams identified the same three key findings. First, mechanism-informed feature engineering and dynamic modelling recover genetic signals that are not detected or discarded in standard analysis pipelines, resulting in traits with improved heritability and meaningful associations with yield. Secondly, machine learning methods proved effective at uncovering genetic associations, with temporally resolved features substantially outperforming single time-point measurements. Third, raw chlorophyll fluorescence and absorbance traces consistently contained more information and predictive power than the extracted parameters currently used. A defining feature of this event was having experimentalists and data scientists working together, enabling AI approaches to be grounded in domain knowledge and biological mechanisms rather than relying on data alone.
Why it matches plant phenotyping methods圃場光合成データから時間分解特徴量や遺伝的シグナルを抽出する計算手法を中心に扱っており、植物生理形質の実質的なフェノタイピング手法応用に該当する。
abstractmechanism-informed feature engineering and dynamic modelling recover genetic signals that are not detected or discarded in standard analysis pipelines, resulting in traits with improved heritability and meaningful associations with yield.
Background: Plant diseases significantly threaten global food security, reducing potential harvests and sometimes causing total crop failure. Traditional detection methods, which rely on manual inspection and laboratory testing, are time-consuming, costly and prone to human error. Methods: To address these challenges, this study applies transfer learning techniques using deep convolutional neural networks for accurate and efficient plant disease detection. A comparative analysis of nine pretrained models, VGG16, VGG19, ResNet50, ResNet101V2, MobileNetV2, InceptionV3, DenseNet121, InceptionResNetV2 and Xception was conducted on the PlantVillage dataset, focusing on apple, potato and peach leaf images. Result: Results show that DenseNet121 and ResNet101V2 achieved the highest accuracy, particularly for potato leaves with 98.5%, while MobileNetV2 also performed well with up to 99% accuracy for apple and peach leaves. The study demonstrates that transfer learning effectively enhances plant disease classification, enabling faster, more reliable and resource efficient detection for precision agriculture.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習手法を比較評価しており、病害表現型の取得・分類が研究の中心である。
abstractthis study applies transfer learning techniques using deep convolutional neural networks for accurate and efficient plant disease detection.
Plant diseases have continued to threaten agricultural productivity, while manual inspection methods have remained inefficient and prone to subjectivity. This study proposed and assessed a hybrid framework integrating a Convolutional Neural Network (CNN) with a Large Language Model (LLM) to perform image-based plant leaf disease classification accompanied by interpretable diagnostic explanations. EfficientNetV2-M was employed as the visual backbone and trained on 11 selected classes of apple, grape, and potato leaf images derived from the PlantVillage dataset. A structured data splitting strategy was applied to ensure reliable model validation and unbiased testing. The classification capability of the CNN component was examined through standard multi-class evaluation indicators, including class-wise predictive consistency and error distribution analysis. Experimental results indicated that the model delivered highly consistent predictions, reaching a peak test accuracy of 99.79%, reflecting its robustness in distinguishing visually similar disease patterns. To overcome the black-box limitation, prediction outputs were transformed into structured prompts and processed by GPT-4o to generate contextual explanations. The generated narratives systematically described observable symptoms, highlighted distinguishing characteristics, and suggested initial management actions. Overall, the proposed hybrid system demonstrated that combining high-performance visual recognition with language-based reasoning enhanced both diagnostic reliability and interpretability in digital agriculture applications.
Why it matches plant phenotyping methods植物葉の画像から病害状態を推定するCNN・LLM統合手法を開発・評価しており、病害分類と説明生成が研究の中心であるため。
abstractThis study proposed and assessed a hybrid framework integrating a Convolutional Neural Network (CNN) with a Large Language Model (LLM) to perform image-based plant leaf disease classification accompanied by interpretable diagnostic explanations.
Reproduction assets foundThe paper uses the public PlantVillage color dataset (11 apple/grape/potato classes, 9,385 images) and explicitly points to it in the DATA AVAILABILITY statement as the replication package data. The authors also provide a public Streamlit demonstration of their hybrid CNN–LLM system. No author analysis code or trained-Dataset · publicaper. The research was conducted for academic purposes, and no financial, commercial, or
personal relationships influenced the study design, data analysis, interpretation of results, or
preparation of the manuscript.
DATA AVAILABILITY
The data associated with this study are publicly available online in the replication package.
[https://github.com/spMohanty/PlantVillage-Dataset/tree/master/raw/color]
AUTHOR CONTRIBUTIONS
Frenky Riski Gilang Pratama: Conceptualization; Programming and coding
implementation; Methodology; Writing-Original Draft. Sugiarto Surono: Conceptualization;
Methodology; Supervision; Writing-Review & Editing. Aris Thobirin: Proofreading Paper;
Writing-Review & Editing; FunOpen asset ↗https://github.com/spMohanty/PlantVillage-Dataset/tree/master/raw/colorpdf-raw-page:10 lines:1-52Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · checked 14 Sept 2026
Quantifying the canopy growth dynamics and light interception capacity under different management practices laid the physiological foundation for potato yield formation. However, the traditional manual measurement methods are labour-intensive, time-consuming, and incapable of capturing time-series dynamics. To address this, we proposed a novel high-throughput strategy that integrates UAV-based RGB imaging with a piecewise physiological model. Furthermore, how Nitrogen(N)-Potassium(K) interaction affects the temporal canopy growth dynamics, light interception, and tuber yield was determined. The results indicated that: (1) Among the 11 secondary indices extracted from the canopy growth dynamic curves, the interaction of N and K had the greatest effect on the maximum canopy duration and the total canopy growth curve integral. The direct path coefficients of N and K inputs on these two parameters were 0.847 and 0.805, and 0.234 and 0.148, respectively. (2) There was a strong linear relationship between the integral area under the curve (S∫) and the total plant dry weight, with R² at 0.90 in 2023-2024. A simplified net photosynthetically active radiation utilisation assessment framework that achieved high accuracy with minimal parameter was built. (3) Prolonging the maximum canopy continuous coverage time is the main way to improve potato yield. The overall effect of N input on yield was significantly higher than that of K fertiliser, with a total effect value of 1.428. Optimising the N-K interaction improves nutrient precision and light interception. The integration of UAV remote sensing and the crop physiological-ecological model enables the tracking of potato canopy dynamics, which is helpful for optimising management practices to improve potato yield.
Why it matches plant phenotyping methodsUAV RGB画像と生理モデルを統合した高スループット手法を開発し、ジャガイモのキャノピー成長動態と光 interception を時系列で推定することが中心である。
abstractTo address this, we proposed a novel high-throughput strategy that integrates UAV-based RGB imaging with a piecewise physiological model.
Accurate and timely crop yield prediction and forecasting are important for improving agricultural productivity and supporting informed management decisions. In this study, we developed and evaluated a framework for estimating in-season potato yield at the field scale using Sentinel-2 satellite time series. A Grouped TreeSHAP Stability Selection (GTSS) was first applied to identify a compact, phenology-aware subset of spectral bands and vegetation indices, thereby reducing redundancy and mitigating overfitting in small-data settings. Two deep learning architectures tailored for limited training data were then introduced: LiteTemporalConv, a lightweight temporal convolutional network, and MS-ConvBiGRU-Attn, a hybrid encoder combining multi-scale convolutions, bidirectional GRUs, and an attention mechanism. Both models were benchmarked against widely used machine learning methods, including Random Forest, Support Vector Machine, Extreme Gradient Boost, Partial Least Squares, as well as standard deep learning baselines (CNN and GRU). Results showed that the proposed models outperformed both machine learning and conventional deep learning baselines, with LiteTemporalConv achieving the highest accuracy under 10-fold cross-validation (R² = 0.84; RMSE = 3.18 t ha⁻¹; rRMSE = 6.36%) and MS-ConvBiGRU-Attn yielding similarly strong performance (R² = 0.82; RMSE = 3.53 t ha⁻¹; rRMSE = 7.03%). By comparison, the best baseline, XGB, achieved an R² of 0.79 with an rRMSE of 9.8%. The two best-performing models were further evaluated on an independent spatial dataset to assess their generalization beyond the training region. In an additional experiment, both deep learning models trained on mid-season observations showed predictive stability for late-season yield estimation. Overall, the results highlight the importance of targeted feature selection and lightweight encoders for yield modeling in data-scarce conditions.
Why it matches plant phenotyping methodsSentinel-2時系列からジャガイモ収量を推定する特徴選択・深層学習手法を開発し、複数モデルとのベンチマークと独立データでの検証を行っており、植物形質取得が中心である。
abstractwe developed and evaluated a framework for estimating in-season potato yield at the field scale using Sentinel-2 satellite time series
Plant disease detection is critical for sustainable agriculture and food security. While deep learning models achieve high accuracy in leaf disease classification, their black box nature poses limitations for trust and adoption among agricultural practitioners. This study presents a comparative evaluation of three convolutional neural network architectures (ConvNeXt-Tiny, MobileNetV2, and VGG16) for classifying potato, maize, and pepper leaf diseases, with emphasis on explainability through Gradient-weighted Class Activation Mapping (Grad-CAM). The experimental results demonstrate that ConvNeXt-Tiny achieves 99-100% accuracy across all plant species, MobileNetV2 attains 97-100% accuracy with lower computational requirements, and VGG16 yields 97-99.5% accuracy. Grad-CAM visualizations reveal that modern architectures precisely focus on lesion regions, whereas older models occasionally attend to irrelevant features such as leaf veins and edges. Misclassification analysis identifies shadows and natural leaf patterns as primary error sources. This research demonstrates that explainable artificial intelligence is not merely complementary but essential for developing trustworthy agricultural decision support systems.
Why it matches plant phenotyping methods植物葉の病変領域を画像から分類・可視化する手法を比較評価しており、病害状態の表現型抽出が研究の中心です。
abstractThis study presents a comparative evaluation of three convolutional neural network architectures (ConvNeXt-Tiny, MobileNetV2, and VGG16) for classifying potato, maize, and pepper leaf diseases, with emphasis on explainability through Gradient-weighted Class Activation Mapping (Grad-CAM).
Abstract Uneven occurrence of potato leaf diseases necessitates site-specific treatment rather than conventional uniform spraying. This study presents a vision-guided autonomous variable-rate spraying system integrating real-time deep learning-based disease detection, temporal disease severity estimation, and PWM-controlled precision spray actuation for targeted crop protection. A composite dataset comprising 1,561 field images containing 14,166 annotated leaf instances was developed under dense canopy conditions. Comparative evaluation of object detection architectures showed that YOLOv26 achieved the highest detection performance with a peak mAP@0.5 of 0.961, outperforming YOLOv8 (0.924) by 3.7% and YOLOv12 (0.938) by 2.3%. The lightweight YOLOv26n variant was selected for embedded deployment. When deployed on a Raspberry Pi 5, the optimized ONNX model achieved an inference speed of approximately 10 FPS, corresponding to a spatial sampling interval of 0.018 m at an operating speed of 0.18 m/s. A 2 s temporal sliding window generated a stable canopy-level disease severity index, which was mapped to PWM duty cycles for variable-rate pesticide application. Field experiments involving 598 spatial spray decision instances validated the proposed perception-driven spray control framework. Compared with conventional constant-rate spraying, the system reduced agrochemical consumption by 32.75% (from 458 to 308 L/ha). These results demonstrate the feasibility of integrating embedded deep learning and adaptive spray control into a field-deployable autonomous spraying platform for precision potato disease management.
Why it matches plant phenotyping methodsジャガイモ葉の病徴検出とキャノピー病害重症度推定を中核とする視覚センシング・深層学習・噴霧制御プラットフォームの開発および実地検証であり、植物状態の定量的推定方法が中心である。
abstractThis study presents a vision-guided autonomous variable-rate spraying system integrating real-time deep learning-based disease detection, temporal disease severity estimation, and PWM-controlled precision spray actuation for targeted crop protection.
Potato leaf disease is one of the main problems in potato cultivation because it can reduce plant quality, decrease crop yield, and cause economic losses for farmers. Manual disease detection still has limitations because it depends on farmers’ experience and is prone to errors, especially when disease symptoms have similar visual characteristics. This study aims to apply the Convolutional Neural Network (CNN) algorithm to predict potato leaf diseases based on digital images. The dataset used in this study was obtained from Kaggle and consisted of 1,500 potato leaf images divided into three classes: healthy leaves, early blight, and late blight. The research stages included dataset collection, data splitting into training, testing, and validation data, CNN modeling using Jupyter Notebook, model training with 50 epochs, model evaluation using a Confusion Matrix, and model implementation into a web-based system using Flask. The test results show that the CNN model was able to classify potato leaf diseases with an accuracy of 97%. These results indicate that CNN is effective in recognizing visual patterns in potato leaf images, such as color changes, spots, and leaf damage. This study is expected to serve as a basis for developing an early detection system for potato leaf diseases that is faster, more accurate, and easier for farmers to use.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病害状態を推定するCNN手法が研究の中心であり、モデル評価と実装も行っているため、植物フェノタイピング手法として含める。
abstractThis study aims to apply the Convolutional Neural Network (CNN) algorithm to predict potato leaf diseases based on digital images.
- Enhancing agricultural productivity and attaining sustainable crop management depend on the early and precise identification of leaf disease. Using state-of-the-art technologies in precision agriculture like machine learning (ML) and image processing greatly increases the effectiveness of disease detection and facilitates well-informed decision-making. But conventional manual inspection techniques are still tedious, unpredictable, and prone to errors. In order to overcome these constraints, this research offers YOLOv12-CropNet, an innovative deep learning-based system for multi-crop leaf disease diagnosis in real time. The proposed YOLOv12-CropNet approach makes use of the Convolutional Block Attention Module (CBAM) for adaptive attention, the Content-Aware Reassembly of Features (CARAFE) up-sampling module to preserve fine-grained disease characteristics, the YOLOv12 architecture improved with Ghost Convolution for effective feature extraction, and Involution layers to capture spatially specific patterns. Inspection techniques are still laborious, arbitrary, and prone to mistakes. A substantial set of data of 38 classes of both healthy and sick leaves from a variety of crops, including tomato, potato, apple, grape, corn, mango and sugarcane, was put together for training and evaluation. Experimental results show that YOLOv12-CropNet finds a suitable balance between computational speed and accurate detection. Accuracy, F1-score, recall, and precision are important performance metrics that verify the model's resilience in challenging environmental and visual circumstances. The suggested technique provides a scalable and field-deployable way to assist effective identification of diseases and precision agricultural decision-making. The proposed YOLOv12-CropNet model exhibits better performance than the other evaluated models, attaining a 98.45% peak accuracy, 98.10% precision ,98.20 % sensitivity and a 98.18% F1 score, thereby highlighting its efficacy in multi-crop leaf disease detection.
Why it matches plant phenotyping methods複数作物の葉の病徴を画像から検出・分類する深層学習手法を開発し、データセットと性能評価を伴うため、植物病害状態のフェノタイピング手法が中心である。
abstractthis research offers YOLOv12-CropNet, an innovative deep learning-based system for multi-crop leaf disease diagnosis in real time.
Reproduction assets foundThe paper uses public Kaggle datasets as its phenotyping image inputs: the PlantVillage dataset (38 crop-disease classes) and the Sugarcane Leaf Disease dataset, both cited with explicit public URLs. No author code, models, or checkpoints are reported as publicly available.Dataset · public[37] PlantVillage Dataset. Available online: https://www.kaggle.com/datasets/abdallahalidev/plantvillage-datasetOpen asset ↗pdf-page:22 lines:1-61Dataset · public[39] Sugarcane leaf Disease Dataset available online: https://www.kaggle.com/datasets/nirmalsankalana/sugarcane-Open asset ↗pdf-page:22 lines:1-61Plant phenotyping relevance match · UnverifiedEurope PMC · checked 14 Sept 2026
PotatoField / plotGrowth / time-series analysisGrowth / development / phenologyWater status / transpiration
Real-time measurement of belowground tuber growth has not been conducted in field crops. Here, a strain-gauge sensor was used to monitor potato tuber growth and estimate mean daily tuber water loss. Over the 13 days preceding harvest, tuber thickness increased by 0.90 mm, corresponding to a daily gain of 1.33 g, or a 4.8% increase. The greatest diurnal fluctuation was 0.453 mm, corresponding to a transpirational water loss of 9.4 ml, or 3% of the tuber’s water content. Daily transpiration showed a positive correlation with air temperature and vapor pressure deficit. This sensor will enable more precise input control and higher temporal resolution than current methods for below-ground crops, supporting improved crop management, yield prediction, and harvest decisions.
Why it matches plant phenotyping methods埋没ジャガイモ塊茎の成長・厚さ変動・水分損失をひずみゲージでリアルタイム測定する手法が研究の中心であり、植物器官形質の取得法として適格。
abstractHere, a strain-gauge sensor was used to monitor potato tuber growth and estimate mean daily tuber water loss.
Plant disease detection under complex climatic conditions and cross-crop scenarios remains a critical challenge. To address this, we propose a novel SimAM-Inception-StyleRandomization (SIS)-YOLOv11 algorithm based on YOLOv11n for early/late blight detection on potato and tomato leaves. Our core innovations are: 1) A C3k2-SSI module integrating Style Randomization, Inception architecture, and SimAM attention to enhance cross-crop generalization; 2) A Fusion-InceptionConv module for fine-grained feature extraction under rainfall/haze noise; 3) SPPF-Inception and C2PSA-IS modules to optimize multi-scale feature fusion; 4) DepGraph pruning to reduce 47.82% parameters while improving performance. Experiments show that the pruned SIS-YOLOv11 outperforms YOLOv11n by 3.7% in precision, 6.6% in recall, 5.4% in mAP50, and 7.9% in mAP50-95, and surpasses mainstream models (Faster R-CNN, SSD, etc.). This study provides a robust, lightweight solution for automated cross-crop disease detection in complex agricultural environments.
Why it matches plant phenotyping methodsジャガイモとトマト葉の病害状態を画像から検出する新規アルゴリズムを開発し、性能比較・軽量化まで行っており、植物フェノタイピング手法が中心である。
abstractwe propose a novel SimAM-Inception-StyleRandomization (SIS)-YOLOv11 algorithm based on YOLOv11n for early/late blight detection on potato and tomato leaves.
Reproduction assets foundThe paper's image dataset (potato/tomato leaf disease images with annotations and climate-noise augmentation) is explicitly declared publicly available on Baidu AI Studio. No author code or trained model deposit is stated.Dataset · publicData Availability: All image datasets used and analyzed in this study are publicly available from the Baidu AI Studio dataset repository at the URL: https://aistudio.baidu.com/datasetdetail/245434 .Open asset ↗Baidu AI Studio · 245434lines:1-133Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 5 Sept 2026
In recent decades, global weather patterns have shifted dramatically, introducing greater unpredictability into agriculture. A major challenge in plant breeding is developing selection strategies that remain accurate under such uncertainty. Sparse testing is a well-established approach to increase the number of genotypes evaluated in field trials while keeping costs manageable. However, incorporating image-based data into sparse testing remains challenging. We developed a strategy to integrate high-throughput phenotyping data into sparse testing in potato breeding to improve predictive performance in multi-environment trials. Our approach involved constructing an environmental kernel derived from the covariance matrix of image-based data. We assessed the predictive performance of several regression models under sparse testing, including those based on genomic or phenomic data alone and in combination. Models using only the proposed environmental kernel achieved predictive accuracies comparable to, or exceeding, those of genomic prediction models in various sparse testing scenarios. The best results were observed for tuber yield, a key trait in potato breeding. These findings highlight the potential of image-based environmental kernels to improve the efficiency and accuracy of sparse testing. This approach is cost-effective and scalable, particularly useful for breeding programs with limited resources.
Why it matches plant phenotyping methods画像ベースの高スループット表現型データを環境カーネルとして構築し、ジャガイモ育種の疎試験に統合する方法が研究の中心であるため、表現型予測手法として収載する。
abstractWe developed a strategy to integrate high-throughput phenotyping data into sparse testing in potato breeding to improve predictive performance in multi-environment trials.
Abstract Crop disease is a major worldwide problem in agricultural production and food security, adversely affecting yield and quality for a variety of plant species. To overcome these drawbacks, this research provides a Double Transfer Learning-based Capsule Network (DTL-CapsNet) approach for automated plant disease classification with multiple crops. Based on the image pre-processing, segmentation, double transfer learning, and Capsule Networks technologies, the proposed framework extracts discriminative features of the diseases and maintains spatial relations between the leaves symptoms effectively. This double transfer learning approach involves extracting general visual features from pre-trained deep learning models and then fine-tuning these features to classify plant diseases. Capsule Networks then leverage the visual similarity of disease patterns to make the recognition more robust, while simultaneously adding hierarchical part–whole relationships in leaf structures, thereby improving the feature representation. Experiments were performed on a heterogeneous data set consisting of 21,927 leaf images belonging to 17 different healthy and diseased classes of apple, chilli, cotton, corn and potato crops. The experimental results proposed DTL-CapsNet framework is more accurate compared to the traditional CNN-based models and conventional transfer learning models. The proposed method of double transfer learning and Capsule Networks offers an efficient and scalable approach for intelligent plant disease diagnosis, offering significant potential in precision agriculture and real-time crop monitoring systems.
Why it matches plant phenotyping methods葉画像から植物病害状態を分類する画像・計算手法が研究の中心であり、提案手法の開発と既存モデルとの比較検証が行われているため。
abstractBased on the image pre-processing, segmentation, double transfer learning, and Capsule Networks technologies, the proposed framework extracts discriminative features of the diseases and maintains spatial relations between the leaves symptoms effectively.
Sweet potato virus disease (SPVD) is one of the most destructive diseases affecting sweet potato production worldwide, causing severe yield losses and posing a significant threat to food security. Vision-based intelligent diagnosis has emerged as a promising solution for large-scale SPVD monitoring due to its low cost and scalability. However, existing publicly available datasets for SPVD are extremely limited and typically focus on a single task, such as disease classification or lesion segmentation, under constrained imaging conditions. This lack of comprehensive, task-oriented datasets significantly restricts the development, evaluation, and fair comparison of advanced computer vision methods for SPVD analysis. In this study, we present SPVD-Field, a task-oriented multi-task visual dataset suite composed of two independently collected sub-datasets optimized for different computer vision tasks. Rather than constructing a single homogeneous dataset, SPVD-Field is deliberately organized into two complementary task-oriented sub-datasets: SPVD-DET, designed for disease detection with bounding-box annotations, and SPVD-SEG, designed for fine-grained lesion segmentation with pixel-level masks. The two sub-datasets were independently collected using different acquisition protocols optimized for their respective tasks, while sharing a unified semantic definition of SPVD symptoms, crop growth stages, and field environments. SPVD-Field captures substantial real-world variability in imaging scale, viewpoint, illumination, background complexity, and symptom manifestation, reflecting the inherent challenges of fieldbased disease diagnosis. We provide detailed documentation of data acquisition, annotation strategies, and quality control procedures, along with baseline benchmark results for both detection and segmentation tasks to demonstrate the usability and difficulty of the dataset. By offering a structured dataset suite rather than a single-task collection, SPVD-Field aims to support diverse research directions, including detection, segmentation, multi-task learning, and disease severity analysis, and to facilitate reproducible and comparable research in SPVD-related plant phenotyping.
Why it matches plant phenotyping methodsサツマイモの病徴を対象とする画像データセットで、検出・病斑セグメンテーション、データ取得・アノテーション・品質管理、ベンチマークを中心的に提供しており、植物病害状態の画像フェノタイピング手法・データ基盤に該当する。
abstractIn this study, we present SPVD-Field, a task-oriented multi-task visual dataset suite composed of two independently collected sub-datasets optimized for different computer vision tasks.
Reproduction assets foundThe paper's core asset is the SPVD-Field dataset (SPVD-DET detection images with bounding-box annotations and SPVD-SEG segmentation images with pixel-level masks), explicitly deposited in a public repository via the data availability statement with a DOI link.Dataset · publicThe datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found below: https://dx.doi.org/10.21227/hq1q-jp43 .Open asset ↗10.21227/hq1q-jp43lines:664-703Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Accurate estimation of evapotranspiration (ET) is critical for irrigation management in water-scarce regions such as the Middle East and North Africa (MENA). This study compares sensible heat flux (H), latent heat flux (LE), and ET derived from eddy covariance (EC) and a boundary-layer scintillometer (BLS) operated with an aperture reducer, deployed simultaneously over an irrigated late-season potato field (1.8 ha) in the Beqaa Valley, Lebanon. Satellite NDVI observations indicate that the BLS–EC overlap period (13 October–27 November 2021) sampled the crop from peak canopy (NDVI ≈ 0.85–0.90) through the onset of senescence (NDVI ≈ 0.79). The BLS (Scintec BLS900) operated along a 140 m path. The EC system showed incomplete daytime energy-balance closure, with a regression slope of ≈0.69 and a seasonal Bowen-ratio-preserving correction factor of CF = 1.24 (a ~19% closure deficit) was used. Across the matched period, daily H from the BLS was strongly correlated with EC (r ≈ 0.82) but systematically lower, with a regression slope of ≈0.63 that persisted across timescales; this scale-invariant amplitude compression reflects the path-averaged, similarity-based nature of the scintillometer retrieval rather than the EC closure deficit, which instead governs the mean bias. BLS-derived daily ET showed a systematic positive bias relative to uncorrected EC (mean bias error, MBE = +0.30 mm d−1; +16% cumulative). Applying the Bowen-ratio-preserving correction (CF = 1.24) to EC reduced this to MBE = −0.14 mm d−1 (−6%), and the residual-to-LE correction yielded MBE = −0.15 mm d−1 (−6.4%); the latter comparison is only partly independent, as both methods share the same Rn and G. The Bowen-ratio-preserving method is therefore recommended for this dataset. Overall, the BLS captured the temporal variability of crop water use well, but residual-based ET estimates require careful treatment of the energy-balance-closure gap and are sensitive to the high BLS gap fraction (61.6% of 15 min records over the overlap, exceeding 90% at night). Once EC is closure-corrected to serve as the reference, the BLS offers a cost-effective alternative for field-scale ET monitoring in the MENA region, subject to the conditional agreement documented here.
Why it matches plant phenotyping methodsジャガイモ圃場の作物蒸発散量（ET）という生理・水利用状態を対象に、ECとBLSを比較検証し、補正法や測定誤差も評価している。センサー測定法の技術的妥当性が中心であり、単なる routine measurement ではない。
abstractThis study compares sensible heat flux (H), latent heat flux (LE), and ET derived from eddy covariance (EC) and a boundary-layer scintillometer (BLS) operated with an aperture reducer
Reproduction assets foundThe paper's flux/ET datasets are only available on request from the corresponding author, so they do not qualify as public assets. However, the Supplementary Information file (available at the MDPI supplementary URL) explicitly contains experiment sensor documentation and field/canopy images (Figures S1–S4: study site,Supplement · publicmeasurements along the beam. Because these results derive from a single crop, season, and phenological window, their generalization awaits multi-site, multi-season replication spanning the full-canopy cycle—the priority for subsequent campaigns.
Supplementary Materials
The following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/s26144398/s1 , Figure S1: Study site and potato canopy—Beqaa Valley, Lebanon; Figure S2: Eddy covariance system—full tower view (peak canopy); Figure S3: EC sensor suite close-up and soil sensor installation; Figure S4: BLS900 scintillometer—transmitter, receiver, and meteorological station.
Author Contributions
Conceptualization, HOpen asset ↗lines:251-268Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · checked 5 Sept 2026
Potato leaf diseases directly reduce yield and quality, and accurate field detection is important for precision plant protection. However, potato disease lesions are often weak in deep semantic representation, easily disturbed by complex field backgrounds, and variable in multi-scale lesion texture. To address these challenges, this study proposes an improved YOLO-based potato leaf disease detection model. The proposed model enhances the detector through three task-oriented modules. Deep Symptom Enhancement is used to strengthen deep disease feature extraction. Lesion Selection Attention based on large separable kernel attention improves the spatial selection of lesion regions. Multi-Scale Refinement Adapter uses a Mona-based C2PSA structure with two stacked Mona adapters to refine multi-scale texture and lesion-boundary information. Experiments were conducted on a potato leaf disease image dataset using mAP50, average recall (AR), parameters, GFLOPs, and FPS as evaluation metrics. The baseline YOLO26s achieved 81.31% mAP50 and 77.85% AR. The proposed SLR-YOLO model achieved 88.92% mAP50 and 83.51% AR, improving mAP50 and AR by 7.61 and 5.66 percentage points, respectively, while maintaining 118.6 FPS. The results show that the proposed framework improves detection accuracy for potato leaf disease images while retaining practical real-time performance.
Why it matches plant phenotyping methodsジャガイモ葉の病斑・病害状態を画像から推定するYOLOベース手法を開発し、データセット上で精度とリアルタイム性能を評価しており、植物表現型取得手法が中心である。
abstractthis study proposes an improved YOLO-based potato leaf disease detection model
Abstract Background Stomata and pavement cells are fundamental components of the leaf epidermis, jointly regulating gas exchange, water loss, and leaf surface expansion. Stomata size, aperture, density, and pavement cell morphology are critical parameters for assessing plant transpiration efficiency, epidermal growth dynamics, and adaptive responses to environmental constraints. Despite their biological importance, quantifying stomatal and pavement-cell traits remains seldom not generalized, simple, and fast enough . Manual or semi-automated approaches limit large-scale phenotyping and restrict the integration of epidermal morphology into crop-improvement pipelines aimed at developing climate-resilient varieties with optimised stomatal patterning. To address such limitations, we developed Stomatalia , a deep learning-based platform designed to automate and standardise the quantification of stomatal and pavement cell traits. The algorithm was trained on epidermal images of cultivated and wild potato and tomato genotypes grown under optimal and abiotic-stress conditions. Stomatalia automatically detects stomata and pavement cells and extracts a broad range of morphological and integrative epidermal parameters, enabling high-throughput phenotyping within a unified workflow. Results Prior to platform development, we optimised a rapid, minimally-destructive leaf-printing protocol that generates negative impressions of the leaf surface within 40–100 s. Transparent positive prints were subsequently produced and imaged under a light microscope at scale settings ranging from 20 to 200 μm. The resulting images are analysed using Stomatalia’s user-friendly web-based interface, which runs an instance-segmentation deep learning algorithm to detect, count, and calculate stomatal and pavement cell parameters. The platform outputs structured files containing raw measurements, derived integrative traits, and associated metadata, facilitating downstream statistical and physiological analyses. Algorithm evaluation on independent datasets demonstrated high performance within the validated dicot imaging domain, with F 1 -scores ranging from 0.86 to 0.94 depending on image scale, species, and resolution, and high segmentation overlap for both stomata and pavement cells. The generality of stomatal detection was also tested on spring onion, chickpea, balsam poplar, and wheat in cross-species feasibility tests, although performance was more variable in monocots, and pavement-cell segmentation remained species- and architecture-dependent. Benchmarking against another publicly available app further showed that, under the tested web interface settings and image types, Stomatalia exhibited closer agreement with manual counts and substantially faster processing times. The practical performance of Stomatalia was further tested in a proof-of-concept trial with potato plants subjected to optimal irrigation and a long, gradual drought. The platform reliably quantified epidermal traits despite variations in leaf morphology and image quality, supporting the integrated interpretation of stomatal and pavement-cell responses under stress. Conclusions We developed Stomatalia as a robust, user-friendly deep learning platform for automated, high-throughput analysis of bright-field leaf epidermal images across varying magnifications and resolutions. Stomatalia facilitates rapid, reproducible, and coordinated phenotyping of stomatal and pavement cells by integrating methodological standardisation, computational automation, and multi-trait extraction in a single analytical workflow. Its strongest current application is the analysis of high-quality dicot leaf-print images, particularly in species and imaging conditions similar to those used for model training and validation. Cross-species and benchmark analyses further define its current scope: stomatal detection can be transferred to some additional epidermal architectures, whereas robust pavement-cell segmentation in monocots or highly divergent species will require further annotation and model retraining. Within these defined boundaries, Stomatalia provides a flexible and extensible framework for studying stomatal and pavement cell morphology and environmental plasticity, while also supporting broader efforts to dissect and optimise plant responses to abiotic stress.
Why it matches plant phenotyping methods気孔・舗装細胞の形態形質を画像から自動抽出する深層学習プラットフォームを開発し、独立データで性能評価・比較検証しているため、植物フェノタイピング手法が中心である。
abstractwe developed Stomatalia , a deep learning-based platform designed to automate and standardise the quantification of stomatal and pavement cell traits.
Reproduction assets foundThe authors publicly deposited the paper's test image datasets (raw/input leaf-print images, detection outputs, manual ground-truth counts, exported datasets) and the model file on Figshare, and provide a public Google Colab demo for running the Stomatalia algorithm. Both are paper-specific, public, and actionable.Dataset · publicThe test datasets and model file used in this work are available through the following link:
https://doi.org/10.6084/m9.figshare.32532672. The test_sets.zip archive contains the test image datasets
(cross-species and benchmark analysis), including raw/input images, detection output images, manual
ground-truth counts and exported datasets.Open asset ↗Figshare · 10.6084/m9.figshare.32532672pdf-page:25 lines:1-75Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
This study compared unsupervised and supervised machine learning, and deep learning (U-Net) classifiers on Unmanned Aerial Vehicle (UAV) multispectral imagery to identify nitrogen status in potato crops under nitrogen (N) fertilization treatments, irrigation (I), and their interaction (N × I). The U-Net model outperformed all other methods, achieving accuracies for crop nitrogen status of 65–99% in N, 84–100% in I, and 41–82% in N × I treatments, with variation due to different input data. Supervised machine learning also performed well, with Support Vector Machine achieving 53–87, 66–86, and 32–66% respectively, and Random Forest 61–96, 70–81, and 33–65%. Unsupervised K-means yielded the lowest accuracies (47–58, 9–65, and 8–34%), demonstrating necessity of substantial supervision to delineate crop nitrogen and water status. These findings were confirmed by repeated analyses of UAV imagery acquired later in the growing season with consistent results. Comparable classification performance was observed for crop water status and leaf area index at both time points. Despite being demonstrated in a single-field, single-crop framework, the results provide proof of concept for applying deep learning classifiers to detect subtle nitrogen and water stress under field conditions in precision agriculture. Future research could test diverse agroecosystems and growing seasons, alternative deep learning algorithms, and sensor data fusion to improve classification accuracies.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からジャガイモの窒素・水分状態およびLAIを推定する分類手法を比較・検証しており、植物状態の取得と手法性能評価が研究の中心である。
abstractThis study compared unsupervised and supervised machine learning, and deep learning (U-Net) classifiers on Unmanned Aerial Vehicle (UAV) multispectral imagery to identify nitrogen status in potato crops
Accurate detection of plant leaf diseases is essential for enhancing crop productivity and supporting global food security. In addition to disease classification, understanding how environmental and soil conditions affect model performance is important for developing robust real-world agricultural monitoring systems. Although deep learning (DL) models achieve high accuracy on benchmark datasets, their performance in real-world settings is often limited by variations in illumination, background complexity, and environmental conditions. This study proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants. The framework combines U2-Net-based leaf segmentation with a Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN–Bi-GRU) architecture. MobileNetV2 is employed as the feature extraction backbone to capture spatial characteristics, while Bi-GRU layers model sequential feature dependencies, forming a spatio-temporal network whose architectural design prioritizes parameter efficiency through depthwise separable convolutions and reduced gating complexity. The model was trained and validated using the PlantVillage benchmark dataset and achieved a classification accuracy of 99.8% with a macro-averaged F1-score of 94%, outperforming several state-of-the-art architectures. To assess robustness under real-world conditions, the trained model was further tested on leaf images collected from open-field environments near Eluru, South India. The field evaluation revealed a reduction in classification accuracy to 61.97%, indicating the impact of domain shift and environmental variability. To investigate potential contributing factors, soil parameters, including pH, temperature, moisture, and NPK levels, were monitored using an IoT-based Arduino sensing system over ten consecutive days. Rather than serving as direct inputs to the disease classification model, these environmental measurements were analyzed to assess their potential influence on disease symptom expression and the observed reduction in model performance under field conditions. The results suggest that environmental conditions may influence disease symptom expression and model transferability. This study highlights the importance of integrating DL-based disease recognition with environmental monitoring for reliable field-level agricultural applications. Nevertheless, computational complexity metrics, including inference latency and memory footprint, were not evaluated in the present work and are identified as a priority for future edge deployment studies.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類するセグメンテーション・深層学習手法を開発し、ベンチマークと圃場画像で性能を検証しているため、植物フェノタイピング手法が中心である。
abstractThis study proposes a smart DL framework for detecting and classifying multiple leaf diseases in tomato, potato, and pepper plants.
To address the insufficient characterization of vertical heterogeneity in potato canopy leaf nitrogen content (LNC), this study developed a layer-specific LNC estimation framework based on canopy hyperspectral reflectance, fractional-order derivative (FOD) transformation, and two-band and three-band optimized spectral indices. Partial least squares regression (PLSR) was then used to evaluate the predictive ability of the selected spectral indices for Top, Middle, and Bottom LNC. Field experiments were conducted from 2022 to 2023 in the semi-arid region of Yulin, Shaanxi Province, China. Canopy hyperspectral reflectance from 350 to 1830 nm and LNC measurements of upper (Top), middle (Middle), and lower (Bottom) leaves were synchronously acquired during the tuber formation stage. The results showed that potato canopy LNC exhibited a clear vertical gradient, following the order Top LNC > Middle LNC > Bottom LNC. Traditional vegetation indices were significantly correlated with LNC, but their correlations decreased with increasing canopy depth, with the highest correlation for Bottom LNC being only 0.524. Compared with traditional vegetation indices, FOD-based two-band indices showed stronger Pearson correlations with layer-specific LNC. Under FOD1.5, the maximum absolute Pearson correlation coefficients (|r|) between the selected two-band indices and LNC reached 0.855, 0.849, and 0.814 for Top, Middle, and Bottom LNC, respectively. The three-band optimized spectral indices further enhanced spectral information extraction, with maximum |r| values of 0.893, 0.885, and 0.852, respectively. However, cross-year validation produced substantially lower R 2 values, indicating limited temporal transferability of the selected indices and the need for further validation before broader application. Compared with the traditional vegetation index model, it increased the testing-set R 2 for Bottom LNC by 0.279 and reduced RMSE from 0.159 to 0.113. These results suggest that FOD1.5-integrated three-band optimized spectral indices can improve the indirect estimation of layer-specific LNC from canopy reflectance, particularly for Bottom LNC, where the reflectance-LNC association is affected by canopy signal attenuation and mixing. The findings provide a methodological reference for describing canopy vertical nitrogen status and functional heterogeneity in potato, while their broader applicability requires further validation across growth stages, cultivars, sites, and nitrogen management conditions.
Why it matches plant phenotyping methodsジャガイモ群落のハイパースペクトル反射から層別葉窒素含量を推定する手法を開発し、相関・予測性能・年次検証で評価しており、植物形質取得・推定法が研究の中心である。
abstractthis study developed a layer-specific LNC estimation framework based on canopy hyperspectral reflectance, fractional-order derivative (FOD) transformation, and two-band and three-band optimized spectral indices.
Abstract Early and accurate detection of plant diseases is vital for global food security and sustainable agriculture. While deep learning offers promising solutions, there is a continuous need for architectures that enhance learning capacity and efficiency. This study introduces ViT-KAN, an innovative hybrid model merging the powerful feature extraction of Vision Transformers (ViT) with the flexible, learnable activation functions of Kolmogorov-Arnold Networks (KAN). By replacing the standard Multilayer Perceptron (MLP) classification head of ViT with a KAN module, the proposed architecture aims to better capture nonlinear patterns in agricultural images. Evaluated on the PlantVillage dataset for potato and maize leaf diseases using standard fivefold cross-validation, with final results reported as mean ± standard deviation across the five folds, the model was trained entirely from scratch. ViT-KAN achieved 99.49 ± 0.13% accuracy on the maize dataset and 98.28 ± 0.51% on the potato dataset, compared with 98.92 ± 0.40% and 97.77 ± 0.88%, respectively, for the standard ViT model. Beyond mean accuracy, ViT-KAN showed lower standard deviation across folds, while representative fold curves suggested smoother early training trajectories under the shared training configuration. These findings suggest that ViT-KAN is a promising alternative to conventional ViT-based classification models for plant disease diagnosis.
Why it matches plant phenotyping methods植物葉画像から病害状態を分類する新規ViT-KANモデルを開発・交差検証しており、病害表現型の取得・推定手法が研究の中心である。
abstractThis study introduces ViT-KAN, an innovative hybrid model merging the powerful feature extraction of Vision Transformers (ViT) with the flexible, learnable activation functions of Kolmogorov-Arnold Networks (KAN).
Crop disease identification is still a big problem in agriculture, which results in large yield losses and food lacks, especially in regions dependent on manual monitoring. Traditional methods of identifying plant diseases are often labor intensive, error-prone, and ineffective in early-stage diagnosis. To overcome these limitations, this study proposes a hybrid machine learning model for accurate crop type identification, disease classification, and severity prediction using image data. The methodology utilizes the PlantVillage dataset, encompassing over 50,000 annotated leaf images across 14 crops. After rigorous preprocessing involving image resizing, normalization, and cleaning, Improved Deep Joint Segmentation is applied to localize disease-affected regions. Feature extraction incorporates color, texture (GLCM, LBP), and shape attributes to enhance classification accuracy. A hybrid approach integrating XGBoost for feature selection and Support Vector Machine (SVM) for classification is proposed to capture both overarching trends and intricate details. Experimental results across four major crops—potato, tomato, corn, and grape—demonstrate superior performance, with the hybrid model achieving 98.6% accuracy, 98.3% precision, 99.0% recall, and 99.1% F1-score. The model outperforms existing approaches, offering a robust, scalable, and accurate solution for early crop disease detection in precision agriculture.
Why it matches plant phenotyping methods画像から病変領域を抽出し、植物病害の分類と重症度を推定する機械学習ワークフローが研究の中心であり、植物状態の表現型計測に該当する。
abstractthis study proposes a hybrid machine learning model for accurate crop type identification, disease classification, and severity prediction using image data.
An early and precise identification of plant diseases helps to increase the efficiency of farming operations and minimize the economic losses associated with plant diseases. Nevertheless, applying deep learning models for plant disease identification in an agricultural setting poses certain difficulties due to high computational costs and insufficient edge device computing power. This paper presents a transfer learning-based framework for multi-class plant disease detection using MobileNetV2 and EfficientNet-B0 models. For the purpose of research, the PlantVillage dataset including potato, bell pepper, and tomato leaves was used. Images from this source underwent pre-processing that included resizing, normalizing, and augmenting images. Both transfer learning approach and fine-tuning helped to modify pre-trained CNNs for multi-class classification of different diseases affecting plants' leaves. Experiments have shown that EfficientNet-B0 model performed much better with accuracy of 95.7% and AUC of 0.98. Moreover, the proposed algorithm was exported as a TensorFlow Lite model and implemented in the Streamlit application for efficient edge deployment.
Why it matches plant phenotyping methods植物葉画像から病害を推定する深層学習フレームワークの開発・性能評価が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採録する。
abstractThis paper presents a transfer learning-based framework for multi-class plant disease detection using MobileNetV2 and EfficientNet-B0 models.
Abstract Rice and potatoes are major crops in Bangladesh, frequently affected by major disease outbreaks that challenge food security. Inaccurate disease identification often contributes to yield losses. Recently, machine learning garnered much attention in identifying crop diseases. The present study was conducted to develop a deep learning model-based image‑analysis system that automatically identifies key diseases of Bangladeshi rice and potato, and integrates it into a web app to provide farmers with rapid, accurate diagnoses. The system employs a convolutional neural network (CNN) implemented with TensorFlow’s Sequential API, featuring ReLU-activated hidden layers and a Softmax output layer. A dataset of 4,809 images, comprising both healthy and diseased, was collected and processed through pre-processing, feature extraction, and classification. A web-based application was deployed utilizing the Python Streamlit framework. This application integrates the proposed model to predict 2 rice diseases viz. blast ( Magnaporthe oryzae ), bacterial leaf blight ( Xanthomonas campestris ), and 2 potato diseases viz. Early blight (Alternaria solani) and Late blight ( Phytophthora infestans ) from uploaded images, providing a confidence score for the predictions with approximately 92.84% for all detected diseases. The proposed model achieved a training accuracy of 0.9357, a validation accuracy of 0.8983, and a test accuracy of 0.9333. The developed web application indicates strong diagnostic performance for four major diseases, offering Bangladeshi farmers an accessible tool to make timely management decisions.
Why it matches plant phenotyping methodsイネ・ジャガイモ葉の病徴を画像から分類するCNNと実用Webアプリを開発・評価しており、植物の病害状態推定が中心的な方法論的貢献である。
abstractdevelop a deep learning model-based image‑analysis system that automatically identifies key diseases of Bangladeshi rice and potato
Reproduction assets foundThe paper's rice/potato leaf disease image dataset partially comes from Kaggle, and the data availability statement points to PlantVillage for additional image data; both are public image assets used for the paper's CNN phenotyping/disease-classification analysis. No author analysis code, trained model checkpoints, or专Dataset · publicch, M.Y.H. analyzed the data, A.A.J.,
452
M.Y.H. and M.S. wrote this manuscript, M.R.I., F.M.A. and S.O.N. reviewed and edited the
453
manuscript. All authors have read and agreed to the published version of the manuscript.
454
Data availability statement
455
Some of the datasets used in this study was obtained from Kaggle
456
(https://www.kaggle.com/datasets). Additional datasets used and/or analyzed during the current
457
study are available from the corresponding author upon reasonable request. More image data can
458
be found at https://www.plantvillage.org/en/plant_images
459Open asset ↗Kagglepdf-raw-page:24 lines:1-57Dataset · publiche manuscript.
454
Data availability statement
455
Some of the datasets used in this study was obtained from Kaggle
456
(https://www.kaggle.com/datasets). Additional datasets used and/or analyzed during the current
457
study are available from the corresponding author upon reasonable request. More image data can
458
be found at https://www.plantvillage.org/en/plant_images
459Open asset ↗PlantVillagepdf-raw-page:24 lines:1-57Plant phenotyping relevance match · UnverifiedEurope PMC · Crossref · checked 5 Sept 2026
Accurate diagnosis of potato nitrogen status is critical for optimized fertilizer management and sustaining productivity. We used data from nine field experiments (2010-2018) across major potato-producing regions in northern China to develop a regional critical nitrogen dilution curve via a Bayesian hierarchical model. The curve, Nc = 4.179 × DW -0.417 (DW = whole-plant dry matter), provided the basis for calculating the nitrogen nutrition index (NNI), which was related to canopy spectral indices from a GreenSeeker sensor. Relationships between spectral indices and NNI were strongly growth-stage dependent. The tuber initiation-bulking period, approximately 29-70 days after emergence (DAE), represented the effective phenological window, with 29-55 DAE as the primary operational window for quantitative spectral diagnosis. Stage-specific ratio vegetation index (RVI) showed the most consistent association with NNI, whereas pooled whole-season models had low predictive power. The Bayesian framework quantified uncertainty, emphasizing that near-threshold NNI values require cautious interpretation. The resulting regional-average reference supports rapid field diagnosis of potato N status while accounting for cultivar, year, and site variability. These findings provide practical guidance for stage-specific N management and demonstrate the importance of growth-stage-aware spectral assessment in operational decision-making.
Why it matches plant phenotyping methodsジャガイモの窒素栄養状態を対象に、Bayesian窒素希釈曲線とキャノピー分光センシングを開発・評価し、成長段階別の診断性能と不確実性を検証しているため、植物表現型取得法が中心である。
abstractWe used data from nine field experiments (2010-2018) across major potato-producing regions in northern China to develop a regional critical nitrogen dilution curve via a Bayesian hierarchical model.
Potato sorting in post-harvest processing relies heavily on manual visual inspection, which is physically demanding, subjective, and insufficiently scalable for modern packing lines. This study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection. A controlled imaging platform was constructed using commodity hardware, and a dataset of 19,805 manually annotated instances across 1361 images was collected from two geographically distinct farm locations in Slovenia. A systematic benchmark of 25 model configurations spanning five YOLO architecture families-YOLOv8, YOLOv9, YOLOv10, YOLOv11, and YOLO26-was conducted across three practical quality classes (Edible, Feed, Rotten) using a strict cross-location evaluation protocol in which models were trained on one location and tested on a completely unseen second location. All models achieved strong in-distribution performance (F1 ≥ 0.906), but showed considerable variation under cross-location conditions, with external F1 ranging from 0.792 to 0.918. The yolo26_l configuration achieved the best cross-location performance (F1 = 0.918, mAP@0.5:0.95 = 0.816, ΔF1 = 0.029), demonstrating that transferable representations are achievable under a standard supervised training protocol. Per-class analysis identified feed detection as the primary generalization bottleneck. The results confirm that affordable RGB-based sorting systems are technically feasible and highlight cross-location evaluation as an essential protocol for assessing real-world deployment readiness.
Why it matches plant phenotyping methodsジャガイモ塊茎の品質・腐敗状態をRGB画像と物体検出で推定する撮像システムを構築し、複数YOLOモデルの交差地域ベンチマークと外部検証を行っており、表現型取得法が中心である。
abstractThis study investigates the feasibility of a low-cost RGB-based optical inspection system for automated potato quality detection using deep learning-based object detection.
The high spatio-temporal resolution of UAV sensors requires robust analytical tools to classify subtle agroecosystem variations. This study compared unsupervised, supervised machine learning (ML), and deep learning (U‑Net) classifiers to identify nitrogen (N) and water (I) status, and their interaction (N×I) in potato crops using UAV multispectral imagery. The U‑Net model outperformed all other methods, achieving accuracies of 85% (N), 93% (I), and 70% (N×I). Supervised ML classifiers also performed well and Support Vector Machine achieved 71, 62, and 40% respectively, whereas Random Forest achieved 67, 61, and 40%. The unsupervised K‑means classifier yielded the lowest accuracies (41, 36, and 23%), demonstrating the necessity of substantial supervision to delineate crop N and water properties. These results were confirmed by repeated analysis on UAV imagery acquired later in the season. Deep learning classifiers should be adopted more widely in precision agriculture, as they offer new potential for optimizing N and irrigation co-management under field conditions with subtle spatial variation that is otherwise difficult to capture. Future research should test alternative deep learning algorithms and sensor data fusion to further improve classification accuracies.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からジャガイモの窒素・水分状態を推定し、複数の分類器を比較・反復検証しており、植物状態の取得・推定手法が研究の中心である。
abstractThis study compared unsupervised, supervised machine learning (ML), and deep learning (U‑Net) classifiers to identify nitrogen (N) and water (I) status, and their interaction (N×I) in potato crops using UAV multispectral imagery.
Abstract Potato quality detection is a critical step that determines their market value. However, manual sorting suffers from low efficiency, high cost, and a high misjudgment rate. Therefore, the rapid and accurate classification of defective potatoes is of great economic significance for reducing industrial losses. In this study, a lightweight convolutional neural network (WavebandCNN) was constructed combined with hyperspectral imaging (HSI) technology to achieve rapid and accurate classification of four categories of potatoes: healthy, greening, skin damage, and dry rot. First, hyperspectral images of 400 potato samples were collected and calibrated, and regions of interest (ROI) were extracted to construct a spectral dataset. The performance of the lightweight convolutional neural network was evaluated using raw spectra and five preprocessed spectra, respectively, and compared with three traditional machine learning models: Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM). Meanwhile, the successive projections algorithm (SPA) was employed to select characteristic wavelengths for data dimensionality reduction. The results show that WavebandCNN achieved the highest classification accuracy of 93.11% with raw spectra, significantly outperforming all comparative models. After screening 20 characteristic wavelengths via SPA, the classification accuracy was improved to 95.98%, while the training time and data redundancy were greatly reduced. This study confirms that the combination of hyperspectral imaging technology and the WavebandCNN model enables accurate identification of potato defects, providing a new approach for the online detection and practical application of potato defects.
Why it matches plant phenotyping methodsジャガイモの欠損・病変状態をハイパースペクトル画像とCNNで直接分類する手法を構築・比較・評価しており、植物状態の取得・推定が研究の中心である。
abstracta lightweight convolutional neural network (WavebandCNN) was constructed combined with hyperspectral imaging (HSI) technology to achieve rapid and accurate classification of four categories of potatoes: healthy, greening, skin damage, and dry rot.
Abstract Potatoes are one of the major crops eaten in developing countries; however, their production is falling due to various diseases. Early identification and detection of potato leaf diseases play a vital role in improving potato quality and quantity. Existing methods are either computationally resource intensive or lack trust in their decision-making process, which makes them difficult to deploy for real-time potato disease classification and limits its accessibility. To mitigate these limitations, this study proposed an attention-enhanced MobileNetV2 with a squeeze-and-excitation architecture, which balances high accuracy with low computational resources. This method incorporates the strength of MobileNetV2 and Squeeze-and-excitation networks. A total of 2152 images of early blight, late blight, and healthy leafs were obtained from the Kaggle public repository, which are partitioned into 70% training, 20% validation, and 10% testing and were utilized to train, validate, and test the proposed model. The MobileNetV2 backbone is utilized for feature extraction, and then a squeeze-and-attention block is used to recalibrate the feature maps by focusing on important features and suppressing irrelevant ones. Gradient-weighted Class Activation Mapping (Grad-CAM) was implemented to visualize the most relevant region of the leaf for decision-making, which increases model interpretability and user trust. The proposed model achieves a remarkable performance of 99% testing accuracy with 9.41 MB total parameters. The proposed model is suitable for real-time potato leaf disease detection and classification, which can be easily accessible to agricultural stakeholders, including farmers, and contributes to food security.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習手法を提案・評価しており、植物表現型（病害状態）の取得・推定が中心である。
abstractthis study proposed an attention-enhanced MobileNetV2 with a squeeze-and-excitation architecture, which balances high accuracy with low computational resources.
Reproduction assets foundThe paper's phenotyping inputs are 2152 potato leaf images (early blight, late blight, healthy) obtained from a public Kaggle repository, explicitly stated as publicly available in the Declarations. No author analysis code is shared (Code Availability: Not applicable), and no trained model checkpoints are released.Dataset · publicAvailability of Data: The datasets generated during and/or analyzed during the current study are
publicly available at https://www.kaggle.com/datasets/faysalmiah1721758/potato-dataset.Open asset ↗Kaggle · faysalmiah1721758/potato-datasetpdf-page:23 lines:1-35Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Potato ( Solanum tuberosum ) is a vital global non-cereal food crop severely threatened by bacterial wilt, caused by Ralstonia solanacearum ( R . solanacearum ). Conventional diagnostics like PCR and ELISA, though effective, are destructive and time-consuming, limiting large-scale field applications. This study investigates hyperspectral imaging (HSI) as a non-invasive, rapid, and accurate alternative for early detection and severity grading of potato bacterial wilt. Using a portable HSI system (400-1000 nm), spectral data were collected from inoculated potato plants ('Longshu No. 7') at 0, 24, 48, and 72 h post-inoculation, alongside disease severity assessment (grades 0-4). After comprehensive spectral preprocessing and feature band extraction via Competitivse Adaptive Reweighted Sampling (CARS), we developed two distinct sets of models: one for early detection (temporal classification) using Partial Least Squares-Discriminant Analysis (PLS-DA) and Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA), and another for severity grading. The SNV + SG + MC + PLS-DA model achieved exceptional accuracy, exceeding 97% for early detection, while the MSC + SG + MC + CARS + PLS-DA model yielded >97% accuracy for severity grading. These results were supported by low misclassification rates in confusion matrices. This work establishes a robust HSI-based framework for high-throughput screening of resistant potato germplasm and advances precision agriculture strategies for bacterial wilt management.
Why it matches plant phenotyping methodsHSIによるジャガイモ植物体の細菌性萎凋病の早期検出と重症度推定が研究の中心であり、画像取得、特徴抽出、分類・重症度モデルを開発している。
abstractThis study investigates hyperspectral imaging (HSI) as a non-invasive, rapid, and accurate alternative for early detection and severity grading of potato bacterial wilt.
Penelitian ini melakukan evaluasi komparatif terhadap tujuh arsitektur Convolutional Neural Network (CNN), yaitu MobileNet, NASNet Mobile, MobileNetV2, VGG16, ResNet50, InceptionV3, dan InceptionResNetV2, dalam mengklasifikasikan penyakit early blight dan late blight pada daun kentang menggunakan pendekatan transfer learning. Dataset yang digunakan adalah Potato Disease Leaf Dataset (PLD), dengan seluruh model diinisialisasi menggunakan bobot pra-latih ImageNet dan dilatih pada citra berukuran 224 × 224 piksel. Untuk meningkatkan keberagaman data dan mengurangi overfitting, augmentasi citra dilakukan secara real-time melalui horizontal flip, vertical flip, dan rotasi ±5°. Proses pelatihan menggunakan optimizer Stochastic Gradient Descent (SGD) dengan learning rate 0,001, batch size 2, selama 30 epoch, serta fungsi loss Binary Crossentropy. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score pada data uji independen. Hasil eksperimen menunjukkan bahwa ResNet50 mencapai kinerja terbaik dengan akurasi 97,16%, loss 0,1153, presisi 94,63%, recall 100,00%, dan F1-score 97,24%, mengungguli VGG16 (96,45%) dan MobileNet (95,04%). Sebaliknya, InceptionV3, NASNet Mobile, dan InceptionResNetV2 menunjukkan stabilitas pelatihan dan kemampuan generalisasi yang lebih rendah pada dataset ini. Temuan ini menegaskan bahwa mekanisme residual connection pada ResNet50 berperan signifikan dalam meningkatkan diskriminasi fitur visual penyakit daun, sementara MobileNet menawarkan kompromi yang efektif antara akurasi dan efisiensi komputasi, sehingga berpotensi diterapkan pada sistem deteksi penyakit tanaman berbasis perangkat terbatas.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類するCNNアーキテクチャを比較・評価しており、植物の病害状態を推定する画像ベースのフェノタイピング手法の技術検証が中心です。
abstractPenelitian ini melakukan evaluasi komparatif terhadap tujuh arsitektur Convolutional Neural Network (CNN), yaitu MobileNet, NASNet Mobile, MobileNetV2, VGG16, ResNet50, InceptionV3, dan InceptionResNetV2, dalam mengklasifikasikan penyakit early blight dan late blight pada daun kentang menggunakan pendekatan transfer learning.
Agriculture constitutes a foundational pillar of the Indian economy, yet crop diseases remain one of the most persistent threats to agricultural productivity, particularly for smallholder farmers who lack immediate access to plant pathology expertise. To bridge this critical gap, the present work proposes Smart Crop Doctor, an intelligent web-based platform that leverages Artificial Intelligence to perform automated detection of crop diseases. Within this framework, users submit photographs of plant foliage, which are subsequently analyzed by a trained Convolutional Neural Network (CNN) capable of recognizing pathological conditions across 15 distinct disease categories spanning tomato, potato, and bell pepper cultivars. A dedicated input validation mechanism is incorporated to ascertain whether a submitted photograph genuinely depicts leaf tissue, thereby filtering out extraneous objects such as rocks or paper-based documents. Upon successful identification, the platform furnishes comprehensive output including disease characterization, recommended treatment protocols, and guidance on both organic and chemical fertilizer application, in addition to broader agronomic advisory content. Beyond disease diagnosis, the system integrates a suite of ancillary services: a%, confirming that the system delivers dependable performance suited to practical deployment in agricultural settings.
Why it matches plant phenotyping methods植物葉の画像から病害状態をCNNで推定する診断システムが研究の中心であり、植物病害フェノタイピング手法・プラットフォームに該当する。
abstractthe present work proposes Smart Crop Doctor, an intelligent web-based platform that leverages Artificial Intelligence to perform automated detection of crop diseases.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · Crossref · checked 5 Sept 2026
Abstract Unmanned aerial vehicle (UAV)-based phenotyping has been applied to assess potato traits, however, its use to identify canopy traits associated with tuber yield across diverse genotypes remains limited. The objective of this study was to evaluate the use of UAV-based field phenotyping, integrating RGB and thermal imaging, to identify key canopy traits associated with tuber yield and it´s agronomic components in a set of eight potato genotypes grown across two environments and two growing seasons. Despite higher seasonal rainfall in Chiloé, tuber yields were consistently greater in Osorno, underscoring that total precipitation alone is less important than its temporal distribution and effective crop water availability; this makes it necessary to supplement with irrigation during the period of highest demand. RGB-derived vegetation indices and canopy temperature successfully differentiated genotypes, although their discriminatory power varied according to developmental stage and environmental conditions, with intermediate to late growth stages generally providing the strongest genotype separation. Canopy temperature supplied complementary physiological information related to canopy water status, whereas RGB traits captured broader variation in canopy structure and greenness. These findings highlight the importance of integrating phenological stage and environmental context when interpreting remote sensing data, and demonstrate the strong potential of UAV-based HTP to support breeding and agronomic strategies aimed at improving drought resilience, yield stability, and selection efficiency in potato.
Why it matches plant phenotyping methodsUAVによるRGB・熱画像を用いた圃場フェノタイピングが中心で、ジャガイモのキャノピー形質を抽出・評価し、遺伝子型間比較や収量関連性を検討している。
abstractevaluate the use of UAV-based field phenotyping, integrating RGB and thermal imaging, to identify key canopy traits associated with tuber yield
This paper explores the use of optimized convolutional neural networks (CNNs) to classify diseases affecting potato leaves using TensorFlow-2. The dataset, sourced from Kaggle's Plant Village repository, includes 152 images of healthy potato leaves and 1000 images each of early and late blight. The methodology covers data preparation, model architecture design, training, evaluation, and deployment. During data preparation, the data set was split into training sets (80%) and testing sets (20%), with images resized to 128x128 pixels. The Deep Learning (DL) models built using CNN with 4 different optimizers (ADAM, SGD, RMSPROP, and ADAMAX) and trained using a sparse categorical cross-entropy loss function, include multiple convolutional and pooling layers for feature extraction, and fully connected layers for classification. Early stopping was used to prevent overfitting. Model performance was assessed using accuracy, loss curves, confusion matrix, ROC curve, precision recall curve, classification report, and F1 score. In addition, we have used data augmentation to balance the dataset by increasing healthy potato leaves 6 times and the use of Ensemble Deep Learning (EDL). EDL10 which contains DL1 (CNN + ADAM), DL2 (CNN + SGD), DL3 (CNN + RMSPROP) and DL4 (CNN + ADAMX) performs best with a accuracy score of 97.0%. This highlights the importance of data balancing and the use of the ensemble classification approach for the detection of blight in Potato Leaves.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類するCNN・アンサンブル手法の設計、評価、データ拡張が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractThis paper explores the use of optimized convolutional neural networks (CNNs) to classify diseases affecting potato leaves using TensorFlow-2.
Reproduction assets foundThe paper uses the public Kaggle PlantVillage potato leaf image dataset and archives its complete analysis source code on Zenodo with explicit availability statements and URLs.Code · publicThe complete source code is hosted in a DOI-minting repository and has been archived on Zenodo to ensure long-term accessibility and reproducibility. The code is released under an open-source license. The archived version corresponding to this publication is available at : https://doi.org/10.5281/zenodo.19624017Open asset ↗Zenodo · 10.5281/zenodo.19624017lines:252-314Dataset · publicThe datasets generated and/or analysed during the current study are available at : PlantVillage Dataset, accessed from https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset.Open asset ↗Kaggle · plantvillage-datasetlines:252-314Plant phenotyping relevance match · UnverifiedEurope PMC · bioRxiv · checked 15 Sept 2026
Potato crop is highly vulnerable to abiotic stresses like salinity and low nutrient availability. Rapid identification of stress-resilient genotypes is therefore essential for breeding, yet conventional phenotyping is often slow, space-demanding and expensive. We present LOCOPOTS — a LOw-COst high-throughput screening platform for in vitro POTatoes under abiotic Stress — which combines individual in vitro plant culture, low-cost RGB imaging and machine-learning-based automatic segmentation using a trained model of a convolutional neural network, based on U-Net architecture. LOCOPOTS enabled the automated extraction of growth, colour, and vegetation-index traits and demonstrated robust performance across independent phenotyping rounds. We screened 30 potato varieties under control, low-nutrient and saltinity conditions, identifying contrasting growth and physiological responses. Integrated traits such as final area and height, Area_AUC and height_AUC, together with GLI, Ch ol , cive and chlorophyll fluorescence parameters, discriminated genotype performance under stress. Metabolic profiling further revealed genotype-specific reprogramming in carbon and nitrogen metabolism under low nutrition and salt stress, including changes in fructose, myo-inositol, β-aminobutyric acid, γ-aminobutyric acid, proline, and certain polyamines, identifying them as specific chemical biomarkers of plant stress responses. LOCOPOTS provides a scalable, affordable and space-efficient platform for early screening of potato genetic diversity and identification of candidate traits associated with stress resilience.
Why it matches plant phenotyping methods低コストRGB撮像とU-Netによる自動セグメンテーションを中核とする、ジャガイモ表現型取得プラットフォームの開発・検証であり、形態・色・植生指数形質を自動抽出している。
abstractWe present LOCOPOTS — a LOw-COst high-throughput screening platform for in vitro POTatoes under abiotic Stress — which combines individual in vitro plant culture, low-cost RGB imaging and machine-learning-based automatic segmentation using a trained model of a convolutional neural network, based on U-Net architecture.
Background High-throughput automated image analysis holds great promise for plant breeding by enabling faster, more accurate assessment of traits relevant to crop improvement. Imaging-based systems, such as the CropReporter, allow automated quantification of photosynthetic parameters like PSII efficiency under ambient light from a top-down 2D perspective. However, standard analysis tools average values across the 2D top view, overrepresenting upper leaves and underrepresenting those in the lower canopy. Upper leaves may occlude lower ones, and due to the pinhole projection of the camera, lower leaves of the same size appear smaller in the image. Consequently, vertical heterogeneity in PSII efficiency within the canopy cannot be resolved using a single 2D image. Results To address these issues, we integrated top-view PSII efficiency data (by CropReporter) with 3D structural data from RGB point clouds (by MaxiMarvin). Alignment accuracy between MaxiMarvin and CropReporter was high, with R² ≥ 0.98 for the x-axis and R² ≥ 0.99 for the y-axis. The method was tested using Chenopodium quinoa, Glycine max, and Solanum tuberosum, exposed to salinity, waterlogging and drought stress respectively. In Chenopodium quinoa, it allowed precise determination of when senescence began in the lower leaves. In Solanum tuberosum, the reduction in PSII efficiency by drought was the same for all leaf layers, while in Glycine max, waterlogging stress most strongly affected the middle layer of the canopy. Conclusions This framework enables the 3D mapping of PSII efficiency across the vertical plant profile by combining top-view chlorophyll fluorescence imaging (CropReporter) with 3D structural data (MaxiMarvin). It reveals vertical variation in photosynthetic activity across canopy layers. With standard 2D chlorophyll fluorescence imaging it is difficult to distinguish between non-photosynthetic tissues like flower heads and lower layers of leaves, that might have the same PSII values. Using height-based filtering, taking data from the 3D mapping, such distinction can be made with the method presented in this paper. This allows estimating the PSII efficiencies of leaves only. By capturing layer-specific responses to abiotic stress and developmental changes, the method provides physiologically relevant input for crop growth modelling and highlights the importance of accounting for canopy structure in photosynthetic analyses.
Why it matches plant phenotyping methods2Dクロロフィル蛍光によるPSII効率を3D植物構造へ投影し、群落層別の葉の生理形質を推定する手法の開発・検証が中心である。
abstractTo address these issues, we integrated top-view PSII efficiency data (by CropReporter) with 3D structural data from RGB point clouds (by MaxiMarvin).
Reproduction assets foundThe authors state that the analysis scripts (2D–3D alignment pipeline) and the phenotyping data used in the study are included with the publication as supplementary material, accessible via the article DOI. This is a paper-specific, publicly available asset containing the authors' analysis code and data.Dataset · publicThe scripts and the data that were used in the current study are available and added to this publication.Open asset ↗lines:143-180Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Crop diseases significantly reduce agricultural output and are a serious problem, especially in the parts of the world where diagnostic experts are not readily available. Deep learning has recently shown us that it is possible for a computer to identify plant diseases directly from images of the leaves. Nevertheless, to make such solutions available on the web or mobile devices one has to really think about how heavy the calculations will be, how easy the user interface should be, and also the limit on the data used. Here is a paper on a web-based applied deep learning system for disease detection in multiple crops. The system detects disease in eight crops Apple, Banana, Grape, Mango, Cauliflower, Tomato, Potato, and Corn with each crop having several disease classes and healthy samples. Three transfer-learning-based CNN architectures MobileNetV3, EfficientNetB4, and ResNet50 were compared for classification performance on the public datasets collected from PlantVillage, Kaggle, and Mendeley. Considering class-wise accuracy, prediction time, and deployment scenarios, MobileNetV3 was picked as the main model to be integrated into the system. To compensate for the differences in image quality often found in pictures taken by users, an optional super-resolution preprocessing step with Real-ESRGAN is added and quantitatively assessed. Disease prediction with spectral activation maps (Grad-CAM) enhances the model's interpretability by highlighting image areas where the disease is detected. The resulting model is embedded in a multilingual Progressive Web Application (PWA). The platform enables users to submit their crop images and receive predicted disease names and treatment options, which are generated by a Large Language Model (LLM) using structured disease metadata. The research acknowledges dataset bias and limitations in extrapolating from curated datasets to the general real-world setting although it reports very good performance of the method on the test sets. In summary, the system proposed here is intended as a practical digital agriculture decision-support tool that demonstrates deployment feasibility and raises a few issues for future validation at the field level and improvement.
Why it matches plant phenotyping methods葉画像から植物病害を推定するCNN手法の比較・前処理評価・実装を中心とした研究であり、植物の病害状態を直接評価するため、植物フェノタイピング手法として中心的です。
abstractDeep learning has recently shown us that it is possible for a computer to identify plant diseases directly from images of the leaves.
This project introduces a Convolutional Neural Network (CNN) as the proposed system for plant disease prediction, with a comparative analysis conducted against two existing models: Recurrent Neural Networks (RNN_GRU) and Artificial Neural Networks (ANN_MLP). The proposed CNN model is specifically designed to address the limitations of traditional approaches, such as lower accuracy and slower prediction times, particularly when handling complex image data. The system allows users to upload images of plant leaves, select the type of plant (e.g., potato, tomato, grape), and choose between RNN_GRU, ANN_MLP, or the newly developed CNN model for disease prediction. Additionally, users can run all three models simultaneously to compare their outputs, enabling a comprehensive evaluation of performance. Predictions are securely stored in a SQLite database, along with metadata such as confidence scores, prediction times, timestamps, and a unique group ID for efficient retrieval and management. Built using Flask, the application provides a professional-grade user interface with features like secure authentication, prediction history tracking, and deletion of past predictions. Comparative analysis demonstrates that the proposed CNN model significantly outperforms RNN_GRU and ANN_MLP in terms of accuracy, prediction speed, and overall reliability, making it a more effective tool for real-time agricultural applications. This advancement highlights the potential of CNNs in transforming agricultural practices by providing faster, more accurate, and reliable disease predictions, thereby contributing to improved crop health, reduced losses, and increased agricultural productivity.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定するCNN手法を開発し、既存モデルとの精度・速度比較を行っているため、植物フェノタイピング手法が中心である。
abstractThis project introduces a Convolutional Neural Network (CNN) as the proposed system for plant disease prediction
Abstract Current phytopathological diagnostic systems rely on manual inspections or laboratory analyses, which delay early detection and limit in-field responsiveness. Phytopathogenic fungal diseases pose a persistent threat to food security, directly affecting the productivity of essential crops such as potato ( Solanum tuberosum ) and tomato ( Solanum lycopersicum ) [1]–[5]. Among these diseases, Phytophthora infestans , the causal agent of late blight, is characterized by its high virulence and rapid spread, capable of generating significant losses in short periods when detection occurs too late [3], [4]. To address this issue, a computer vision and deep learning–based system for multistage detection of fungal infections in potato and tomato crops is proposed. The system comprises a convolutional neural network optimized for edge processing and a mobile robotic platform equipped with a manipulator arm for localized treatment application. The developed model was deployed on a Raspberry Pi 4 connected to a 12-MP Raspberry Pi Camera Module 3 NoIR, responsible for acquiring RGB images in the field. The proposed network was compared with reference architectures—ResNet-50, VGG16, MobileNetV2, and Inception-v3—within a four-stage detection pipeline: crop identification, health-state classification, infection diagnosis, and foliar severity estimation. A dataset of 18,200 images obtained from publicly accessible online sources, under diverse lighting and background conditions, was used, partitioned into 70% for training, 20% for validation, and 10% for testing. Preliminary results show an average accuracy in the range of 0.90–0.92, with inference latencies below 60 ms per image, ensuring smooth performance on the Raspberry Pi 4 without requiring cloud connectivity. Additionally, the network demonstrated higher sensitivity to visual variations compared to the baseline models.
Why it matches plant phenotyping methods植物病害の健康状態・感染・葉面重症度を画像から推定するコンピュータビジョン手法を開発・比較検証しており、植物表現型取得が中心である。
abstracta computer vision and deep learning–based system for multistage detection of fungal infections in potato and tomato crops is proposed
Reproduction assets foundThe paper's CNN training data are two publicly available third-party plant-disease image datasets (Mendeley Data and Kaggle Plant Village) with explicit URLs in the Data Availability Statement. The authors' field-test images and experimental records are only available on request, and no analysis code or trained model/сDataset · public10
Network, DOI: 10.17632/tywbtsjrjv.1, available at
https://data.mendeley.com/datasets/tywbtsjrjv/1, and the
Kaggle Plant Village dataset, available at
https://www.kaggle.com/datasets/emmarex/plantdisease.The field-test images and experimental records generated during
the current study during the real-world evaluation of the
embedded-vision system are available from the corresponding
author on reasonable request.
IX. REFERENCOpen asset ↗10.17632/tywbtsjrjv.1pdf-raw-page:11 lines:1-98Dataset · public10
Network, DOI: 10.17632/tywbtsjrjv.1, available at
https://data.mendeley.com/datasets/tywbtsjrjv/1, and the
Kaggle Plant Village dataset, available at
https://www.kaggle.com/datasets/emmarex/plantdisease.The field-test images and experimental records generated during
the current study during the real-world evaluation of the
embedded-vision system are available from the corresponding
author on reasonable request.
IX. REFERENCES
[1] P. W. Crous, A. Y. Rossman, M. C. Aime, W. C. Allen, T.
Burgess, J. Z. Groenewald y L. A. CastlebuOpen asset ↗Kagglepdf-raw-page:11 lines:1-98Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Abstract Monitoring spatial variations in plant growth and forecasting yield before harvest provides valuable insights for optimizing agronomic decision‐making in potato ( Solanum tuberosum L.) cultivation. Although unmanned aerial vehicle (UAV)‐based remote sensing has recently enabled the development of tuber fresh weight (TW) estimation models, their integration into practical yield‐forecasting systems remains limited. In this study, we developed machine learning models to estimate tuber weights at multiple preharvest time points using RGB and multispectral UAV imagery. Image‐derived features were extracted from the orthomosaic and digital surface model images for each plot, and a random forest regression model was trained for TW estimation. The estimated values were subsequently used to fit the Gompertz growth curves, which were then used to forecast the yield at the expected harvest time. The correlation between the estimated and observed values was strong in the UAV‐based TW estimation, with correlation coefficients exceeding 0.8 and coefficients of determination ( R 2 ) above 0.6 at all time points. Yield forecasts based on fitted growth curves achieved a correlation of 0.78 and an R 2 of −0.17 in 2023 and 0.70 and an R 2 of 0.47 in 2024. These results demonstrate that UAV‐based sampling combined with machine learning is a feasible approach for monitoring spatiotemporal variations in tuber growth and forecasting potato yield at the plot level prior to harvest.
Why it matches plant phenotyping methodsUAV画像からジャガイモ塊茎重量を推定し、機械学習と成長曲線で収量を予測する手法が研究の中心であり、推定精度も検証している。
abstractwe developed machine learning models to estimate tuber weights at multiple preharvest time points using RGB and multispectral UAV imagery.
An effective framework based on deep learning (DL) is developed in this study for reliable and accurate performance. The multi-class detection of crops such as corn, tomato and potato is accurate and reliable. The aim is to improve early disease detection which guarantees good classification accuracy, strong generalization across datasets, enhanced interpretability through XAI methods and enabling realistic agricultural applications. : The study uses two large publicly available datasets of plant leaf disease images of corn, tomato and potato. The first dataset designated as D-I consists of 39,203 images belonging to 18 classes of disease and the second dataset designated as D-II consists of 65,565 images also belonging to 18 classes of disease. The two datasets contain images showing different visual scenarios and variations of disease which will help form a multi-class classifier. In this study, five DL architectures were used; InceptionNetV3, ResNet152V2, ViT, BERT, and the proposed hybrid model (ResViT-152) that combined convolutional feature extraction with transformer-based global attention. Every model was trained, validated, and tested under the same experimental setup. Cross validation and multi-phase testing assessed their performances in their capacity to learn discriminative parameters in corn, tomato and potato disease classes. The hybrid model exhibited a better performance in all test conditions. In IntraTest1, the accuracies were 99.12%, 98.94% and 99.06% for corn, tomato and potato respectively. In IntraTest2, the model achieves accuracy of 99.23% for corn, 98.97% for tomato, and 98.98% for potato on D-II. The precise percentages for the cross-tests were 96.27% (corn), 95.14% (tomato), 95.06% (potato) for CrossTest1 and 95.77% (corn), 96.22% (tomato), 96.15% (potato) for CrossTest2. The performance across datasets for all three crops is good and generalization is robust. A study is conducted on an efficient, high-performing, and interpretable DL framework for plant leaf disease detection. The experimental results verify that the proposed work provides superior performance. Generalization outperforms standard architectures in effectiveness. In addition, there is also stable performance with varying datasets. With Explainability included, the model becomes more transparent and a strong candidate for further validation toward deployment in precision agriculture, pending evaluation on real-world field datasets.
Why it matches plant phenotyping methods植物葉の画像から病害状態を分類・検出する深層学習手法の開発と、複数データセットでの交差検証・比較評価が中心であり、植物フェノタイピング手法に該当する。
abstractA study is conducted on an efficient, high-performing, and interpretable DL framework for plant leaf disease detection.
Plant diseases are a major problem for farmers around the world, reducing crop yields. The absence of expertise makes plant disease detection difficult and complicated. Plant disease detection is made easier by deep learning algorithms; however, they are computationally demanding and need huge training datasets. This research work proposes a novel Conv-7 DCNN model with modified ParNet attention layer to classify plant leaves into distinct categories with improved accuracy. Because of its architecture, the proposed network can identify leaf diseases with more accuracy by extracting the wider range of features from the images. The proposed Conv-7 DCNN model classifies the leaf diseases of three plants such as tomato, potato, and pepper-bell into fifteen categories. The CNN model is trained using publicly accessible Kaggle dataset, utilising image augmentation techniques. It is evident from the simulation results that the proposed model outperforms several pre-trained, and other trending deep learning models. Proposed model achieves 99.18% classification accuracy with an average precision of 99.17% and area under the curve (AUC) of 1, making this model highly effective in leaf diseases detection. Additionally, Conv-7 DCNN achieved high FPS of 112.49, low inference time of 18.34 s, and low GFLOPS of 13.98, making it suitable for real-time applications in smart agriculture systems.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習モデルを開発・比較しており、病害表現型の取得・分類手法が研究の中心である。
abstractThis research work proposes a novel Conv-7 DCNN model with modified ParNet attention layer to classify plant leaves into distinct categories with improved accuracy.
Reproduction assets foundThe paper's plant-phenotyping measurements (leaf disease classification of tomato, potato, and pepper-bell) are based on a publicly available Kaggle dataset explicitly named in the Data Availability statement. No author analysis code, trained model checkpoints, or other paper-specific assets are disclosed.Dataset · publicThe dataset is available online at https://www.kaggle.com/datasets/emmarex/plantdisease.Open asset ↗Kaggle · emmarex/plantdiseasehtml-lines:824-854Plant phenotyping relevance match · UnverifiedEurope PMC · bioRxiv · checked 5 Sept 2026
Potato ( Solanum tuberosum L.) is a staple crop crucial to global food security, yet its production is severely threatened by late blight (LB), caused by Phytophthora infestans , one of the most destructive plant diseases worldwide. Breeding programs for LB resistance have traditionally relied on labor-intensive and subjective visual assessments, which limit scalability and consistency, particularly in early-generation trials. Unmanned aerial vehicle (UAV)-based remote sensing combined with machine learning (ML) offers a promising alternative for objective, high-throughput disease phenotyping. This study evaluated the potential of UAV-derived multispectral imagery and ML techniques to estimate LB severity across large and genetically diverse potato breeding populations, comprising 2,745 clones in one trial and 492 accessions in another, conducted in Oxapampa, Pasco, Peru. We compared vegetation index–based approaches with a machine learning framework that integrates K-means clustering and Kernel Ridge Regression (KRR) and assessed their ability to capture genotypic variation and support selection decisions. NDVI consistently showed a strong correlation with visually assessed LB severity, particularly at advanced stages of disease development, enabling objective discrimination between healthy and diseased canopy tissues. However, the KRR-based approach outperformed linear NDVI-based models by capturing nonlinear relationships between spectral responses and disease progression. Estimates of LB severity derived from NDVI and KRR models, expressed as best linear unbiased estimates (BLUEs), showed strong and biologically consistent relationships with the area under the disease progress curve (AUDPC), particularly during later UAV acquisitions. Selection coincidence between UAV-derived estimates and AUDPC-based rankings was substantially higher at intermediate to advanced stages of disease progression, suggesting that UAV assessments at these stages may capture sufficient phenotypic variation to distinguish genotypes. These findings indicate that UAV-based multispectral phenotyping, especially when integrated with ML, provides a practical and scalable approach for assessing LB severity in potato breeding programs while reducing the need for time-consuming field evaluations.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像と機械学習により、ジャガイモの疫病重症度を推定する表現型取得・解析手法を評価しており、方法が研究の中心である。
abstractThis study evaluated the potential of UAV-derived multispectral imagery and ML techniques to estimate LB severity across large and genetically diverse potato breeding populations
Abstract Common scab in potato is caused by multiple Streptomyces species that harbour various virulence factors. Varietal resistance is commonly evaluated with multi-year – multi-location field trials with known high infection potential or using the phytotoxin thaxtomin applied to in vitro mini tubers or potato tissue culture. In this study, we aimed to develop an efficient root inoculation assay to assess the resistance levels of potato genotypes and to evaluate whether the assay could identify resistant and susceptible genotypes, thus facilitating selection of scab resistant clones. We isolated 24 potential Streptomyces strains from fields in Ireland, of which 11 were identified as S. europaescabiei . All S. europaescabiei strains tested positive for txtAB gene but lacked n ec1 and t omA genes. The root inoculation assay resulted in plants exhibiting necrotic symptoms on roots and stunted root growth. Image analysis software was used to collect quantitative data from our assay. We observed a Spearman’s rank correlation of 0.61 between field data and our assay using a panel comprising 50 clones from the bi-parental cross Electra × Désirée and five control varieties. The root inoculation assay is rapid, as symptoms are observed within 6 to 10 days post-inoculation, and requires minimal manipulation since a bacterial suspension is applied instead of purified thaxtomin. Notably, this assay identifies resistant and susceptible progeny reliably, with some disparities between the resistance pattern in the field and the assay. This tool has potential to be useful for screening large numbers of genotypes and discarding the susceptible ones in a breeding program.
Why it matches plant phenotyping methodsジャガイモ根の壊死症状と生育阻害を定量化する根部接種アッセイを開発し、画像解析で表現型を取得、圃場データとの相関で検証しているため、フェノタイピング手法が中心です。
abstractIn this study, we aimed to develop an efficient root inoculation assay to assess the resistance levels of potato genotypes and to evaluate whether the assay could identify resistant and susceptible genotypes
Vulnerability of potato crops to diseases and pest infestation can affect its quality and lead to significant yield losses. Timely detection of such diseases can help take effective decisions. For this purpose, a deep learning-based object detection framework is designed in this study to identify and classify major potato diseases and pests under real-world field conditions. A total of 2,688 field images were collected from two research farms in Punjab, Pakistan, across multiple growth stages in various seasonal conditions. Excluding 285 symptoms-free images from the earliest collection led to 2,403 images which were annotated into four biotic-stress classes: blight disease (n = 630), leaf spot disease (n = 370), leafroll virus (viral symptom complex; n = 888), and Colorado potato beetle (larvae/adults; n = 515), indicating class imbalance. Several state-of-the-art models were used including YOLOv8 variants (n/s/m), YOLOv7, YOLOv5, and Faster R-CNN, and the results are discussed in relation to recent potato disease classification studies involving cropped leaf images. Stratified splitting (70% training, 20% validation, 10% testing) was applied to preserve class distribution across all subsets. YOLOv8-medium achieve the best performance with mean average precision (mAP)@0.5 of 98% on the held-out test images. Results for stable 5-fold cross-validation show a mean mAP@0.5 of 97.8%, which offers a balance between accuracy and inference time. Model robustness was evaluated using 5-fold cross-validation and repeated training with different random seeds, showing a low variance of ±0.4% mAP. Results demonstrate promising outcomes under the real-world field conditions, while, broader cross-region and cross-season validation is intended for the future.
Why it matches plant phenotyping methodsジャガイモ葉の病害症状を圃場画像から検出・分類する深層学習法を開発し、複数モデル比較、交差検証、頑健性評価まで実施しており、植物の病害状態推定が中心的な方法論的貢献である。
abstracta deep learning-based object detection framework is designed in this study to identify and classify major potato diseases and pests under real-world field conditions.
Potato crops are essential to worldwide food safety; however, their cultivation is progressively imperiled by illnesses like early blight and late blight, which lead to significant yield deficiencies. Early identification is indispensable to mitigate these deficiencies, yet conventional strategies are gradual and ineffective, usually missing infections before they become apparent. To address this, we unveil PotatoNet-X, an ingenious hybrid deep learning design that combines Residual Networks (ResNet), DenseNet, and Consideration Mechanisms for precise and effective potato leaf sickness identification. PotatoNet-X leverages these advanced architectures to boost characteristic extraction, improve model generalization, and focus attention on disease-relevant regions of the leaf. The model is prepared and assessed on two freely accessible datasets: PlantVillage and Potato Illness Categorization Dataset (PDCD). PotatoNet-X achieves 98.5% precision and 99% accuracy on the PlantVillage dataset, and 97.79% precision and 98.13% accuracy on the more difficult PDCD dataset. Additionally, the design parses each photo in just 0.045 s, making it perfect for real-time uses in the field. To ensure interpretability, Grad-CAM visualizations are utilized to underscore the areas of the leaf that contribute to illness identification. PotatoNet-X provides a scalable, dependable, and interpretable resolution for early sickness detection in precision agriculture, enabling improved disease management and crop security.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から判定する深層学習手法を開発・評価しており、植物フェノタイピング手法が中心である。
titleEarly Detection of Potato Leaf Diseases with PotatoNet-X: A Deep Learning Model Combining ResNet, DenseNet, and Attention Mechanisms
Accurate recognition of potato leaf diseases plays an essential role in precision agriculture and crop protection. Traditional convolutional neural networks achieve promising results but mainly rely on texture and colour cues, neglecting lesion geometry and morphological evolution. This paper introduces a morphology-aware convolution (MAC) framework that embeds learnable morphological operations into deep feature extraction. The learnable morphological kernel adaptively performs differentiable dilation and erosion to capture lesion boundaries, while the structure-guided fusion module integrates structural and textural cues through adaptive weighting. Experiments on the PlantVillage-Potato dataset demonstrate that MAC achieves higher accuracy and robustness than existing convolutional and attention-based architectures with minimal parameter overhead. The method effectively enhances lesion boundary perception and shape consistency, offering improved interpretability and generalisation. These findings suggest that embedding morphological priors into neural networks provides a principled and efficient approach for fine-grained plant disease recognition and other structure-aware visual analysis tasks.
Why it matches plant phenotyping methods植物葉の病徴・病斑形状を画像から認識する新規深層学習手法を開発し、既存手法と精度・頑健性を比較検証しているため、植物フェノタイピング手法が中心です。
abstractThis paper introduces a morphology-aware convolution (MAC) framework that embeds learnable morphological operations into deep feature extraction.
Crop disease detection is critical for agricultural productivity and global food security. Traditional methods rely on labour-intensive field surveys prone to human error. This paper presents an image-based crop disease detection system using a hybrid Convolutional Neural Network (CNN) augmented with pre-trained AlexNet weights. The system captures leaf images, applies preprocessing (resizing, normalization, augmentation), and classifies diseases with high accuracy. A Flask-based web application enables real-time prediction accessible to farmers via smartphone. Trained on 2,000 field-collected images across potato, pepper, and tomato crops, the proposed model achieves approximately 97% classification accuracy, outperforming standalone classifiers including SVM, Logistic Regression, Decision Tree, and Naïve Bayes
Why it matches plant phenotyping methods葉画像から植物病害を推定する画像ベース手法の開発・比較検証が研究の中心であり、植物の病害状態を直接評価しているため。
abstractThis paper presents an image-based crop disease detection system using a hybrid Convolutional Neural Network (CNN) augmented with pre-trained AlexNet weights.
This paper investigates the performance of YOLOv8 classification models: YOLOv8n, YOLOv8s, and YOLOv8m for potato leaf disease classification. Two datasets were used: the Plant-Village (Potato) dataset collected under controlled environmental conditions and the Potato Leaf Disease Dataset captured under uncontrolled field conditions. The models were evaluated independently on each dataset and subsequently on a combined dataset to assess their robustness and generalization. The experimental results demonstrate strong classification performance across all datasets, with test accuracies of 90% on the Potato Leaf Disease Dataset collected under uncontrolled environmental conditions and 96% on the combined dataset. Compared with other models in the literature, including EfficientNetV2B3, MobileNetV3-Large, VGG-16, ResNet50, and DenseNet121, the YOLOv8n model achieved the best performance on the uncontrolled dataset, attaining 90% accuracy, 92% precision, 88% recall, and an F1-score of 90% on the uncontrolled dataset. On the combined dataset, YOLOv8m achieved 96% accuracy, 96% precision, 94% recall, and F1-score of 95%, demonstrating strong generalization and robustness under diverse imaging conditions.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類するYOLOv8手法を中心に、複数データセットで性能・頑健性・汎化性を評価しているため、植物病害フェノタイピング手法に該当する。
abstractThis paper investigates the performance of YOLOv8 classification models: YOLOv8n, YOLOv8s, and YOLOv8m for potato leaf disease classification.
Phosphorus is essential for potato cultivation; however, its low natural availability and high fixation in the soil require efficient management strategies. In this context, rapid and non-destructive methods for estimating foliar phosphorus content are important to reduce waste and improve production efficiency. This study evaluated the use of multispectral images acquired by a Survey 3 (MAPIR) camera to estimate foliar phosphorus content in potato crops at the tuberization stage, when topdressing fertilization is typically applied. To generate variability in foliar phosphorus levels, an experiment was conducted under greenhouse conditions using a randomized complete block design with eight P₂O₅ rates (0, 50, 100, 200, 400, 800, 1,600, and 3,200 kg ha⁻¹) and 40 replications. Spectral indices (NDVI, GNDVI, and GRVI) were analyzed, and regression models and machine learning algorithms (Random Forest, Multilayer Perceptron, and SMOreg) were applied to predict foliar phosphorus content. NDVI showed a significant inverse correlation with phosphorus content, attributed to the nutritional dilution effect. Among the evaluated methods, Random Forest showed the best performance, with a relative root mean square error of 19.01%. The results demonstrate that the integration of multispectral variables and machine learning techniques increases diagnostic accuracy, highlighting the potential of these technologies for nutritional monitoring of potato crops in precision agriculture.
Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習により、ジャガイモ葉のリン含量という植物生理形質を非破壊推定する手法が研究の中心である。
abstractrapid and non-destructive methods for estimating foliar phosphorus content are important
Potato disease recognition has emerged as a high-impact application of deep learning in precision agriculture. However, existing datasets exhibit severe class imbalance, which adversely affects the generalization ability of standard classifiers. To address this challenge, we introduce a conditional GAN named FFRA-CGAN (Frequency-aware and Focal Residual-Attention CGAN), along with a two-stage training strategy tailored to potato pathology. In the first stage, the conditional generator, augmented with residual connections and self-attention, produces structurally faithful potato leaf images. The training process is guided by Focal Frequency Loss (FFL), which enforces frequency-domain alignment to retain vein topology and lesion morphology. In the second stage, the discriminator pretrained on a balanced mix of real and frequency-aligned synthetic images is reused as an independent classifier, thereby eliminating the need for explicit resampling or augmentation. Extensive experiments on the PlantVillage potato dataset demonstrate that FFRA-CGAN achieves state-of-the-art accuracy, significantly improving recognition of the underrepresented healthy class. This study demonstrates that integrating frequency-aligned image generation with discriminator reuse provides a robust and generalizable solution to long-tailed recognition challenges in agricultural disease detection, supporting improved decision-making in crop management.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から認識する生成・分類手法を開発し、植物病害フェノタイピングを中心に評価している。
titleFrequency-Aware and Residual-Attention CGAN with Two-Stage Training for Imbalanced Potato Leaf Disease Detection in Crop Management
Abstract The precise classification of plant diseases is crucial for ensuring food security for all people and boosting agricultural productivity. Although there has been significant progress in this field using deep learning approaches, cross-dataset training hasn’t drawn as much attention from researchers as intra-dataset training has. Moreover, very few models have successfully blended intra-dataset and cross-dataset training approaches. This paper proposes a novel attention-based Convolutional Neural Network (CNN) to overcome these limitations. The model improves feature extraction and classification accuracy across multiple datasets by using attention mechanisms. It was tested on five datasets (Digipathos, Northern Leaf Blight (NLB), PlantVillage, PlantDoc, and the CD&S dataset) that covered leaf diseases of both corn and potatoes. During intra-dataset training, the model achieved the highest classification accuracy of 99.38% when trained on images of potato leaves from the PlantVillage dataset. During cross-dataset training, the model exhibited the highest average classification accuracy of 82.93% for corn leaf diseases when trained on images from the CD&S dataset with their backgrounds removed. When compared to the techniques taken into consideration in this study under comparable experimental conditions, the results demonstrate improved performance. This study shows how the model may be flexible for both intra- and cross-datasets, offering a flexible way to categorize diseases that affect plants. Because of its ability to generalize across different datasets, it may be helpful in real-world agricultural applications with a wide variety of image quality and situations. This encourages the advancement of precision farming techniques and disease control.
Why it matches plant phenotyping methods植物葉の画像から病害状態を分類するCNN手法の開発・データセット間検証が中心であり、植物病害の表現型推定に該当する。
abstractThis paper proposes a novel attention-based Convolutional Neural Network (CNN) to overcome these limitations.
Reproduction assets foundThe paper's plant disease classification experiments rely on five publicly available leaf-image datasets, each cited with an explicit public access URL in the reference list: PlantVillage (GitHub), PlantDoc (GitHub), Digipathos (Embrapa), NLB (SciDB), and CD&S (OSF). No author analysis code or trained model checkpoint,Dataset · publicHughes, D., & Salathé, M. (2015). An open access repository of images on plant health to enable the development of mobile disease diagnostics. arXiv preprint arXiv:1511.08060. Dataset accessed via GitHub: https://github.com/spMohanty/PlantVillage-DatasetOpen asset ↗GitHub · spMohanty/PlantVillage-Datasethtml-lines:1013-1082Dataset · publicDataset available at: https://github.com/pratikkayal/PlantDoc-DatasetOpen asset ↗GitHub · pratikkayal/PlantDoc-Datasethtml-lines:979-1012Dataset · publicCD&S dataset: Handheld imagery dataset acquired under field conditions for corn disease identification and severity estimation. arXiv preprint arXiv:2110.12084. Dataset available at: https://osf.io/s6ru5/files/osfstorageOpen asset ↗OSF · s6ru5html-lines:1013-1082Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
MaizePotatoSoybeanLeafClassificationObject detectionCalibration / preprocessingSegmentationStress / disease detectionVisualization / data management
Background: Plant diseases significantly reduce global crop productivity, creating an urgent demand for intelligent, automated diagnostic systems in agriculture. Traditional manual inspection is labor-intensive, subjective and often ineffective in detecting early or latent symptoms. This study presents a multi-class classification and severity estimation framework for ten plant disease categories: Maize brown spot, maize rust, maize healthy, potato early blight (Alternaria solani), potato late blight (Phytophthora infestans), potato healthy, soybean mosaic virus (SMV), soybean pod mottle virus (SPMV), soybean sudden death syndrome (SDS/SBS) and soybean healthy. The objective is to develop a robust hybrid deep learning model capable of accurate early detection and quantitative severity assessment to support precision agriculture. Methods: A hybrid architecture combining convolutional neural networks (CNN) with LSTM and BiLSTM networks was implemented. The preprocessing pipeline included leaf segmentation, binary masking, defect localization and edge detection to enhance lesion visibility. CNN layers extracted spatial and textural features, while recurrent layers modeled contextual dependencies within feature representations. Performance was evaluated using Precision, Recall, F1-score, defect percentage estimation, convergence analysis and t-SNE visualization. Result: Results demonstrated stable convergence with decreasing loss (0.8-1.2) and improved feature clustering. Defect severity ranged from 0.00% (Soybean healthy) to 87.93% (Maize brown spot). The framework enables early detection (0.29-5% infection), reduces yield loss, minimizes chemical overuse and promotes sustainable smart agriculture systems.
Why it matches plant phenotyping methodsCNN-LSTM/BiLSTMによる葉画像からの病害検出と病徴重症度推定手法の開発が中心であり、植物状態を直接推定している。
abstractThis study presents a multi-class classification and severity estimation framework for ten plant disease categories
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · Crossref · checked 5 Sept 2026
Abstract Fitness costs of plant disease defence are often subtle and difficult to quantify. In this study, we therefore used comparative high-throughput phenotyping in two independent facilities to assess growth, morphology and physiology of potato (cv. Désirée) with high time-resolution monitoring different defence mechanisms under pathogen-free conditions. Plants were either treated weekly with the resistance inducers β-aminobutyric acid (BABA; 10 mM) or potassium phosphite (KPhi; 36 mM) or comprised six transgenic lines expressing late blight resistance genes (single Rpi genes or a three-gene stack) or reduced jasmonate perception (StCOI1-RNAi). Over four weeks, image-derived traits revealed consistent cross-facility effects for plant height and colour: BABA treatment increased plant height but reduced canopy area and induced a paler greenness signature, whereas KPhi caused minimal and transient growth effects. Chlorophyll fluorescence at the NaPPI facility indicated reduced vitality (Rfd_Lss) in BABA-treated plants and increased Rfd_Lss following KPhi, while maximum PSII efficiency was largely unchanged. Several transgenic lines showed somewhat reduced above-ground biomass. Enzyme activity profiling produced distinct treatment and genotype signatures, but was strongly modulated by facility conditions that overrode these specificities. Overall, high-throughput phenotyping robustly detected subtle growth–defence trade-offs across platforms. Highlight High-throughput optical phenotyping validated across two independent research facilities reveals that stacked resistance genes and resistance inducers in potato trigger subtle growth trade-offs. Graphical abstracts Experimental timeline for high-throughput plant phenotyping platforms. Created in BioRender. Poque, S. (2026) https://BioRender.com/nmkve7g
Why it matches plant phenotyping methods二つの独立施設で高スループット光学フェノタイピングを比較・検証し、画像由来形質と蛍光指標の再現性を評価しており、フェノタイピング手法が研究の中心である。
titleComparative high-throughput phenotyping across two facilities reveals differential impact of defence mechanisms on plant growth and development
Smart irrigation management is essential for improving crop resilience under increasing drought frequency driven by climate change. Although satellite-based remote sensing provides valuable tools for monitoring crop water status at large spatial scales, its accuracy is often limited in mountainous and heterogeneous agricultural landscapes. In this study, we investigated drought-induced metabolic responses in potato ( Solanum tuberosum L.) to identify biochemical biomarkers that could complement satellite-based irrigation advisories in the mid-Himalayan region of India. A field experiment was conducted using a gradient of soil moisture regimes corresponding to moderate (50% field capacity), critical (25% field capacity), and extreme drought stress (5-8% field capacity). Satellite-derived evapotranspiration-based irrigation advisories were validated against in situ soil moisture measurements, revealing discrepancies attributed to the inability of satellite estimates to capture actual water loss under drought stress conditions, highlighting the need for additional ground-truth biomarkers across heterogeneous field conditions. To capture plant-level physiological responses, untargeted metabolite profiling of potato leaves was performed using gas chromatography–mass spectrometry (GC-MS). Approximately fifty metabolites belonging to amino acids, organic acids, sugars, and sugar alcohols were detected. Multivariate statistical analyses revealed distinct metabolic signatures associated with progressive drought stress. Notably, accumulation of proline, serine, isoleucine, sucrose, fructose, glucose, and polyols such as mannitol and myo-inositol reflected key metabolic reprogramming associated with osmoprotection, redox homeostasis, and energy metabolism under drought conditions. Collectively, this ensemble of stress-responsive metabolites represents a robust panel of drought stress biomarkers. As a proof of concept, proline was validated as a qualitative biomarker of plant water status through a rapid and cost-effective colorimetric biochemical assay, demonstrating its practical applicability for field-level irrigation management. These findings demonstrate that metabolomics-derived biomarkers can provide sensitive plant-level indicators of drought stress that complement satellite-based monitoring systems. The integration of biochemical diagnostics with remote sensing platforms offers a promising approach for improving drought detection and developing low-cost, field-deployable tools for smart irrigation advisories in heterogeneous agricultural landscapes. Graphical abstract
Why it matches plant phenotyping methods植物の水分状態・乾燥ストレスを示す代謝バイオマーカーを開発・検証し、迅速な比色 assay として実用化可能性を評価しており、単なる乾燥処理実験の routine 測定を超えて表現型取得法が中心的です。
abstractAs a proof of concept, proline was validated as a qualitative biomarker of plant water status through a rapid and cost-effective colorimetric biochemical assay, demonstrating its practical applicability for field-level irrigation management.
ABSTRACT Potato common scab ( Streptomyces sp.) is an economically important disease that reduces the quality and market value of tubers. A key aspect in developing management strategies involves accurately quantifying the disease. Due to the three-dimensional nature of the tuber and the heterogeneous distribution of lesions across its surface, visual estimates of severity can be challenging. Therefore, the objectives of this study were to develop and validate a standard area diagram (SAD) for estimating common scab severity on potato tubers and to compare validation outcomes obtained using real tubers and digital images. A SAD comprising six severity levels (from 1.3 to 66.8%) was developed based on image analysis of naturally infected tubers. Validation was conducted using two complementary approaches in which inexperienced raters evaluated either real potato tubers or digital images of the same tubers under unaided and aided conditions. Accuracy, bias components, and inter-rater reliability were quantified using absolute error metrics, Lin’s concordance correlation coefficient, intraclass correlation coefficients, and overall concordance correlation coefficients. Use of the SAD significantly improved accuracy, reduced systematic bias, and increased inter-rater reliability across both validation approaches. No significant differences were detected between assessments conducted on real tubers and images, although image-based evaluations showed a slight, non-significant tendency toward reduced scale and location bias under aided conditions. These results demonstrate that a dimension-aware SAD integrating information across the full tuber surface enhances the reliability and reproducibility of visual severity assessments and supports the use of image-based evaluations for training, large-scale surveys, and remote or collaborative applications involving three-dimensional plant organs.
Why it matches plant phenotyping methodsジャガイモ塊茎の病徴重症度を定量化する標準面積図を開発・検証し、画像評価と実物評価の性能を比較しているため、植物フェノタイピング手法が研究の中心である。
abstractThese results demonstrate that a dimension-aware SAD integrating information across the full tuber surface enhances the reliability and reproducibility of visual severity assessments and supports the use of image-based evaluations
Background: Automated monitoring of crop health and the precise detection of abiotic stress, such as herbicide damage, are demanding challenges for modern agriculture. Abiotic stresses are a demanding challenge for modern agriculture, responsible for up to 82% of yield losses in major food crops. To address this, researchers are increasingly leveraging artificial intelligence (AI) to automate the detection and management of these stressors. Methods: In particular, this paper presents an instance segmentation framework to precisely detect interveinal chlorosis and leaf curling on potato leaves, two common symptoms of herbicide damage and soft wind. Within the context of precision agriculture and the need to address the inherent ambiguity in manual leaf assessment, this study employs a partial label learning approach to refine the dataset. This method utilizes an EfficientNet-b1 model to classify ambiguous samples, generating high-confidence pseudo-labels for instances that are difficult to categorize visually. The core of the proposed framework is a Mask2Former model, which is first fine-tuned on general potato leaf dataset to enhance its segmentation capabilities and then transferred on the refined, pseudo-labeled dataset. Results & Conclusions: This two-stage approach yields a highly accurate segmentation tool, achieving 89% mAP50 and a pseudo-label classification accuracy of 95%, designed for integration into smart agriculture systems like ground level robotics or unmanned aerial vehicles for real-time, automated crop monitoring.
Why it matches plant phenotyping methodsジャガイモ葉の症状（葉間クロロシスと葉巻）をインスタンスセグメンテーションで直接抽出する画像ベースの表現型測定法を開発・評価しており、手法が中心である。
abstractthis paper presents an instance segmentation framework to precisely detect interveinal chlorosis and leaf curling on potato leaves
Pest and pathogen pressure in potato cultivation is increasingly affecting the potato quality and yield. The Netherlands, as the largest seed potato producer around the world, is particularly threatened by blackleg disease and potato virus Y (PVY). Uncrewed aerial vehicle (UAV)-based imaging combined with machine- and deep-learning methods have shown clear potential for potato disease identification, offering advantages over conventional human inspections, which are labor-intensive, expertise-demanding, and often subjective. Most existing studies focused on RGB data and pixel-level classification, producing maps that have limited practical value for targeted removal of infected plants. Earlier work demonstrated the potential of plant-level disease detection approaches. For example, Jia[1] employed hyperspectral data (specifically the first three principal component analysis (PCA) bands) with a YOLOv5s model to distinguish the blackleg- and PVY-infected plants from healthy ones, yielding average mAP@.50 scores of 0.85 for blackleg detection and 0.82 for PVY detection. Gibson-Poole[2] applied object-based image analysis (OBIA) to detect blackleg disease with RGB imagery, achieving a total accuracy of 87%. The findings suggest that multi-modal data (combining hyperspectral and RGB imagery) hold strong potential for plant-level disease detection. We aim to identify the most informative features derived from hyperspectral data and to investigate their integration with RGB data to enhance potato disease detection performance.We proposed early fusion (E), where data were concatenated channel-wise before network input, and middle fusion (M) architectures, where features were extracted separately within a two-branch network and then merged at an intermediate stage, to integrate hyperspectral features and RGB imagery for potato disease detection. To reduce hyperspectral dimensionality, two feature sets were extracted: (i) the first three PCA bands, and (ii) 10 vegetation indices (VIs) selected from 64 candidates using variance inflation factor analysis to mitigate multicollinearity. Consequently, four models were developed and evaluated: E-PCA-RGB, E-VI-RGB, M-PCA-RGB, and M-VI-RGB. Unlike previous studies that focused on a single disease, our models detected blackleg-infected, PVY-infected, and healthy plants simultaneously. E-VI-RGB achieved the highest mAP@.50 value of 86.65±1.53, followed by M-VI-RGB (85.74±1.75). E-PCA-RGB and M-PCA-RGB yielded mAP@.50 scores of 83.00±2.52 and 83.11±2.20, respectively. These results demonstrate that combining hyperspectral features with RGB imagery improves detection performance compared with single-modality approaches (RGB 83.21±1.31, PCA 79.71±1.30, VIs 85.31±2.11). Our findings highlight the potential of multimodal fusion for potato disease detection in practice. The methods could enable automated systems not only to identify infected plants but also to support timely removal with machinery, mitigating the spread of disease in potato fields. The generalizability of our approach will be further tested and analyzed in future work.References[1] Jia, T., Smigaj, M., Kootstra, G. and Kooistra, L., 2024. Detection of Diseased Potato Plants with UAV Hyperspectral Imagery. In 2024 14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS) (pp. 1-5). IEEE.[2] Gibson-Poole, S., Humphris, S., Toth, I. and Hamilton, A., 2017. Identification of the onset of disease within a potato crop using a UAV equipped with un-modified and modified commercial off-the-shelf digital cameras. Advances in Animal Biosciences, 8(2), pp.812-816.
Why it matches plant phenotyping methodsUAVのハイパースペクトル・RGB画像からジャガイモ個体の病害状態を推定するマルチモーダル融合手法を開発・評価しており、植物表現型の取得・抽出が研究の中心です。
abstractWe proposed early fusion (E), where data were concatenated channel-wise before network input, and middle fusion (M) architectures, where features were extracted separately within a two-branch network and then merged at an intermediate stage, to integrate hyperspectral features and RGB imagery for potato disease detection.
Precise monitoring of crop canopy cover (CC) is crucial for evaluating growth and health under diverse water and nutrient conditions. Although nano liquid urea has been promoted in India as an eco-friendly alternative to conventional nitrogen (N) fertilizers. Its effectiveness in potato cultivation, particularly for canopy development and yield, remains unclear. To address this gap, a field experiment was conducted during the 2024–25 winter season using three N treatments under a micro-irrigation system: T1-recommended granular urea (46% N), T2-without N, and T3-IFFCO nano liquid urea (4% w/v). Images were captured using a downward-looking smartphone camera positioned 2.5 meters above the crop near each treatment, serving as the primary input for estimating canopy cover. The images were processed using both a prompt-based segmentation model (SAM3) and an image-processing pipeline (Modified Excess Green Index + Otsu thresholding) to estimate CC. The SAM3 occasionally overestimated or failed to detect the potato canopy with the prompt “Green plants, leaves, vegetations, canopy cover”, whereas the image-processing approach consistently provided accurate CC estimates and was therefore used for subsequent analysis. The result revealed that the CC clearly showed differentiation among the treatments after 25 days after sowing (DAS). With this most of the treatment comparisons depict the CC peaking after 45 DAS, where the T1 recorded the highest canopy cover (~71%), indicating a healthy crop, while the pairwise comparisons showed CC values of ~55% (T1–T2), ~66% (T1–T3), ~33% (T2–T2), ~36% (T3–T3), and ~36% (T2–T3), depicting the nitrogen deficit. Similarly, the yield followed the same trend, with T1 producing the highest yield (26.78 t/ha), compared to 10.89 t/ha in T2 and 11.90 t/ha in T3. The results indicate that nano liquid urea does not supply sufficient nitrogen to support optimal potato canopy growth and productivity, resulting almost similar response to the no nitrogen application treatment. Increasing the nitrogen concentration in nano liquid urea formulations may improve their effectiveness. This study provides evidence to guide farmers in selecting appropriate nitrogen fertilizers for potato cultivation. In the future, such fertilizers should be evaluated across different crops to ensure their efficacy and to prevent farmers from adopting products that may not meet crop nutrient requirements.
Why it matches plant phenotyping methodsジャガイモのキャノピー被覆率という植物形質を、SAM3と画像処理パイプラインで推定し、両手法の性能を比較・評価しているため、施肥試験を含むがフェノタイピング手法が中心的です。
titleEvaluating SAM3 and Conventional Image Processing Method for Potato Canopy Cover Estimation as an Indicator of Crop Health
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · checked 5 Sept 2026
Abstract Accurate pre-harvest prediction of crop yield informs variety selection, optimizes management, and accelerates breeding. As potato is the world’s leading non-grain staple, here we evaluate a diverse panel of varieties in a three-year field trial across five European locations. Canopy development and environmental parameters are monitored throughout the growing season using drone-based imaging, in-field sensors and gene expression measurements, while tuber yield and quality traits are quantified at harvest. We show that these data enable the identification of climate-resilient, high-yielding genotypes and support the development of machine learning models that explain over 80% of yield variation in independent test sets. Strikingly, measurements collected within the first two months after planting achieve predictive performance comparable to models trained on full-season data. Model interrogation further shows that over 70% of yield variation can already be predicted based on a simple five-parameter linear equation. Our framework thus demonstrates the potential of integrative field phenotyping and data-driven modeling to improve variety selection across heterogeneous environments.
Why it matches plant phenotyping methodsドローン画像と圃場センサーによる作物表現型取得、および収量予測モデルの開発が研究の中心であり、単なる収量測定ではない。
abstractCanopy development and environmental parameters are monitored throughout the growing season using drone-based imaging, in-field sensors and gene expression measurements
Common beanCucumberMaizePeaPotatoTomatoWheatMultispectral / hyperspectralLeafPhysiological trait estimation
The objective of this study was to assess the predictability of leaf dry matter content across a diverse range of plant species using hyperspectral reflectance data. The dataset encompassed leaves from multiple crops, including potatoes, beans, wheat, maize, peas, tomatoes, basil, and cucumbers, collected under varying growth conditions, cultivation systems, seasonal contexts, and developmental stages. As an initial benchmark, commonly used narrow-band spectral indices and their combinations were evaluated, but they exhibited limited predictive performance for dry matter content. Consequently, several full-spectrum machine learning models were trained and compared to assess their individual predictive ability. Given their complementary strengths, these models were integrated into a stacked ensemble framework to enhance overall accuracy. The resulting ensemble, combining the outputs of multiple base learners through a meta-learner, achieved a coefficient of determination of R2=0.896 on an independent test set, outperforming all individual models. The findings highlight the potential of a multi-model stacking approach to improve the accuracy and robustness of leaf biochemical property estimation from hyperspectral data.
Why it matches plant phenotyping methodsハイパースペクトル反射データから葉乾物含量を推定する機械学習手法を開発・比較・検証しており、植物形質の取得方法が研究の中心である。
abstractassess the predictability of leaf dry matter content across a diverse range of plant species using hyperspectral reflectance data
Solanum tuberosum (potato) is one of the most important global food crops relative to economic opportunities and food security. Potato Virus Y (Potyviridae, PVY), a detrimental plant pathogen propagated by insect vectors, negatively affects tuber yield and quality. This has forced industry stakeholders to adopt many different types of mitigation strategies including pesticide applications, manual field scouting, and potato seed certification programs. Despite these efforts, PVY continues to disrupt industry production regions resulting in significant economic losses due to the lack of robust diagnostic tools. Machine learning algorithms trained on remotely sensed spectral features show promise as a diagnostic tool for many plant diseases including PVY. This study proposes a novel Convolutional Neural Network (CNN) architecture to detect potato plant canopy regions of plants infected with PVY based on unmanned aerial system (UAS) hyperspectral pixel features comprised of bands matching the center wavelengths of nine spectral channels captured by the European Space Agency’s Sentinel 2 multispectral instrument. Accuracy and F1 metrics of 0.815 and 0.766 respectively were achieved on test data collected over multiple growing seasons and locations. Additionally, efforts were made to identify optimal combinations of spectral bands that are most beneficial for the CNN classifier by evaluating every possible combination of the nine spectral wavelengths in groups ranging from 3 to 9 channels. Results show that hyperspectral channels centered on 783 nm, 739 nm, and 560 nm are the most important features for the CNN architecture. Additionally, six hyperspectral features consisting of the three previously mentioned along with 665 nm, 704 nm, and 864 nm yielded the best results of all possible combinations achieving accuracy and F1 Score metrics of 0.833 and 0.791 respectively.
Why it matches plant phenotyping methodsCNNとUASハイパースペクトル画像を用いて、PVY感染植物のキャノピー状態を検出する手法を開発・評価しており、植物病害表現型の取得が中心である。
abstractThis study proposes a novel Convolutional Neural Network (CNN) architecture to detect potato plant canopy regions of plants infected with PVY based on unmanned aerial system (UAS) hyperspectral pixel features
Abstract Solanum tuberosum L. (potato) is the world's most important vegetable crop, and developing improved cultivars is paramount for global food security. The efficacy of the genomic prediction models that accelerate breeding and genome‐wide association studies (GWAS) depends on large, high‐quality phenotypic datasets, which are often associated with inhibitory large costs for manual phenotyping. Recent advances in drone‐based phenotyping offer an affordable, high‐throughput phenotyping approach. This study evaluated the reliability of novel drone‐based phenotyping for GWAS in tetraploid potato. Image‐derived data on plant emergence and late blight resistance were collected using a drone‐mounted red‐green‐blue camera across separate field trials over two to three growing seasons. The dataset comprised 6262 phenotypic observations of emergence and 6972 observations of late blight resistance. A total of 2576 clones in an emergence panel and 1520 clones in a late blight resistance panel were genotyped for 8731 markers using a custom single nucleotide polymorphism array. GWAS yielded five significant quantitative trait loci (QTLs) for late blight resistance—three coinciding with known Rpi ‐gene clusters and StCDF1 —and four significant minor‐effect QTLs underpinning emergence. Rediscovery of known late blight loci supports the reliability of the approach. Flanking regions of the emergence QTLs include candidate genes encoding proteins involved in plant growth and development, stress response, compound trafficking, and nutrient assimilation. However, 58%–76% of genes in the flanking regions lack functional annotation, underscoring the need for transcriptomic studies of early plant development. We demonstrate that integrating remote phenotyping and GWAS can yield robust results in tetraploid potatoes, overcoming the past limitation of phenotyping costs.
Why it matches plant phenotyping methodsドローン画像によるジャガイモの出芽・疫病抵抗性表現型取得を中心に、その信頼性を評価し、GWASへの適用を検証しているため。
abstractThis study evaluated the reliability of novel drone‐based phenotyping for GWAS in tetraploid potato.
This paper presents a three-phase deep learning framework comprising (i) multi-modal data acquisition from drones and satellites, (ii) standardized pre-processing including interpolation for missing temporal data, and (iii) CNN-based feature extraction for real-time health classification. This framework relies on a mathematical model based on neural networks that classifies and detects the condition of agriculture, removing the reliance on manual tasks and subjective diagnosis. This paper focuses on three main aspects of our framework: data acquisition, training and prediction. Data is collected using sensors like drones, cameras, and satellite imagery and is pre-processed to filter out noise and improve quality. The training part uses CNN to learn features from the data and become more meaningful. The prediction part of the task classifies, and diagnoses crop health through the trained model using the features. The framework accuracy for crops such as maize, potato, and wheat has been tested and yielded over 90% accuracy. The novelty of this work resides in the development of a multi-modal deep learning architecture that fuses macro-scale satellite imagery with micro-scale drone and IoT sensor data to improve diagnostic reliability. The framework was validated on a multi-source agricultural dataset using a 70% training, 15% validation, and 15% testing protocol. Experimental results demonstrate an accuracy exceeding 90% for staple crops. Using this framework can increase the visibility and quality of information maintained for crop health and improve the decision-making routine of farmers in real time. Additionally, automation of this process can significantly reduce labor costs and increase productivity per crop. Implementing this framework can contribute to precision agriculture and sustainable management practices.
Why it matches plant phenotyping methods作物の健康状態を植物の表現型・状態として推定するマルチモーダル画像・センサ基盤と深層学習手法を開発し、複数作物・データセットで検証しているため、方法が中心である。
abstractThis paper presents a three-phase deep learning framework comprising (i) multi-modal data acquisition from drones and satellites, (ii) standardized pre-processing including interpolation for missing temporal data, and (iii) CNN-based feature extraction for real-time health classification.
Reproduction assets foundThe article's Data availability section points to a public Kaggle dataset used for the crop classification/health diagnosis experiments, matching an allowed URL. No code or model checkpoints are disclosed.Dataset · publicript. The research work was guided by Dr. B.D.K.P. The Corresponding author Shshank Chaube collaborated for review and supervision. All authors reviewed the manuscript.
Funding
Open access funding provided by Symbiosis International (Deemed University). No funds, grants, or other support was received.
Data availability
Dataset: https://www.kaggle.com/datasets/bhagvendersingh/precision-agriculture-dataset .
Declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
References
1. Mohyuddin, G. et al. Evaluation of machine learning approaches for preciOpen asset ↗kaggle · bhagvendersingh/precision-agriculture-datasetlines:473-545Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Plant Leaf Diseases represent a significant risk to global agricultural production. Crops ranging from Peppers and Tomatoes to Potatoes are affected by these diseases. Traditional methods of identifying leaf diseases based primarily on visual inspection have historically been slow and relatively inaccurate. A deep learning-based solution for the automated identification of plant leaf diseases utilizes Convolutional Neural Networks (CNNs) as the primary methodology. To identify leaf images into 15 disease categories, both pre-trained models such as VGG16, EfficientNetB3, Inception V3 and a custom CNN model were used. Using pre-trained models to allow for the use of Transfer Learning helps to mitigate some of the issues associated with computational resource limitations and data limitations in providing faster convergence rates and higher accuracy when compared to training a model from scratch. The Plant Village image collection which contains over 20,000 images of different plant leaf diseases was utilized for training and testing purposes. Each model's performance was evaluated based on its accuracy, loss and generalization capabilities. Additionally, each model was fine-tuned through hyperparameter optimization. As a result, the model that achieved the highest validation accuracy rate of 95% was the EfficientNetB3 model while the second highest accuracy rate was achieved by the Inception V3 model at 92%. This methodology provides an excellent answer to addressing early disease detection, enabling farmers to take the necessary actions quickly to reduce their losses and maximize their harvest.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習手法を比較・評価しており、病害フェノタイピングと手法検証が研究の中心です。
abstractA deep learning-based solution for the automated identification of plant leaf diseases utilizes Convolutional Neural Networks (CNNs) as the primary methodology.
Reproduction assets foundThe paper's plant-phenotyping measurements (CNN classification of 15 leaf disease classes) were performed on the public PlantVillage-derived Kaggle 'Plant Disease Dataset' by E. Marrex, which the authors cite as their training/testing image source. No author analysis code, trained model checkpoints, or paper-specific衍生Dataset · publicD. E. Popescu, M. K. Chowdary, and J. Hemanth, "Deep learning-based leaf
disease detection in crops using images for agricultural applications," Agronomy, vol. 12, no. 10,
p. 2395, 2022. doi: 10.3390/agronomy12102395. Available:
https://doi.org/10.3390/agronomy12102395.11. E. Marrex, "Plant Disease Dataset," Kaggle, Available:
https://www.kaggle.com/datasets/emmarex/ plantdisease. [Accessed: 03- Apr-2025].Open asset ↗Kagglepdf-raw-page:12 lines:1-8Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published18 Feb 2026International Journal For Multidisciplinary ResearchCited by 0 · OpenAlex ↗
Plant diseases continue to pose a serious challenge to agriculture, leading to substantial yield losses and posing a threat to global food security. Accurate and early identification of plant diseases is crucial for effective crop management. However, traditional manual inspection methods are time-consuming, subjective, and heavily dependent on expert knowledge. With recent advances in artificial intelligence and computer vision, automated plant disease detection systems have emerged as a reliable alternative. These systems depend strongly on large, well-annotated image datasets for training and evaluation. Among publicly available resources, the PlantVillage dataset is one of the most widely used benchmarks for plant disease research. It contains over 50,000 high-resolution RGB leaf images captured under controlled conditions and covers 14 crop species, including tomato, potato, and bell pepper, along with multiple other plants. The dataset represents 38 distinct classes encompassing both healthy and diseased leaf categories. All images are collected against uniform backgrounds, providing visual consistency and making the dataset suitable for benchmarking machine learning and deep learning–based plant disease classification models. This survey provides a comprehensive review of the PlantVillage dataset and its contribution to the advancement of automated plant disease detection. It traces the progression from traditional handcrafted feature–based classifiers to convolutional neural networks, transfer learning approaches, and recent transformer-based architectures. Various methods are compared in terms of classification accuracy, generalization ability, computational efficiency, and robustness. In the survey we have identified that Transfer Learning model showed 99.75% accuracy. The survey also discusses key limitations of the dataset, particularly its controlled imaging conditions and challenges related to real-field deployment. Finally, future research directions are highlighted, including domain adaptation, explainable artificial intelligence, multi-disease recognition, and real-world agricultural applications. This work aims to offer researchers a structured understanding of the PlantVillage dataset and support the development of next-generation intelligent crop disease diagnostic systems.
Why it matches plant phenotyping methodsPlantVillage画像を用いた植物病害状態の画像ベース推定手法とデータセットを中心に、複数の機械学習手法を比較・レビューしているため、植物フェノタイピング方法論のレビューとして含める。
abstractThis survey provides a comprehensive review of the PlantVillage dataset and its contribution to the advancement of automated plant disease detection.
Monitoring plant health is an important factor in maintaining agricultural productivity. Manual identification of leaf diseases requires expert knowledge and is prone to errors due to visual similarities among disease symptoms. This study aims to develop a plant leaf disease classification system based on digital images using a Convolutional Neural Network (CNN) approach. The dataset consists of plant leaf images representing three disease classes: Corn–Common rust, Potato–Early blight, and Tomato–Bacterial spot. Prior to model training, the images undergo preprocessing steps including image resizing and pixel normalization. The performance of the CNN model is evaluated using a testing dataset that is not involved in the training process, employing accuracy, confusion matrix, precision, recall, and F1-score as evaluation metrics. Experimental results show that the proposed model achieves a test accuracy of 95.56%, with balanced performance across all disease classes. In addition to quantitative evaluation, the trained model is implemented in a Streamlit-based application, allowing users to upload plant leaf images and obtain disease classification results interactively. The findings indicate that the CNN-based approach is effective for plant leaf disease classification and has potential application as an early decision-support system for plant health monitoring.
Why it matches plant phenotyping methods植物葉の画像から病害状態を推定するCNN分類法を開発し、独立テストデータで性能評価しているため、植物フェノタイピング手法が中心である。
abstractThis study aims to develop a plant leaf disease classification system based on digital images using a Convolutional Neural Network (CNN) approach.
Reproduction assets foundThe paper's phenotyping input is a publicly available PlantVillage image dataset (900 leaf images across three disease classes) obtained from Kaggle, with an explicit authors' URL. No author analysis code or trained model is publicly deposited.Dataset · publicleaf disease images obtained from the PlantVillage Dataset, which is publicly available through the Kaggle platform [17]. The dataset is
organized using a folder-based class structure, where each folder represents a specific leaf disease category. In this study, three disease
classes are used—Corn–Common rust, Potato–Early blight, and Tomato–Bacterial spot—with 300 images per class, resulting in a total of
900 images.Open asset ↗Kagglepdf-page:3 lines:1-51Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Potato leaf diseases, if left undetected, threaten food security in agricultural economies and cause substantial crop losses. To address this critical challenge, we developed an AI-based system called the Enhanced Single Shot Multibox Detector(EF-SSD), a variant of SSD that integrates multiscale feature fusion and Squeeze-and-Excitation attention to improve fine-grained lesion detection. The enhanced model processes high-resolution images (512×512 pixels) and analyzes leaves at ten magnification levels, enabling it to identify even minor signs of infection. The inclusion of Squeeze-and-Excitation filters allows the system to focus more effectively on characteristic disease patterns, increasing detection precision. After scanning the leaves, the system applies advanced image processing techniques to localize disease regions and assess their severity. We evaluated EF-SSD using 2,500 labeled potato leaf images representing healthy plants and cases of early and late blight. The proposed model achieved a mean Average Precision (mAP) of 97% at 0.5 IoU, an F1-score of 95%, and an Intersection over Union (IoU) of 89%, outperforming advanced detectors such as YOLOv5, YOLOv8, RetinaNet, and Faster R-CNN across all metrics. It also delivers real-time inference at 47 FPS, confirming its suitability for on-field deployment. An ablation study further demonstrates the effectiveness of SE blocks and extended feature hierarchies in enhancing detection accuracy. These outcomes highlight EF-SSD’s potential as a reliable, efficient, and scalable tool for smart agriculture and early crop disease management.
Why it matches plant phenotyping methodsジャガイモ葉の病斑を画像から検出・局在化し、病害の重症度を評価する深層学習手法を開発・検証しており、植物表現型取得が中心である。
abstractwe developed an AI-based system called the Enhanced Single Shot Multibox Detector(EF-SSD)
Reproduction assets foundThe paper's Data Availability statement explicitly provides a public GitHub repository with the authors' analysis/training code and a public Google Drive link to the custom 2,500-image potato leaf disease dataset with Pascal VOC annotations used in this study.Code · publicThe code implemented in this study is openly available at the following GitHub repository: https://github.com/bhavanisravan/potato-leaf-diseases-code.Open asset ↗bhavanisravan/potato-leaf-diseases-codehtml-lines:414-439Dataset · publicThe dataset used for training and evaluation can be accessed at: https://drive.google.com/drive/folders/1Yin9zp0gQKwqJ0LD3GWdLq_V_idLO2bG?usp=sharing.Open asset ↗html-lines:414-439Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Potatoes are a globally important crop, crucial to food security and nutrition, particularly in developing countries. However, their yield is often threatened by leaf diseases such as early blight and late blight, causing a severe loss of yield. Although deep learning–based models have shown promise in the identification of plant diseases, most of them rely on computationally intensive architectures and datasets collected in laboratories, restricting their application in practical agricultural fields. This paper proposes a lightweight and interpretable two-stage hybrid deep learning model aimed at addressing these challenges. The first stage separates disease-relevant features from complex field backgrounds through the use of Ghost convolutional layers, significantly reducing redundant computation. Feature refinement is enhanced via Convolutional Block Attention Modules (CBAM), which selectively focus on spatial and channel-level disease features. The second phase employs Lite Vision Transformer (LiteViT) blocks to capture global dependencies at a low computational cost, facilitating strong disease classification. The proposed model was trained and tested on a field-acquired potato leaf dataset obtained from Kannauj, India. Our hybrid model, called Ghost-CBAM-LiteViT, achieves high classification accuracy with low computational intensity, reaching performance rates of more than 99.67% in the test data set. Unlike existing heavy-transformer-based or CNN-only approaches, this is the first lightweight hybrid framework that jointly integrates Ghost Convolutions, CBAM, and LiteViT, delivering both state-of-the-art accuracy and practical deployability in real agricultural conditions. This model provides a deployable and scalable solution for real-time monitoring of potato leaf disease in smart agriculture, particularly in resource-poor settings.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する軽量深層学習手法の開発が主題であり、植物病害フェノタイピング手法として中心的です。
abstractThis paper proposes a lightweight and interpretable two-stage hybrid deep learning model aimed at addressing these challenges.
Internal potato diseases significantly affect the quality of processed products in production. In this study, a potato quality near-infrared online detection system was designed to improve detection efficiency. The proposed system consists of four parts: a transmission device, a spectral acquisition device, a light source system, and a culling device. To improve the accuracy of the detection model, this study used four preprocessing methods and three feature wavelength extraction algorithms to process the original spectra and develop the soft independent modeling of the class analogy (SIMCA) potato quality discrimination model. The results showed that the SIMCA potato quality identification model using mean-normalization preprocessing and competitive adaptive reweighted sampling (CARS) feature wavelength extraction algorithm was the most effective with sensitivity = 100.00%, specificity = 95.83%, and ACCP = 97.92%. The sensitivity = 100.00%, specificity = 90.48%, and ACCP = 95.24% were tested for the NIR online detection system. The results of this study show that the use of near-infrared reflectance spectroscopy combined with preprocessing algorithms and variable selection algorithms to construct discriminative models can achieve online detection of internal potato diseases.
Why it matches plant phenotyping methodsジャガイモ内部病害という植物状態を、近赤外分光オンライン計測と前処理・波長選択・識別モデルで推定するシステムの設計・検証が中心であり、植物フェノタイピング手法に該当する。
abstracta potato quality near-infrared online detection system was designed to improve detection efficiency
Potato plants, valued globally for their nutritional and economic importance, are highly vulnerable to various diseases, making early and accurate detection crucial to reducing yield loss and economic impact. This work presents a novel approach that integrates Fuzzy C-Means (FCM) clustering-based segmentation with convolutional neural network (CNN) models for the classification of potato leaf diseases. The method begins by segmenting leaf images in the Lab color space, chosen for its perceptual uniformity and its enhanced ability to separate color and luminance compared to the conventional RGB space. FCM, a soft clustering technique, allows each pixel to belong to multiple clusters with varying degrees of membership, effectively capturing ambiguous boundaries between healthy and diseased regions. By segmenting the images prior to classification, the influence of background noise on disease identification is significantly reduced. Experimental results demonstrate that the FCM-based segmentation approach achieves a test accuracy of approximately 94%, outperforming the baseline (no segmentation), which achieves around 91%. Additionally, FCM surpasses traditional clustering methods such as K-means, providing an accuracy improvement of over 2%. The integration of Lab color space segmentation, FCM clustering, and CNN classification forms a robust framework that significantly improves the accuracy and timeliness of potato disease detection, supporting sustainable crop management.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から推定するため、FCMによる病斑画像分割とCNN分類を統合・比較評価しており、植物フェノタイピング手法が中心である。
abstractThis work presents a novel approach that integrates Fuzzy C-Means (FCM) clustering-based segmentation with convolutional neural network (CNN) models for the classification of potato leaf diseases.
Introduction The potato is one of the most consumed vegetable crops worldwide. However, the environmental changes and various crop diseases have a significant impact on potato production, indicating severe damage to yield quality and quantity. Farmers mostly employ manual disease classification methods in agriculture, which have limitations in detecting subtle disease symptoms, are time-intensive, and often necessitate specialized expertise, which may not be accessible in all farming communities. Therefore, automated systems are designed for accurate and rapid disease classification, mitigating the risks of misdiagnoses and delayed treatments. However, differences in the size, mass, and structure of the diseased areas of potato leaf diseases, combined with complex environmental conditions, complicate the effective identification of these diseases. Methods Therefore, to address the existing issues, we propose an improved deep learning approach, namely the PotatoGuardNet, which is an Inception-ResNet-V2-based Faster-RCNN model, for locating and classifying various potato leaf diseases. Precisely, the InceptionResNet-V2 approach is employed as the base network to capture the visual attributes of the samples, which are later recognized and classified by the 2-stage detector of the Faster-RCNN model. Results The model is tested on huge and complex data samples of potato plants from the PlantVillage dataset and reported a classification accuracy of 99.41%, along with an mAP of 0.9556. Further, the core working of the proposed method is evaluated by generating the heatmaps to show its explanatory power. Discussion Extensive experiments and comparative analyses against several recent state-of-the-art approaches confirm the effectiveness and reliability of PotatoGuardNet for potato leaf disease detection. The results demonstrate that the proposed framework successfully captures disease-specific visual patterns and provides accurate localization and classification, indicating its potential for practical deployment in automated agricultural disease monitoring systems.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から局在化・分類する深層学習手法を提案し、精度とmAPによる評価および比較実験を行っており、植物病害状態の表現型取得が中心である。
abstractwe propose an improved deep learning approach, namely the PotatoGuardNet, which is an Inception-ResNet-V2-based Faster-RCNN model, for locating and classifying various potato leaf diseases.
Introduction Potato foliar diseases, particularly early and late blight, pose a serious threat to yield and food security, yet reliable visual recognition remains challenging due to cultivar heterogeneity, variable symptom expression, and acquisition noise in field-like imagery. To address these issues, we propose PotatoLeafNet, a two-stage deep learning framework that combines a fixed-sequence image-augmentation pipeline with a compact, task-optimized 11-layer convolutional neural network (CNN) using 3 × 3 kernels for robust, data-efficient classification of potato leaf conditions (Healthy, Early Blight, Late Blight). Methods We construct a dataset of 4,072 labeled potato leaf images from the PlantVillage-Potato subset and standardize all inputs to 224 × 224 RGB tensors with pixel intensities normalized to [0,1]. A balanced, fixed-order augmentation policy-comprising rotation, translation, shear, zoom, horizontal flipping, brightness adjustment, and channel jitter-is applied exclusively to the training split, increasing it to 6,000 images (2,000 per class) while keeping the validation and test sets free of synthetic samples. The second stage consists of an 11-layer CNN implemented in TensorFlow/Keras and trained with categorical cross-entropy loss and the Adam optimizer under a unified training and evaluation protocol. Performance is benchmarked against strong CNN and hybrid baselines, including ResNet-50 + VGG-16, VGG-16 + MobileNetV2, MobileNetV2, and Inception-V3. Results On the PlantVillage-Potato test set, PotatoLeafNet achieves 98.52% accuracy, 98.67% macro-precision, 99.67% macro-recall, 99.16% macro-F1, and 1.00 macro-AUC, outperforming all baseline models under identical preprocessing and training conditions. In particular, PotatoLeafNet surpasses ResNet-50 + VGG-16 (97.10% accuracy, AUC 0.98), VGG-16 + MobileNetV2 (94.80% accuracy, AUC 0.93), MobileNetV2 (93.20% accuracy, AUC 0.92), and Inception-V3 (92.50% accuracy, AUC 0.91). Short 10-epoch runs yield stable convergence (training accuracy 88.22%, validation accuracy 86.91%, test accuracy 88.15%), indicating efficient learning from the augmented distribution. Discussion The results demonstrate that explicitly coupling a fixed sequential augmentation stage with a lightweight 3×3-kernel CNN enables high tri-class accuracy, strong recall for disease classes, and improved generalization relative to deeper or fused architectures, without incurring substantial computational cost. By emphasizing disease-relevant structure while limiting overfitting, PotatoLeafNet provides a practical and resource-efficient solution for automated screening of potato leaf health in real-world agronomic settings, supporting timely and data-driven disease management.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類するCNN手法を開発し、複数モデルとの性能比較で検証しており、植物フェノタイピング手法が研究の中心である。
abstractwe propose PotatoLeafNet, a two-stage deep learning framework
Reproduction assets foundThe paper's potato leaf disease classification is built on two publicly available Kaggle image datasets: the PlantVillage dataset (source of the PlantVillage-Potato subset) and the Potato Leaf Disease Dataset (PLD, 4,072 images across Healthy, Early Blight, Late Blight). Both are cited with public Kaggle URLs in the 3.Dataset · publicPotato Leaf Disease Dataset ( 2025 ). Kaggle dataset 2024. Available online at: https://www.kaggle.com/datasets/rizwan123456789/potato-disease-leaf-datasetpldOpen asset ↗Kaggle · rizwan123456789/potato-disease-leaf-datasetpldlines:788-867Dataset · publicPlant Village Dataset ( 2024 ). Kaggle [dataset]. Available online at: https://www.kaggle.com/datasets/mohitsingh1804/plantvillage (Accessed April 29, 2024).Open asset ↗Kaggle · mohitsingh1804/plantvillagelines:788-867Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Early and precise diagnosis of crop diseases is crucial for global food security, particularly in developing countries where agriculture still plays a dominant role. This study presents a deep learning approach for labelling ten different plant disease conditions across three principal crops—maize, potato, and soybean. The Convolutional Neural Network (CNN) model incorporates multiple convolutional and batch normalization layers, achieving an overall classification accuracy of 95 %. Class-wise F1-scores range from 0.84 to 0.96, with notably strong performance for the Potato-Healthy and Soybean-Healthy categories. The model demonstrates robust generalization to variations in background, lighting, and leaf orientation, highlighting its suitability for real-world agricultural environments. This work supports the development of automated, scalable, and accurate multi-crop disease detection systems. The study also examines challenges such as class imbalance and overfitting, and proposes improvements including the integration of attention mechanisms and transfer learning. However, the model’s performance is still limited by the relatively small dataset size and restricted environmental diversity, suggesting future scope for expansion through larger field-based datasets, multimodal sensing, and advanced hybrid architectures.
Why it matches plant phenotyping methods葉画像から植物病害状態を分類するCNN手法が研究の中心であり、精度やF1スコアによる性能評価も行っているため、植物フェノタイピング手法として収録する。
titleA Convolutional Neural Network (CNN) Based Classification Framework for Multi-Crop Disease Detection using Leaf Images
Potato plants are highly vulnerable to numerous diseases that can substantially affect both yield and quality. Conventional approaches for detecting these diseases are often labor-intensive, slow, and prone to inaccuracies, particularly under variable environmental conditions. This study presents a hybrid deep learning architecture, termed potato leaf diseases DenseNet (PLDNet), which integrates a DenseNet-based convolutional neural network with a Transformer-based attention module to accurately classify potato leaf diseases. Furthermore, an adaptive parametric activation function, referred to as Adaptive Flatten p-Mish (AFpM), is proposed to enhance the model's learning flexibility and representational capacity. When evaluated on the PlantVillage and Mendeley datasets, PLDNet attains classification accuracies of 99.54% and 87.50%, respectively, surpassing contemporary state-of-the-art models and activation techniques. The proposed framework exhibits strong generalization performance and offers a scalable, efficient approach for automated plant disease identification. To highlight the novelty, the proposed AFpM activation function introduces a learnable parameter enabling adaptive nonlinearity, improving over Mish, Swish, and PFpM activation functions through dynamic gradient control. AFpM improves accuracy by 2.52% on Mendeley dataset, and 1.93% on PlantVillage dataset compared to PFpM, and by more than 3% compared to Swish and Mish.
Why it matches plant phenotyping methods葉画像から植物病害状態を推定する深層学習モデルと新規活性化関数を開発・評価しており、植物フェノタイピング手法が研究の中心である。
abstractThis study presents a hybrid deep learning architecture, termed potato leaf diseases DenseNet (PLDNet), which integrates a DenseNet-based convolutional neural network with a Transformer-based attention module to accurately classify potato leaf diseases.
Reproduction assets foundThe paper's phenotyping inputs are two public leaf-image datasets used directly for its classification experiments: the Mendeley Potato Leaf Disease dataset (explicitly deposited with URL) and the PlantVillage dataset via Kaggle (explicitly linked in Data availability). The authors' PLDNet code is only promised 'upon' Dataset · publicsis. A.M initially drafted the paper, and all the authors (A.M, A.C, and N.A) reviewed and edited the paper.
Funding
Open access funding provided by University of Inland Norway. INN have subscription for open-access (OA) publication in Scientific Reports, Nature.
Data availability
The dataset used in this study is available at: https://data.mendeley.com/datasets/ptz377bwb8/1 and https://www.kaggle.com/datasets/emmarex/plantdisease .
Code availabilityOpen asset ↗Mendeley · ptz377bwb8/1lines:1390-1403Dataset · publicthors (A.M, A.C, and N.A) reviewed and edited the paper.
Funding
Open access funding provided by University of Inland Norway. INN have subscription for open-access (OA) publication in Scientific Reports, Nature.
Data availability
The dataset used in this study is available at: https://data.mendeley.com/datasets/ptz377bwb8/1 and https://www.kaggle.com/datasets/emmarex/plantdisease .
Code availabilityOpen asset ↗Kaggle · emmarex/plantdiseaselines:1390-1403Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published1 Jan 2026International Journal of Advanced Computer Science and ApplicationsCited by 0 · OpenAlex ↗
The Moroccan agricultural sector is currently navigating a pivotal transformation driven by the “Generation Green 2020–2030” national strategy, which places a high priority on the digitalization of farming practices to bolster resilience against climate volatility and phytopathological risks. This study proposes a robust Smart Agriculture Framework engineered to automate crop disease diagnosis within mobile environments with limited resources. Unlike generic standard Deep Learning models often unsuited for local specificities, the methodology presented here is specifically tailored to Morocco’s agroecological context, targeting three strategic crops: Tomato (Souss-Massa region), Potato (Gharb plains), and Wheat (Chaouia region). A hybrid intelligent architecture is introduced that integrates a lightweight Convolutional Neural Network (CNN) with Particle Swarm Optimization (PSO-CNN) for autonomous hyperparameter tuning. The proposed framework was validated using a curated dataset of 15,000 images, rigorously augmented to reflect local field conditions, yielding a classification accuracy of 94.7%. This work effectively bridges the gap between theoretical AI architectures and practical Precision Farming, providing a rapid decision support system to minimize yield losses and align with the national objective of establishing a digitally empowered agricultural ecosystem.
Why it matches plant phenotyping methods植物画像から病害状態を推定するCNNベースの診断手法を開発し、画像データセットで検証しており、表現型取得・推定が中心である。
abstractThis study proposes a robust Smart Agriculture Framework engineered to automate crop disease diagnosis within mobile environments with limited resources.
Potato yield is a key indicator for optimizing cultivation practices in agriculture. Potato yield can be estimated on harvesters using RGB-D cameras, which capture three-dimensional (3D) information of individual tubers moving along the conveyor belt. However, point clouds reconstructed from RGB-D images are incomplete due to self-occlusion, leading to systematic underestimation of tuber weight. To address this, we introduce PointRAFT, a high-throughput point cloud regression network that directly predicts continuous 3D shape properties, such as tuber weight, from partial point clouds. Rather than reconstructing full 3D geometry, PointRAFT infers target values directly from raw 3D data. Its key architectural novelty is an object height embedding that incorporates tuber height as an additional geometric cue, improving weight prediction under practical harvesting conditions. PointRAFT was trained and evaluated on 26,688 partial point clouds collected from 859 potato tubers across four cultivars and three growing seasons on an operational harvester in Japan. On a test set of 5,254 point clouds from 172 tubers, PointRAFT achieved a mean absolute error of 12.0 g and a root mean squared error of 17.2 g, substantially outperforming a linear regression baseline and a standard PointNet++ regression network. With an average inference time of 6.3 ms per point cloud, PointRAFT supports processing rates of up to 150 tubers per second, meeting the high-throughput requirements of commercial potato harvesters. Beyond potato weight estimation, PointRAFT provides a versatile regression network applicable to a wide range of 3D phenotyping and robotic perception tasks. The code, network weights, and a subset of the dataset are publicly available at https://github.com/pieterblok/pointraft.git.
Why it matches plant phenotyping methods部分点群からジャガイモ塊茎重量を推定する3D深層学習手法を開発・評価しており、植物形質取得が研究の中心である。
abstractwe introduce PointRAFT, a high-throughput point cloud regression network that directly predicts continuous 3D shape properties, such as tuber weight, from partial point clouds.
Reproduction assets foundThe paper publicly releases its authors' analysis code and trained network weights on GitHub, and a subset of its potato tuber partial point cloud dataset (with ground truth weights) on Hugging Face. Both are paper-specific, public, and actionable.Code · publicThe code, network weights, and a subset of the dataset are publicly available at https://github.com/pieterblok/pointraft.git .Open asset ↗pieterblok/pointraftlines:1-93Dataset · publicA subset of the datasets generated and/or analyzed during this study is publicly available at: https://huggingface.co/datasets/UTokyo-FieldPhenomics-Lab/3DPotatoTwinOpen asset ↗UTokyo-FieldPhenomics-Lab/3DPotatoTwinlines:447-463Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published29 Dec 2025Middle East Research Journal of Engineering and TechnologyCited by 0 · OpenAlex ↗
Abstract: Agriculture forms a cornerstone of the Indian economy, with food and cash crops playing a critical role in sustaining both the environment and human livelihoods. However, crop yields are significantly impacted each year by various plant diseases. The lack of efficient diagnostic methods, combined with limited awareness of disease symptoms and treatment options, often leads to widespread crop losses. This study explores the application of machine learning for plant disease detection, focusing on Convolutional Neural Networks (CNNs) to identify and classify diseases. The proposed approach employs advanced image processing techniques to analyze infected leaf regions, examining metrics such as time complexity and lesion area. The model was trained and tested on a curated dataset comprising 15 cases, including 12 disease categories such as Bell Pepper Bacterial Spot, Potato Early Blight, and Tomato Leaf Mold, alongside 3 categories of healthy leaves. The system achieved a test accuracy of 88.8%, demonstrating its potential for accurate plant disease detection. Performance evaluation was conducted using standard metrics to validate the model's reliability.
Why it matches plant phenotyping methods感染葉の画像から病害を分類し、病斑面積を解析するCNN手法の開発・評価が中心であり、植物の病害状態を直接推定するため含める。
abstractThis study explores the application of machine learning for plant disease detection, focusing on Convolutional Neural Networks (CNNs) to identify and classify diseases.
Timely and precise detection of diseases on plants is crucial for minimizing losses during crop production in order to sustain food supply demands worldwide. In this work, deep learning (DL) was used to develop an automatic disease identification system for the leaves of potato and mango plants using two publicly available datasets, the PlantVillage Potato Leaf Disease (2,152 images) dataset and the Kaggle Mango Leaf Disease dataset (4,000 images). Images were pre-processed, augmented, and split into training and testing datasets (80:20), to enable better model generalization. Four deep learning architectures, namely Convolutional Neural Networks (CNN), AlexNet, Residual Networks (ResNet), and EfficientNet, were evaluated in the context of multi-class disease classification. The baseline CNN achieved a training accuracy of 93.67% and a testing accuracy of 92.61%, with balanced precision and recall (92.5%), thus providing a very strong feature extraction and classification capability. AlexNet showed moderate performance (91.3% training, 90.2% validation), and a very small overfitting was observed. ResNet had an efficient convergence, and attained 96.7% validation accuracy in just a few epochs, thus pointing out the advantage of residual connections in the context of deeper learning. EfficientNet surpassed all the other architectures, since it reached a training accuracy of 98.2% and a validation accuracy of 97.8%, with very small loss (≈ 0.015) and no overfitting, thus proving to have the best generalization ability. The models demonstrated stability and discriminative ability with the support of confusion matrices and accuracy and loss plots produced on an epoch-wise basis. Therefore, the findings indicate that DL models can be adapted for real-time and accurate plant disease diagnosis, establishing a pathway for early remediation, and supporting precision agriculture. The research establishes the opportunity for EfficientNet to be considered a promising solution for scalable smart farming.
Why it matches plant phenotyping methods葉画像から植物病害を分類する深層学習手法を開発・比較し、複数データセットで精度を検証しており、植物の病害状態の取得・推定が研究の中心である。
abstractdeep learning (DL) was used to develop an automatic disease identification system for the leaves of potato and mango plants
Reproduction assets foundThe paper uses two public Kaggle leaf-image datasets (PlantVillage potato, mango leaf disease) and states that all code, preprocessing scripts, dataset splits, and model artifacts are publicly available in a GitHub repository (also archived on Zenodo). All three are paper-specific, public, and actionable.Dataset · publicThe datasets analyzed during the current study are available in (https://www.kaggle.com/datasets/aarishasifkhan/plantvillage-potato-disease-dataset)Open asset ↗html-lines:473-503Code · publicAll code, preprocessing scripts, dataset splits, and model artifacts used in this study are publicly available in the GitHub repository at: [https://github.com/logeswarig/PROJECT_1].Open asset ↗logeswarig/PROJECT_1html-lines:473-503Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Sustainable precision agriculture has become increasingly vital for enhancing crop productivity, minimizing environmental impact, and ensuring global food security. Potato leaf diseases, such as blight, pose significant threats to crop yield. The accurate and timely detection of potato leaf diseases is critical for minimizing yield losses. This study proposes a pair a lightweight MobileNetV3 classifier with a MapReduce-style data pipeline that parallelizes preprocessing and batch inference across nodes. The model utilizes a dataset comprising 2152 images categorized into three classes. The preprocessing pipeline includes image resizing, normalization, and data augmentation to enhance model generalization. MobileNetV3 is employed for high-level feature extraction and classification, while MapReduce enables parallel processing and efficient handling of large datasets. The experimental results achieved a detection accuracy of 98.6% across the training phase, 96.9% in the validation phase, and 96.8% in the testing phase, and testing sensitivity (95.3%), Specificity (97.7%), and F1-Score (96.4%) While training for this dataset is performed on GPU, the MapReduce pipeline makes the system horizontally extensible for larger deployments and continuous image ingest. We report per-class confusion matrices and standard clinical metrics, and analyze when MapReduce provides throughput gains versus a single-node baseline. The proposed model significantly outperforms several state-of-the-art methods, as validated through statistical measures such as sensitivity, specificity, and misclassification rate. Its high accuracy, scalability, and robustness make it suitable for large-scale agricultural disease monitoring and precision farming applications.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から推定する分類手法と、MapReduceによる推論パイプラインを中心に開発・評価しており、植物フェノタイピング手法として適格。
abstractThis study proposes a pair a lightweight MobileNetV3 classifier with a MapReduce-style data pipeline that parallelizes preprocessing and batch inference across nodes.
Leaf area is a key indicator of plant health and development. However, manual measurement is time-consuming and labor-intensive, especially when monitoring aeroponic-grown potato plants with multiple leaves over extended periods. This study applied a computer vision-based system to automate leaf growth monitoring using the YOLO (You Only Look Once) v8 framework. A dataset was collected from a controlled aeroponic system: 25 images of young leaves (4,869 individual leaf segments) and 35 of mature leaves (12,368 segments). Based on evaluation of various YOLOv8 model configurations, the best model achieved a mask mAP@50 of 0.396 and 0.250 for young leaves and mature leaves, respectively. The challenge to track the mature canopy was due to severe leaf occlusion and self-similarity in dense foliage. Despite the challenge, this study demonstrates proof of concept for tracking early leaf growth and highlights the significant computer vision challenges posed by dense, mature canopies in aeroponic systems.
Why it matches plant phenotyping methods植物の葉面積・葉成長をコンピュータビジョンで自動追跡する手法の開発と評価が中心であり、植物表現型の取得方法を直接扱っている。
abstractThis study applied a computer vision-based system to automate leaf growth monitoring using the YOLO (You Only Look Once) v8 framework.
Limited annotated data often constrain accurate yield prediction in underrepresented crops. To address this challenge, we developed a cross-crop deep transfer learning (TL) framework that leverages potato (Solanum tuberosum L.) as the source domain to predict sweet potato (Ipomoea batatas L.) yield using multi-temporal uncrewed aerial vehicle (UAV)-based multispectral imagery. A hybrid convolutional–recurrent neural network (CNN–RNN–Attention) architecture was implemented with a robust parameter-based transfer strategy to ensure temporal alignment and feature-space consistency across crops. Cross-crop feature migration analysis showed that predictors capturing canopy vigor, structure, and soil–vegetation contrast exhibited the highest distributional similarity between potato and sweet potato. In comparison, pigment-sensitive and agronomic predictors were less transferable. These robustness patterns were reflected in model performance, as all architectures showed substantial improvement when moving from the minimal 3 predictor subset to the 5–7 predictor subsets, where the most transferable indices were introduced. The hybrid CNN–RNN–Attention model achieved peak accuracy (R2≈0.64 and RMSE ≈ 18%) using time-series data up to the tuberization stage with only 7 predictors. In contrast, convolutional neural network (CNN), bidirectional gated recurrent unit (BiGRU), and bidirectional long short-term memory (BiLSTM) baseline models required 11–13 predictors to achieve comparable performance and often showed reduced or unstable accuracy at higher dimensionality due to redundancy and domain-shift amplification. Two-way ANOVA further revealed that cover crop type significantly influenced yield, whereas nitrogen rate and the interaction term were not significant. Overall, this study demonstrates that combining robustness-aware feature design with hybrid deep TL model enables accurate, data-efficient, and physiologically interpretable yield prediction in sweet potato, offering a scalable pathway for applying TL in other underrepresented root and tuber crops.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から作物収量を推定する深層転移学習法を開発し、複数モデル・予測子構成で性能を比較検証しているため、植物表現型推定法が中心である。
abstractwe developed a cross-crop deep transfer learning (TL) framework that leverages potato (Solanum tuberosum L.) as the source domain to predict sweet potato (Ipomoea batatas L.) yield using multi-temporal uncrewed aerial vehicle (UAV)-based multispectral imagery.
Why it matches plant phenotyping methodsジャガイモ塊茎の病斑・生理障害を画像から検出する深層学習モデルを開発・比較し、精度を検証しているため、植物フェノタイピング手法が中心です。
abstractwe propose YOLOv8-ST, an enhanced deep learning model that incorporates the Swin Transformer and Triplet Attention modules to effectively distinguish between these visually similar tuber blemishes.
The internal quality assessment of potato tubers is a crucial task in agro-laboratory processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in laboratory. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 95% and precision near 97.2% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.
Why it matches plant phenotyping methodsジャガイモ塊茎の内部欠陥という植物器官の状態を、RGB画像と複数の画像解析モデルで検出・分割する手法の開発および性能評価が中心である。
abstractWe present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices
Leaf protein content (LPC) is a critical physiological parameter for assessing crop nitrogen status, optimizing fertilization strategies, and predicting crop yield. Although hyperspectral remote sensing offers a nondestructive alternative, it still faces challenges such as overlapping protein and water absorption spectral features. This study presents a “physics-constrained + data-driven” hybrid modeling framework, LPCNet, for remote sensing–based LPC estimation. The core innovations of LPCNet include (1) leveraging the physics-based PROSPECT-PRO and SAIL radiative transfer models to generate a simulated spectra dataset, addressing the challenges of small sample sizes and distribution bias in field measurements through pretraining and transfer learning; (2) incorporating leaf chlorophyll content (LCC) as an auxiliary training target within a multitask learning framework, which exploits the strong absorption features of LCC in the visible–near infrared (VNIR) range to enhance the ability of the model to interpret weak LPC absorption signals in the shortwave infrared (SWIR) range; and (3) employing a multiscale convolutional network with a feature fusion mechanism to explicitly model the complex nonlinear relationships between spectral reflectance and LPC. This study utilized field-measured data from three growing seasons of wheat and potato to develop and validate the LPCNet model. The results demonstrate the following: (1) the LPCNet model pretrained with a simulated spectra dataset notably outperforms nonpretrained models; (2) the pretrained and LCC-assisted strategy further improves LPC-estimation accuracy to RMSE = 0.000100 g/cm² (R² = 0.866), showing a substantial advantage over traditional RF (R² = 0.760, RMSE = 0.000134 g/cm²). This study proposes a hybrid deep learning modeling framework utilizing hyperspectral remote sensing for high-precision monitoring of crop LPC.
Why it matches plant phenotyping methodsハイパースペクトル計測から作物葉のタンパク質含量という植物生理形質を推定するモデルを開発し、複数年の圃場データで検証しており、表現型取得・推定手法が中心である。
abstractThis study presents a “physics-constrained + data-driven” hybrid modeling framework, LPCNet, for remote sensing–based LPC estimation.
Soil and plant analyser development (SPAD) is a key indicator of plant nutritional status and nitrogen stress, reflecting crop growth. During potato tuber formation, multispectral and thermal infrared sensors were used to monitor leaf chlorophyll content. Four data sources—texture indices (TIs), vegetation indices (VIs), thermal infrared vegetation indices (TVIs), and texture features (TFs)—were analysed for correlation with SPAD values. The correlation coefficient was calculated, and the feature variables were screened. Then, the selected features were randomly combined with the ground measured data to construct random forest (RF), support vector machine (SVM), and partial least squares regression (PLSR) models. Results showed that among TIs, the ratio texture index (RTI) had the highest correlation with SPAD (R = 0.703). Among VIs, the visible light difference vegetation index (VDVI) correlated best (R = 0.576). Among TVIs, normalised canopy temperature (NRCT) showed the strongest correlation (R = 0.640). Nearly half of TFs reached significant levels (P < 0.01). VIs provided the highest accuracy (R² = 0.741) in chlorophyll monitoring, with TIs improving prediction accuracy by up to 17.81% compared to TFs. Multi-source fusion (VIs + TIs + TVIs) achieved the highest model accuracy (R² = 0.854), a 15.2% improvement over traditional VIs input, with mean square error (RMSE) reduced by 40.8% and mean relative error (MRE) by 77.7%. RF models outperformed others under identical input conditions. This study offers a robust methodology for UAV-based multi-source remote sensing to monitor potato leaf chlorophyll, supporting precision agriculture practices.
Why it matches plant phenotyping methodsUAVマルチスペクトル・熱赤外画像からジャガイモ葉のクロロフィル含量を推定する画像・センサー解析手法が中心であり、特徴量選択と複数の予測モデルの比較・検証を含むため。
titleEstimation of Chlorophyll Content in Potato Leaves Based on UAV Multi-Spectral and Thermal Infrared Images
Plant diseases significantly affect agricultural yields, leading to economic loss. The timely and accurate detection of potato leaf diseases is important to facilitate early intervention. Existing deep learning models struggle to detect minor variations in potato diseases due to uneven lighting condition, occlusions, complex background noise, and blur presence in the test images. To handle these problems, a multi-path, multi-attention, and lightweight transformer-based method incorporating shifted window multi-head self-attention (SW-MSA) with multi-scale channel attention and pixel attention is proposed in this paper. Additionally, an image super-resolution (ISR) module is also developed and incorporated with SW-MSA to further improve the disease detection accuracy by enhancing the quality of the original test images. Exhaustive experiments demonstrate that the proposed method performs superior compared to existing methods with an accuracy of 99.3% with lesser inference time. Confusion matrix and classification report-based evaluations affirm its better capability in identifying various types of diseases i.e., early blight and late blight with healthy classes. The proposed method provides a stable and accurate solution to real-time disease detection, facilitating early intervention and minimizing agricultural losses.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習・超解像手法を開発し、精度比較で検証しており、植物表現型取得が中心である。
abstracta multi-path, multi-attention, and lightweight transformer-based method incorporating shifted window multi-head self-attention (SW-MSA) with multi-scale channel attention and pixel attention is proposed in this paper.
Crop diseases have a major impact on global food security by causing significant reductions in agricultural yields. Traditional methods are often slow and expert-dependent, highlighting the need for a more efficient, automated, and precise approach to minimize economic losses for farmers and enhance production efficiency. Potato is a vital crop used globally in various cuisines, and blight disease in potato leaves is a major contributor to crop deterioration worldwide. Plant leaf diseases often arise due to abrupt climate changes, improper fertilization, and excessive use of nitrogen-based fertilizers. The proposed research work addresses the challenges in potato leaf disease detection by introducing a novel lightweight deep-learning model named ‘uvaNet’. In this model, max-pooling operations have been reduced by half compared to the convolution operations to minimize information loss during the down-sampling of feature map dimensions. Additionally, skip connections are incorporated to preserve important features, and variable-sized kernels are strategically chosen to ensure the model remains lightweight. The effectiveness of the proposed method for blight disease classification is demonstrated on a publicly accessible Plant Village dataset containing potato leaf images. The efficacy of the proposed blight disease classification model has been evaluated using potato leaves from the Plant Village dataset. The proposed method exhibited a remarkable accuracy of 99.31% compared to the state-of-the-art techniques. Furthermore, a web-based portal has been developed for farmers to address the need for real-time pesticide optimization. The portal allows farmers to upload images of potato leaves suspected of blight infection, enabling them to quickly receive classification results and customized pesticide recommendations in both Hindi and English. Hence, this approach promotes early intervention, supports sustainable agricultural production, and helps reduce crop losses across the agricultural supply chain.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類する深層学習モデルの開発と評価が中心であり、植物病害状態の表現型推定に該当する。
abstractintroducing a novel lightweight deep-learning model named ‘uvaNet’
Accurate mass estimation of agricultural products plays a vital role in enhancing post-harvest handling, storage and processing efficiency. This study presents a constructive approach to modelling the mass of potato (Solanum tuberosum) using targeted dimensional attributes, employing both artificial neural networks (ANN) and response surface methodology (RSM). By leveraging a dataset that encompasses essential physical parameters, such as length, width, projected area and perimeter, we have successfully constructed predictive models that can significantly improve the accuracy of mass estimations. The ANN model was carefully trained and optimised to effectively capture the nonlinear relationships inherent in the data, while the RSM approach offers a robust analytical framework for examining variable interactions. Our performance evaluation, utilising metrics like the coefficient of determination (R²), root mean square error (RMSE) and mean square error (MSE), reveals that the ANN model excels in predicting potato mass, surpassing traditional regression techniques. Notably, the RSM exhibited an impressive R² of 0.9981, and the ANN model reached an R² of 0.9943, both demonstrating a strong correlation with actual mass measurements. These findings underscore the potential of our proposed models for image-based weight estimation, facilitating improved sorting and grading of potatoes. By implementing these innovative mass estimation techniques, we can enable automated sorting processes, enhance yield estimations, optimise supply chains, conduct non-destructive quality assessments, incorporate smart farming practices and minimise post-harvest losses—all while ensuring standardised food processing. In conclusion, this research highlights the promising avenues for intelligent modelling techniques in agricultural engineering, offering scalable solutions that can significantly contribute to the efficiency and effectiveness of mass estimation in the agricultural sector.
Why it matches plant phenotyping methods画像からジャガイモ塊茎の寸法を抽出し、ANNおよびRSMで質量を推定する手法の構築・評価が研究の中心であり、植物器官形質の測定法に該当する。
abstractThis study presents a constructive approach to modelling the mass of potato (Solanum tuberosum) using targeted dimensional attributes, employing both artificial neural networks (ANN) and response surface methodology (RSM).
Accurately detecting potato leaf diseases is essential for sustainable agriculture, as early intervention can reduce crop losses and minimize the environmental impact of excessive pesticide use. However, this task remains challenging due to the high-dimensional nature of image data and the variability of disease symptoms under different environmental conditions. This study presents a deep learning framework that integrates advanced feature extraction, dimensionality reduction, and metaheuristic optimization to address these challenges to enhance classification performance. Deep features were extracted using the pretrained InceptionV3 (GoogleNet architecture), followed by feature selection techniques, including principal component analysis (PCA), t-distributed stochastic neighbor embedding (t-SNE), random forests, and logistic regression, to refine the most informative features. To capture complex feature dependencies, copula preprocessing was employed, transforming data into a standardized, dependency-aware representation. The baseline Deep Q-Network (DQN) model achieved a promising accuracy of 0.90625, demonstrating strong initial performance. Further optimization using the Ocotillo Optimization Algorithm (OcOA) significantly improved this accuracy to 0.980168269, confirming the effectiveness of OcOA in hyperparameter tuning for deep reinforcement learning. These findings underscore the potential of combining deep learning, copula-based preprocessing, and advanced metaheuristic optimization to enhance the precision and sustainability of automated agricultural disease detection, supporting more efficient crop management and reduced environmental impact.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習フレームワークの開発が研究の中心であり、植物病害表現型の推定手法に該当する。
titlePotato Leaf Disease Detection Using Deep Reinforcement Learning and the Ocotillo Optimization Algorithm
Identifying leaf diseases beforehand is essential for both production and early prevention in contemporary agriculture. Early diagnosis of potato leaf spot is difficult to complicated symptoms of crop diseases and interactions with climatic conditions. Conventional methodologies of plant disease detection are labour-intensive, time-consuming, and require a great deal of experience. Scholars, researchers, and administrators have recently focused a great deal of emphasis on the crucial field of autonomous plant disease identification. Various deep learning and computer vision methods have emerged to detect potato leaf diseases. They also often involve complicated efforts and are subject to inaccuracy. This study develops a convolutional AEVGG19 network and compares it with existing approaches on different performance assessment metrics, including accuracy, F1-score, specificity, and sensitivity. The suggested approach achieves an astounding 98.36% training accuracy in accurately detecting illnesses, while maintaining a validation accuracy of 94%. By offering a reliable and effective method for the early detection of leaf diseases, this research advances agricultural technology and helps to safeguard crops and increase productivity.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から深層学習で検出する手法を開発・比較しており、植物の病害状態の表現型取得が研究の中心である。
abstractThis study develops a convolutional AEVGG19 network and compares it with existing approaches on different performance assessment metrics, including accuracy, F1-score, specificity, and sensitivity.
Accurate and rapid identification of potato diseases is essential for preserving yield and quality. However, existing deep learning models suffer from low accuracy and redundancy issues. Moreover, models trained on datasets with idealized backgrounds often fail to meet the requirements for potato disease identification under real-field conditions. To address the aforementioned challenges, this study proposes a potato disease identification model named Potato-ShuffleNetV2, based on an improved ShuffleNetV2 architecture. First, a grouped efficient channel attention (GECA) mechanism is introduced to suppress interference from natural field backgrounds. Subsequently, a feature fusion module is constructed to reduce the loss of critical information. The ReLU activation function is then replaced with Gaussian error linear unit (GELU) to enhance model robustness. Finally, model pruning is applied to remove redundant feature layers and reduce model complexity. The final model achieves an accuracy of 97.78% on the potato disease test dataset, with only 0.13 M parameters and 0.03G FLOPs. Compared with state-of-the-art models such as ResNet50, DenseNet121, and EfficientNetV2_m, the proposed model improves classification accuracy by 1.53%, 2.29%, and 5.41%, respectively, while reducing the number of parameters by 99.45%, 98.13%, and 99.75%, respectively. Experimental results demonstrate that the proposed model achieves significant advantages in both recognition accuracy and model compactness, making it highly suitable for deployment in real-world field environments.
Why it matches plant phenotyping methods圃場画像からジャガイモ病害を識別する深層学習モデルを開発し、精度・モデル規模・実環境での性能を評価しており、植物病害状態の表現型取得が中心である。
abstractthis study proposes a potato disease identification model named Potato-ShuffleNetV2, based on an improved ShuffleNetV2 architecture.
Early blight, caused by the fungus Alternaria solani, is a prevalent disease in potato crops that severely impacts yield and quality. Traditional detection methods are time-consuming, require expert knowledge, and depend on laboratory facilities. This study aims to develop an efficient and automated approach for detecting early blight in potato leaves using deep learning techniques. A deep learning-based software solution was created, utilizing a convolutional neural network (CNN) trained on a large, annotated dataset of potato leaf images showing various disease symptoms. Five widely used CNN architectures (ResNet, NasNet, MobileNet, VGG16, InceptionNet) were implemented and compared within a consistent MATLAB environment. The comparative analysis revealed differences in model performance, offering valuable insights into the suitability of each architecture for real-time disease detection on different devices. The study demonstrates that CNN-based models can effectively and automatically detect early blight in potato leaves, with certain architectures offering better adaptability and accuracy for practical, field-level applications.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から検出するCNNソフトウェアを開発し、複数モデルを比較評価しており、植物病害状態の画像ベース表現型取得が中心である。
abstractThis study aims to develop an efficient and automated approach for detecting early blight in potato leaves using deep learning techniques.
Understanding growth patterns and yield dynamics in potato cultivation is essential for optimising agricultural practices and improving productivity. This study leverages machine learning techniques to analyse and predict potato growth stages and yield outcomes based on environmental and physiological data. Various machine learning models were developed using multispectral imaging, soil parameters and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in identifying growth stages and forecasting yield performance. Key physiological trends were identified during the tuber initiation, bulking and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R² values above 0.90 across validation datasets. Additionally, the study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth and yield optimization.
Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習を用いてジャガイモの生育段階と塊茎収量を推定し、検証しており、植物形質の取得・推定手法が主要な貢献です。
abstractVarious machine learning models were developed using multispectral imaging, soil parameters and climatic factors collected across diverse cultivation environments.
Addressing the challenging issue of complex background interference in plant disease identification, recent research employs diverse deep learning (DL) methodologies on both publicly available and customized datasets. This study introduces a two-step DL approach for plant disease classification. Initially, an enhanced convolutional neural network (CNN) is developed through a comparative analysis of prominent CNN architectures, including customized and cascaded versions of select DL models, achieving an accuracy of 93.3%. To further enhance accuracy, segmentation architectures such as DeepLabV3+, UNet, Iterative UNet, and UNet with Atrous Spatial Pyramid Pooling (ASPP) are integrated before customized CNN architectures. These segmentation algorithms effectively isolate the diseased portions of leaf images. Notably, the UNet with ASPP architecture demonstrates reduced time complexity, minimizing the number of features to be trained, and significantly improves accuracy to 99.8%, outperforming other predefined architectures. The models are trained on a plant village dataset, detecting 10 different diseases across various plant species, including tomato, corn, and potato.
Why it matches plant phenotyping methods葉画像から病変部位を分離し、植物の病害状態を分類する画像解析手法が研究の中心であるため、植物フェノタイピング手法として含める。
abstractThis study introduces a two-step DL approach for plant disease classification.
Agriculture contributes enormously to global food security, but crop diseases result in huge yield losses every year, compromising food production globally. Conventional disease identification practices depend mostly on visual inspection by agricultural specialists, which is time-consuming, subjective, and not accessible to small farmers. Deep Learning (DL) has come forward as a revolutionary technology to implement automated plant disease detection with the promise of quick, precise, and scalable applications. This work introduces an end-to-end deep learning-based plant disease detection and classification system using Convolutional Neural Networks (CNNs). The system applies transfer learning using pre-trained networks like VGG16, ResNet50, and MobileNetV2 with a high accuracy and efficiency in computations. The system takes leaf images using smartphones or Internet of Things (IoT)-based cameras, performs processing using a trained CNN model, and makes real-time diagnosis along with treatment suggestions. Experimental outcomes show classification accuracy of over 95% for various crop species like tomato, potato, apple, and corn. Combining this technology with IoT devices and mobile applications facilitates farmers to make prompt decisions based on accurate information, saving losses on crops and ensuring eco-friendly farming. This work contributes to precision agriculture by narrowing the gap between cutting-edge AI technologies and effective farming requirements
Why it matches plant phenotyping methods植物の葉画像から病害状態をCNNで検出・分類する手法が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThis work introduces an end-to-end deep learning-based plant disease detection and classification system using Convolutional Neural Networks (CNNs).
Crop diseases pose a significant threat to global food security, causing substantial yield losses estimated at 10-40% annually. Traditional methods of disease identification, reliant on visual inspection by farmers or experts, are often subjective, time-consuming, and limited by the availability of specialists. This study proposes an ensemble learning framework for robust image-based crop disease detection, specifically designed to address the challenges of heterogeneous, non-Independent and Identically Distributed (non-IID) agricultural datasets in decentralized environments. Utilizing the Plant Village dataset, we implement a stacking ensemble model integrating diverse Convolutional Neural Networks (CNNs) such as VGG (Visual Geometry Group), ResNet, and Inception as base learners, with a meta-learner to optimize prediction fusion. The system employs comprehensive data preprocessing, including resizing, normalization, noise removal, segmentation, and augmentation, to enhance robustness against real-world variability. Transfer learning with ResNet50 was adopted as a baseline model. The baseline ResNet50 achieved 59% test accuracy across seven grape and potato disease classes. The ensemble model improved performance, attaining 63% accuracy with average precision, recall, and F1-scores of 56%, 52%, and 52% respectively. Class imbalance remained a limiting factor for certain categories. The ensemble learning approach outperformed individual models, demonstrating improved generalization across diverse datasets. Although computational demands and imbalance challenges persist, the system provides a promising AI-driven pipeline for accurate crop disease diagnosis, supporting sustainable agricultural practices.
Why it matches plant phenotyping methods植物画像から病害状態を推定するCNNアンサンブル手法の開発と性能評価が中心であり、植物病害フェノタイピング手法に該当する。
titleEnsemble Learning Framework for Image-Based Crop Disease Detection Using CNN Models
Reproduction assets foundThe paper's crop disease detection models were trained on the public PlantVillage dataset, which the authors explicitly state is available on Kaggle. This is the image input used directly for the paper's analysis. No author code, trained models, or other paper-specific assets are disclosed.Dataset · public-
Original Draft; Chinwe Gilean Onukwugha: Writing - Review & Editing, Visualization,
Project administration; Nneka Martina Oragba: Supervision, Project administration.
6.2. Institutional Review Board Statement
Not applicable.
6.3. Informed Consent Statement
Not applicable.
6.4. Data Availability Statement
Available on Kaggle: https://www.kaggle.com/datasets/sarahgmn/plant-village-dataset.Open asset ↗Kaggle · sarahgmn/plant-village-datasetpdf-raw-page:6 lines:1-88Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published18 Nov 2025International Journal of Innovative Science and Research TechnologyCited by 0 · OpenAlex ↗
Crop diseases cause large yield losses worldwide and represent a serious threat to food security. Traditional detection methods rely on manual inspection, which is time-consuming and error-prone. The AI-driven Crop Disease Detection and Management System presented in this paper combines environmental data analytics utilizing Random Forest regression for disease risk predictions with Convolutional Neural Networks (CNNs) for image-based disease identification. A carefully selected portion of the PlantVillage dataset, with an emphasis on the crops maize, tomato, and potato, is used to train the model. The hybrid approach leverages temperature, humidity, and rainfall data to increase prediction reliability. When compared to traditional CNN-only methods, experimental evaluation shows an accuracy of 94.33% and enhanced early disease prediction skills. The system, which offers real-time disease monitoring, is implemented as a mobile application and web platform. detection, forecasting, and treatment suggestions. This hybrid approach promotes sustainable agriculture through proactive disease management and optimized resource use.
Why it matches plant phenotyping methods植物画像から病害状態を識別するAI手法と、その評価・実装が研究の中心であり、植物病害フェノタイピングに該当する。
titleAI Driven Crop Disease Detection and Management System
Potato leaf diseases pose a serious challenge to global food security, often leading to considerable yield losses if not detected promptly. The growing maturity of deep learning has enabled automated, high-precision plant disease recognition, even on devices with limited computational resources. In this study, several lightweight convolutional neural network (CNN) models—MobileNetV3 (Small and Large), EfficientNet-Lite, ShuffleNet, and SqueezeNet—are comparatively assessed for the task of potato leaf disease classification. The models were trained under identical preprocessing and fine-tuning conditions, incorporating checkpoint-based training for stability. Among the evaluated networks, ShuffleNet delivered the highest overall performance with 99% accuracy, 0.97 precision, 0.99 recall, and an F1-score of 0.98, making it well-suited for real-time field deployment. EfficientNet-Lite also demonstrated a strong balance between speed and accuracy (91.9%), outperforming both MobileNet variants. Conversely, SqueezeNet, though the most compact model, recorded lower metrics (76% accuracy), indicating limited feature discrimination capability. This analysis underscores the balance between efficiency, robustness, and predictive accuracy, providing practical insights for deploying deep learning models in precision agriculture and low-resource environments.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類する軽量CNN手法を比較・評価しており、植物病害状態のフェノタイピング手法が中心である。
abstractThe models were trained under identical preprocessing and fine-tuning conditions, incorporating checkpoint-based training for stability.
Abstract This work presents a lightweight imaging-based AI model for rapid, point-of-care diagnosis of potato leaf diseases. Using the PlantVillage dataset comprising approximately 3,000 labeled images across three classes— Healthy , Early Blight , and Late Blight —a transfer learning approach was implemented with the MobileNetV2architecture. The dataset was split into 80% training and 20% validation sets, with preprocessing and augmentation to enhance generalization. Trained for 10 epochs using the Adam optimizer (learning rate = 0.001), the model achieved a training accuracy of 96.8% and a validation accuracy of 93.7% , with respective losses of 0.13and 0.21 . Class-wise evaluation confirmed balanced precision and recall across all categories, while external testing yielded correct disease identification with 57.2% confidence . The model demonstrates that high diagnostic accuracy can be achieved on basic hardware, making it suitable for low-resource agricultural settings. Compared to complex multimodal architectures, this MobileNetV2-based design offers fast inference, minimal computational demand, and strong generalization—establishing an efficient foundation for real-time, AI-driven plant disease diagnostics.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から推定するAI診断モデルの開発・検証が研究の中心であり、植物表現型の取得方法に該当する。
abstractThis work presents a lightweight imaging-based AI model for rapid, point-of-care diagnosis of potato leaf diseases.
The internal quality assessment of potato tubers is a crucial task in agro-industrial processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in industrial sorting lines. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 90\% and precision near 100\% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.
Why it matches plant phenotyping methodsジャガイモ塊茎の内部欠陥をRGB画像から検出・分割する画像解析パイプラインの開発と性能評価が中心であり、植物器官の状態を直接推定するため、植物フェノタイピング手法に該当する。
abstractWe present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices
Abstract - The global agricultural sector faces significant challenges due to plant diseases that threaten food security and sustainable agriculture. Traditional methods of disease detection are often labour-intensive, time-consuming, and require specialized expertise. This research presents a comprehensive machine learning framework for automated plant disease detection, leveraging both traditional machine learning and deep learning approaches. We implemented and evaluated multiple models including VGG19, Inception v3, Support Vector Machines (SVM), and k-Nearest Neighbors (kNN) on four distinct datasets: Banana Leaf, Custard Apple Leaf and Fruit, Fig Leaf, and Potato Leaf. Our experimental results demonstrate remarkable performance variations across different crops, with the highest achievement of 99.1% accuracy using VGG19 with kNN on the Custard Apple dataset, while the Potato Leaf dataset presented the greatest challenges with 62.6% accuracy using Inception v3 with SVM. The study provides valuable insights into model selection for specific agricultural applications and highlights the importance of customized solutions based on crop-specific characteristics. We also address critical challenges including dataset limitations, computational requirements, and implementation barriers in real-world agricultural settings. Keywords - Plant disease detection, machine learning, deep learning, convolutional neural networks, agricultural technology, precision agriculture.
Why it matches plant phenotyping methods植物病害状態を対象に、機械学習・深層学習による自動検出フレームワークを提示し、複数モデルとデータセットで性能評価しているため、病害表現型の取得・判定手法が中心である。
abstractThis research presents a comprehensive machine learning framework for automated plant disease detection, leveraging both traditional machine learning and deep learning approaches.
Chlorophyll fluorescence parameters (CFPs), especially maximum photosynthetic efficiency of optical system II (Fv/Fm), are the intrinsic photosynthesis probes of crop stress and photosynthetic function. Hyperspectral image (HSI) offers a rapid alternative to traditional pulse amplitude modulation for Fv/Fm, but selecting the uninformative wavelengths reduce accuracy. To address this, a Wavelet Cluster (WCL) method based on Continuous wavelet transform (CWT) was proposed to enhance sensitive wavelengths extraction. Spectral data was preprocessed by Savizky-Golay smoothing (SG) and Multiple scattering correction (MSC), followed by CWT decomposition with bior3.3, gaus4 and meyr wavelet functions to form WCL. Sensitive wavelet coefficients (WCs) were selected using Monte Carlo uninformative variable elimination (MC-UVE), and the Partial Least Squares Regression (PLSR) and Random Forest (RF) modeling methods were established. The results showed that (1) the reflectance spectrum decreased with the increase of Fv/Fm in potato leaf. (2) WCL effectively captured chlorophyll fluorescence spectral features. (3) The WCL-RF model outperformed WCL-PLSR, with a calibration set Rc2 of 0.75, RMSEc of 0.0209, a prediction set Rp2 of 0.73, RMSEp of 0.0225, respectively. This study demonstrates the potential of WCL for accurate Fv/Fm detection, and supports for potato canopy photosynthetic activity assessment.
Why it matches plant phenotyping methodsジャガイモ葉のクロロフィル蛍光指標Fv/Fmという植物生理形質を、ハイパースペクトル画像と新規のウェーブレットクラスタ解析で推定し、モデル性能も評価しているため、フェノタイピング手法が中心である。
abstractTo address this, a Wavelet Cluster (WCL) method based on Continuous wavelet transform (CWT) was proposed to enhance sensitive wavelengths extraction.
In the domain of plant morphological studies, three-dimensional scanning technologies have brought about a paradigm shift in the field of leaf structure modelling. Nevertheless, the high cost and operational complexity of these systems act as significant barriers to widespread adoption. To address this issue, a single-image 3D reconstruction pipeline was developed, focusing on potato leaves and optimized for use with mobile phone cameras. The algorithm begins with image preprocessing to enhance quality, followed by leaf instance segmentation to isolate the target leaf. Subsequently, a precise 2D leaf contour is extracted to capture planar geometry. Subsequently, 3D spatial features are recovered from a single image to infer depth information. Contour back-projection is a process that Links the extracted 2D contour to the estimated 3D space. The discretization of the 3D contour is enabled by boundary sampling, thereby facilitating the generation of an initial 3D polygonal mesh. Finally, mesh surface refinement is applied to optimize model accuracy and visual fidelity. The methodology employed in this study successfully reconstructed potato and other crop leaves, demonstrating minimal deviation in key morphological shape descriptors and negligible error in surface area measurements in comparison to the ground truth. The reconstructed models exhibited high geometric congruence with the original leaves. This demonstrates the potential of our technique to broaden the accessibility of conventional modelling approaches and to advance methodologies within the field of crop phenotyping.
Why it matches plant phenotyping methods単一画像から葉の3D形状を再構成し、形態形状記述子や表面積を推定・検証する手法開発であり、植物フェノタイピングが中心である。
abstracta single-image 3D reconstruction pipeline was developed, focusing on potato leaves and optimized for use with mobile phone cameras.
The early detection of plant diseases is critical for ensuring optimal crop health and maximizing yield. This study presents an AI-driven autonomous robotic system, “AgriScout”, designed for the early identification and mapping of Potato Virus Y (PVY) infections in potato crops. The developed system integrates an electric field robot equipped with RGB cameras and a GPS-RTK module for precise image capture and geolocation of infected plants. The collected high-resolution images are transmitted to a cloud-based server, where a YOLO (You Only Look Once) deep learning model processes them to detect PVY-infected plants. The system generates an infestation map with accurate geospatial coordinates of affected areas, facilitating targeted intervention. Field trials were conducted in Prince Edward Island, Canada, to develop a labeled dataset comprising healthy and PVY-infected plants across different growth stages and environmental conditions. The YOLO model was trained and validated using this dataset, achieving a mean Average Precision (mAP@0.5) of 85%, an F1-score of 0.80, a Precision of 0.85, and a Recall of 0.76 during testing. The model demonstrated robust detection capabilities under varying foliage densities, effectively distinguishing infected plants with high accuracy. The results underscore the potential of “AgriScout” as a scalable, real-time disease detection solution for precision agriculture. By automating disease monitoring and reducing reliance on manual scouting, the system enhances farm productivity, minimizes yield losses, and supports sustainable disease management practices. The integration of robotics and AI in pathogen detection represents a significant advancement in agricultural automation, paving the way for intelligent, data-driven decision-making in modern farming systems.
Why it matches plant phenotyping methods植物のPVY感染状態を画像から検出・地理化するロボット撮像とYOLO解析が研究の中心であり、データセット作成とモデル検証も行っているため、病害表現型の計測手法として適格。
abstractThis study presents an AI-driven autonomous robotic system, “AgriScout”, designed for the early identification and mapping of Potato Virus Y (PVY) infections in potato crops.
Potassium is a key element for potato growth and development, playing an important role in enhancing stress resistance, improving tuber quality, and ensuring stable high yields. Therefore, precise and dynamic management of potassium is of vital importance. This study conducted a two-year field experiment on potatoes, setting three irrigation levels (W1: 100 % ETC, W2: 80 % ETC, W3: 60 % ETC) and five potassium fertilizer gradients (K0: 0 kg·ha⁻¹, K1: 100 kg·ha⁻¹, K2: 200 kg·ha⁻¹, K3: 300 kg·ha⁻¹, K4: 400 kg·ha⁻¹). The results showed that the W1K3 treatment achieved the highest potato yield of 59,482.16 kg·ha⁻¹, while excessive potassium application (K4) led to a yield reduction. Subsequently, a critical potassium concentration dilution curve was constructed, and the Measured Potassium Nutrition Index (KNIM) and Theoretical Potassium Nutrition Index (KNIT) were calculated. Under the K3 gradient, the KNI values across all irrigation levels were close to 1, corresponding to the maximum potato yield, with a strong correlation observed between KNIM and KNIT (r > 0.87). Concurrently, multispectral data were collected to construct vegetation indices, extract image texture features, and generate texture indices through random combination of these features. The results indicated that most vegetation indices and some texture features were significantly correlated with KNI (P < 0.05), while all constructed texture indices exhibited extremely significant correlations with KNI (P < 0.01). Different variable combinations were used as input variables to develop KNI prediction models based on machine learning. The optimal performance was achieved by the model integrating spectral information and texture indices with the Random Forest (RF) algorithm, which yielded validation set results for KNIM and KNIT as follows: determination coefficients (R²) of 0.824 and 0.795, root mean square errors (RMSE) of 0.061 and 0.064, and mean relative errors (MRE) of 4.817 % and 5.787 %, respectively. As a theoretically calculated index, the correlation between predicted KNIT values and relative yield further confirmed the validity of KNIT, while the generated potassium nutrition status maps intuitively and clearly demonstrated the feasibility and accuracy of KNIT. This study successfully realized non-destructive and real-time prediction of KNIT through machine learning models, providing a quantitative basis for accurately analyzing the dynamic potassium demand of plants. It holds significant practical implications for promoting the green and sustainable development of the potato industry.
Why it matches plant phenotyping methodsジャガイモのカリウム栄養状態を対象に、マルチスペクトル情報・画像テクスチャ・機械学習を統合してKNIを非破壊かつリアルタイムに推定し、検証しているため、表現型取得・推定手法が中心である。
abstractmultispectral data were collected to construct vegetation indices, extract image texture features, and generate texture indices through random combination of these features.
In modern precision agriculture, early and accurate identification of crop diseases is crucial for reducing yield loss and minimizing pesticide overuse. This study proposes an IoT-enabled framework that integrates convolutional neural networks (CNNs) with image processing techniques for automated classification and quantification of diseases in rice and potato crops. A custom-curated dataset was developed, comprising over 1,800 images acquired through smartphone cameras and foldscope devices under natural lighting conditions. The proposed CNN model achieved a classification accuracy of over 95%, with a disease quantification accuracy of 90.5%, calculated using pixel-level segmentation of infected regions. Experimental results revealed infection percentages ranging from 0.68% in early-stage cases to 13.98% in severely affected samples, enabling precise disease severity analysis. The framework includes a MATLAB-based graphical user interface (GUI) for real-time visualization of classification results and severity scores. Training convergence was demonstrated with a mini-batch loss reduction from 1.0879 to 0.0094 over 200 iterations, and classification confidence scores exceeding 90% for most disease categories. In addition to software implementation, the model was synthesized for hardware deployment using FPGA, demonstrating less than 5% LUT and 1% register usage for 512 × 512 images, ensuring resource-efficient performance in IoT environments. This work introduces a scalable, field-deployable tool for crop health monitoring, with potential to enhance sustainable farming practices through timely disease management.
Why it matches plant phenotyping methodsイネ・ジャガイモの病害画像を用いて感染領域と病害重症度を定量化するCNN・画像処理・GUI・FPGA実装を開発しており、植物表現型（病害状態）の取得・抽出が研究の中心です。
abstractThis study proposes an IoT-enabled framework that integrates convolutional neural networks (CNNs) with image processing techniques for automated classification and quantification of diseases in rice and potato crops.
To enhance crop yield, detecting leaf diseases has become a crucial research focus. Deep learning and computer vision excel in digital image processing. Various techniques grounded in deep learning have been utilized for detecting plant leaf diseases; however, achieving high accuracy remains a challenge. Basic convolutional neural networks (CNNs) in deep learning struggle with issues such as the abnormal orientation of images, rotation, and others, resulting in subpar performance. CNNs also need extensive data covering a wide range of variations to deliver strong performance. CapsNet is an innovative deep-learning architecture designed to address the limitations of CNNs. It performs well without needing a vast amount of data in various variations. CapsNets have their limitations, such as the encoder network considering every element in the image and the crowding issue. Due to this, they perform well on simple image recognition tasks but struggle with more complex images. To address these challenges, we introduced a new CapsNet model known as CCFM-CapsNet. This model incorporates CLAHE to reduce image noise and CDH to extract crucial features. Also, max-pooling and dropout layers are incorporated in the original CapsNet model for identifying and classifying diseases in apples, bananas, grapes, corn, mangoes, pepper, potatoes, rice, tomato and also for classifying fashion-MNIST and CIFAR-10 datasets. The proposed CCFM-CapsNet demonstrates significantly high validation accuracies, achieving 99.53%, 95.24%, 99.75%, 97.40%, 99.13%, 100%, 99.77%, 100%, 98.54%, 93.48%, and 82.34% with corresponding parameters in millions(M) 4.68M, 4.68M, 4.68M, 4.68M, 4.79M, 4.63M, 4.66M, 4.68M, 4.84M, 2.39M, and 4.84M for the datasets aforementioned respectively, outperforming the traditional CapsNet and other advanced CapsNet models. Consequently, the CCFM-CapsNet model can be utilized effectively as a smart tool for identifying plant diseases and also in achieving Sustainable Development Goal 2 (Zero Hunger), which aims to end global hunger by the year 2030.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習モデルを提案・評価しており、画像取得・分類手法が研究の中心であるため。
abstractTo address these challenges, we introduced a new CapsNet model known as CCFM-CapsNet.
The accurate classification of plant diseases is vital for global food security, as diseases can cause major yield losses and threaten sustainable and precision agriculture. The classification of plant diseases in low-light noisy environments is crucial because crops can be continuously monitored even at night. Important visual cues of disease symptoms can be lost due to the degraded quality of images captured under low-illumination, resulting in poor performance of conventional plant disease classifiers. However, researchers have proposed various techniques for classifying plant diseases in daylight, and no studies have been conducted for low-light noisy environments. Therefore, we propose a novel model for classifying plant diseases from low-light noisy images called dilated pixel attention network (DPA-Net). DPA-Net uses a pixel attention mechanism and multi-layer dilated convolution with a high receptive field, which obtains essential features while highlighting the most relevant information under this challenging condition, allowing more accurate classification results. Additionally, we performed fractal dimension estimation on diseased and healthy leaves to analyze the structural irregularities and complexities. For the performance evaluation, experiments were conducted on two public datasets: the PlantVillage and Potato Leaf Disease datasets. In both datasets, the image resolution is 256 × 256 pixels in joint photographic experts group (JPG) format. For the first dataset, DPA-Net achieved an average accuracy of 92.11% and harmonic mean of precision and recall (F1-score) of 89.11%. For the second dataset, it achieved an average accuracy of 88.92% and an F1-score of 88.60%. These results revealed that the proposed method outperforms state-of-the-art methods. On the first dataset, our method achieved an improvement of 2.27% in average accuracy and 2.86% in F1-score compared to the baseline. Similarly, on the second dataset, it attained an improvement of 6.32% in average accuracy and 6.37% in F1-score over the baseline. In addition, we confirm that our method is effective with the real low-illumination dataset self-constructed by capturing images at 0 lux using a smartphone at night. This approach provides farmers with an affordable practical tool for early disease detection, which can support crop protection worldwide.
Why it matches plant phenotyping methods低照度画像から植物病害状態を分類する新規画像解析モデルを開発し、複数データセットで性能評価しており、植物表現型取得・判定手法が中心である。
abstractwe propose a novel model for classifying plant diseases from low-light noisy images called dilated pixel attention network (DPA-Net).
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicWe have made the trained
DPA-Net with all the codes publicly available on the GitHub [25].Open asset ↗DPA-Netpdf-page:4 lines:1-47Code / dataset availability confirmedCrossref · Europe PMC · checked 8 Sept 2026
Common beanPotatoTomatoField / plotLeafObject detectionDisease symptoms / severity
In order to overcome the key challenges associated with detecting tomato leaf disease in complex agricultural environments, such as leaf occlusion, variation in lesion size and light interference, this study presents a lightweight detection model called ToMASD. This model integrates multi-scale feature decoupling and an adaptive alignment mechanism. The model innovatively comprises a dual-branch adaptive alignment module (TAAM) that achieves cross-scale lesion semantic alignment via a dynamic feature pyramid, a local context-aware gated unit (Faster-GLUDet) that uses a spatial attention mechanism to suppress background noise interference, and a multi-scale decoupling detection head (MDH) that balances the detection accuracy of small and diffuse lesions. On a dataset containing six types of disease under various weather conditions, ToMASD achieves an average precision of 84.3%,.by a margin of 4.7% to 12.1% over thirteen mainstream models. The computational load is compressed to 7.1 GFLOPs. Through the introduction of a transfer learning paradigm, the pre-trained weights of the tomato disease detection model can be transferred to common bean and potato detection tasks. Through domain adaptation layers and adversarial feature decoupling strategies, the domain shift problem is overcome, achieving an average precision of 92.7% on the target crop test set. False detection rates in foggy and strong light conditions are controlled at 6.3% and 9.8%, respectively. This study achieves dual breakthroughs in terms of both high-precision detection in complex scenarios and the cross-crop generalization ability of lightweight models. It provides a new paradigm for universal agricultural disease monitoring systems that can be deployed at the edge.
Why it matches plant phenotyping methodsトマト葉の病斑・病害状態を画像から検出するモデルを開発し、複数モデル比較、悪条件評価、他作物への汎化検証を行っており、植物病害フェノタイピング手法が中心である。
abstractthis study presents a lightweight detection model called ToMASD.
Reproduction assets foundThe paper's data availability statement points to a public potato disease dataset hosted on GitCode, which was used in the study's cross-crop transfer experiments (potato disease detection). The tomato dataset is from Roboflow (third-party platform, no direct URL given), and no author analysis code or trained model is,Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://gitcode.com/open-source-toolkit/829ec .Open asset ↗gitcode.com/open-source-toolkit/829eclines:649-666Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Introduction The timely and precise detection of foliar diseases in potatoes, a food crop of worldwide importance, is essential to safeguarding agricultural output. In complex field environments, traditional recognition methods encounter significant challenges, including the difficulty in extracting features from small and diverse early-stage lesions, blurred edge features due to gradual transitions between diseased and healthy tissues, and degraded robustness from background interference such as leaf texture and varying illumination. Methods To address these limitations, this study proposes an optimized lightweight convolutional neural network architecture, termed LDL-MobileNetV3S. The model is built upon the MobileNetV3 Small backbone and incorporates three innovative modules: a Lightweight Multi-scale Lite Fusion (LF) module to enhance the perception of small lesions through cross-layer connections, a Dynamic Dilated Convolution (DDC) module that employs deformable convolutions to adaptively capture pathological features with blurred boundaries, and a Lightweight Attention (LA) module designed to suppress background interference by assigning spatially adaptive weights. Results Experimental results demonstrate that the proposed model achieves a recognition accuracy of 94.89%, with corresponding Precision, Recall, and F1-score values of 93.54%, 92.53%, and 92.77%, respectively. Notably, these results are attained under a highly compact model configuration, requiring only 6.17 MB of storage and comprising 1.50 million parameters. This is substantially smaller than benchmark models such as EfficientNet-B0 (15.61 MB / 3.83 M parameters) and ConvNeXt Tiny (106 MB / 27.8 M parameters). Conclusion The proposed LDL-MobileNetV3S model demonstrates superior performance and efficiency compared to several existing lightweight models. This study provides a cost-effective and high-accuracy solution for potato leaf disease diagnosis, which is particularly suitable for deployment on intelligent diagnostic devices operating in resource-limited field environments.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から診断する軽量CNNモデルの開発と性能評価が研究の中心であり、植物の病害状態を推定するフェノタイピング手法に該当する。
abstractThe proposed LDL-MobileNetV3S model demonstrates superior performance and efficiency compared to several existing lightweight models.
Potato cyst nematodes pose a major threat to potato cultivation, with infestations often going undetected for years. Early and accurate detection is crucial for effective management, necessitating reliable, large-scale monitoring methods. Hyperspectral imaging shows great promise for non-invasive nematode detection, yet distinguishing between biotic (e.g., nematodes) and abiotic (e.g., drought) stressors remains a challenge. This study investigated the stress responses of potato plants to potato cyst nematodes Globodera rostochiensis and G. pallida , and water deficiency. We generated datasets to isolate and evaluate single and combined stressor effects on plant physiology and morphology. Various machine learning models and spectral processing techniques were applied to assess classification performance. Exploratory methods identified key spectral wavelengths, while statistical analyses evaluated the significance of physiological and morphological traits. Results showed that water deficiency was the dominant classification factor (F1 = 0.95). The distinction between infected and non-infected plants reached F1 = 0.70 in well-watered conditions and 0.80 in water-deficient plants. Distinguishing nematode species and inoculation levels yielded moderate accuracy (F1 = 0.65-0.80), improving to 0.80 when combining biotic and abiotic stress. However, classifying multiple stress categories simultaneously reduced performance (F1 = 0.58). These findings highlight the challenges of stressor separation and the potential of hyperspectral imaging for nematode detection. Further research is needed to refine classification models and validate findings under field conditions, facilitating the integration of hyperspectral imaging into precision agriculture.
Why it matches plant phenotyping methodsジャガイモの感染状態・生理／形態ストレスをハイパースペクトル画像と機械学習で推定する手法が研究の中心であり、植物病害状態の表現型推定に該当する。
abstractHyperspectral imaging shows great promise for non-invasive nematode detection
Reproduction assets foundThe authors explicitly state that processed hyperspectral data plus morphology and physiology measurements are publicly available on Zenodo, and their analysis code is on GitHub. Both are paper-specific, public, and actionable. The SiaPy library is a generic third-party tool and is excluded.Code · publicthe code repository at https://github.com/Manuscripts-code/Potato-plants-nemdetect--PP-2025 (accessed on October 5, 2025)Open asset ↗github · Manuscripts-code/Potato-plants-nemdetect--PP-2025lines:539-558Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published10 Oct 20252025 8th World Engineering Conference on Contemporary Technologies (WECON)Cited by 0 · OpenAlex ↗
Plant diseases reduce agricultural productivity, and farmers struggle to precisely identify and control these diseases which leads to crop losses. The early identification of plant diseases is a challenging task in agriculture due to the variation in the size, shape, colour, and texture caused by environmental changes. This research employs convolutional neural networks (CNNs) for the identification of plant leaf diseases, namely, corn common rust, potato early blight, and tomato bacterial spot. The model was trained with the augmented dataset on 15 epochs with and without the additional convolution layer in the CNN architecture. The accuracy achieved by CNN without adding additional layers is 99.4% and after adding additional layers, the accuracy is 75.5% at 10 epoch. These results show that the proposed method can be optimized in the future and can be used as the most effective method in predicting plant leaf disease. This model may lead to enhanced crop yields and quality by rapid prediction of leaf diseases.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定するCNN手法が研究の中心であり、構造変更と性能比較による評価も行っているため、植物フェノタイピング手法として採用する。
abstractThis research employs convolutional neural networks (CNNs) for the identification of plant leaf diseases, namely, corn common rust, potato early blight, and tomato bacterial spot.
The quality of seed pieces is crucial for potato planting. Each seed piece should contain viable potato eyes and maintain a uniform size for mechanized planting. However, existing intelligent methods are limited by a single view, making it difficult to satisfy both requirements simultaneously. To address this problem, we present an intelligent 3D potato cutting simulation system. A sparse 3D point cloud of the potato is reconstructed from multi-perspective images, which are acquired with a single-camera rotating platform. Subsequently, the 2D positions of potato eyes in each image are detected using deep learning, from which their 3D positions are mapped via back-projection and a clustering algorithm. Finally, the cutting paths are optimized by a Bayesian optimizer, which incorporates both the potato’s volume and the locations of its eyes, and generates cutting schemes suitable for different potato size categories. Experimental results showed that the system achieved a mean absolute percentage error of 2.16% (95% CI: 1.60–2.73%) for potato volume estimation, a potato eye detection precision of 98%, and a recall of 94%. The optimized cutting plans showed a volume coefficient of variation below 0.10 and avoided damage to the detected potato eyes, producing seed pieces that each contained potato eyes. This work demonstrates that the system can effectively utilize the detected potato eye information to obtain seed pieces containing potato eyes and having uniform size. The proposed system provides a feasible pathway for high-precision automated seed potato cutting.
Why it matches plant phenotyping methods多視点画像と点群融合によりジャガイモの体積および芽の3D位置を推定し、精度を検証するシステム開発が中心であるため、植物形質取得手法として含める。
abstractA sparse 3D point cloud of the potato is reconstructed from multi-perspective images, which are acquired with a single-camera rotating platform.
Accurately detecting and counting potatoes during early harvest is essential for estimating yield, automating sorting, and supporting data-driven agricultural decisions. However, field environments often present practical challenges-such as soil occlusion, overlapping tubers, and inconsistent lighting-that hinder robust visual recognition. In response, we introduce SCG-YOLOv8n, a compact and field-adapted detection framework built upon the YOLOv8n architecture and specifically tailored for small-object detection in real-world farming conditions. The model incorporates three practical enhancements: a C-SPD module that preserves spatial detail to improve recognition of partially buried tubers; an S-CARAFE operator that reconstructs fine-scale features during upsampling; and GhostShuffleConv layers that reduce computational overhead without sacrificing accuracy. Through extensive field-based experiments, SCG-YOLOv8n consistently outperforms YOLOv5n and its base version across all key metrics. Float16 quantization compresses the model to 3.2 MB, enabling real-time inference on Android devices. We also developed PotatoDetector, a mobile application that demonstrates stable performance in field trials, achieving an RMSE of 1.38 and [Formula: see text] of 0.96 in counting tasks. These results suggest that SCG-YOLOv8n offers a practical and scalable tool for precision agriculture, with potential applicability to other root and tuber crop monitoring scenarios.
Why it matches plant phenotyping methodsジャガイモ塊茎の画像検出・計数を行うモデルとモバイル実装を開発し、圃場で性能検証している。塊茎数という植物器官形質の取得が中心であり、単なる収量測定ではない。
abstractwe introduce SCG-YOLOv8n, a compact and field-adapted detection framework built upon the YOLOv8n architecture and specifically tailored for small-object detection in real-world farming conditions.
Reproduction assets foundThe paper's custom potato image dataset is not publicly available (available only from the corresponding author on request), but the authors provide a public GitHub repository for the SCG-YOLOv8n analysis code with an explicit availability statement and URL.Code · publicCode availability
Code can be found at https://github.com/AiXia520/SCG-YOLOv8n.git.Open asset ↗https://github.com/AiXia520/SCG-YOLOv8n.githtml-lines:359-392Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Potatoes are the most extensively cultivated vegetable crop in Canada and rank as the fifth largest primary agricultural commodity. Given their diverse end uses and significant market value, particularly in processed forms, ensuring consistent quality from harvest to consumption is of critical importance. Total glycoalkaloids (TGA) are nitrogen-containing secondary metabolites that are known to accumulate in the tuber as an effect of greening in-field or elsewhere in the supply chain. In this study, 210 Yukon Gold (YG) potatoes were exposed to a constant light source to green over a period of 14 days and sampled in 7-day intervals. The samples were scanned using a short-wave infrared (SWIR) hyperspectral imaging camera in the 900-2500 nm wavelength range. Once individually scanned, pixel-wise spectral data was extracted and averaged for each tuber and matched with its respective ground truth TGA values which were obtained using a High-Performance Liquid Chromatography (HPLC) system. Prediction models using the partial least squares regression technique were developed from the extracted hyperspectral data and reference TGA values. Wavelength selection techniques such as competitive adaptive re-weighted sampling (CARS) and backward elimination (BE) were deployed to reduce the number of contributing wavelengths for practical applications. The best model resulted in a correlation coefficient of cross-validation (R 2 cv ) of 0.72 with a root mean square error of cross-validation (RMSE cv ) of 51.50 ppm.
Why it matches plant phenotyping methodsジャガイモ塊茎のグリコアルカロイド量という器官形質を、SWIRハイパースペクトル画像から推定する予測モデルを開発・交差検証しており、形質取得・抽出手法が中心である。
abstractPrediction models using the partial least squares regression technique were developed from the extracted hyperspectral data and reference TGA values.
Accurate 3D phenotyping of agricultural produce remains challenging due to the trade-off between reconstruction quality and acquisition throughput in existing sensing technologies. While RGB-D cameras enable high-throughput scanning in operational settings like harvesting conveyors, they produce incomplete, low-quality 3D models. Conversely, close-range Structure-from-Motion (SfM) produces high-quality reconstructions but is not suitable for high-throughput field application. This study bridges this gap through 3DPotatoTwin , a paired dataset containing 339 tuber samples across three cultivars collected in Hokkaido, Japan. Our dataset uniquely combines: (1) conveyor-acquired RGB-D point clouds, (2) ground measurement, (3) SfM reconstructions under indoor controlled environment, and (4) aligned model pairs with transformation matrices. The multi-sensory alignment employs an semi-supervised pin-guided pipeline incorporating single-pin extraction and referencing, cross-strip matching, and binary-color-enhanced ICP, achieving 0.59 ± 0.11 mm registration accuracy. Beyond serving as a benchmark for 3D phenotyping algorithms, the dataset enables training of 3D completion networks to reconstruct high-quality 3D models from partial RGB-D point clouds. Meanwhile, the proposed semi-automated annotation pipeline has the potential to accelerate 3D dataset generation for similar studies. The presented methodology demonstrates broader applicability for multi-sensor data fusion across crop phenotyping applications. The dataset and pipeline source code are publicly available at HuggingFace and GitHub, respectively.
Why it matches plant phenotyping methodsジャガイモ塊茎の3D表現型計測を対象に、RGB-D・SfM・地上計測を統合したデータセット、位置合わせパイプライン、ベンチマークを開発しており、表現型取得手法が中心である。
abstractAccurate 3D phenotyping of agricultural produce remains challenging due to the trade-off between reconstruction quality and acquisition throughput in existing sensing technologies.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicAll the batch processing scripts mentioned in this section were provided in the 3dscan folder at Github (https://github.com/UTokyo-FieldPhenomics-Lab/PotatoScan/).Open asset ↗UTokyo-FieldPhenomics-Lab/PotatoScanhtml-lines:119-131Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
As climate extremes increasingly threaten global food security, precision tools for early detection of crop stress have become vital, particularly for root crops such as potato ( Solanum tuberosum L.) and sweet potato ( Ipomoea batatas L. Lam.), which are especially susceptible to environmental stressors throughout their life cycles. In this study, plants were monitored from the initial onset of seasonal stressors, including spring drought, heat, and episodes of excessive rainfall, through to harvest, capturing the full range of physiological and biochemical responses under seasonal, simulated conditions in greenhouses. The spectral data were obtained from regions of interest (ROIs) of each cultivar's leaves, with over 3000 data points extracted per cultivar; these data were subsequently used for model development. A comprehensive classification framework was established by employing machine learning models, Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Partial Least Squares-Discriminant Analysis (PLS-DA), to detect stress across various growth stages. Furthermore, severity levels were objectively defined using photoreflectance indices and principal component analysis (PCA) data visualizations, which enabled consistent and reliable classification of stress responses in both individual cultivars and combined datasets. All models achieved high classification accuracy (90-98%) on independent test sets. The application of the Successive Projections Algorithm (SPA) for variable selection significantly reduced the number of wavelengths required for robust stress classification, with SPA-PLS-DA models maintaining high accuracy (90-96%) using only a subset of informative bands. Furthermore, SPA-PLS-DA-based chemical imaging enabled spatial mapping of stress severity within plant tissues, providing early, non-invasive insights into physiological and biochemical status. These findings highlight the potential of integrating hyperspectral imaging and machine learning for precise, real-time crop monitoring, thereby contributing to sustainable agricultural management and reduced yield losses.
Why it matches plant phenotyping methods植物葉のハイパースペクトル画像からストレス状態・重症度を抽出し、機械学習で分類・空間マッピングする方法が研究の中心であり、独立テストによる性能評価も行っている。
abstractA comprehensive classification framework was established by employing machine learning models, Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and Partial Least Squares-Discriminant Analysis (PLS-DA), to detect stress across various growth stages.
The Transition to a Data-Driven Agriculture (TTADDA) project focuses on advancing the shift toward high-tech, circular agriculture. By developing cutting-edge sensor technologies and AI-driven tools, the project aims to boost productivity through a data-centric potato production system that supports circular agricultural practices. Potato phenotyping is crucial for creating high-yielding, resilient, and sustainable potato crops, which are essential in global food systems. Specifically in the Netherlands, the global leader in seed potato production and Japan that produces certified seed potatoes under strict quality controls and phytosanitary regulations. A multi-season drone dataset from five potato trials—three in Japan and two in the Netherlands was collected. Each trial field was divided into small plots, each planted with a specific cultivar to assess varietal performance. Data included drone imagery (RGB and multispectral), manual yield and ground coverage measurements, and weather data. The combination of sensor versatility, diverse potato varieties, and varying climate and soil conditions between Japan and the Netherlands makes this dataset highly valuable and potentially reusable for a wide range of applications. Using MIAPPE for this dataset ensures consistent, clear documentation of sensors, varieties, and conditions, making the data findable, reusable, and easy to integrate with other studies. It also supports reproducibility and automated analysis across the multi-location trials.
Why it matches plant phenotyping methodsジャガイモの表現型解析を目的とした、RGB・マルチスペクトルUAV画像と地上測定を含む多季節・多地点データセットであり、再利用性と再現性を意識したフェノタイピング基盤として中心的です。
abstractA multi-season drone dataset from five potato trials—three in Japan and two in the Netherlands was collected.
Nitrogen (N) management is one of the main factors enhancing potato productivity and promoting sustainable agricultural practices. The Nitrogen Nutrition Index (NNI, obtained as the ratio of actual plant N, to the critical plant N concentration) is widely applied to assess the N status of various crops. Traditionally, NNI is calculated using field data, but remote sensing (RS) technologies can offer more rapidly and timely assessment of the spatiotemporal (within field) variability of this index. This study employs multispectral data acquired via Unmanned Aerial Vehicle (UAV) and machine learning (ML) models to estimate potato NNI. A Bayesian hierarchical partially pooled method was fitted to a three-year field experiment in Denmark and extensive ground-based potato datasets to model the critical nitrogen dilution curve (CNDC) and calculate the NNI. Multispectral UAV data were processed to extract four spectral bands and calculate several vegetation indices, which were used as predictors to train and test six ML models: Linear regression, support vector machines, gaussian process regression, stepwise linear regression, ensemble trees and neural networks. Among the compared models, gaussian process regression outperformed, showing R² equal to 0.83 and a RMSE of 0.10 and providing accurate NNI predictions, comparable to ground-based Bayesian estimates. The variability of the NNI was analyzed over the seasons using 28 NNI maps derived from UAV surveys at spatial resolution of 0.04–0.09 m/pixel, capturing spatial variations in crop N status over time. The proposed framework, designed for NNI prediction at the intra-field scale, has the potential to be adapted to different environments and crops. The framework can support practical decisions for precision N management, reducing the environmental impact of potato cultivations and enhancing sustainability.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像と機械学習により、ジャガイモの窒素栄養状態（NNI）を推定する手法を開発・比較・検証しており、植物表現型の取得が研究の中心である。
abstractThis study employs multispectral data acquired via Unmanned Aerial Vehicle (UAV) and machine learning (ML) models to estimate potato NNI.
PotatoRaman / spectroscopyPhysiological trait estimationWater status / transpiration
Near infrared spectroscopy (NIRS) has been widely used as a nondestructive testing technique and plays a crucial role in the quality inspection of agricultural products. However, the variability between different batches of samples hinders the application of commercial NIRS processes. Therefore, model transfer is usually performed on new samples to enhance the generalizability of the device. In this study, a new algorithm was developed based on the slope and bias correction algorithm (SBC) for model transfer between two different batches of samples, using potatoes of different origins as experimental samples for prediction models of potato quality, and based on this algorithm, model transfer between two different batches of samples was successfully implemented in a self-made portable non-destructive potato detection device. The results showed that the device developed based on the new algorithm gives good results for subsamples prediction. In the dry matter model, the correlation coefficient (R), root mean square error (RMSE) and relative standard deviation (RSD) of the new algorithm optimized compared with the traditional SBC algorithm were improved from 0.7843, 1.2080% and 6.59% to 0.8251, 1.1307 and 6.17%, respectively; in the starch model, the new algorithm optimized R, RMSE and RPD improved from 0.7971, 1.0023% and 7.43% to 0.8176, 0.9570% and 7.31%, respectively, compared with the traditional SBC algorithm. The transfer of NIR correction models for the dry matter and starch content of potatoes was basically achieved, which provided technical and theoretical support to enhance the model universality of convenient nondestructive detection devices.
Why it matches plant phenotyping methodsジャガイモの乾物・デンプン含量という植物器官形質を非破壊NIRで測定する携帯型デバイスと、バッチ間モデル移 transferアルゴリズムを開発・評価しており、表現型取得法が中心である。
abstracta new algorithm was developed based on the slope and bias correction algorithm (SBC) for model transfer between two different batches of samples
Plant diseases pose a significant threat to global agricultural productivity, particularly affecting key crops like tomato and potato. Traditional disease detection methods are often slow, subjective, and labour-intensive, leading to delayed responses and increased crop losses. This study proposes a hybrid machine learning framework that integrates ResNet9 for classification and U-Net for segmentation to detect and localize leaf diseases in tomato and potato plants. A comprehensive dataset of over 22,500 images spanning 13 classes, including healthy and diseased samples, was compiled from multiple sources and preprocessed using image normalization, histogram equalization, and data augmentation techniques. The model was trained using a 70:20:10 data split and optimized through early stopping and cyclic learning rates. Evaluation metrics including accuracy, precision, recall, F1-score, and ROC-AUC were used to assess performance, with the proposed model achieving a remarkable accuracy of 96.3%, F1-score of 95.2%, and ROC-AUC of 97.1%. The use of U-Net enabled accurate segmentation of infected regions, improving model interpretability and trustworthiness. Confusion matrix analysis revealed minimal misclassifications, and visual tools such as saliency maps confirmed the model’s attention to disease-prone areas. Real-world testing demonstrated the system’s robustness across different environments and lighting conditions. Comparative results showed superior performance of the hybrid model over VGG16, EfficientNet-B0, and baseline CNNs in both accuracy and inference speed. This approach offers a scalable, real-time solution for automated plant disease detection and diagnosis, particularly suited for use in resource-constrained agricultural settings. The hybrid model not only supports early intervention and precision agriculture practices but also bridges the gap between advanced machine learning and practical farming needs.
Why it matches plant phenotyping methods植物葉の病変領域を画像から検出・分類・分割する手法が研究の中心であり、病害状態という植物表現型を直接推定しているため含める。
abstractThis study proposes a hybrid machine learning framework that integrates ResNet9 for classification and U-Net for segmentation to detect and localize leaf diseases in tomato and potato plants.
Introduction: This research aims to develop an advanced deep learning (DL) model for the accurate detection of potato leaf diseases, specifically Early Blight and Late Blight, which significantly affect crop yield in India. By modifying the DenseNet architecture, the proposed model achieves an accuracy of 99.54%, surpassing previous benchmarks. A mobile app has also been introduced to assist farmers with real-time disease diagnosis, actionable solutions, and expert consultation, thereby improving overall crop management and food security. Artificial Intelligence (AI) and deep learning provide promising solutions for accurate and efficient disease detection. Methods: This study proposes a novel deep learning approach that modifies the DenseNet architecture for improved disease classification. The model was trained on a dataset of potato leaf images, leveraging image processing and deep learning techniques to enhance detection accuracy. Results: The modified Dense-Net model achieved a classification accuracy of 99.54%, outperforming previous existing literature. This significant improvement underscores the robustness and reliability of the proposed approach in effectively detecting potato plant diseases. Discussions: The proposed model achieves a high accuracy of 99.54%, surpassing previous approaches and demonstrating significant advancement in potato disease detection. Its integration into a mobile app bridges the gap between AI research and practical farming applications, offering real-time diagnosis and expert support. However, limitations such as dataset variability and the need for broader field validation remain, highlighting the importance of continuous model updates and testing. Conclusion: To aid farmers, a user-friendly mobile application powered by a deep learning model was developed. The app provides disease diagnosis, treatment recommendations, and real- time consultations with certified agronomists. This AI-driven tool enhances accessibility and decision-making for farmers, promoting sustainable agricultural practices.
Why it matches plant phenotyping methodsジャガイモ葉画像から植物病害状態を推定する深層学習手法を開発・評価しており、植物フェノタイピングが中心的である。
abstractThis research aims to develop an advanced deep learning (DL) model for the accurate detection of potato leaf diseases
The internal quality assessment of potato tubers is a crucial task in agro-industrial processing. Traditional methods struggle to detect internal defects such as hollow heart, internal bruises, and insect galleries using only surface features. We present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in industrial sorting lines. Our pipeline combines high-recall multi-threshold YOLO detection, contextual patch validation using ResNet, precise segmentation via the Segment Anything Model (SAM), and skin-contact analysis using VGG16 with a Random Forest classifier. Experimental results on a labeled dataset of over 6000 annotated instances show a recall above 90\% and precision near 100\% for most defect classes. The approach offers both robustness and interpretability, outperforming previous methods that rely on costly hyperspectral or MRI techniques. This system is scalable, explainable, and compatible with existing 2D imaging hardware.
Why it matches plant phenotyping methodsジャガイモ塊茎の内部欠陥という植物器官の状態を、RGB画像と複数のAIモデルで検出・分割する方法が研究の中心であり、性能評価も行っているため。
abstractWe present a novel, fully modular hybrid AI architecture designed for defect detection using RGB images of potato slices, suitable for integration in industrial sorting lines.
Potato above-ground biomass (AGB) and tuber yield estimation remain challenging due to the subjectivity of farmer-based assessments, the high data requirements of spectral analysis methods, and the sensitivity of traditional Structure from Motion (SfM) techniques to soil elevation variability. To address these challenges, this study proposes a novel UAV-based visible-light remote sensing framework to estimate the AGB and predict the tuber yield of potato crops. First, a new vegetation index, the Green-Red Combination Vegetation Index (GRCVI), was developed to improve the separability between vegetation and non-vegetation pixels. Second, an improved single-period SfM method was designed to mitigate errors in canopy height estimation caused by terrain variations. Fractional vegetation coverage (FVC) and plant height (PH) derived from UAV imagery were then integrated into a feedforward neural network (FNN) to predict AGB. Finally, potato tuber yield was predicted using polynomial regression based on AGB. Results showed that GRCVI combined with the numerical intersection method and SVM classification achieved FVC extraction accuracy exceeding 95%. The improved SfM method yielded canopy height estimates with R2 values ranging from 0.8470 to 0.8554 and RMSE values below 2.3 cm. The AGB estimation model achieved an R2 of 0.8341 and an RMSE of 19.9 g, while the yield prediction model obtained an R2 of 0.7919 and an RMSE of 47.0 g. This study demonstrates the potential of UAV-based visible-light imagery for cost-effective, non-destructive, and scalable monitoring of potato growth and yield, providing methodological support for precision agriculture and high-throughput phenotyping.
Why it matches plant phenotyping methodsUAV画像からFVC・草丈・地上部バイオマス・収量を推定する画像解析およびSfM手法を開発・検証しており、植物形質取得が研究の中心である。
abstractthis study proposes a novel UAV-based visible-light remote sensing framework to estimate the AGB and predict the tuber yield of potato crops.
Abstract Potato (Solanum tuberosum), the fourth most abundant food crop in the world, is subjected to significant challenges due to diseases such as late blight, causing global annual yield loss exceeding $6.7 billion [1]. Current methods of detection are time-consuming and frequently fail to identify early-stage infections. Deep learning, and particularly the Convolutional Neural Networks (CNNs) provide fast and scalable automation of disease classification compared to traditional methods. In this work, potato leaf diseases were classified by many CNNs such as XceptionNet, DenseNet121, a 5-layer CNN, a 6-layer CNN, and a custom hybrid CNN model (SpudNet5–R3). The datasets we used are as follows: (1) PlantVillage dataset was used and (2) PLD dataset which contains healthy, early blight, and late blight potato leaves. A full preprocessing pipeline was carried out which includes resizing, colour normalization, and Contrast Limited Adaptive Histogram Equalization (CLAHE). Targeted data augmentation strategies were applied to tackle the class imbalance. The models were trained, validated, and tested individually on three datasets and the input images were resized to 224×224. We analysed performance measures such as accuracy, precision, recall, F1-score, and inference time for finding the best model. In addition, Grad-CAM visualization was used to provide interpretable insights into the model predictions, showing the particular leaf regions that contributed to the classification. Experimental results show the strong competitiveness of our custom SpudNet5-R3 architecture, obtaining testing accuracy of 99.07% and macro F1-score of 99% on the PlantVillage (D1) potato dataset. It achieved also the testing accuracy of 95.56% and a macro f1-score of 96% on PLD (D2) dataset, demonstrating the successfulness of CNN architectures customized for robust and accurate recognition of the potato diseases.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病害状態を分類するCNNモデルを開発・比較し、複数データセットで性能検証しているため、植物病害表現型の取得・推定が中心である。
abstractIn this work, potato leaf diseases were classified by many CNNs such as XceptionNet, DenseNet121, a 5-layer CNN, a 6-layer CNN, and a custom hybrid CNN model (SpudNet5–R3).
Reproduction assets foundThe paper's phenotyping inputs are two public Kaggle leaf-image datasets (PlantVillage potato subset D1 and PLD D2), explicitly named in the Data Availability Statement with URLs. No author code, trained models, or checkpoints are deposited.Dataset · publicThe used datasets are online available on Kaggle repository,
https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset (Dataset D1)Open asset ↗Kaggle · plantvillage-datasetpdf-page:23 lines:1-36Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published10 Sept 2025International Journal of Basic and Applied SciencesCited by 0 · OpenAlex ↗
This article is coined for investigating the Village Plant dataset. Many researchers worldwide, carrying out their research in the domain of agriculture, are dependent on this open source dataset. A plant is vulnerable to several infirmities during its period of growth. Detection of the plant’s ill health and monitoring the environmental parameters is the most challenging task in agriculture. Plant disease epidemic may have a significant effect on crop production, reducing the country’s wealth. Early diagnosis of the occurrence of ill health in plants and the remedies are feasible using Artificial Intelligence (AI). Currently, methods like Deep Learning (DL) algorithms, machine vision techniques, and robotics play an important role in monitoring plant diseases and the growth status. This dataset contains multi-fold in-information about the plants. They include the normal and diseased images of plants like Bell Pepper, Tomato, Cucumber, and Potato. An Internet of Things (IoT) based plant data collection and integration system will provide data for this research, which optimizes the feature set through Ant Colony Optimization (ACO) for improving prediction in feature selection using deep learning models like DenseNet, ResNet 50, VGG 19, and Long Short-Term Memory (LSTM) networks, which in turn enhances plant productivity with advances in AI-driven agricultural diagnostics for plant stress prediction.
Why it matches plant phenotyping methods植物の正常・罹病画像から植物の病気・ストレス状態を推定する画像解析ワークフローとデータセット利用が研究の中心であり、植物状態のフェノタイピング手法に該当する。
abstractThis dataset contains multi-fold in-information about the plants. They include the normal and diseased images of plants like Bell Pepper, Tomato, Cucumber, and Potato.
Our lives are greatly impacted by the agricultural sector.The most significant industry in our economy is agriculture.The result of effective management is a successful agricultural product.Farmers that are unaware of leaf disease produce less.Profit and loss are determined by production, hence identifying plant leaf diseases is essential.The solution for categorizing and identifying leaf diseases is CNN.This study aims to identify leaf diseases in potato, tomato, corn, grape, and apple plants.Large agricultural disease monitoring fields are monitored for plant leaf diseases, which automatically identify certain disease characteristics and cure them.Comparing the proposed CNN model to popular transfer learning methods such as VGG16.There are numerous applications for plant leaf disease detection across a range of sectors, including biological research and agricultural institutions.One of the necessary study topics is plant leaf disease detection since it may help monitor vast agricultural fields and automatically identify disease symptoms.
Why it matches plant phenotyping methods植物葉の病徴を画像からCNN/VGG16で検出・分類する手法が研究の中心であり、植物病害状態の画像ベース表現型計測に該当する。
abstractThis study aims to identify leaf diseases in potato, tomato, corn, grape, and apple plants.
Introduction Potato ( Solanum tuberosum L .) production in semi-arid regions requires precision irrigation management to address water scarcity, highlighting the critical need for real-time, non-destructive plant water status assessment techniques. This study aimed to investigate the feasibility of measuring the leaf-air temperature difference (LAD) as an indicator for diagnosing potato water status. Methods A field experiment was conducted with five irrigation levels (0-300 mm) to evaluate LAD responses at three leaf positions (L 1 , L 4 , and L 8 ) across different growth stages. Results The results demonstrated that LAD significantly correlated with irrigation levels, plant water content (PWC), and soil moisture, with the strongest relationships observed for the fourth leaf from the top (L 4 ). L 4 exhibited the highest sensitivity to water status, the lowest variability among plants. A binomial regression between LAD and yield was identified, revealing a threshold LAD beyond which further LAD increases did not enhance the yield. These findings not only suggest that LAD can be a reliable indicator for monitoring potato water status but also identify L 4 as the optimal leaf position for LAD-based water status monitoring. Discussion The study provides a foundation for precision irrigation in potato production, enabling improved water use efficiency and sustainable potato production in a semiarid region.
Why it matches plant phenotyping methods葉温−気温差（LAD）によるジャガイモの水分状態推定を中心に、葉位別の感度・変動性・指標性能を評価しており、植物生理状態の計測法の検証に該当する。
abstractThis study aimed to investigate the feasibility of measuring the leaf-air temperature difference (LAD) as an indicator for diagnosing potato water status.
Multispectral leaf canopy reflectance as measured by unmanned aerial vehicles is the result of genetic and environmental interactions driving plant physiochemical processes. These measures can then be used to construct relationship matrices for modeling genetic main effects. This type of phenotypic prediction is particularly relevant for trials with many entries, such as those used in early generation potato (Solanum tuberosum) breeding. We compared three methods for making predictions in our potato breeding program: first, using multispectral-derived relationship matrices; second, using the traditional approach based on genomic derived relationships; and third, using a combination of both. Multispectral bands were collected at five different time points for two market classes of potato: chipping and fresh market. We modeled genetic main effects for yield and quality traits at each time point and all stages combined. Models with multispectral relationship matrices exhibited better prediction accuracy for yield and roundness than genomic only models and models featuring spectra plus genomic kernels outperformed both single-kernel predictions in terms of accuracy for most traits. Time points were variably informative depending on the trait measured, however, for all traits combining across time points performed as well or better than single time point models. Similarly, using feature selection to limit our models to important variables did not improve prediction accuracy significantly. This work highlights two potential uses for spectral data in genomic prediction: first, as an alternative to genetic data and second, in combination with genetic data to increase precision of selection.
Why it matches plant phenotyping methodsUAVマルチスペクトルセンシングを用いたキャノピー反射データをゲノム予測に組み込み、複数手法と予測精度を比較しており、植物表現型取得・推定ワークフローが研究の中心です。
abstractMultispectral leaf canopy reflectance as measured by unmanned aerial vehicles is the result of genetic and environmental interactions driving plant physiochemical processes.
Reproduction assets foundThe paper's data availability statement points to a public GitHub repository containing all data and scripts used for the multispectral genomic prediction analysis.Code · publicAll data and scripts used for this work are available at: https://github.com/shannonlabumn/GS_multispectra_analysis.git .Open asset ↗shannonlabumn/GS_multispectra_analysislines:375-518Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Canopy chlorophyll content (CCC) is a critical indicator for assessing crop photosynthetic capacity, nitrogen status, and the occurrence of diseases. Accurate estimation of CCC holds significant importance for precision agriculture, providing a scientific basis for crop management, yield prediction, and stress detection. CCC is commonly defined as the product of leaf area index (LAI) and leaf chlorophyll content (LCC). Traditional methods of acquiring CCC rely on destructive sampling, which limits large-scale application. Hyperspectral remote sensing enables non-destructive acquisition of rich spectral information from the crop canopy across the visible to near-infrared spectrum, offering a promising approach for CCC estimation. This study proposes a convolutional neural network-based model, CanopyChlNet, to jointly estimate LAI and LCC, thereby deriving CCC. The model utilizes a one-dimensional CNN structure to effectively extract deep spectral features from hyperspectral data, improving estimation accuracy. Field-measured canopy hyperspectral reflectance and corresponding LAI and LCC data from winter wheat and potato were used to train and validate the model. The CanopyChlNet model outperformed both Random Forest (RF) and Partial Least Squares Regression (PLSR) in estimating LAI, LCC, and CCC, achieving R2 values of 0.709, 0.775, and 0.718, with RMSE values of 0.803 m2 ·m−2, 5.288 µg·cm− 2, and 34.938 µg·cm− 2, respectively. In comparison, RF yielded R2 values of 0.636, 0.685, and 0.667, and RMSE values of 0.896 m2 ·m− 2, 6.396 µg·cm− 2, and 37.901 µg·cm− 2. PLSR achieved R2 values of 0.522, 0.709, and 0.586, with RMSE values of 1.029 m2 ·m− 2, 6.042 µg·cm− 2, and 42.332 µg·cm− 2.These results demonstrate that CanopyChlNet is a high-precision model for estimating crop LCC and CCC. This study demonstrates that integrating deep learning with hyperspectral remote sensing significantly enhances the estimation accuracy of key crop parameters, providing an effective tool for crop growth monitoring.
Why it matches plant phenotyping methods作物キャノピーのLAI・LCC・CCCという植物形質を、ハイパースペクトルデータとCNNで推定する手法を開発・検証しており、フェノタイピング手法が研究の中心である。
abstractThis study proposes a convolutional neural network-based model, CanopyChlNet, to jointly estimate LAI and LCC, thereby deriving CCC.
Potato blight is a serious disease that affects potato crops and leads to substantial agricultural and economic losses. To enhance detection accuracy, we propose Bayesian Optimized CNN Weighted Ensemble Potato Blight Detection, a deep learning-based approach that optimizes CNN models through Bayesian optimization and ensemble learning. In the proposed study, extensive experiments were conducted to develop an optimized Bayesian Weighted Ensemble CNN model for the detection of potato leaf blight. First, multiple CNN architectures were trained using different optimizers: ADAM (DL1), SGD (DL2), RMSProp (DL3), and ADAMAX (DL4), evaluating their individual performance. To mitigate class imbalance, data augmentation techniques were applied, increasing the number of healthy leaves by 6 times. In addition, fuzzy image enhancement was implemented to improve feature extraction and classification accuracy. Bayesian optimization was then used to determine the optimal weights for a deep ensemble model, exploring 11 possible model combinations. The final EDL7 ensemble model (DL1 + DL2 + DL3), optimized through Bayesian optimization, achieved the highest accuracy of 97.94%, outperforming individual models. Furthermore, the ensemble model achieved a precision of 0.981, recall of 0.983, and an F1 score of 0.982, ensuring a well-balanced trade-off between precision and recall. These results highlight the effectiveness of Bayesian-optimized ensemble learning in improving potato blight detection, making it a robust and reliable solution for agricultural disease classification.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類するCNN・画像強調・ベイズ最適化アンサンブルを中心に開発・評価しており、植物病害状態の取得手法が主題である。
abstractwe propose Bayesian Optimized CNN Weighted Ensemble Potato Blight Detection, a deep learning-based approach that optimizes CNN models through Bayesian optimization and ensemble learning.
Reproduction assets foundThe paper's potato leaf blight detection models were trained on a public Kaggle dataset, explicitly declared in the Data availability statement. No author analysis code or trained model checkpoints are reported as publicly available.Dataset · publicThe datasets generated and analyzed during the current study are available in the Kaggle repository https://www.kaggle.com/datasets/muhammadardiputra/potato-leaf-disease-datasetOpen asset ↗Kaggle · muhammadardiputra/potato-leaf-disease-datasetlines:308-345Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
The Transition to a Data-Driven Agriculture (TTADDA) project focuses on advancing the shift toward high-tech, circular agriculture. By developing cutting-edge sensor technologies and AI-driven tools, the project aims to boost productivity through a data-centric potato production system that supports circular agricultural practices. Potato phenotyping is crucial for creating high-yielding, resilient, and sustainable potato crops, which are essential in global food systems. Specifically in the Netherlands, the global leader in seed potato production and Japan that produces certified seed potatoes under strict quality controls and phytosanitary regulations. A multi-season drone dataset from five potato trials-three in Japan and two in the Netherlands was collected. Each trial field was divided into small plots, each planted with a specific cultivar to assess varietal performance. Data included drone imagery (RGB and multispectral), manual yield and ground coverage measurements, and weather data. The combination of sensor versatility, diverse potato varieties, and varying climate and soil conditions between Japan and the Netherlands makes this dataset highly valuable and potentially reusable for a wide range of applications. Using MIAPPE for this dataset ensures consistent, clear documentation of sensors, varieties, and conditions, making the data findable, reusable, and easy to integrate with other studies. It also supports reproducibility and automated analysis across the multi-location trials.
Why it matches plant phenotyping methodsジャガイモの表現型解析を目的としたUAV RGB・マルチスペクトル画像と圃場測定を含む、多季節・多地点の再利用可能なデータセットの構築・標準化が中心である。
abstractA multi-season drone dataset from five potato trials-three in Japan and two in the Netherlands was collected.
Reproduction assets foundThe paper is a data descriptor for the TTADDA-UAV potato phenotyping dataset (RGB/multispectral orthomosaics, DSMs, yield, ground coverage, weather) publicly deposited on 4TU.ResearchData with a DOI, plus an authors' GitHub repository for loading the MIAPPE-formatted data.Dataset · publicThe dataset is part of the following collection:
Data identification number: doi.org.10.4121/936b5772–09fc–4856–983d-1f9cc2f38d15
Direct URL to data: ( https://doi.org/10.4121/936b5772-09fc-4856-983d-1f9cc2f38d15 )
The collection consist of metadata, and five related studies: TTADDA_NARO_2021, TTADDA_NARO_2022, TTADDA_NARO_2023, TTADDA_WUR_2022, TTADDA_WUR_2023
To visualise the metadata and download the dataset we recommend the following GIT:
https://github.com/NPEC-NL/MIAPPE_TTADDA_dataset
Related research article
None
1
Value of the DOpen asset ↗10.4121/936b5772-09fc-4856-983d-1f9cc2f38d15lines:57-83Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Published23 Aug 2025International Journal of Advanced Research in Science, Communication and TechnologyCited by 0 · OpenAlex ↗
Machine learning and deep learning have significantly transformed various domains, including medicine, engineering, and agriculture. In this work, we propose a novel deep learning-based approach for detecting stressed potato plants using drone-captured images. Early detection of crop stress, particularly due to insufficient water, is critical as stressed potato plants exhibit symptoms such as leaf yellowing, which can be difficult and time-consuming to monitor manually in large-scale fields. A RetinaNet architecture, a single-stage object detector developed by Facebook, to identify and classify stressed potato crops is employed in the work. The model was trained on an augmented dataset of 1,400 drone images of potato fields using TensorFlow and Keras. Experimental results demonstrate that the trained model effectively detects and classifies stressed plants, offering a reliable alternative to manual field inspection. The proposed system has the potential to save farmers substantial time and labour, thereby enhancing productivity and resource management. Future work will focus on extending the model to multiple crops and disease types, improving accuracy, and exploring faster detection architectures for real-time applications.
Why it matches plant phenotyping methodsドローン画像からジャガイモのストレス状態を検出・分類する画像解析手法が研究の中心であり、植物状態の直接的な推定に該当する。
abstractwe propose a novel deep learning-based approach for detecting stressed potato plants using drone-captured images.
Abstract. Field-scale estimation of evapotranspiration (ET) using high-resolution data supports water conservation and yield optimization by enabling localized water use monitoring and early detection of crop stress. This study applies the Priestley–Taylor Two-Source Energy Balance (TSEB-PT) model at 15 cm resolution using unmanned aerial vehicle (UAV) data over a 10-hectare field across three seasons: sugar beet (2021), potato (2022), and winter wheat (2023). Key inputs included thermal infrared (TIR) for land surface temperature (LST), multispectral (MS) and LiDAR data for canopy characterization, and a fusion of MS derived green area index (GAI) and LiDAR derived plant area index (PAI) to derive the fraction of green LAI (fg). Model outputs were validated against eddy covariance (EC) flux data using footprint modeling. Results showed high sensitivity to LST, emphasizing the importance of accurate thermal calibration. While both GAI and PAI provided comparable LAI inputs during peak growth, GAI better captured functional canopy decline during stress and senescence, especially in winter wheat, where dense structure led to cooling effects unrelated to transpiration. Dynamic fg improved ET accuracy across all crops, particularly under declining canopy function. Overall, TSEB-PT showed strong agreement with EC measurements (RMSE = 0.14 mm/h, R² = 0.49; R² = 0.81 excluding senescence). UAV TIR based ET maps also revealed early stress signals prior to changes in MS or LiDAR based metrics. This study demonstrates the value of integrating very-high-resolution UAV data with the TSEB-PT model for multi-crop and season-long ET monitoring and early stress detection.
Why it matches plant phenotyping methodsUAVの熱・マルチスペクトル・LiDARデータとTSEB-PTモデルにより、作物の蒸発散と水ストレスを推定する手法を中心に扱い、渦相関データで技術検証しているため、植物フェノタイピング手法研究に該当する。
abstractThis study applies the Priestley–Taylor Two-Source Energy Balance (TSEB-PT) model at 15 cm resolution using unmanned aerial vehicle (UAV) data over a 10-hectare field across three seasons: sugar beet (2021), potato (2022), and winter wheat (2023).
Abstract Leaf Chlorophyll Concentration (LCC) is a vital biochemical parameter for assessing plant status due to its essential role in physiological activities, photosynthesis, and overall plant health. In order to illustrate the development of potato crops and offer advice for precision agriculture management, research was conducted on non-invasive testing methods for chlorophyll levels and methods for mapping crop yield in potatoes. The objective of this study is to examine the spatial distribution of chlorophyll content and yield of potato crops using Sentinel 2 data, SPAD chlorophyll measurements, and laboratory analyses. Artificial intelligence (AI) using the Random forest (RF) classification method was used to study the spatial distribution of crop type and discriminate the potato crop. The overall accuracy and kappa statistics for the spatial distribution derived from Sentinel 2 satellite imagery for potato crops in the study area were 0.79 and 82.5%, respectively. Stepwise Multilinear regression model (SWMLR) between Spectral vegetation indices (Normalized Difference Vegetation Indexed NDVI, Modified Chlorophyll Absorption Ratio Index (MCARI), Leaf Chlorophyll Index (LCI), derived from spectral vegetation indices (SVI), (SPAD chlorophyll and chemical analysis through potato crop growth stages (S1, S2 and S3) were correlated to estimate chlorophyll content and crop yield map. The model accuracy between vegetation indices and Total chlorophyll showed that models based on VIS and selected spectral bands derived from ASD to predict total chlorophyll(chlt) and SPAD chlorophyll values achieved a high coefficient of determination (R 2 ) at the different growth stages, which were 0.983 and 0.986. The produced map for the potato crop, total chlorophyll derived from Sentinel 2, showed high accuracy at 0.966 and 0.974 based on SPAD, VIS, and selected spectral bands, respectively. The study showed that the estimation and mapping of Chlt and SPAD values of a potato crop under an irrigation system pivot can be done with the help of RS and AI techniques.
Why it matches plant phenotyping methodsSentinel-2、近接センサー、SPAD、分光データとAI・回帰モデルを用いて、ジャガイモのクロロフィル量と収量を推定・マッピングする技術的評価が研究の中心であり、植物形質の取得・推定方法を扱っている。
abstractresearch was conducted on non-invasive testing methods for chlorophyll levels and methods for mapping crop yield in potatoes
Introduction Technology is becoming essential in agriculture, especially with the growth of smart devices and edge computing. These tools help boost productivity by automating tasks and allowing real-time analysis on devices with limited memory and resources. However, many current models struggle with accuracy, size, and speed particularly when handling multi-label classification problems. Methods This paper proposes a Convolutional Neural Network with Squeeze and Excitation Enabled Identity Blocks (CNN-SEEIB), a hybrid CNN-based deep learning architecture for multi-label classification of plant diseases. CNN-SEEIB incorporates an attention mechanism in its identity blocks to leverage the visual attention that enhances the classification performance and computational efficiency. PlantVillage dataset containing 38 classes of diseased crop leaves alongside healthy leaves, totaling 54,305 images, is utilized for experimentation. Results CNN-SEEIB achieved a classification accuracy of 99.79%, precision of 0.9970, recall of 0.9972, and an F1 score of 0.9971. In addition, the model attained an inference time of 64 milliseconds per image, making it suitable for real-time deployment. The performance of CNNSEEIB is benchmarked against the state-of-the-art deep learning architectures, and resource utilization metrics such as CPU/GPU usage and power consumption are also reported, highlighting the model’s efficiency. Discussion The proposed architecture is also validated on a potato leaf disease dataset of 4,062 images from Central Punjab, Pakistan, achieving a 97.77% accuracy in classifying Healthy, Early Blight, and Late Blight classes.
Why it matches plant phenotyping methods植物病害画像から病害状態を分類するCNN手法の開発と、複数データセットでの性能比較・検証が中心であり、植物フェノタイピング手法に該当する。
abstractThis paper proposes a Convolutional Neural Network with Squeeze and Excitation Enabled Identity Blocks (CNN-SEEIB), a hybrid CNN-based deep learning architecture for multi-label classification of plant diseases.
Reproduction assets foundThe paper's experiments use the public PlantVillage dataset (54,305 images, 38 classes), explicitly linked in the Data availability statement. No author code or model checkpoints are shared.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/datasets/mohitsingh1804/plantvillage .Open asset ↗Kaggle · mohitsingh1804/plantvillagelines:868-933Plant phenotyping relevance match · UnverifiedCrossref · checked 6 Sept 2026
Drones have been widely used in precision agriculture to capture high-resolution images of crops, providing farmers with advanced insights into crop health, growth patterns, nutrient deficiencies, and pest infestations. Although several machine and deep learning models have been proposed for plant stress and disease detection, their performance regarding accuracy and computational time still requires improvement, particularly under limited data. Therefore, this paper aims to address these challenges by conducting a comparative analysis of three State-of-the-Art object detection deep learning models: YOLOv8, RetinaNet, and Faster R-CNN, and their variants to identify the model with the best performance. To evaluate the models, the research uses a real-world dataset from potato farms containing images of healthy and stressed plants, with stress resulting from biotic and abiotic factors. The models are evaluated under limited conditions with original data of size 360 images and expanded conditions with augmented data of size 1560 images. The results show that YOLOv8 variants outperform the other models by achieving larger mAP@50 values and lower inference times on both the original and augmented datasets. The YOLOv8 variants achieve mAP@50 ranging from 0.798 to 0.861 and inference times ranging from 11.8 ms to 134.3 ms, while RetinaNet variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 118.7 ms to 158.8 ms, and Faster R-CNN variants achieve mAP@50 ranging from 0.587 to 0.628 and inference times ranging from 265 ms to 288 ms. These findings highlight YOLOv8’s robustness, speed, and suitability for real-time aerial crop monitoring, particularly in data-constrained environments.
Why it matches plant phenotyping methods植物のストレス状態をドローン画像から推定する物体検出手法を比較・評価しており、モデル性能と推論時間の検証が中心であるため。
abstractthis paper aims to address these challenges by conducting a comparative analysis of three State-of-the-Art object detection deep learning models: YOLOv8, RetinaNet, and Faster R-CNN
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 6 Sept 2026
Diseases pose significant threats to crop production, leading to substantial yield reductions and jeopardizing global food security. Timely and accurate detection of crop diseases is essential for ensuring sustainable agricultural development and effective crop management. While deep learning-based computer vision techniques have emerged as powerful tools for crop disease recognition, these methods are heavily reliant on large datasets, which are often difficult to obtain in practical agricultural settings. This challenge highlights the need for models capable of learning from limited data, a scenario known as the few-shot learning problem. In this paper, we introduce a novel few-shot learning approach, the Sequence-Weighted Ensemble Model-Agnostic Meta-Learning (SWE-MAML), designed to train crop disease recognition models with minimal sample sizes. The SWE-MAML framework employs meta-learning to sequentially train a set of base learners, followed by a weighted sum of their predictions for classifying plant disease images. This method integrates ensemble learning with Model-Agnostic Meta-Learning (MAML), allowing the effective training of multiple classifiers within the MAML framework. Experimental results show that SWE-MAML demonstrates strong competitiveness compared to state-of-the-art algorithms on the PlantVillage dataset. Compared to the original MAML, SWE-MAML improves accuracy by 3.75%–8.59%. Furthermore, we observe that the number of base learners significantly influences model performance, with an optimal range of 5–7 learners. Additionally, pre-training with a larger number of disease classes enhances the model’s ability to recognize “unseen” classes. SWE-MAML was also applied to a real-world few-shot potato disease recognition task, achieving an accuracy of 75.71% using just 30 images per disease class in the support set. These findings validate that SWE-MAML is a highly effective solution for the few-shot recognition of crop diseases, offering a promising approach for practical deployment in agricultural settings where data scarcity is a major challenge. The integration of ensemble learning with meta-learning enables high-performance disease recognition with minimal data, marking a significant advancement in the field.
Why it matches plant phenotyping methods植物病害画像から病害状態を認識する少数ショット手法を開発し、PlantVillageおよび実画像で性能検証しており、病害表現型の取得・推定手法が中心である。
abstractwe introduce a novel few-shot learning approach, the Sequence-Weighted Ensemble Model-Agnostic Meta-Learning (SWE-MAML), designed to train crop disease recognition models with minimal sample sizes.
Agriculture plays a critical role in the global economy, providing livelihoods and ensuring food security for billions. Progress in agricultural techniques has helped boost crop yield, along with a growing need for precise disease monitoring solutions. This requires accurate, efficient, and timely disease detection methods. The research presented in this paper addresses this need by analyzing a hybrid model built using Graph Attention Network (GAT) and Graph Convolution Network (GCN) models. The integration of these models has witnessed a notable improvement in the accuracy of leaf disease classification. GCN has been widely used for learning from graph-structured data, and GAT enhances this by incorporating attention mechanisms to focus on the most important neighbors. The methodology incorporates superpixel segmentation for efficient feature extraction, partitioning images into meaningful, homogeneous regions that better capture localized features. The robustness of the model is further enhanced by the edge augmentation technique. The edge augmentation technique in the context of graph has introduced a significant degree of generalization in the detection capabilities of the model as analyzed on apple, potato, and sugarcane leaves. To further optimize training, weight initialization techniques are applied. The hybrid model is evaluated against the individual performance of the GCN and GAT models and the hybrid model achieved a precision of 0.9822, recall of 0.9818, and F1-score of 0.9818 in apple leaf disease classification, a precision of 0.9746, recall of 0.9744, and F1-score of 0.9743 in potato leaf disease classification, and a precision of 0.8801, recall of 0.8801, and F1-score of 0.8799 in sugarcane leaf disease classification. The results indicate that the model is effective and consistent in identifying leaf diseases in plants.
Why it matches plant phenotyping methods植物葉画像から病害状態を分類するGAT-GCNモデルを開発・比較評価しており、病害表現型の抽出手法が中心である。
abstractThe methodology incorporates superpixel segmentation for efficient feature extraction, partitioning images into meaningful, homogeneous regions that better capture localized features.
Reproduction assets foundThe paper evaluates its GAT-GCN hybrid leaf disease classifier on three public leaf image datasets. Two of them (apple and potato) are cited with explicit Kaggle URLs that match allowed_urls entries; the sugarcane dataset is cited without a public URL. No author code or model release is mentioned.Dataset · publicAdvanced Comput. Sci. Appl.
10 ( 8 ), 486 – 492 . doi:
10.14569/IJACSA.2019.0100863
Alsayed A. Alsabei A. Muhammad A.
( 2021 ).
Classification of apple tree leaves diseases using deep learning methods
. Int. J. Comput. Sci. Network Secur.
21 , 324 – 330 .
Antor M. H.
( 2020 ). Apple leaf diseases dataset . Available online at: https://www.kaggle.com/datasets/mhantor/apple-leaf-diseases (Accessed October 13, 2024 ).
Bansal P. Kumar R. Kumar S.
( 2021 ).
Disease detection in apple leaves using deep convolutional neural network
. Agriculture
11 , 617 . doi:
10.3390/agriculture11070617
Bera A. Bhattacharjee D. Krejcar O.
( 2024 ).
Pnd-net: plant nutrition deficiency and disease classification usOpen asset ↗Kaggle · mhantor/apple-leaf-diseaseslines:548-708Dataset · publicnt. J. Res. Eng.
5 , 516 – 523 . doi:
10.21276/ijre.2018.5.9.4
Peng Y. Wang Y.
( 2022 ).
Leaf disease image retrieval with object detection and deep metric learning
. Front. Plant Sci.
13 , 963302 . doi:
10.3389/fpls.2022.963302
, PMID:
36176678
PMC9513793
Putra M. A.
( 2020 ). Potato leaf disease dataset . Available online at: https://www.kaggle.com/datasets/muhammadardiputra/potato-leaf-disease-dataset (Accessed October 13, 2024 ).
Rao S. U. M. Sreekala K. Rao P. Srinivas Shirisha N. Srinivas G. Sreedevi E.
( 2024 ).
Plant disease classification using novel integration of deep learning cnn and graph convolutional networks
. Indonesian J. Electrical Eng. Comput. Sci.
36 , 1721 – 1730 .
RathOpen asset ↗Kaggle · muhammadardiputra/potato-leaf-disease-datasetlines:709-821Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Plant diseases significantly harm crops, resulting in significant economic losses across the globe. In order to reduce the harm that these diseases produce, plant diseases must be diagnosed accurately and timely manner. In this work, a YOLO-LeafNet approach is proposed for detecting diseases from leaf images of four distinct species, namely, grape, bell pepper, corn, and potato. About 8850 leaf images have been acquired for this work from five different publicly available datasets on Kaggle. All the acquired images were pre-processed by applying four different image pre-processing operations. The number of images in the training dataset was tripled for better model performance by applying five different augmentation operations. The augmented dataset was then used to train YoloV5, YoloV8, and the proposed YOLO-LeafNet. The performance of all three models is evaluated in terms of recall, precision, and Mean Average Precision (mAP). The YoloV5 attained a precision of 0.861, recall of 0.868, mAP50 of 0.944, and 0.815 of mAP50-95, and YoloV8 attained 0.977 precision, 0.975 recall, 0.984 of mAP50, and mAP50-95 of 0.915, whereas the proposed the YOLO-LeafNet attained precision of 0.985, recall of 0.980, mAP50 of 0.990, and mAP50-95 of 0.940. The experimental results reveal that the proposed YOLO-LeafNet outperformed YOLOv5 and YOLOv8 in terms of all performance metrics.
Why it matches plant phenotyping methods葉画像から植物病害を検出する深層学習手法を開発し、既存モデルと性能比較しており、植物状態の画像ベース表現型取得が中心である。
abstractIn this work, a YOLO-LeafNet approach is proposed for detecting diseases from leaf images of four distinct species, namely, grape, bell pepper, corn, and potato.
The vigor of potato plants is of crucial importance for potato seed producers, who are interested in predicting it at scale by exploiting the dependence of plant growth and development on the origin and physiological state of the seed tuber. In this article we present the results of a three-year long experiment in which we studied six potato varieties in three test fields. We identify a 73-[Formula: see text] overall correlation in the vigor of plants from the same seedlot grown in different test fields. Similarly, the biochemical tuber data produce plant vigor predictions that correlate up to 70-[Formula: see text] with the measurements. However, these relatively large data and prediction correlations are mostly due to the strong dependence of the seedlot vigor on the tuber genotype. For five out of six studied varieties, variety-specific cross-field and cross-year vigor predictions produce negligible or even negative correlations when the seed tubers and young plants experience environmental stress. At the same time, for the variety that appeared to be less sensitive to environmental stresses, we obtained cross-field and cross-year vigor predictions correlating up to [Formula: see text] with the measurements. Analysis of individual predictor variables, such as the abundance of a particular metabolite, indicates that the vigor-enhancing properties of the seed tubers are also variety-specific and that the FTIR spectroscopy data is the most reliable predictor.
Why it matches plant phenotyping methodsFTIR・生化学データからジャガイモ植物の vigor を予測し、圃場間・年次間で予測性能を検証しており、植物形質の取得・推定法が中心です。
abstractinterested in predicting it at scale
Reproduction assets foundThe paper's Data Availability statement points to a public 4TU.ResearchData deposit containing the seed tuber and plant canopy (drone-derived vigor) datasets plus the Python code needed to reproduce the regression results — a paper-specific, publicly actionable asset.Dataset · publicBoth the seed tuber and plant canopy datasets are available at http://doi.org/10.4121/3a97fa0c-8c7d-451a-b8fe-d521f1cec55e . The data also includes the Python code necessary to reproduce the results of regression.Open asset ↗10.4121/3a97fa0c-8c7d-451a-b8fe-d521f1cec55elines:267-336Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Accurate and non-destructive monitoring of potato late blight (PLB) using unmanned aerial vehicle (UAV) remote sensing data is of great significance for field management. However, during disease outbreaks, there is a lack of universally applicable rapid monitoring models. On the one hand, different varieties exhibit varying levels of resistance and disease monitoring progression, which can be attributed to genetic and environmental factors. On the other hand, the heterogeneity, imbalance, and noise in spectral and textural data across regions pose significant challenges for disease monitoring. To address these issues, this study first improves upon the noise problem in Synthetic Minority Over-sampling Technique (SMOTE) by employing an enhanced feature selection algorithm based on the Feature Selection with Compactness and Separability (FS-CS) principle. Subsequently, the feature ranking is then used with the Importance-Ordered Weighted Averaging (IOWA) operator to calculate the induced Minkowski OWA distance (IMOWAD), replacing the nearest neighbor distance used in SMOTE. This refinement emphasizes the boundaries of synthetic sample regions and mitigates noise-related issues. This improved method is referred to as SMOTE-CS. Secondly, nine models were constructed to evaluate the effectiveness of FS-CS in feature selection when integrating multiple datasets. Compared to mRmR and ReliefF, FS-CS achieved higher accuracy with a smaller number of features. Finally, to address varietal and environmental differences, modeling was conducted using a shallow transfer learning 1D-CNN model and a deep DRSN model incorporating nonlinear soft thresholding processing, respectively. The results indicate that the 1D-CNN model achieved overall accuracies (OA) of 0.99 and 0.93 on the two datasets, respectively. However, its performance was affected by the poor interpretability of the boundary between the synthetic source and target domain samples. The integration of nonlinear soft-thresholding into the DRSN model enhanced its feature extraction capability and noise suppression. It demonstrated strong performance on the two datasets, achieving an OA of 0.91 and a Kappa coefficient of 0.86. Compared to the original SMOTE version, the proposed approach exhibited superior generalization ability. The results of this study provide new insights into the problems of small sample imbalance, noise, and technical support for multi-species PLB monitoring in different regions.
Why it matches plant phenotyping methodsUAVリモートセンシングでジャガイモ疫病の重症度を推定し、SMOTE-CS、特徴選択、CNN/DRSNモデルを開発・評価しており、植物病害状態の取得・推定手法が中心である。
abstractAccurate and non-destructive monitoring of potato late blight (PLB) using unmanned aerial vehicle (UAV) remote sensing data is of great significance for field management.
Phenotypes, which define an organism’s behaviour and physical attributes, result from the complex interplay of genetics, development, and environment. Predicting future plant traits is mainly challenging due to these dynamic interactions. This work presents AMULET, a modular approach that combines imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible. Trained with over 30,000 Arabidopsis thaliana plants, AMULET streamlines the phenotyping process by integrating plant detection, prediction, segmentation, and data analysis, enhancing workflow efficiency and reducing time. AMULET achieved impressive performance metrics, including a dice loss of 0.0104 and an IoU score of 0.9948 for the test set, indicating high accuracy in the segmentation task or an R² score of 0.9289 for descriptor estimation. Moreover, Simpler yet Better Video Prediction (SimVP) appeared as the most effective model in predicting plant growth and health status. Using phenotyping images from studies focused on the Arabidopsis thaliana-Pseudomonas syringae pathosystem, AMULET analysed the latent phenom by identifying traits restrictive to human perception and essential to understanding plant response to concrete growth conditions. Techniques like TorchGrad and Gradient-weighted Class Activation Mapping helped to reveal these new hidden traits. AMULET also demonstrated its adaptability by accurately detecting and predicting phenotypes of in vitro potato plants after minimal fine-tuning with just 100 plants. This versatile approach streamlines phenotyping and holds significant promise for improving breeding programs and agricultural management by enabling pre-emptive interventions optimising plant health andproductivity.
Why it matches plant phenotyping methodsAMULETは画像ベースのハイスループット植物表現型取得、セグメンテーション、形質推定、将来予測を統合する手法・ワークフローとして開発・評価されており、方法が研究の中心である。
abstractThis work presents AMULET, a modular approach that combines imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible.
• AMULET represents a groundbreaking advancement in plant phenotyping. • AMULET integrates plant detection, prediction, segmentation, and data analysis. • AMULET identify the latent space of the phenom by using machine learning models. • AMULET demonstrates unparalleled adaptability across species. Phenotypes, which define an organism’s behaviour and physical attributes, result from the complex interplay of genetics, development, and environment. Predicting future plant traits is mainly challenging due to these dynamic interactions. This work presents AMULET, a modular approach that combines imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible. Trained with over 30,000 Arabidopsis thaliana plants, AMULET streamlines the phenotyping process by integrating plant detection, prediction, segmentation, and data analysis, enhancing workflow efficiency and reducing time. AMULET achieved impressive performance metrics, including a dice loss of 0.0104 and an IoU score of 0.9948 for the test set, indicating high accuracy in the segmentation task or an R 2 score of 0.9289 for descriptor estimation. Moreover, Simpler yet Better Video Prediction (SimVP) appeared as the most effective model in predicting plant growth and health status. Using phenotyping images from studies focused on the Arabidopsis thaliana-Pseudomonas syringae pathosystem, AMULET analysed the latent phenom by identifying traits restrictive to human perception and essential to understanding plant response to concrete growth conditions. Techniques like TorchGrad and Gradient-weighted Class Activation Mapping helped to reveal these new hidden traits. AMULET also demonstrated its adaptability by accurately detecting and predicting phenotypes of in vitro potato plants after minimal fine-tuning with just 100 plants. This versatile approach streamlines phenotyping and holds significant promise for improving breeding programs and agricultural management by enabling pre-emptive interventions optimising plant health and productivity.
Why it matches plant phenotyping methodsAMULETは画像ベースのハイスループット植物表現型解析と機械学習による形態・生理形質の推定、予測、セグメンテーションを中核として開発・評価しており、方法論的貢献が明確です。
abstractThis work presents AMULET, a modular approach that combines imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible.
The determination of reducing sugars in potatoes is important due to their impact on product quality during industrial processing. The significant variability of these compounds between genotypes presents a challenge to the development of accurate predictive models. This study evaluated the potential of near-infrared hyperspectral imaging (NIR-HSI) for the prediction of reducing sugars in potatoes. For this, a wide range of genotypes (n = 92) from two seasons (2020–2021) was selected. Partial Least Squares Regression (PLSR) and Support Vector Machine Regression (SVMR) methods were used to build the prediction models. Furthermore, interval PLS (iPLS), recursive weighted PLS (rPLS), Genetic Algorithm (GA) and Competitive Adaptive Reweighted Sampling (CARS) were used for relevant wavelength identification to develop less computationally complex models. The best full spectrum model (SNV-PLSR) achieved coefficient of determination and root mean square error values of 0.88 and 0.053 % and 0.86 and 0.057 %, for calibration and external validation, respectively. Variable selection algorithms successfully reduced the dimensionality of the data without compromising the performance of the models. Robust predicted models were built with only 2.65 % (CARS-PLSR) and 3.57 % (iPLS-SVMR) of the total wavelengths. Finally, a pixel-wise prediction was performed on the validation set and chemical images were built to visualise the spatial distribution of reducing sugars. This study demonstrated that NIR-HSI is a feasible technique for predicting reducing sugars in several potato genotypes.
Why it matches plant phenotyping methodsジャガイモ塊茎の還元糖という植物器官形質を、NIR-HSIと回帰モデルで予測・可視化する手法を開発し、外部検証および波長選択による性能評価を行っており、表現型取得が中心である。
abstractThis study evaluated the potential of near-infrared hyperspectral imaging (NIR-HSI) for the prediction of reducing sugars in potatoes.
To address the poor real-time detection of potato damage during harvesting and the high computational complexity of the model, this paper proposed a lightweight detection algorithm based on the YOLOv8 framework—Light-YOLOv8. The algorithm achieved lightweight detection by integrating EfficientNet-B0 composite scaling strategy to optimize model parameters and integrating the MBConv network module to reduce the backbone network’s weight. By combining the lightweight network Slim-neck with the CARAFE upsampling operator, the SNC neck network was designed and constructed, to reduce the weight and enhance its ability to process detailed information. Additionally, Light-YOLOv8 employed the PReLU activation function to optimize network performance. Experimental results demonstrated that Light-YOLOv8 achieved a mean average precision (mAP@50–95) of 95.23%, significantly reduced model parameters (only 1.88 M) and floating-point operations (as low as 5.5G), and reduced the inference speed for a single image to 12 ms per image, with a model memory footprint of only 3.93 MB. In edge computing device deployment, Light-YOLOv8 balances speed and accuracy effectively compared to other models, providing technical support for real-time potato damage detection.
Why it matches plant phenotyping methodsジャガイモ塊茎の損傷状態を画像から検出する軽量YOLO手法の開発・評価が中心であり、単なる収穫対象の位置検出を超えた器官状態の推定に該当する。
abstractthis paper proposed a lightweight detection algorithm based on the YOLOv8 framework—Light-YOLOv8
Potatoes are one of the world's most widely cultivated crops, but their yield is coming under mounting pressure from early blight, a fungal disease caused by Alternaria solani . Early detection and accurate identification are key to effective disease management and yield protection. This paper introduces a novel deep learning framework called ZeroShot CNN, which integrates convolutional neural networks (CNNs) and ZeroShot Learning (ZSL) for the efficient classification of seen and unseen disease classes. The model utilizes convolutional layers for feature extraction and employs semantic embedding techniques to identify previously untrained classes. Implemented on the Kaggle potato disease dataset, ZeroShot CNN achieved 98.50% accuracy for seen categories and 99.91% accuracy for unseen categories, outperforming conventional methods. The hybrid approach demonstrated superior generalization, providing a scalable, real-time solution for detecting agricultural diseases. The success of this solution validates the potential in harnessing deep learning and ZeroShot inference to transform plant pathology and crop protection practices.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習手法が論文の中心であり、未学習病害クラスへの汎化性能も評価しているため、植物フェノタイピング手法として採用する。
abstractThis paper introduces a novel deep learning framework called ZeroShot CNN, which integrates convolutional neural networks (CNNs) and ZeroShot Learning (ZSL) for the efficient classification of seen and unseen disease classes.
Reproduction assets foundThe paper's primary phenotyping input is the Kaggle Potato Disease Dataset (2151 labeled potato leaf images: 1000 healthy, 1151 early blight), explicitly declared publicly available in the Data Availability Statement with an authors' URL matching an allowed URL. No author analysis code or trained model checkpoints are.Dataset · publicupervision, M.S.F.; project administration, M.F.W.; funding acquisition, N.J.H. All authors have read and agreed to the published version of the manuscript.
Institutional Review Board Statement
Not applicable.
Informed Consent Statement
Not applicable.
Data Availability Statement
The dataset is available on the Kaggle database. https://www.kaggle.com/code/amankrpandey1/potato-disease-classification/input (accessed on 1 June 2025).
Conflicts of Interest
Author Muhammad Farooq Wasiq was employed by the company METICS Solutions Ltd. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conOpen asset ↗Kaggle · amankrpandey1/potato-disease-classificationlines:402-431Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Early detection of drought stress is critical for taking timely measures for reducing crop loss before the drought impact becomes irreversible. The subtle phenotypical and physiological changes in response to drought stress are captured by non-invasive imaging techniques and these imaging data serve as valuable resource for machine learning methods to identify drought stress. While convolutional neural networks are in wide use, vision transformers (ViTs) present a promising alternative in capturing long-range dependencies and intricate spatial relationships, thereby enhancing the detection of subtle indicators of drought stress. We propose an explainable deep learning pipeline that leverages the power of ViTs for drought stress detection in potato crops using aerial imagery. We applied two distinct approaches: a synergistic combination of ViT and support vector machine (SVM), where ViT extracts intricate spatial features from aerial images, and SVM classifies the crops as stressed or healthy and an end-to-end approach using a dedicated classification layer within ViT to directly detect drought stress. Our key findings explain the ViT model's decision-making process by visualizing attention maps. These maps highlight the specific spatial features within the aerial images that the ViT model focuses as the drought stress signature. Our findings demonstrate that the proposed methods not only achieve high accuracy in drought stress identification but also shedding light on the diverse subtle plant features associated with drought stress. This offers a robust and interpretable solution for drought stress monitoring for farmers to undertake informed decisions for improved crop management.
Why it matches plant phenotyping methodsジャガイモの干ばつストレスという植物状態を航空画像から推定する、説明可能なViT画像解析パイプラインを開発・評価しており、表現型取得・抽出手法が中心である。
abstractWe propose an explainable deep learning pipeline that leverages the power of ViTs for drought stress detection in potato crops using aerial imagery.
Delayed identification of crop diseases, which significantly impact agricultural yields, remains a critical challenge. Crop diseases are a major factor contributing to reducing productivity. Since leaves are the mirrors of crop health, by investigating the leaves, a prediction of crop health can be made. This study aims to predict crop disease in the vegetative growth phase with greater efficiency. The two most prominent features, color and texture of the leaves, are extracted with different techniques, followed by fuzzification of these features. Two machine learning models, the bootstrap model and the multi-class support vector machine (MSVM), are employed for disease prediction. The findings show that for multi-class disease prediction, the bootstrap model with histogram and modified co-occurrence matrix features obtains a superior average accuracy of 98.07%, while the MSVM with fuzzy features delivers an average accuracy of 80.11% in the potato crop with early blight disease.
Why it matches plant phenotyping methods葉の色・テクスチャを画像特徴として抽出し、植物病害状態を推定する手法が研究の中心であり、病害フェノタイピング手法として適格です。
abstractThe two most prominent features, color and texture of the leaves, are extracted with different techniques, followed by fuzzification of these features.
Monitoring of plant health based on the leaf images is a common practice in agriculture for effective disease detection and handling with preferred approach. In this work, potato leaf-image based disease analysis with deep-transfer-learning (DTL) is proposed with conventional and fused-features and the attained outcome is presented. This work considered the following stages to obtain better detection; leaf-data collection and resizing, feature extraction with DTL-model, feature based disease detection with SoftMax, features-fusion using 50% dropout, and classification with 3-foldc cross validation. This research considered 1200 images per class for analysis and performance is verified with individual-, and fused-features. This work considered the ResNet (RN) variants for the examination and the outcome of this work presents classification accuracy of >96% with Random-Forest (RF) classifier.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定する画像ベース手法を、深層転移学習・特徴抽出・特徴融合・分類・交差検証により中心的に開発・評価しているため。
titlePotato Plant Disease Detection from Leaf Images: A Study with Deep Transfer Learning and Features Fusion
Introduction Volatile organic compounds (VOCs) are products of plant secondary metabolism with the potential for signalling early stress response. This pilot study investigated the potential of VOCs as markers for drought stress in potato. We hypothesised that differences in VOC emissions between cultivars may reflect genotypes with greater adaptive efficiency to drought stress. Methods Using thermal desorption collection and gas chromatography-mass spectrometry (GC-MS) techniques, we profiled the VOCs emitted by two potato cultivars, Maris Piper and Désirée, under well-watered and drought conditions, across a four-week period ( n = 3 per cultivar, treatment, and time-point). Results We identified 23 compounds, and tentatively identified another 49 compounds, including sesquiterpenes, alkanes, monoterpenes, and methylbenzenes. Statistical analysis revealed that seven compounds showed significant differences between cultivars and drought/well-watered treatments. Two farnesene isomers, a xylene isomer, 2,6-dimethyldecane, decahydronaphthalene, and 2-methyldecalin were identified as tentative markers of drought stress. Discussion Our findings suggest that VOCs could be used for detection of drought stress in potato plants, contributing to improved irrigation management and the breeding of more drought-tolerant varieties. Further research is needed to validate these findings and explore the underlying mechanisms.
Why it matches plant phenotyping methodsジャガイモの干ばつストレスという植物状態をVOC測定で検出する可能性を検証し、GC-MSによる取得・解析と候補マーカーの評価が研究の中心であるため。
abstractThis pilot study investigated the potential of VOCs as markers for drought stress in potato.
Precision irrigation plays a crucial role in managing crop production in a sustainable and environmentally friendly manner. This study builds on the results of the GreenWaterDrone project, aiming to estimate, in real time, the actual water requirements of crop fields using the crop water stress index, integrating infrared canopy temperature, air temperature, relative humidity, and thermal and near-infrared imagery. To achieve this, a state-of-the-art aerial micrometeorological station (AMMS), equipped with an infrared thermal sensor, temperature–humidity sensor, and advanced multispectral and thermal cameras is mounted on an unmanned aerial system (UAS), thus minimizing crop field intervention and permanently installed equipment maintenance. Additionally, data from satellite systems and ground micrometeorological stations (GMMS) are integrated to enhance and upscale system results from the local field to the regional level. The research was conducted over two years of pilot testing in the municipality of Trifilia (Peloponnese, Greece) on pilot potato and watermelon crops, which are primary cultivations in the region. Results revealed that empirical irrigation applied to the rhizosphere significantly exceeded crop water needs, with over-irrigation exceeding by 390% the maximum requirement in the case of potato. Furthermore, correlations between high-resolution remote and proximal sensors were strong, while associations with coarser Landsat 8 satellite data, to upscale the local pilot field experimental results, were moderate. By applying a comprehensive model for upscaling pilot field results, to the overall Trifilia region, project findings proved adequate for supporting sustainable irrigation planning through simulation scenarios. The results of this study, in the context of the overall services introduced by the project, provide valuable insights for farmers, agricultural scientists, and local/regional authorities and stakeholders, facilitating improved regional water management and sustainable agricultural policies.
Why it matches plant phenotyping methods熱・マルチスペクトル画像と気象センサーを統合し、作物の水ストレス状態（crop water stress index）を推定する取得・推定システムが研究の中心であり、フィールドおよび衛星データとの相関検証も行っている。
abstractaiming to estimate, in real time, the actual water requirements of crop fields using the crop water stress index, integrating infrared canopy temperature, air temperature, relative humidity, and thermal and near-infrared imagery.
Abstract The article presents a methodology for the quantitative assessment of seed potato tuber and mini-tuber parameters, comparing traditional manual measurements with an automated digital method using a machine vision system based on OpenCV in Python. Five major Kazakh potato varieties—Astana, Alliance, Janaysan, Narly, and Eden—were analyzed. Each tuber’s mass and linear dimensions (length, width, thickness) were measured manually and digitally. The automated setup uses two cameras to capture images from perpendicular planes, allowing calculation of mass, dimensions, area, and perimeter from images. An algorithm was developed to convert image data from pixels to millimeters and ensure accurate physical measurements. Results showed close agreement between manual and digital methods, with a relative error not exceeding 1.6% for mass and 3.0% for dimensions. Shape descriptors such as index and form coefficient were also calculated. Regression models for mass prediction were developed, offering high accuracy and potential for refinement. The digital method increased measurement productivity by seven times compared to manual approaches. The findings and regression equations will contribute to the development of machine learning algorithms for automated varietal classification of potato tubers based on their physical traits.
Why it matches plant phenotyping methodsジャガイモ塊茎の質量・寸法・形状を画像から定量化するデジタル計測法を開発し、手動測定との精度比較で検証しているため、植物フェノタイピング手法が中心である。
abstractpresents a methodology for the quantitative assessment of seed potato tuber and mini-tuber parameters, comparing traditional manual measurements with an automated digital method using a machine vision system based on OpenCV in Python
Global challenges such as climate change and population growth require improvements in crop monitoring models. To address these issues, this study advances the identification of potato crop phenological stages using satellite remote sensing, a field where cereals have been the primary focus. We introduce a methodology using Sentinel-1 (S1) and Sentinel-2 (S2) time series data to pinpoint critical phenological stages—emergence, canopy closure, flowering, senescence onset, and harvest timing—at the field scale. Our approach utilizes analysis of NDVI, fAPAR, and IRECI2 from S2, alongside VH and VV polarizations from S1, informed by domain knowledge of the spectral and morphological responses of potato crops. We propose the integration of NDVI and VH indices, NDVI_VH, to improve stage detection accuracy. Comparative analysis with ground-observed stages validated the method’s effectiveness, with NDVI proving to be one of the most informative indices, achieving RMSEs of 12 and 14 days for emergence and closure, and 17 days for the onset of senescence. The integrated NDVI_VH approach complemented NDVI, particularly in harvest and flowering stages, where VH enhanced accuracy, achieving an overall R2 value of 0.80. The study demonstrates the potential of combining SAR and optical data for post-season crop phenology analysis, providing insights that can inform the development of new methods and strategies to enhance on-season crop monitoring and yield forecasting.
Why it matches plant phenotyping methodsSentinel-1/2時系列からジャガイモの生育ステージを抽出する手法を開発し、地上観測で精度検証しており、植物フェノタイピングが中心である。
abstractWe introduce a methodology using Sentinel-1 (S1) and Sentinel-2 (S2) time series data to pinpoint critical phenological stages—emergence, canopy closure, flowering, senescence onset, and harvest timing—at the field scale.
Globally, potatoes are the fourth most produced food crop, and in the United Kingdom alone, they generated approximately £705 million in 2022. However, to achieve the United Nations (UN) Sustainable Development Goals (SDG), potato farmers need to sustainably increase yields to address the growing demand for both food and land. Crop yield can be affected by various factors, including disease, pests, and nutrient deficiencies. To tackle these challenges and optimise yields, researchers have leveraged remote sensing platforms for high-throughput non-destructive phenotyping. Data collected from these platforms can be used to develop machine learning (ML) models aimed at addressing the aforementioned issues. To summarise recent developments in ML models applied to potato plant phenotyping, a systematic review of journal articles from the last seven years was conducted. This review underscored the advantages of Deep Learning (DL) approaches and the rising trend of Convolutional Neural Network (CNN)-based architectures, while also noting the limited availability of data for training these models. This review is intended to benefit researchers and farmers by providing an up-to-date review of ML models in potato plant phenotyping. • Remote sensing and ML models can optimise potato yield through non-destructive phenotyping. • Deep Learning (DL) and CNN-based approaches show promise in potato phenotyping. • Limited training data availability remains a challenge in ML model development for agriculture. • This review supports researchers and farmers with current insights on ML advancements in potato crop phenotyping.
Why it matches plant phenotyping methodsジャガイモ植物フェノタイピングにおけるリモートセンシングと機械学習手法を主題とする体系的レビューであり、フェノタイピング手法のレビューが中心です。
abstractTo summarise recent developments in ML models applied to potato plant phenotyping, a systematic review of journal articles from the last seven years was conducted.
Globally, potatoes are the fourth most produced food crop, and in the United Kingdom alone, they generated approximately £705 million in 2022. However, to achieve the United Nations (UN) Sustainable Development Goals (SDG), potato farmers need to sustainably increase yields to address the growing demand for both food and land. Crop yield can be affected by various factors, including disease, pests, and nutrient deficiencies. To tackle these challenges and optimise yields, researchers have leveraged remote sensing platforms for high-throughput non-destructive phenotyping. Data collected from these platforms can be used to develop machine learning (ML) models aimed at addressing the aforementioned issues. To summarise recent developments in ML models applied to potato plant phenotyping, a systematic review of journal articles from the last seven years was conducted. This review underscored the advantages of Deep Learning (DL) approaches and the rising trend of Convolutional Neural Network (CNN)-based architectures, while also noting the limited availability of data for training these models. This review is intended to benefit researchers and farmers by providing an up-to-date review of ML models in potato plant phenotyping.
Why it matches plant phenotyping methodsジャガイモ植物フェノタイピングに用いるリモートセンシングと機械学習モデルを体系的にレビューしており、フェノタイピング手法のレビューが中心です。
titlePotato plant phenotyping and characterisation utilising machine learning techniques: A state-of-the-art review and current trends
Why it matches plant phenotyping methods干ばつ耐性を評価するための高スループット水耕アッセイを開発・提示し、植物表現型（バイオマス、光合成、回復）を再現可能なプラットフォームで取得することが中心である。
abstractwe present a rapid, high-throughput hydroponic assay designed as an efficient pre-screening tool for evaluating potato cultivars and CRISPR-edited lines.
Early crop disease detection remains challenging for precision agriculture. This research presents an AI-drone surveillance system using YOLOv12 deep learning model to automatically identify diseases for real-time monitoring in potato, banana, and cotton crops. The complete pipeline includes automated image acquisition, intelligent preprocessing, and real-time analysis. Compared to traditional manual inspection, this approach reduces diagnosis time from days to minutes while improving reliability. Key innovations include optimized model architectures for resource-limited environments and multi-spectral disease pattern recognition. Field tests confirm the system's robustness across varying weather conditions and growth stages. Proposed method processes the drone-captured images through Raspberry Pi edge computing, achieving 99.5%, 98.1%, and 89.7% detection accuracy of potato, banana, and cotton crops respectively. The lightweight YOLO-Nano variants enable efficient field deployment while maintaining precision. A merged dataset across 28 disease classes demonstrates 91.8% overall accuracy through comprehensive validation metrics. Farmers receive immediate alerts for targeted treatment, reducing pesticide use by 30-45% in trial implementations. This scalable solution outperforms existing methods in both speed (4.2ms per image) and accuracy. Results demonstrate practical potential for transforming global agricultural monitoring through accessible AI technology.
Why it matches plant phenotyping methods植物の病害状態をドローン画像から推定するYOLOベースの取得・解析パイプラインを開発し、圃場で検証しており、表現型取得法が研究の中心である。
abstractThis research presents an AI-drone surveillance system using YOLOv12 deep learning model to automatically identify diseases for real-time monitoring in potato, banana, and cotton crops.
Abstract Potato crops are a vital part of global food security. Potato leaf and crop health play a crucial role in determining the yield and quality of potato production. This paper presents a novel approach to potato disease detection by integrating a Vision Transformer (ViT) model with a Large Language Model (LLM) for enhanced classification of potato plant diseases. We developed a multi-modal pipeline that not only accurately identifies diseases affecting potato leaves and tubers but also provides contextual explanations for the diagnoses. Experimental results demonstrate that our integrated approach outperforms traditional individual models, with the potato leaf disease classifier achieving 99.44% validation accuracy and the potato tuber disease classifier reaching 76.19% accuracy when trained separately, while the combined model maintains excellent performance of 95.06% on the validation set. The fusion of computer vision with Mistral AI's LLM capabilities creates an interpretable system that can assist agricultural experts with both disease identification and recommended treatment actions. This paper contributes to the growing field of AI-assisted agriculture by demonstrating how multi-modal deep learning systems can provide more comprehensive solutions to potato disease management challenges, potentially reducing crop losses and improving food security.
Why it matches plant phenotyping methodsジャガイモ葉・塊茎の病徴を画像から分類するマルチモーダル手法が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として適格です。
abstractThis paper presents a novel approach to potato disease detection by integrating a Vision Transformer (ViT) model with a Large Language Model (LLM) for enhanced classification of potato plant diseases.
Advances in image processing and techniques in artificial intelligence have made it possible for computers to see and learn. This article introduced a technology that has utilised MobilenetV2 Deep Convolution Neural Network architecture to automatically identify and diagnose plant diseases from images. The identification and classification of plant diseases are now carried out by only human experts-crop extension agents, and farmers, expensive labour that is prone to mistakes. This study relies on dataset gathering as a technique of classifying and identifying plant diseases. It is a multistep process involving pre-process data on the raw set, mask green area of the leaf, remove green section, convert to grayscale and then obtain some characteristics, select, and classify with regard to disease management, etc. Two different types of plants, maize and potato, have been taken in consideration to show effectiveness of the outcome of the proposed model. The confusion matrix and classification performance report were used to evaluate the system. The dataset for potato and maize comprised 6228 and 6878 images, respectively, of leaves. Precise, recall, and F1-scores of 95.15%, 94.76%, and 94.93% were recorded as a cumulative performance across the datasets of potato and maize respectively. This translates to its resistance in picking most diseases for these crops, making it a resource that can be used with confidence in agriculture disease detection. The MobileNetV2 model performs well in both crops, especially for potato early blight and maize common rust. Lower performance in recognizing healthy potato leaves suggests that the feature space of healthy and diseased leaves may overlap. The MobileNetV2 model performed a robust ability in general in the detection of most diseases affecting both potato and maize leaves, but some specific areas need to be targeted for further enhancement.
Why it matches plant phenotyping methods葉画像から植物病害を自動検出・分類する深層学習手法の開発と性能評価が研究の中心であり、植物の病害状態を直接推定するため適格。
abstractThis article introduced a technology that has utilised MobilenetV2 Deep Convolution Neural Network architecture to automatically identify and diagnose plant diseases from images.
Recently, the classification of plant leaf diseases has become a critical research area to improve the agricultural productivity.Early and accurate identification of diseases is needed to prevent the disease transmission and reduce the crop losses.Deep learning approaches enables to learn complex meaningful patterns within the various leaves.In the paper, enhanced convolutional neural network with attention mechanism (ECNNA) model is proposed to extract the discriminative features and classify the types of leaf diseases.The ECNNA comprises of prior feature extraction with convolution layers and maximum pooling layers, feature enhancement with attention mechanism, classification using SoftMax classifier.Additionally, the model utilizes data augmentation techniques to increase dataset diversity and improve generalization ability of model.The attention layer is incorporated in convolutional neural network to improve the performance of system that increase crop yield and quality.The system classifies the various diseases categories.Experimental results demonstrate that the proposed ECNNA model achieves the classification accuracy of 99.99% on Potato dataset, 97.27% on Corn dataset, 97.95% on Apple dataset, 99.14% on Grape dataset, 99.62% on Peach dataset, 99.31% on six classes dataset, and 98.90% on eight classes dataset.The classification results are also compared with previous studies, indicating the higher classification rate.This research contributes to the early detection and diagnosis of plant leaf disease for supporting sustainable agriculture and food security.
Why it matches plant phenotyping methods植物葉の画像から病害状態を分類する深層学習手法を開発し、複数データセットで性能比較・評価しており、病害表現型の取得・判定が中心です。
abstractenhanced convolutional neural network with attention mechanism (ECNNA) model is proposed to extract the discriminative features and classify the types of leaf diseases.
Abstract: The agricultural sector holds paramount importance in our economy, impacting our daily lives significantly. Effective management of agricultural resources is crucial for ensuring profitability in crop production. However, farmers often lack expertise in identifying and managing plant leaf diseases, leading to reduced yields. Detecting and classifying leaf diseases is pivotal for maximizing agricultural productivity. Utilizing Convolutional Neural Networks (CNNs) offers a promising solution for automated leaf disease detection and classification. This research focuses on detecting diseases in key crops such as apple, grape, corn, potato, and tomato plants. By leveraging deep CNN models, this study aims to enhance disease monitoring in large crop fields, enabling prompt identification of disease symptoms and facilitating timely intervention. Such advancements in plant leaf disease detection have broad applications in biological research and agricultural institutes, offering immense potential to optimize crop health management and maximize yields. Comparing the proposed deep CNN model with established transfer learning approaches like VGG16 underscores the significance of this research endeavor in addressing the critical need for efficient disease detection and management in agriculture..
Why it matches plant phenotyping methods植物葉の病徴を画像から検出・分類するCNN手法が研究の中心であり、植物の病害状態を直接推定するため、表現型計測手法として採用。
abstractUtilizing Convolutional Neural Networks (CNNs) offers a promising solution for automated leaf disease detection and classification.
Humans need food to sustain their lives. Therefore, agriculture is one of the most important issues in nations. Agriculture also plays a major role in the economic development of countries by increasing economic income. Early diagnosis of plant diseases is crucial for agricultural productivity and continuity. Early disease detection directly impacts the quality and quantity of crops. For this reason, many studies have been carried out on plant leaf disease classification. In this study, a simple and effective leaf disease classification method was developed. Disease classification was performed using seven state-of-the-art pretrained convolutional neural network architectures: VGG16, ResNet50, SqueezeNet, Xception, ShuffleNet, DenseNet121 and MobileNetV2. A simplified SqueezeNet model, GAPNet, was subsequently proposed for grape, apple and potato leaf disease classification. GAPNet was designed to be a lightweight and fast model with 337.872 parameters. To address the data imbalance between classes, oversampling was carried out using the synthetic minority oversampling technique. The proposed model achieves accuracy rates of 99.72%, 99.53%, and 99.83% for grape, apple and potato leaf disease classification, respectively. A success rate of 99.64% was achieved in multiplant leaf disease classification when the grape, apple and potato datasets were combined. Compared with the state-of-the-art methods, the lightweight GAPNet model produces promising results for various plant species.
Why it matches plant phenotyping methods植物葉の病害状態を画像から分類する軽量CNN手法を開発・評価しており、病害表現型の抽出が研究の中心です。
abstractIn this study, a simple and effective leaf disease classification method was developed.
Reproduction assets foundAuthors publicly release GAPNet implementation code via GitHub and Zenodo, and the paper's leaf image datasets (PlantVillage, New Plant Disease, Plant Pathology 2020) are publicly available at listed URLs.Code · publiccle, and approved the final draft.
Asuman Günay Yılmaz conceived and designed the experiments, analyzed the data, authored or reviewed drafts of the article, and approved the final draft.
Data Availability
The following information was supplied regarding data availability:
The data and code are available at GitHub and Zenodo:
- https://github.com/ozgenurr/GAPNet.git .Open asset ↗ozgenurr/GAPNetlines:727-762Dataset · public- Ozge Ozaras. (2025). ozgenurr/GAPNet: GAPNET (GAPNET). Zenodo. https://doi.org/10.5281/zenodo.15163686 .
The datasets are publicly available at:
- Plant Village Dataset: https://github.com/spMohanty/PlantVillage-Dataset/tree/master/raw/color .
- New Plant disease Dataset: https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset/data .
- Plant Pathology: https://www.kaggle.com/competitions/plant-pathology-2020-fgvc7/data .
References
Babalola, Kpai & Toygar (2023) Babalola FO, Kpai NI, Toygar Ö. Deep learning-based classification of apple leaf diseases uOpen asset ↗PlantVillage-Datasetlines:763-789Dataset · public- Ozge Ozaras. (2025). ozgenurr/GAPNet: GAPNET (GAPNET). Zenodo. https://doi.org/10.5281/zenodo.15163686 .
The datasets are publicly available at:
- Plant Village Dataset: https://github.com/spMohanty/PlantVillage-Dataset/tree/master/raw/color .
- New Plant disease Dataset: https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset/data .
- Plant Pathology: https://www.kaggle.com/competitions/plant-pathology-2020-fgvc7/data .
References
Babalola, Kpai & Toygar (2023) Babalola FO, Kpai NI, Toygar Ö. Deep learning-based classification of apple leaf diseases using AlexNet. Computer Science, IDAP-2023: International Artificial Intelligence and Data Processing SympOpen asset ↗lines:763-789Dataset · publicGAPNET (GAPNET). Zenodo. https://doi.org/10.5281/zenodo.15163686 .
The datasets are publicly available at:
- Plant Village Dataset: https://github.com/spMohanty/PlantVillage-Dataset/tree/master/raw/color .
- New Plant disease Dataset: https://www.kaggle.com/datasets/vipoooool/new-plant-diseases-dataset/data .
- Plant Pathology: https://www.kaggle.com/competitions/plant-pathology-2020-fgvc7/data .
References
Babalola, Kpai & Toygar (2023) Babalola FO, Kpai NI, Toygar Ö. Deep learning-based classification of apple leaf diseases using AlexNet. Computer Science, IDAP-2023: International Artificial Intelligence and Data Processing Symposium (IDAP-2023) 2023:67–74. doi: 10.53070/bbd.1349566.
BanjaOpen asset ↗lines:763-789Plant phenotyping relevance match · UnverifiedEurope PMC · checked 14 Sept 2026
The detection of plant diseases in the modern era offers a promising first step toward sustainable agriculture and food security. Plant physiology can be studied quantitatively thanks to advances in imaging and computer vision. Conversely, manual interpretation requires a great deal of labor, knowledge of plant diseases. Numerous innovative methods for identifying and classifying particular diseases have been widely used. In order to diagnose potato diseases more accurately and quickly using a machine learning model, this study uses a new feature extraction method based on GJPs image features. The methodology of this study relies on:•Modules for preprocessing, feature extraction, dimension reduction, and classification.•Generalized jones polynomials as new image features method is used to extract the texture features from potato images for diagnosing potato diseases. The data used in this model were collected from the plant village image dataset using samples of potato leaves. Using an SVM classifier on potato leaf images, the disease was accurately identified in 98.45 % of cases. The recommended feature extraction technique can reduce financial loss while also assisting in the efficient management of plant diseases, enhancing crop productivity and ensuring food security.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定する画像特徴抽出・分類手法が研究の中心であり、植物病害フェノタイピング手法として適格。
abstractthis study uses a new feature extraction method based on GJPs image features.
Genetic gain in potato breeding is limited by the heterozygous tetraploid genome of cultivated potato. Recent efforts to breed potato at the diploid level promise to improve genetic gain and allow more straightforward genetics and introgression breeding. Diploid F1 hybrid potato breeding relies on the ability to create diploid inbred lines via repeated self-fertilization. However, self-fertilization of diploid potato is hampered by a gametophytic self-incompatibility system encoded by the S-locus that prevents fertilization by self-pollen. Nonetheless, self-compatible diploid potato genotypes exist and have been used to create inbred lines. The S-locus inhibitor (Sli) gene is a dominant gene that provides strong self-compatibility in diploid potato and was previously mapped to Chromosome 12. While the Sli gene has already been identified and characterized, the most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene. To this end, we developed an effective phenotyping protocol to identify suitable parents and create diploid populations segregating for Sli. We show that an accurate phenotyping method is crucial to discriminate between confounding fertility factors and self-compatibility. In addition, we found that the Sli locus shows extreme segregation distortion on Chromosome 12. Finally, we used these insights to develop three F1 populations that segregate for Sli, which we later used for the identification of the Sli gene.
Why it matches plant phenotyping methodsSli遺伝子の識別に向け、自己適合性を評価する表現型判定プロトコルを開発しており、フェノタイピング手法が研究の中心である。
abstractthe most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene.
Accurate assessment of plant leaf disease severity is crucial for implementing precision pesticide application, which in turn significantly enhances crop yields. Previous methods primarily rely on global perceptual learning, often leading to the misidentification of non-lesion regions as lesions within complex backgrounds, thereby compromising model accuracy. To address the challenge of background interference, we propose a location-guided lesion representation learning method (LLRL) based on image generation to assess the severity of plant leaf diseases. Our approach comprises three key parts: the image generation network (IG-Net), the location-guided lesion representation learning network (LGR-Net), and the hierarchical lesion fusion assessment network (HLFA-Net). IG-Net is designed to construct paired images necessary for LGR-Net by utilizing a diffusion model to generate diseased leaves from healthy ones. First, the LGR-Net facilitates the network's focus on the lesion area by contrasting paired images: healthy and diseased leaves, obtaining a pre-trained dual-branch feature encoder (DBF-Enc) that incorporates lesion-specific prior knowledge, providing focused visual features for HLFA-Net. Second, the HLFA-Net, which shares and freezes the DBF-Enc, further fuses and optimizes the features extracted by DBF-Enc, culminating in a precise classification of disease severity. In addition, we construct an image dataset containing three plant leaf diseases from apple, potato, and tomato plants, with a total of 12,098 photos, to evaluate our approach. Finally, experimental results demonstrate that our method outperforms existing classification models, with at least an improvement of 1 % in accuracy for severity assessment, underscoring the efficacy of the LLRL method in accurately identifying the severity of plant leaf diseases. Our code and dataset are available at http://llrl.samlab.cn/.
Why it matches plant phenotyping methods植物葉の病害重症度という状態を画像から推定する手法を開発し、データセットで評価しており、フェノタイピング手法が中心です。
abstractwe propose a location-guided lesion representation learning method (LLRL) based on image generation to assess the severity of plant leaf diseases.
Estimating leaf nutrient concentration in field crops is essential to increase crop yield by optimum fertiliser application. Notably, these practices become more critical for short-cycle crops like potatoes (Solanum tuberosum L.), where conventionally, laborious in-field plant sampling and laboratory analysis take a long time. Multiple samples are frequently required to reach the field’s representation and reliability. The alternative technique of optical spectroscopy, which reports the canopy reflectance to the specific band of the electromagnetic spectrum, can be used to estimate the plant nutrient concentration. Previous studies have made such efforts using the electromagnetic spectrum’s visible to near-infrared (VNIR, 400–1100 nm) and short-wave infrared (SWIR, 1100–2400 nm) ranges. In this study, we are testing the ability of the spectroscopy with a full-range spectroradiometer (400–2400 nm) along with a comparison of VNIR and SWIR to estimate the total Kjeldahl nitrogen (TKN), phosphorus (P), potassium (K), and sulphur (S) nutrient concentration in freshly picked petiole/leaf samples of potato plants. Results show that the full-range spectrum predicted TKN with an accuracy of R² = 0.91 external validation (0.74 internal validation), followed by K, R² = 0.87 (0.69), P, R² = 0.86 (0.82), and S with R² = 0.75 (0.68). It was also reported that the maximum difference in the estimation accuracy among VNIR and SWIR was reported for K, where VNIR had R² = 0.48 (0.54) and SWIR had R² = 0.86 (0.80). This study lays a foundation for further development of models that can estimate the canopy nutrient concentration in the field with spectral reflectance and scale up these models with hyperspectral imaging.
Why it matches plant phenotyping methodsジャガイモ葉の分光反射から栄養状態を推定する手法を開発・比較し、外部検証も実施しており、植物形質取得が研究の中心である。
abstractIn this study, we are testing the ability of the spectroscopy with a full-range spectroradiometer (400–2400 nm) along with a comparison of VNIR and SWIR to estimate the total Kjeldahl nitrogen (TKN), phosphorus (P), potassium (K), and sulphur (S) nutrient concentration in freshly picked petiole/leaf samples of potato plants.
Potatoes are an essential crop cultivated in numerous regions around the globe, but they frequently get impacted by diseases that lower their production and quality. To ensure the crop reaches its maximum potential, controlling the diseases in the initial or early stages is necessary. Recent developments in deep learning algorithms have demonstrated significant improvements in predicting agricultural diseases at various stages. However, contemporary deep learning models frequently exhibit real-world performance and generalization capabilities limitations. This study proposes an ensemble convolutional neural network model that combines the three most widely used models, VGG16, MobileNetV2, and ResNet50, to increase generalizability and improve accuracy in the classification of potato crop diseases. The proposed model is trained on a large dataset containing 6644 images of potato leaves, which is constructed by merging three different publicly available datasets. These datasets are originally collected from three distinct locations around the globe (the USA, Ethiopia, and Pakistan). The model aims to achieve improvement in accuracy and maintain generalizability for classifying potato fungal diseases. The proposed ensemble architecture achieved an accuracy of 98.49%, surpassing the individual models. In this study, a web-based interface is developed for the evaluation of the model. The proposed model is tested on this web interface with the images obtained through the Google Image Search Engine. A plant pathologist supervised the selection of images and the pre-processing of the dataset. The results of the evaluation indicate that the model will perform better when deployed in real-world situations.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病害状態を分類するCNN手法の開発・評価が中心であり、植物の病害表現型を直接推定しているため。
abstractThis study proposes an ensemble convolutional neural network model that combines the three most widely used models, VGG16, MobileNetV2, and ResNet50, to increase generalizability and improve accuracy in the classification of potato crop diseases.
This review paper investigates the utilization of Convolutional Neural Networks (CNNs) for disease detection in potato agriculture, highlighting their pivotal role in efficiently analyzing large-scale agricultural datasets. The datasets used, preprocessing methodologies applied, specific data collection zones, and the efficacy of prominent algorithms like ResNet, VGG, and MobileNet variants for disease classification are scrutinized. Additionally, various hyperparameter optimization techniques such as grid search, random search, genetic algorithms, and Bayesian optimization are examined, and their impact on model performance is assessed. Challenges including dataset scarcity, variability in disease symptoms, and the generalization of models across diverse environmental conditions are addressed in the discussion section. Opportunities for advancing CNN-based disease detection, including the integration of multi-spectral imaging and remote sensing data, and the implementation of federated learning for collaborative model training, are explored. Future directions propose research into robust transfer learning techniques and the deployment of CNNs in real-time monitoring systems for proactive disease management in potato agriculture. Current knowledge is consolidated, research gaps are identified, and avenues for future research in CNN-based disease detection strategies to sustain potato farming effectively are proposed by this review. This study paves the way for future advancements in AI-driven disease detection, potentially revolutionizing agricultural practices and enhancing food security. Also, it aims to guide future research and development efforts in CNN-based disease detection for potato agriculture, potentially leading to improved crop management practices, increased yields, and enhanced food security.
Why it matches plant phenotyping methodsジャガイモの病徴をCNN画像解析で分類・検出する手法を主題としたレビューであり、植物病害状態の表現型推定に関する方法論を中心に扱っている。
titleA Comprehensive Review of Convolutional Neural Networks based Disease Detection Strategies in Potato Agriculture
Timely and accurate monitoring of plant nitrogen concentration (PNC) is vital for optimizing field N management. Hyperspectral indices are commonly used as a predictor for monitoring the PNC of crops, but individual spectral indices are often susceptible to cultivars and growth stages. Machine learning (ML) is a promising method for mining more spectral variables to assess the PNC of crops. To monitor the PNC of potatoes, therefore, this study extended previous work to further use hyperspectral optimized spectral indices (OSI) as input variables of ML, while, comparing with the ML models that used full-spectrum (FS), existing spectral indices (ESI) and sensitive spectral bands (SSB) as input variables, as well as simple regression model based on OSI alone. The partial least squares regression (PLSR), random forest (RF), support vector regression (SVR), and artificial neural network (ANN) models were calibrated using a dataset encompassing three cultivars and critical fertigation growth stages under three to six N levels. The calibrated ML models were evaluated using the datasets from independent experiments and two farmers´ fields. The OSI as an input variable in ML models showed superiority for predicting the potato PNC compared to FS, SSB, and ESI. The OSI-based RF model with an R² of 0.79, RMSE of 0.27%, and RPD of 2.18 had higher accuracy for predicting potato PNC than other ML models. Comparing the simple optimized spectral indices regression model alone, the OSI-based RF model reduced RMSE by mitigating the effects of cultivars and growth stages on PNC prediction. The OSI-based RF model significantly contributes to optimum fertilization management based on actual potato N status during critical growth periods.
Why it matches plant phenotyping methodsジャガイモの植物窒素濃度という形質をハイパースペクトル指標と機械学習で推定し、独立実験および農家圃場でモデル性能を評価しているため、形質取得・推定手法が中心です。
abstractMachine learning (ML) is a promising method for mining more spectral variables to assess the PNC of crops.
Potatoes are a vital part of our diet worldwide, but their cultivation poses challenges due to environmental impacts from traditional farming methods. Precision agriculture offers a promising solution by managing variability in crop growth and reducing environmental disturbance. Remote sensing technologies have become crucial for monitoring crops and field dynamics more efficiently. In potato farming, the use of remote and proximal sensing technologies facilitates the prediction of yields and nutrient levels. This capability allows farmers to pinpoint the spatiotemporal variations in yields and nutrients, allowing them to make precise management decisions for each specific area of their fields. It is also valuable for monitoring nitrogen levels in plants during the growing season. This helps farmers apply the right amount of fertilizer at the right time, optimizing yields without affecting the environmental quality. While still evolving, remote sensing transforms potato farming by providing detailed, non-invasive insights that can enhance productivity and sustainability. Research into different technologies and machine learning models for potato farming in Canada has been largely confined to a few provinces. This review aimed to identify this knowledge gap, underscoring the need for broader exploration of innovative agricultural methods across diverse regions of the country.
Why it matches plant phenotyping methodsジャガイモの収量・植物栄養状態・窒素レベルを対象に、リモート／近接センシングと機械学習による推定技術をレビューしており、植物形質の取得・推定手法が中心である。
titleA Review on Potato Crop Yield and Nitrogen Management Utilizing Remote/Proximal Sensing Technologies and Machine Learning Models in Canada
Accurate assessment of plant leaf disease severity is crucial for implementing precision pesticide application, which in turn significantly enhances crop yields. Previous methods primarily rely on global perceptual learning, often leading to the misidentification of non-lesion regions as lesions within complex backgrounds, thereby compromising model accuracy. To address the challenge of background interference, we propose a location-guided lesion representation learning method (LLRL) based on image generation to assess the severity of plant leaf diseases. Our approach comprises three key parts: the image generation network (IG-Net), the location-guided lesion representation learning network (LGR-Net), and the hierarchical lesion fusion assessment network (HLFA-Net). IG-Net is designed to construct paired images necessary for LGR-Net by utilizing a diffusion model to generate diseased leaves from healthy ones. First, the LGR-Net facilitates the network's focus on the lesion area by contrasting paired images: healthy and diseased leaves, obtaining a pre-trained dual-branch feature encoder (DBF-Enc) that incorporates lesion-specific prior knowledge, providing focused visual features for HLFA-Net. Second, the HLFA-Net, which shares and freezes the DBF-Enc, further fuses and optimizes the features extracted by DBF-Enc, culminating in a precise classification of disease severity. In addition, we construct an image dataset containing three plant leaf diseases from apple, potato, and tomato plants, with a total of 12,098 photos, to evaluate our approach. Finally, experimental results demonstrate that our method outperforms existing classification models, with at least an improvement of 1 % in accuracy for severity assessment, underscoring the efficacy of the LLRL method in accurately identifying the severity of plant leaf diseases. Our code and dataset are available at http://llrl.samlab.cn/.
Why it matches plant phenotyping methods植物葉の病害重症度という可視的な状態を画像から推定する手法を開発・評価しており、病害フェノタイピングが研究の中心です。
abstractwe propose a location-guided lesion representation learning method (LLRL) based on image generation to assess the severity of plant leaf diseases.
In-season nitrogen (N) status diagnosis is an effective way to guide split N applications for improved profitability and minimized negative environmental impacts. Petiole nitrate-N concentration (PNNC) has been an industry standard indicator for in-season potato (Solanum tuberosum L.) N status diagnosis but is limited because of destructive sampling and chemical processing needs. Leaf sensors can be used to predict PNNC and other N status indicators and overcome these challenges. The SPAD meter is a sensor commonly used to estimate leaf chlorophyll (Chl) based on transmittance, while Dualex is a newer leaf sensor that can also measure leaf flavanol (Flav) and anthocyanin (Anth) through Chl fluorescence. Limited research has been conducted to compare the two leaf sensors for potato N status assessment, despite their respective success in N status diagnosis for other crops. Therefore, the objectives of this study were to 1) compare the performance of the Dualex sensor relative to the SPAD meter for predicting potato N status indicators when only sensor data are used, 2) evaluate the potential of improving potato N status prediction using multi-source data fusion compared with only using leaf sensor data, and 3) develop practical strategies for leaf-sensor-based in-season potato N status diagnosis. The plot-scale experiments were conducted in Becker, Minnesota, USA in 2018, 2019, 2021, and 2023 involving different cultivars, N treatments, and irrigation treatments in a split plot design with three replications. Leaf sensor data and plant samples were simultaneously collected and processed multiple times at key growth stages each year. Daily weather data were also collected at the on-site weather station. Different in-season potato N status indicators including PNNC and N nutrition index (NNI) were derived from plant samples, while weather- and management-related parameters were calculated using the weather data and management records. Dualex’s N balance index (NBI; Chl/Flav) always outperformed Dualex Chl but did not consistently perform better than the SPAD meter. All N status indicators were predicted with significantly higher accuracy with multi-source data fusion using machine learning models. A practical in-season potato N status diagnostic strategy was developed using linear support vector regression model with SPAD, cultivar information, accumulated growing degree days (GDDs), accumulated total moisture, and as-applied N rate to predict vine or whole plant NNI, achieving an R² of 0.80 - 0.82, accuracy of 0.75 - 0.77, and a Kappa statistic of 0.57 - 0.58 (near-substantial). Further research is also required to determine the critical N dilution curve and sufficiency ranges of NNI for potatoes based on different genetic, environmental, and management conditions to better support decision-making.
Why it matches plant phenotyping methodsジャガイモのN栄養状態という植物生理状態を、Dualex/SPADセンサーと機械学習・データ融合で推定する方法の比較、評価、診断戦略開発が研究の中心である。
abstractcompare the performance of the Dualex sensor relative to the SPAD meter for predicting potato N status indicators
Agriculture, a crucial sector for global economic development and sustainable food production, faces significant challenges in detecting and managing crop diseases. These diseases can greatly impact yield and productivity, making early and accurate detection vital, especially in staple crops like potatoes. Traditional manual methods, as well as some existing machine learning and deep learning techniques, often lack accuracy and generalizability due to factors such as variability in real-world conditions. This study proposes a novel approach to improve potato plant disease detection and identification using a hybrid deep-learning model, EfficientNetV2B3+ViT. This model combines the strengths of a Convolutional Neural Network - EfficientNetV2B3 and a Vision Transformer (ViT). It has been trained on a diverse potato leaf image dataset, the "Potato Leaf Disease Dataset", which reflects real-world agricultural conditions. The proposed model achieved an accuracy of 85.06 % , representing an 11.43 % improvement over the results of the previous study. These results highlight the effectiveness of the hybrid model in complex agricultural settings and its potential to improve potato plant disease detection and identification.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定する深層学習モデルを開発・評価しており、植物病害表現型の取得・分類が研究の中心です。
abstractThis study proposes a novel approach to improve potato plant disease detection and identification using a hybrid deep-learning model, EfficientNetV2B3+ViT.
Reproduction assets foundThe paper explicitly states code availability with a public GitHub repository URL (which is in the allowed list) for the EfficientNetV2B3+ViT potato disease detection model. The two image datasets (Plant Village, Potato Leaf Disease Dataset) are noted as publicly available but no paper-specific URLs are provided in theCode · publicCode availability
The code is available at https://github.com/HJacksons/potato-efficientViTOpen asset ↗HJacksons/potato-efficientViTlines:152-185Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Early and accurate detection of crop diseases is critical for global food security and efficient agricultural management. Recent advances in deep learning, particularly convolutional neural networks (CNNs) and vision transformers (ViT), have demonstrated exceptional ability to recognize disease symptoms from leaf images. In this article, we present a comprehensive framework for plant disease detection that integrates state-of-the-art deep learning models into smart agriculture systems. We review publicly available datasets (e.g. the PlantVillage dataset with 54,306 leaf images across 14 crop species and 26 disease classes), and discuss data preprocessing and augmentation techniques. We then detail various model architectures: traditional CNNs (e.g. ResNet, MobileNet), efficient CNN variants, ViT-based models, and hybrid CNN–ViT architectures (e.g. FOTCA, AppViT). Our proposed models leverage transfer learning and attention mechanisms to improve accuracy. We describe an experimental setup using multiple leaf-image datasets (tomato, potato, apple, cassava, wheat) and report hypothetical results: for example, our hybrid model achieves ≈99.7% accuracy on PlantVillage and 98–99% on tomato/potato datasets. We include precision, recall, F1 metrics and confusion matrices to analyze performance. Integration into smart farming is discussed: IoT sensors and mobile devices capture leaf images, which are processed by on-device or cloud CNN/ViT models to alert farmers in real time, the depthwise separable convolution block, and the ViT encoding block, respectively. We compare results across models and examine the trade-offs between model complexity and accuracy. Our findings confirm that hybrid CNN–ViT architectures yield the best performance, while lightweight models (e.g. MobileViT, AppViT) enable on-device inference.
Why it matches plant phenotyping methods葉画像から植物病害症状を推定する深層学習手法の開発・比較・評価が中心であり、植物の病害状態を直接推定する画像ベース表現型解析に該当する。
abstractwe present a comprehensive framework for plant disease detection that integrates state-of-the-art deep learning models into smart agriculture systems.
Accurate classification of plant disease by farming robot cameras can increase crop yield and reduce unnecessary agricultural chemicals, which is a fundamental task in the field of sustainable and precision agriculture. However, until now, disease classification has mostly been performed by manual methods, such as visual inspection, which are labor-intensive and often lead to misclassification of disease types. Therefore, previous studies have proposed disease classification methods based on machine learning or deep learning techniques; however, most did not consider real-world plant images with complex backgrounds and incurred high computational costs. To address these issues, this study proposes a computationally effective residual convolutional attention network (RCA-Net) for the disease classification of plants in field images with complex backgrounds. RCA-Net leverages attention mechanisms and multiscale feature extraction strategies to enhance salient features while reducing background noises. In addition, we introduce fractal dimension estimation to analyze the complexity and irregularity of class activation maps for both healthy plants and their diseases, confirming that our model can extract important features for the correct classification of plant disease. The experiments utilized two publicly available datasets: the sugarcane leaf disease and potato leaf disease datasets. Furthermore, to improve the capability of our proposed system, we performed fractal dimension estimation to evaluate the structural complexity of healthy and diseased leaf patterns. The experimental results show that RCA-Net outperforms state-of-the-art methods with an accuracy of 93.81% on the first dataset and 78.14% on the second dataset. Furthermore, we confirm that our method can be operated on an embedded system for farming robots or mobile devices at fast processing speed (78.7 frames per second).
Why it matches plant phenotyping methods植物画像から病害状態を推定する画像解析手法を開発・評価しており、病害分類とモデル性能検証が研究の中心であるため。
abstractthis study proposes a computationally effective residual convolutional attention network (RCA-Net) for the disease classification of plants in field images with complex backgrounds.
Reproduction assets foundThe authors explicitly state their RCA-Net model and code are publicly available on GitHub, which constitutes the paper's computational analysis asset. The sugarcane and potato leaf disease datasets are cited third-party prior datasets, not paper-specific deposits.Code · publicData Availability Statement: Our model and code are made publicly available on GitHub site
(https://github.com/mhamza92/RCA-Net, accessed on 15 April 2025).Open asset ↗https://github.com/mhamza92/RCA-Netpdf-page:33 lines:1-57Code / dataset availability confirmedEurope PMC · Crossref · checked 14 Sept 2026
Abstract The identification of plant diseases has become increasingly challenging due to the interference of complex backgrounds in images, which often hinders the accuracy of classification models. Recent studies have employed various Deep Learning (DL) techniques to overcome this issue, utilizing both publicly available and custom datasets. However, achieving high accuracy while managing background complexity remains a significant hurdle. This paper aims to address this challenge by introducing a two-step DL approach for plant disease classification. The approach begins with an enhanced Convolutional Neural Network (CNN), developed through a comparative analysis of several CNN architectures, including customized and cascaded versions of prominent DL models, achieving an accuracy of 93.3%. To further enhance accuracy, segmentation techniques such as DeepLabV3+, UNet, Iterative UNet, and UNet with Atrous Spatial Pyramid Pooling (ASPP) are integrated before applying customized CNN architectures. These segmentation methods effectively isolate diseased portions of leaf images, improving classification performance. The proposed methodology introduces model pruning to optimize performance and computational efficiency by removing redundant parameters and less significant features. The UNet with ASPP architecture, in combination with pruning strategies, significantly reduces time complexity and feature redundancy, leading to an impressive accuracy of 99.8%. This approach outperforms other existing models in terms of accuracy and efficiency. The model is trained on the Plant Village dataset, which includes 10 different diseases across plant species such as tomato, corn, and potato, offering a comprehensive solution for plant disease identification.
Why it matches plant phenotyping methods植物病葉画像から病変部を分離し、分類する深層学習手法の開発が中心であり、植物の病害状態を直接推定するため、方法論文として採用。
abstractThis paper aims to address this challenge by introducing a two-step DL approach for plant disease classification.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicThe manuscript data set can be freely downloaded from
https://www.tensorflow.org/datasets/catalog/plant_villageOpen asset ↗plant_villagepdf-page:33 lines:1-34Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
This study presents a proof-of-concept evaluation of optimized whole-cell biosensors designed for the real-time detection of crop infections. Genetically engineered luminescent bacterial strains were used to detect volatile organic compounds (VOCs) emitted by crops during spoilage. Key factors investigated include bacterial uniformity, nutrient supply, and temperature effects. The results demonstrated that lower temperatures (+4 °C) yielded higher sensor sensitivity and prolonged bacterial viability. A proof-of-concept evaluation was conducted in storage-like conditions, showing effective infection detection in potatoes. These findings underscore the potential of whole-cell-based biosensors for monitoring postharvest production in cold storage environments.
Why it matches plant phenotyping methods作物感染状態を検出する全細胞バイオセンサーの最適化と実証が研究の中心であり、植物状態のセンシング手法に該当する。
abstractThis study presents a proof-of-concept evaluation of optimized whole-cell biosensors designed for the real-time detection of crop infections.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · checked 6 Sept 2026
Productivity and fitness of cultivated plants are influenced by genetic heritage and environmental interactions, shaping certain phenotypes. Phenomics is the -omics methodology providing applicative approaches for the analysis of multidimensional phenotypic information, essential to understand and foresee the genetic potential of organisms relevant to agriculture. While plant phenotyping provides information at the whole organism level, cellular level phenotyping is crucial for identifying and dissecting the metabolic basis of different phenotypes and the effect of metabolic-related genetic modifications. Phenotype Microarray (PM) is a high-throughput technology developed by Biolog ™ for metabolic characterization studies at cellular level, which is based on colorimetric reactions to monitor cellular respiration under different conditions. Nowadays, PM is widely used for bacteria, fungi, and mammalian cells, but a procedure for plant cells characterization has not yet been developed, due to difficulties linked in identifying a suitable reporter of cell activities. Here, we tested for the first time, PM technology on plant cells using protoplasts as a means of evaluating metabolic activity. Indeed, studying the metabolism of plant protoplasts can be a valuable method for predicting the inherent metabolic potential of an entire plant organism. Protoplasts are indeed valuable tools in plant research and biotechnology because they offer a simplified, isolated cellular system where researchers can focus on intracellular processes without interference from the cell wall. As a proof-of-principle, we used protoplasts of Solanum tuberosum L . as model system. Protoplasts were isolated from leaf tissue of in vitro-grown plants, purified and then diluted until desired concentration. Microplates were inoculated with protoplasts suspension and various markers of redox potential as indicators of cell activity were tested. After identifying the optimal conditions for PM testing, metabolic tests were extended to protoplasts from S. lycopersicum L., evaluating plant response to different NaCl concentrations and some of the toxic compounds present in pre-configured Biolog ™ microplates. The standardized high-throughput system developed was effective for the metabolic characterization of plant protoplasts. This method lays the foundation for plant cell metabolic phenotype studies enabling comparative studies at cellular level among cultivars, species, wild-type organisms, and genome-edited plants.
Why it matches plant phenotyping methods植物プロトプラストの代謝表現型を取得するためのフェノタイプマイクロアレイ手法を開発し、条件最適化と複数種・処理で実証した研究であり、表現型取得法が中心である。
abstracta procedure for plant cells characterization has not yet been developed
Abstract: Fruit and vegetable crops experience diminished agricultural production output because of pests along with diseases that rank as major factors worldwide. The correct identification of these issues becomes vital because delayed detection results in decreased quantity and quality of yields which then causes problems for food supply networks and regional economic stability. Farmers traditionally monitor plant diseases through individual observation assisted by expert consultations because they search for clear indicators of leaf damage including discolorations or spotted lesions or deteriors on leaves. The approach fails to meet standards because it often produces unsuitable results and unreliable human involvement. The proposed deep learning-based Disease Recognition Model employs Convolutional Neural Networks (CNNs) for processing leaf disease diagnosis within apple and corn and tomato and potato crops. The system enables automatic disease detection of leaves through image processing which delivers precise results. The training data consists of multiple leaf images which come from healthy subjects and disease-infected samples enabling precise identification of various diseases. The tool aims to become an affordable solution that supports farmers and agronomists and policymakers for better crop health management and minimal chemical usage while ensuring sustainable farming practices . Key Words: The system employs key terms including Leaf disease detection, plant health monitoring, CNN classification, fruit and vegetable crops, automated diagnosis, early disease intervention, sustainable agriculture, precision farming.
Why it matches plant phenotyping methods葉画像から植物病害状態をCNNで推定する画像ベースの植物フェノタイピング手法が研究の中心であるため。
abstractThe proposed deep learning-based Disease Recognition Model employs Convolutional Neural Networks (CNNs) for processing leaf disease diagnosis within apple and corn and tomato and potato crops.
Introduction Potatoes are a vital global product, and prompt identification of foliar diseases is imperative for sustaining healthy yields. Computer vision is essential in precision agriculture, facilitating automated disease diagnosis and decision-making through real-time data. Inconsistent data in uncontrolled contexts undermines classic image classification techniques, hindering precise illness detection. Methods We present a novel model that integrates EfficientNet-LITE for enhanced feature extraction with KE-SVM Optimization for effective classification. KE-SVM Optimization cross-references misclassified instances with correct classifications across kernels, iteratively refining the confusion matrix to improve accuracy across all classes. EfficientNet-LITE improves the model's emphasis on pertinent features through Channel Attention (CA) and 1-D Local Binary Pattern (LBP), while preserving computational economy with a reduced model size of 12.46 MB, fewer parameters at 3.11M, and a diminished FLOP count of 359.69 MFLOPs. Results Before optimization, the SVM classifier attained an accuracy of 79.38% on uncontrolled data and 99.07% on laboratory-controlled data. Following the implementation of KE-SVM Optimization, accuracy increased to 87.82% for uncontrolled data and 99.54% for laboratory-controlled data. Discussion The model's efficiency and improved accuracy render it especially appropriate for settings with constrained computational resources, such as mobile or edge devices, offering substantial practical advantages for precision agriculture.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類する新規コンピュータビジョン手法を開発・評価しており、植物状態の推定が中心的な方法論的貢献である。
abstractWe present a novel model that integrates EfficientNet-LITE for enhanced feature extraction with KE-SVM Optimization for effective classification.
Potato (Solanum tuberosum) is widely recognized as the leading vegetable crop in the United States, with millions of tons produced annually. Despite many advancements in cultivars, crop production still suffers from meager progress in the assessment of early maturity. One potential solution to this problem is Ground-Penetrating Radar (GPR), a near-surface geophysical tool that has recently been applied to agriculture for assessment of root systems by detecting dielectric variations in sub-surface and soil layers by means of electromagnetic waves emitted into the ground. This study seeks to assess GPR’s capability to serve as a non-destructive proximal-sensing technique for quantifying potato tuber biomass by estimating the size of potatoes by measuring changes in the reflected GPR signal. Two methods, thresholding analysis and continuous wavelet transform (CWT), were employed in this study to extract features from GPR responses to predict tuber biomass. The dataset was collected in a controlled sandbox system. Thresholding analysis on the interpolated amplitude values yielded significant results, being able to predict tuber biomass with an accuracy of r = 0.82 and R2 = 0.64 based upon Multiple Linear regression. CWT was somewhat less successful, yet still significant, with a prediction accuracy of r = 0.6 and R2 = 0.32. These results indicate that GPR technology is suitable as a decision-support tool for potato breeders seeking to monitor tuber growth.
Why it matches plant phenotyping methodsGPRを用いてジャガイモ塊茎バイオマスを非破壊推定し、thresholdingとCWTによる特徴抽出・予測精度を評価しており、植物形質取得法が研究の中心です。
abstractThis study seeks to assess GPR’s capability to serve as a non-destructive proximal-sensing technique for quantifying potato tuber biomass
Accurate estimation of above-ground biomass (AGB) in potato plants is essential for effective monitoring of potato growth and reliable yield prediction. Remote sensing technology has emerged as a promising method for monitoring crop growth parameters due to its high throughput, non-destructive nature, and rapid acquisition of information. However, the sensitivity of remote sensing vegetation indices to crop AGB parameters declines at moderate to high crop coverage, known as the “saturation phenomenon,” which limits accurate AGB monitoring during the mid-to-late growth stages. This challenge also hinders the development of a multi-growth-cycle AGB estimation model. In this study, a novel VGC-AGB model integrated with hyperspectral remote sensing was utilized for multi-stage estimation of potato AGB. This study consists of three main components: (1) addressing the “saturation problem” encountered when using spectral indices from remote sensing to monitor crop biomass across multiple growth stages. The VGC-AGB model calculates the leaf biomass by multiplying leaf dry mass content (Cm) and leaf area index (LAI) and vertical organ biomass using the multiplication of crop density (Cd), crop height (Ch) and the crop stem and reproductive organs’ average dry mass content (Csm); (2) estimating the VGC-AGB model parameters Cm and LAI by integrating hyperspectral remote sensing data with a deep learning model; (3) comparing the performance of three methods—(i) hyperspectral + Ch, (ii) ground-measured parameters + VGC-AGB model, and (iii) hyperspectral remote sensing + VGC-AGB model—using a five-year dataset of potato above-ground biomass. Results indicate that (1) the VGC-AGB model achieved high accuracy in estimating AGB (R² = 0.853, RMSE = 751.12 kg/ha), significantly outperforming the deep learning model based on hyperspectral + Ch data (R² = 0.683, RMSE = 1122.03 kg/ha); (2) the combination of the VGC-AGB model and hyperspectral remote sensing provided highly accurate results in estimating AGB (R² = 0.760, RMSE = 965.59 kg/ha), surpassing the results obtained using the hyperspectral + Ch-based method. Future research will primarily focus on streamlining the acquisition of VGC-AGB model parameters, optimizing the acquisition and processing of remote sensing data, and enhancing model validation and application. Furthermore, it is essential to conduct cross-regional validation and optimize model parameters for various crops to improve the universality and adaptability of the proposed model.
Why it matches plant phenotyping methodsジャガイモの地上部バイオマスという植物形質を、ハイパースペクトルリモートセンシングと深層学習・VGC-AGBモデルで推定し、複数手法と5年データで性能比較しているため、形質取得・推定手法が中心である。
abstracta novel VGC-AGB model integrated with hyperspectral remote sensing was utilized for multi-stage estimation of potato AGB.
Abstract— Plant leaf diseases significantly impact agricultural productivity, leading to substantial crop losses if not detected early. This paper introduces a deep learning approach for automatically identifying and classifying potato leaf diseases using image data. By utilizing transfer learning with MobileNetV2, a lightweight yet efficient CNN, the system accurately distinguishes between Early Blight, Late Blight, and Healthy leaves. The process includes dataset collection, preprocessing, model training, and real-time web application deployment for user interaction. Experimental results highlight high prediction accuracy and practical feasibility, making this system a valuable asset for precision agriculture and crop protection. Keywords— Plant leaf Disease Detection, Convolutional Neural Networks (CNNs), Image Classification, Transfer Learning, MobileNetV2, Image Preprocessing, Crop Protection, Deep Learning.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習手法が研究の中心であり、植物病害表現型の取得・推定に該当する。
abstractThis paper introduces a deep learning approach for automatically identifying and classifying potato leaf diseases using image data.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 15 Sept 2026
Computer vision holds tremendous potential in crop disease classification, but the complex texture and shape characteristics of crop diseases make disease classification challenging. To address these issues, this paper proposes a dual-branch model for crop disease classification, which combines Convolutional Neural Network (CNN) with Vision Transformer (ViT). Here, the convolutional branch is utilized to capture the local features while the Transformer branch is utilized to handle global features. A learnable parameter is used to achieve a linear weighted fusion of these two types of features. An Aggregated Local Perceptive Feed Forward Layer (ALP-FFN) is introduced to enhance the model’s representation capability by introducing locality into the Transformer encoder. Furthermore, this paper constructs a lightweight Transformer block using ALP-FFN and a linear self-attention mechanism to reduce the model’s parameters and computational cost. The proposed model achieves an exceptional classification accuracy of 99.71% on the PlantVillage dataset with only 4.9M parameters and 0.62G FLOPs, surpassing the state-of-the-art TNT-S model (accuracy: 99.11%, parameters: 23.31M, FLOPs: 4.85G) by 0.6%. On the Potato Leaf dataset, the model attains 98.78% classification accuracy, outperforming the advanced ResNet-18 model (accuracy: 98.05%, parameters: 11.18M, FLOPs: 1.82G) by 0.73%. The model proposed in this paper effectively combines the advantages of CNN and ViT while maintaining a lightweight design, providing an effective method for the precise identification of crop diseases.
Why it matches plant phenotyping methods植物の病徴を画像から分類するCNN・ViT融合モデルを開発し、複数データセットで精度・計算量を比較検証しているため、病害状態の画像ベース表現型推定が中心である。
abstractthis paper proposes a dual-branch model for crop disease classification, which combines Convolutional Neural Network (CNN) with Vision Transformer (ViT).
Key message Chlorophyll fluorescence (CF) measurements have been demonstrated to be an efficient and non-invasive tool for identifying and developing PVY-resistant potato cultivars. The validity of CF measurements was confirmed through viral titer and yield-loss assays. In the quest to identify resistant sources for potato virus Y (PVY) within Indian potato germplasm, we developed a phenotyping approach leveraging plant physiological responses against PVY infection. The study evaluated 71 potato genotypes including cultivated and experimental clones, during the year 2021-2022 and 2022-23 through mechanical inoculation in experimental fields at the Punjab Agricultural University, Ludhiana. We employed a combination of serological and molecular screening, complemented with chlorophyll fluorescence (CF) measurements to classify resistant and susceptible genotypes. Out of 71 genotypes, 34 exhibited PVY resistance, with KP-16-19-14 being the highly resistant line with minimal yield loss (i.e., only 1.64% reduction) and undetectable viral titer. This genotype holds promise as a valuable resistance source for future breeding programmes. Our findings revealed that resistant genotypes maintained stable CF metrics and experienced minimal yield reductions (up to 5.15% only), with very low viral titer. In contrast, the photosynthetic efficiency was significantly declined in susceptible genotypes, which also experienced yield losses up to 58.84% with very high viral titer. Correlation coefficient and principal component analysis (PCA) revealed a strong association among the CF parameters, disease severity, viral titer, and yield losses. This emphasizes the utility of CF as a valuable tool for assessing resistance through physiological responses to PVY. Study demonstrates that photochemistry, heat dissipation, and fluorescence emission patterns of PS-II effectively differentiate resistant and susceptible genotypes. Moreover, this study highlights the potential of integrating physiological assessments with molecular diagnostics in large-scale preliminary screening to identify and develop PVY-resistant potato genotypes.
Why it matches plant phenotyping methodsPVY抵抗性判定のためのクロロフィル蛍光測定を中心的な表現型解析手法として開発・適用し、ウイルス量および収量損失で妥当性を検証している。
abstractwe developed a phenotyping approach leveraging plant physiological responses against PVY infection.
This paper presents the design and implementation of a Potato Crop Disease Detection system utilizing deep learning for accurate classification and early diagnosis. The system employs convolutional neural networks to analyze images of potato plants, identifying various diseases such as late blight, early blight, and bacterial wilt. By leveraging advanced image processing techniques and a large dataset of annotated potato plant images, the model achieves high accuracy in distinguishing between healthy and diseased specimens. This automated approach offers farmers a rapid and reliable tool for monitoring crop health, enabling timely interventions to prevent yield losses and reduce the need for extensive pesticide use. The system integrates a convolutional neural network (CNN) model trained on a dataset of diseased and healthy potato leaf images to identify infections with high precision. A camera module captures real-time images, which are processed to detect symptoms such as blight, mosaic virus, and leaf spot. Additionally, a mobile application provides instant feedback, enabling farmers to take timely preventive measures. The combination of image processing, machine learning, and real-time monitoring enhances the efficiency and reliability of disease detection, making it a valuable tool for sustainable agriculture.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病徴・病害状態を推定する画像ベース手法とCNNシステムが研究の中心であり、植物表現型計測に該当する。
abstractThis paper presents the design and implementation of a Potato Crop Disease Detection system utilizing deep learning for accurate classification and early diagnosis.
Abstract Background Determining the sample size of Deep learning models still remains a challenges in the Artificial Intelligence world. This is because most of the developers of deep learning models utilize available data collected from public datasets sites such PlantVillage or Kaggle. This study proposes using the acreage method putting into consideration of the machine learning dataset condition. Objective The main objective of this research is to experiment the methods that can be used to determine the appropriate sample size for a Deep learning model. Methods This study used the experimental and statistical methodologies and incorporated the boundaries of the Machine learning condition. Results The average sample estimation of the measurements in the piece of land (plot) was (1x4X10) cm. The measurement of the leaves was 3.5-5cm in length and 1.5-3 cm in width. The experiments were done between (2:00-4:00) am to have a good lighting condition. The optimal leaning rate of the deep learning architectures involved in the study used a learning rate of 0.0001. The study covered an acreage of 28000.25 acres and the Dataset 2145 Irish potato leaves was obtained and got 9,660 images after augmentation. This was purposively collected from ten sub-counties due to time and financial constraints in this study. Conclusion This study proposed a methodology for obtaining the sample size using the acreage methodology and purposive sampling and there use the Machine learning condition for sample sizes for creation of deep learning models from potato leaf images targeted at preventing late blight based on leaf images. Future research may extend this study to further more validate the acreage methodology putting into account the Machine learning condition and also developing the Deep learning condition.
Why it matches plant phenotyping methodsジャガイモ葉画像から疫病を推定する深層学習モデルについて、データセットのサンプルサイズ決定法を中心に提案・検討しており、植物病害の画像ベース表現型取得に関する方法開発である。
abstractThis study proposes using the acreage method putting into consideration of the machine learning dataset condition.
This dataset comprises of 58,709 annotated images of irish potato leaves, categorized into three classes (healthy, early blight and late blight). The data was collected over six months from smallholder farms in Southern Highlands Tanzania, using Samsung Galaxy A03 smartphones with 8-megapixel camera. Researchers, farmers and agricultural extension officers were trained to capture images under diverse conditions, including varying lighting, angles and backgrounds to ensure the dataset is diverse and representative. Plant pathologists were used to validate the images to ensure and enhance the reliability of the labels. Pre-processing steps such as duplicate removal, filtering of irrelevant images, annotation and metadata integration were applied resulting in a high-quality dataset. The dataset is organized into three folders (healthy, early blight and late blight) and is freely available on the Zenodo repository to promote accessibility for researchers working in the field of plant diseases. This dataset holds significant potential for reuse in training machine learning models for crop disease detection, transfer learning and data augmentation studies. By enabling early detection and classification of potato diseases, the dataset supports the development of innovative agricultural tools aimed at reducing crop losses and enhancing food security in Sub-Saharan Africa. Its robust design and regional specificity make it a valuable resource for advancing research and innovation in sustainable farming practices.
Why it matches plant phenotyping methodsジャガイモ葉の画像から健全・初期疫病・後期疫病という植物病害状態を判定する、注釈付き大規模データセットであり、再利用可能なフェノタイピング資源として中心的です。
abstractThis dataset comprises of 58,709 annotated images of irish potato leaves, categorized into three classes (healthy, early blight and late blight).
Reproduction assets foundThe paper is a data descriptor for the authors' own Irish potato leaf imagery dataset (58,709 annotated images for healthy/early blight/late blight classification), publicly deposited on Zenodo with an explicit DOI and direct URL matching an allowed URL. This is a paper-specific public plant image/phenotyping asset.Dataset · publiccollected from farms located in Southern Highlands of Tanzania, specifically in Mbeya (8.9090° S, 33.4589° E), Iringa (7.7673° S, 35.6900° E), Njombe (9.3333° S, 34.7667° E) and Songwe (9.1333° S, 32.9333° E) regions.
Data accessibility
Repository name: ZENODOData identification number: 10.5281/zenodo.8286529Direct URL to data: https://zenodo.org/records/8286529
1.
Value of the Data
•
This dataset serves as a valuable resource as it addresses critical data gaps in the field of Artificial Intelligence in Agriculture by providing region-specific dataset with over 58,000 annotated images captured under diverse environment in the real-world smallholder farming conditions.
•
This dataset caOpen asset ↗Zenodo · 10.5281/zenodo.8286529html-lines:1-30Plant phenotyping relevance match · UnverifiedCrossref · checked 14 Sept 2026
Aim: This study aimed to propose a computationally cost-effective method for automated estimation of plant leaf disease severity in resource-limited settings. Study Design: The performance of four image segmentation algorithms—global thresholding, adaptive thresholding, Otsu thresholding, and edge detection—was evaluated using nine curated images of disease-affected leaves from tomato, bell pepper, and potato plants. Each image was segmented into healthy and diseased regions, and quantitative metrics—including diseased pixel counts, percentage of affected area, healthy-to-diseased ratios, and computational time—were analyzed to assess algorithm performance. Results: The segmentation methods executed with near-instantaneous speed (0–0.001 seconds per image). Global and Otsu thresholding consistently demonstrated high segmentation accuracy, leading to reliable severity estimations. Adaptive thresholding tended to overestimate disease severity, while edge detection, despite providing precise lesion boundaries, significantly underestimated overall disease severity. Conclusion: Comparative analysis, supported by visual validation, suggests that Otsu thresholding, closely followed by global thresholding, is the most effective approach for leaf disease severity estimation, offering high accuracy with minimal computational overhead. These findings indicate that classical computer vision techniques can play a valuable role in supporting plant disease diagnostics and estimation in resource-constrained environments.
Why it matches plant phenotyping methods植物葉の病害重症度という観察可能な状態を、画像セグメンテーションで定量推定する手法を提案し、複数アルゴリズムを比較評価しているため、植物フェノタイピング手法が中心である。
abstractThis study aimed to propose a computationally cost-effective method for automated estimation of plant leaf disease severity in resource-limited settings.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 14 Sept 2026
Abstract Conventional techniques for identifying plant leaf diseases can be labor-intensive and complicated. This research uses artificial intelligence (AI) to propose an automated solution that improves plant disease detection accuracy to overcome the difficulty of the conventional methods. Our proposed method uses deep learning (DL) to extract features from photos of plant leaves and machine learning (ML) for further processing. To capture complex illness patterns, convolutional neural networks (CNNs) such as VGG19 and Inception v3 are utilized. Four distinct datasets—Banana Leaf, Custard Apple Leaf and Fruit, Fig Leaf, and Potato Leaf—were used in this investigation. The experimental results we received are as follows: for the Banana Leaf dataset, the combination of Inception v3 with SVM proved good with an Accuracy of 91.9%, Precision of 92.2%, Recall of 91.9%, F1 score of 91.6%, AUC of 99.6% and MCC of 90.4%, FFor the Custard Apple Leaf and Fruit dataset, the combination of VGG19 with kNN with an Accuracy of 99.1%, Precision of 99.1%, Recall of 99.1%, F1 score of 99.1%, AUC of 99.1%, and MCC of 99%, and for the Fig Leaf dataset with Accuracy of 86.5%, Precision of 86.5%, Recall of 86.5%, F1 score of 86.5%, AUC of 93.3%, and MCC of 72.2%. The Potato Leaf dataset displayed the best performance with Inception v3 + SVM by an Accuracy of 62.6%, Precision of 63%, Recall of 62.6%, F1 score of 62.1%, AUC of 89%, and MCC of 54.2%. Our findings explored the versatility of the amalgamation of ML and DL techniques while providing valuable references for practitioners seeking tailored solutions for specific plant diseases.
Why it matches plant phenotyping methods植物葉の画像から病害状態を推定する深層学習・機械学習手法が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractThis research uses artificial intelligence (AI) to propose an automated solution that improves plant disease detection accuracy
In modern agriculture, timely and precise nitrogen monitoring and pre-harvest tuber yield assessment for potato (Solanum tuberosum L.) crop is essential to optimize resource management, in-time decision-making and trade benefits. Traditional nitrogen assessment methods are labor-intensive and time consuming. Utilizing multispectral data from unmanned aerial vehicles (UAV) and satellite imagery integrated with artificial intelligence (AI) modeling offers high resolution solution for efficient field monitoring throughout the growing season. The aim of this study was to use AI algorithms trained and validated solely on high-resolution multispectral UAV and Sentinel-2 satellite data to evaluate their potential in estimating in-season plant nitrogen status and pre-harvest tuber yield assessment in commercial potato production fields. A study was conducted on four commercial potato fields located in Prince Edward Island, Canada. UAV and Sentinel-2 images were used at the early flowering (S1) and pre-harvest (H) stages of potato to extract multispectral bands and vegetative indices. Extracted multispectral bands and vegetative indices were used to assess ground truth data (petiole nitrate concentration as crop N status and tuber yield) at S1 and H phenological stages using five different machine learning algorithms. Results indicated that the bagged tree machine learning algorithm trained on UAV S1 images revealed a relative root mean square error (RRMSE) of 12.7 % and a relative mean absolute error (RMAE) of 9.6 %. In contrast, the random forest model trained on Sentinel-2 S1 data showed an RRMSE of 15.5 % and an RMAE of 12.6 %. The random forest models trained on UAV H and Sentinel-2H data demonstrated an RRMSE of 16.1 % and 13.8 %, and an RMAE of 12.5 % and 11.3 %, respectively. These models revealed the best estimation results when compared with the rest of the machine learning models. The fitted models effectively estimated petiole nitrate concentration and pre-harvest tuber yield in commercial potato fields, demonstrating their practical utility. Key features, such as the Canopy Chlorophyll Content Index via UAV and the red edge band via Sentinel-2, were crucial in the prediction process. These findings underscore the potential of AI algorithms to enhance agricultural productivity and precision in crop management. The use of AI algorithms trained on high-resolution air-borne data can significantly improve the accuracy of estimating the petiole nitrate concentration and pre-harvest tuber yield. By leveraging key important features with the robust feature engineering techniques, farmers and researchers can make more informed decisions regarding crop management. This approach provides a valuable tool for advancing sustainable and efficient farming practices.
Why it matches plant phenotyping methodsUAV・衛星マルチスペクトル画像とAIモデルによる植物窒素状態および収量推定を開発・検証しており、表現型取得手法が研究の中心である。
abstractAI algorithms trained and validated solely on high-resolution multispectral UAV and Sentinel-2 satellite data to evaluate their potential in estimating in-season plant nitrogen status and pre-harvest tuber yield assessment
Timely and accurate monitoring of potato crop growth and estimating yields are essential to improve agricultural production. Unmanned aerial vehicle (UAV)-based hyperspectral remote sensing is a non-destructive method for crop growth monitoring (CGM) and yield estimation, which plays a vital role in the agricultural application. However, CGM and yield estimation are typically achieved through quantitative inversion of specific crop traits, which lacks consideration for the interactive impacts among traits. Thus, this study aimed to integrate multiple agronomic traits using a fuzzy comprehensive evaluation (FCE) method to construct a new crop growth monitoring indicator (CGMI) for CGM and yield estimation. In 2018 and 2019, UAV hyperspectral images and ground parameters were acquired during three growth stages of potatoes. Compared to single agronomic traits, CGMI could be better described by vegetation indices (VIs). The accuracy and stability of the CGMI estimation model were effectively validated, while the single trait estimation model performed poorly on the validation set. The coefficient of determination (R²) values of CGMI estimation for three stages were in the range of 0.56–0.72 and 0.56–0.66 for calibration and validation sets. The CGMI at different stages was closely correlated with potato yield, reaching a highly significant level. The VIs selected based on CGMI and Akaike information criterion (AIC) were input into the PLSR model to estimate potato yields. The R² values of yield estimation for three stages were in the range of 0.63–0.69 and 0.54–0.60 for calibration and validation sets. The study demonstrated that integrating multiple crop traits could enhance the relationship with yield and provided a comprehensive reflection of crop growth. The CGMI constructed in this study can provide decision-making services for crop production management in the field.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像からジャガイモの複数農業形質を統合した成長指標と収量を推定し、モデルの精度・安定性を検証しているため、植物フェノタイピング手法が中心です。
abstractThus, this study aimed to integrate multiple agronomic traits using a fuzzy comprehensive evaluation (FCE) method to construct a new crop growth monitoring indicator (CGMI) for CGM and yield estimation.
Abstract Potato disease management is crucial to reducing significant crop losses in agriculture. The timely identification and classification of potato leaf diseases are necessary but time-consuming and labor-intensive. Therefore, an automated model capable of accurate and timely recognition and classification is key to resolving these challenges. In this research, a novel Normalized Long- Short Convoluted Temporal Attention Network (NLSCTAN) with Internet of Things (IOT) is developed to classify infected potato leaves and provide fertilizer suggestions to combat diseases. This work introduces a diverse dataset collected from IOT sensors by merging similar classes from three distinct potato leaf datasets: the potato leaf disease dataset, potato leaf diseases, and the plant village dataset. Preprocessing is performed using adaptive Contrast-Limited Adaptive Histogram Equalization (CLAHE) with double gamma correction to enhance the image quality. Feature extraction involves extracting different texture features using ternary patterns and discrete wavelet transform. Subsequently, dimensionality reduction is achieved through an auto encoder. Finally, the NLSCTAN model combines segmentation and classification processes to extract infected regions, determine their identity, and suggest appropriate fertilizers. Modified walrus optimization further enhances accuracy by minimizing the loss function of the neural network. The proposed procedure outperforms existing models, achieving a mean accuracy of 99.2% across various potato disease types. Experimental findings validate its competitiveness and effectiveness.
Why it matches plant phenotyping methodsジャガイモ葉の感染領域抽出と病害分類を行う画像解析モデルを開発・検証しており、植物病害状態のフェノタイピング手法が中心である。
abstractan automated model capable of accurate and timely recognition and classification is key to resolving these challenges
Abstract This study investigates the use of deep learning models, Visual Geometry Group 16-layer network (VGG16), AlexNet and a custom Convolutional Neural Network (CNN), for classifying potato leaf images into categories of Early Blight, Late Blight, and Healthy leaves. The dataset, comprising 3,293 images, combined locally sourced images from Anand Agricultural University (AAU), Gujarat, India, and images from the Plant Village (PV) repository. Various configurations were tested, including batch sizes of 32 and 64 and training epochs of 30 and 60. Results indicate that the custom CNN achieved the highest performance, with an accuracy of 98.8% and a low loss of 0.055, surpassing both VGG16 and AlexNet. Notably, the custom CNN required only 128,387 trainable parameters, significantly fewer than VGG16 (138 million) and AlexNet (58 million), highlighting its efficiency. This efficiency demonstrates the custom CNN’s optimized architecture, enabling high classification performance with lower computational demands.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定する画像処理・深層学習手法の最適化と性能比較が研究の中心であり、植物病害フェノタイピング手法に該当する。
abstractThis study investigates the use of deep learning models, Visual Geometry Group 16-layer network (VGG16), AlexNet and a custom Convolutional Neural Network (CNN), for classifying potato leaf images into categories of Early Blight, Late Blight, and Healthy leaves.
Abstract Understanding growth patterns, cultivar identification, and yield dynamics in potato cultivation is essential for optimizing agricultural practices and improving productivity. This study leverages machine-learning techniques to analyze and predict potato growth stages, identify cultivars, and forecast yield outcomes based on hyperspectral data, environmental factors, and physiological traits. Various machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in classifying potato cultivars, identifying growth stages, and predicting yield performance. Key physiological trends were identified during the tuber initiation, bulking, and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R² values above 0.90 across validation datasets. Additionally, this study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth monitoring, cultivar differentiation, and yield optimization.
Why it matches plant phenotyping methods機械学習とハイパースペクトル／マルチスペクトルデータを用いて、ジャガイモの生育段階・品種・収量を推定する手法を開発・評価しており、植物形質の取得・推定が中心である。
abstractThis study leverages machine-learning techniques to analyze and predict potato growth stages, identify cultivars, and forecast yield outcomes based on hyperspectral data, environmental factors, and physiological traits.
This study aimed to provide the first results and lessons of the transfer of the ALPHI® phenotyping tool to potato. The ALPHI® device is a tractor with two arms carrying RGB cameras and spectroradiometers, able to acquire proximal sensing variables on microplot experiments. Originally developed for cereals, its transfer was one of the objectives of the INNO-VEG project. Based on two field trials comparing yield and nitrogen uptake of five potato cultivars under two nitrogen rates, the work done demonstrated the ability of the ALPHI® tool (1) to practically operate on potato microplot experiments and (2) to provide a range of proximal sensing variables already known to be of interest in other crops (green fraction computed from RGB cameras and vegetation indices CIgreen, CIrededge, MTCI, MCARI2, and NDVI). A first analysis of the results indicated that the proximal sensing variables obtained were consistent with previous studies both for their general pattern across time related to the dynamic of the plant cover, and for their relationship with agronomic variables related to biomass accumulation, nitrogen content, nitrogen uptake, and yield. Further investigations are already planned to strengthen the results with other sources of data. The ALPHI® tool will also be continuously optimized toward an even more operational device and to include more complex and informative proximal sensing variables.
Why it matches plant phenotyping methodsジャガイモのマイクロプロットで高スループット近接センシング装置を適応・検証し、RGB画像と分光計から植物形質関連変数を取得することが研究の中心である。
abstractThis study aimed to provide the first results and lessons of the transfer of the ALPHI® phenotyping tool to potato.
In-season nitrogen (N) management is a promising strategy to achieve high tuber yield/quality and N use efficiency in potato (Solanum tuberosum L.) production. The SPAD-502 chlorophyll meter (SPAD) provides relative readings on plant N status using leaf chlorophyll transmittance and has the potential to replace the traditionally used expensive petiole analysis by estimating petiole nitrate-N (PNN) concentration non-destructively. The objective of this study was to develop a robust machine learning (ML) model for PNN concentration prediction across various genetic, environmental, and management conditions. Plot-scale experiments were conducted on an irrigated loamy sand soil in central Minnesota using a number of varieties and N fertilizer sources, application methods, and rates between 2010 and 2022. In each plot, approximately 20 petiole samples were collected for laboratory analysis, and 20 SPAD readings were collected and averaged. Weather information was collected by a nearby weather station. Three ML models (i.e. Random Forest, Extreme Gradient Boosting, and Support Vector Regression) were trained using Bayesian optimization in a nested 5-fold cross-validation. A near-linear trend was found between PNN concentration and the selected important features. Random Forest and Extreme Gradient Boosting regression models demonstrated that PNN concentrations could be predicted with an R² of 0.8 using 15 features in a new site-year. When simplified by only using SPAD readings, cultivar information, accumulated growing degree days, accumulated total moisture, and as-applied N rates, these two tree-based models maintained the R² values and achieved a 75 % diagnostic accuracy, outperforming both simple regression (66 %) and multivariate linear regression (70 %) models. We found that potato N status could be diagnosed accurately through PNN concentration prediction using chlorophyll meter and multi-source data fusion. The results of this study can be used as a baseline for future research on in-season N status diagnosis of potatoes involving different proximal and remote sensing technologies and N stress indicators.
Why it matches plant phenotyping methodsジャガイモの窒素状態を示す葉柄硝酸態窒素濃度を、クロロフィルメーターと機械学習で非破壊推定する方法を開発・検証しており、表現型取得・推定が研究の中心である。
abstractThe objective of this study was to develop a robust machine learning (ML) model for PNN concentration prediction across various genetic, environmental, and management conditions.
The current study proposes a novel approach for assessing the effect of storage on potato tuber texture using biospeckle imaging. Agria potato tubers were subjected to biospeckle imaging using three low-power laser diodes and mechanical reference tests including uniaxial compression and creep tests for 6 months. The speckle activity indices of features such as inertia moment, absolute value of differences, autocorrelation function, and energy of wavelet transform were computed from the images. Mechanical and rheological properties were also measured using mechanical tests. An adaptive neuro-fuzzy inference system (ANFIS) coupled with the genetic algorithm was employed to develop models for predicting mechanical properties. The models for retarded compliance, maximum force, and retarded viscosity, with correlation coefficients of 0.812, 0.773, and 0.750, provided the best results. These findings can be used to non-invasively predict the mechanical properties of potatoes. The study demonstrates the potential of biospeckle imaging in assessing the texture of potato tubers during storage.
Why it matches plant phenotyping methodsジャガイモ塊茎の硬さ・テクスチャという植物器官形質を、バイオスペックル画像から非破壊推定する手法を開発し、機械試験で検証しているため、フェノタイピング手法が中心である。
abstractThe current study proposes a novel approach for assessing the effect of storage on potato tuber texture using biospeckle imaging.
Crop intelligence and yield prediction of potato (Solanum tuberosum L.) are important to farmers and the processing industry. Remote sensing can provide timely information on growth status and accurate yield predictions during the growing season. However, there is limited documentation on the most suitable vegetation indices (VIs) and optimal growth stages for acquiring remote sensing imagery of potato. To address this knowledge gap, a systematic review was conducted. Original scientific manuscripts published between 2000 and 2022 were identified using various databases. The findings indicate that satellite imagery is the most widely used source of remote sensing data for tuber yield prediction, whereas unmanned aerial vehicle systems (UAVs) and handheld sensors are more frequently applied for growth monitoring. The normalized difference vegetation index (NDVI), red-edge chlorophyll index (CIᵣₑd₋ₑdgₑ), green chlorophyll index (CIgᵣₑₑₙ), and optimized soil-adjusted vegetation index (OSAVI) are the most frequently used VIs for the growth and yield estimation of potato. The tuber initiation stage was found to be the most appropriate stage for remote sensing data acquisition. This review will assist potato farmers, agronomists and researchers in selecting the most suitable VIs for monitoring specific growth variables and selecting the optimal timing during the growing season to obtain remote sensing images.
Why it matches plant phenotyping methodsジャガイモの生育状態と塊茎収量を推定するリモートセンシング指標・取得時期を体系的に比較したレビューであり、植物表現型の取得・推定手法が中心です。
titleA Systematic Review of Vegetation Indices for Potato Growth Monitoring and Tuber Yield Prediction from Remote Sensing
Potato blight, sometimes referred to as late blight, is a deadly disease that affects Solanaceae plants, including potato. The oomycete Phytophthora infestans is causal agent, and it may seriously damage potato crops, lowering yields and causing financial losses. To ensure food security and reduce economic losses in agriculture, potato diseases must be identified. The approach we have proposed in our study may provide a reliable and efficient solution to improve potato late blight classification accuracy. For this purpose, we used the ResNet-50, GoogLeNet, AlexNet, and VGG19Net pre-trained models. We used the AlexNet model for feature extraction, which produced the best results. After extraction, we selected features using ten optimization algorithms in their binary format. The Binary Waterwheel Plant Algorithm Sine Cosine (WWPASC) achieved the best results amongst the ten algorithms, and we performed statistical analysis on the selected features. Five machine learning models—Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and K-Nearest Neighbour (KNN)—were used to train the chosen features. The most accurate model was the MLP model. The hyperparameters of the MLP model were optimized using the Waterwheel Plant Algorithm Sine Cosine (WWPASC). The results indicate that the suggested methodology (WWPASC-MLP) outperforms four other optimization techniques, with a classification accuracy of 99.5%.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習・特徴選択・最適化手法が研究の中心であり、植物病害フェノタイピング手法に該当する。
titleOptimized Deep Learning for Potato Blight Detection Using the Waterwheel Plant Algorithm and Sine Cosine Algorithm
This paper introduces AI-PotatoGuard, an artificial intelligence (AI) tool which enhances the management of diseases in potatoes through the use of generative models and convolutional neural networks (CNN). In contrast to traditional practices, AI-PotatoGuard is a tool which provides the ability to detect potatoes in the early stages of the disease and also precisely detects the area affected. Through AI-PotatoGuard, it was observed that the conventional approach of identifying the diseases have been surpassed with 95% success observed in terms of getting the detection perfectly right and 85% in terms of getting the detection right at a much earlier stage. Traditional practices lagged with 75% detection right observation and a mere 50% in terms of detecting the disease early on. While traditional methods applied chemicals 2–3 times in practice in an area, the monitoring with AI-PotatoGuard resulted in only 2 out of 6 times in the same area. Hence, efficient and sustainable agriculture is achieved using AI.
Why it matches plant phenotyping methodsジャガイモ病害の早期検出と罹病領域の定量的特定を目的とするAI画像解析ツールが研究の中心であり、植物の病態を直接評価するフェノタイピング手法に該当する。
abstractThis paper introduces AI-PotatoGuard, an artificial intelligence (AI) tool which enhances the management of diseases in potatoes through the use of generative models and convolutional neural networks (CNN).
Potato is a food crop at a global scale, bearing a hefty importance for the food security and nutrition of millions of people worldwide. Nonetheless, some obstacles have to be overcome in the cultivation of potatoes, such as susceptibility to a number of diseases that affect quality and yield. Thus, sound disease management approaches are critical to protect potato crops and support maximum production. In this perspective, optimization techniques are vital in improving disease classification accuracy, thus helping in early detection and timely intervention. In this research, we suggest the hybridization of the Greylag Goose Optimizer (GGO) with the Grey Wolf Optimizer (GWO), which is called GGGWO, for the optimization of convolutional neural network (CNN) models for potato disease classification. Through our approach, we are seeking to enhance precision and timeliness in the diagnosis of diseases that will eventually lead to the development of appropriate crop management practices and sustainable agriculture. The performance of the GGGWO-CNN model is assessed in terms of accuracy and is compared to other optimization algorithms using statistical testing methods like ANOVA and Wilcoxon signed rank tests. The results exhibit the excellent performance of the GGGWO-CNN model with an accuracy of 0.9904 and a sensitivity of 0.9421 in identifying potato diseases accurately, highlighting its potential to aid farmers and general agriculture practitioners. Utilizing optimization techniques and CNN models, our research helps in the development of precision agriculture as well as the improvement of resilient potato cropping systems. The proposed method’s approach provides an exciting way of dealing with the problem of potato diseases. It provides an excellent platform for carrying out further studies on improving agricultural decision-making processes aimed at better crop health and productivity.
Why it matches plant phenotyping methodsジャガイモの病害状態を分類するCNNの最適化手法を開発し、複数手法との精度比較と統計的検証を行っており、植物病害フェノタイピング手法が中心である。
abstractwe suggest the hybridization of the Greylag Goose Optimizer (GGO) with the Grey Wolf Optimizer (GWO), which is called GGGWO, for the optimization of convolutional neural network (CNN) models for potato disease classification.
Potato diseases pose a significant threat to farmers, impacting potato crops’ productivity, quality, and financial stability. Among the most notorious diseases is late blight, caused by Phytophthora infestans, famously responsible for triggering the Irish Potato Famine in the 1840s. Late blight swiftly devastates potato foliage and tubers, particularly in damp, humid conditions. Another common disease is early blight, attributed to Alternaria solani. This disease affects various parts of the potato plant—leaves, stems, and tubers. It mainly shows up in the form of dark stains around the center of a bull’s eye on the leaves, bringing down both the yield and the crop quality. A model consisting of a Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) enhanced for potato disease detection was proposed in our paper. The dataset used was Z-score standardized before the training and testing process using the proposed CNN-LSTM model was started. The performance of the implemented model, CNN-LSTM, was analyzed alongside five traditional machine learning algorithms, namely Random Forest (RF), Extra Trees (ET), K-Nearest Neighbours (KNN), Adaptive Boosting (AdaBoost), and Support Vector Machine (SVM). Accuracy, sensitivity, specificity, F-score, and AUC were the metrics included in the evaluation, confirming the effectiveness of the models. The results of the experiments showed that our CNN-LSTM reached the highest accuracy at 97.1%.
Why it matches plant phenotyping methodsジャガイモ病害の植物状態をCNN-LSTMで検出し、複数手法との性能比較・検証を行うことが論文の中心であるため、植物フェノタイピング手法として含める。
abstractA model consisting of a Convolutional Neural Network - Long Short-Term Memory (CNN-LSTM) enhanced for potato disease detection was proposed in our paper.
Early recognition of plant diseases is crucial, and one practical approach is using deep learning models. Models, such as MLP-Mixer and gMLP, based on multi-layer perceptron, offer a compelling option due to their simple architecture. This study aimed to assess the performance of these models in classifying crop leaf diseases. Our findings reveal that both MLP-Mixer and gMLP models, with their similar architectures, exhibit promising performance. We conducted tests using public potato and wheat datasets to evaluate their classification performance. Furthermore, we incorporated gradient centralization during training to enhance the models’ generalization performance. The results indicate that both MLP-Mixer and gMLP achieved classification performance above 0.9100 for both datasets. Specifically, MLP-Mixer achieved 0.9819, and gMLP achieved 0.9873 for potato leaf diseases, while for wheat leaf diseases, MLP-Mixer achieved 0.9121, and gMLP achieved 0.9189. These outcomes emphasize the potential of these models in classifying and identifying diseases in crop leaves.
Why it matches plant phenotyping methods作物葉の病害状態を画像から分類する深層学習手法を比較・評価しており、植物表現型取得が研究の中心である。
abstractThis study aimed to assess the performance of these models in classifying crop leaf diseases.
As potato is an important crop, potato disease detection and classification are of key significance in guaranteeing food security and enhancing agricultural production efficiency. Aiming at the problems of tiny spots, blurred disease edges, and susceptibility to noise interference during image acquisition and transmission in potato leaf diseases, we propose a CBSNet-based potato disease recognition method. Firstly, a convolution module called Channel Reconstruction Multi-Scale Convolution (CRMC) is designed to extract the upper and lower features by separating the channel features and applying a more optimized convolution to the upper and lower features, followed by a multi-scale convolution operation to capture the key changes more effectively. Secondly, a new attention mechanism, Spatial Triple Attention (STA), is developed, which first reconstructs the spatial dimensions of the input feature maps, then inputs the reconstructed three types of features into each of the three branches and carries out targeted processing according to the importance of the features, thereby improving the model performance. In addition, the Bat-Lion Algorithm (BLA) is introduced, which combines the Lion algorithm and the bat optimization algorithm and makes the optimization process more adaptive by using the bat algorithm to adjust the gradient direction during the updating process of the Lion algorithm. The BLA not only boosts the model's ability to recognize potato disease features but also ensures training stability and enhances the model's robustness in handling noisy images. Experimental results showed that CBSNet achieved an average Accuracy of 92.04% and a Precision of 91.58% on the self-built dataset. It effectively extracts subtle spots and blurry edges of potato leaf diseases, providing strong technical support for disease prevention and control in large-scale potato farming.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類する深層学習手法を開発し、自作データセットで性能評価しており、植物病害状態の取得・推定が中心的である。
abstractwe propose a CBSNet-based potato disease recognition method.
Plants are susceptible to pathogen infections during their growing period leading to reduced crop quality and yield. Traditional disease detection methods such as expert diagnosis and pathogen analysis rely on experienced professionals and could be time-consuming and prone to errors. Deep convolutional neural networks (CNNs) have exhibited their potential to detect plant diseases on the basis of visual patterns of leaves. Most of the existing CNN based methods do not take advantage of additional information. Most of the disease significantly affects the texture of the plant leaves. Therefore, texture features can provide complementary information to get better results. In this paper, local binary pat tern (LBP) technique is used to extract texture information that is stacked with original image. A CNN model is proposed that takes embedded texture and spectral information to detect crop diseases using leaf images. The experiments are carried out on Apple, Corn, and Potato crops from Plant Village dataset. The proposed method achieved the overall accuracy up to 98.73% (κ = 98.04). It is found that LBP makes significant difference in disease classification accuracy and helps the proposed method exhibit better performance than some existing well known CNN models.
Why it matches plant phenotyping methods葉画像から植物病害状態を推定するLBP＋CNN手法を開発・評価しており、植物表現型（病害）の取得・抽出が中心である。
abstractIn this paper, local binary pat tern (LBP) technique is used to extract texture information that is stacked with original image.
Potato is the third major crop in the world and more than 375 million metric tonnes of potatoes are produced globally on an annual basis. Potato Virus Y (PVY) poses a significant threat to the production of seed potatoes thus resulting in a substantial economic loss and a threat to food security. The traditional approach uses serological assays to detect PVY in potato leaves and PCR is used to detect PVY in tubers, however, the processes are sophisticated, labor-intensive, and time-consuming. We propose to use Unmanned Aerial Vehicles (UAVs) integrated with hyperspectral cameras included with a downwelling irradiance spectrometer, to detect the PVY virus in commercial growers’ fields. We have used a 400-1000 nm visible and near-infrared (Vis-NIR) hyperspectral camera. We have trained several machine learning and deep learning models with optimized hyperparameters on the curated dataset. The performance of the models are very promising, and we found the convolutional neural network (CNN) is reliable in identifying the healthy plants (precision 0.980), and the feedforward neural neural network (FNN) is reliable in identifying the PVY-infected plants (recall 0.988). The hyperspectral camera provides a wide spectrum and most of them are redundant in identifying PVY. According to our analysis, five spectra regions are impactful in identifying the PVY. Two of them are in the visible spectrum, two in the near-infrared spectrum, and one in the red-edge spectrum. This research shows that PVY detection is possible in the early growing season minimizing the economic and yield losses, and identifies the most relevant spectra carrying the signatures of PVY.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像と機械学習により、ジャガイモ個体のPVY感染状態を直接推定する手法を開発・評価しており、植物フェノタイピング手法が研究の中心である。
abstractWe propose to use Unmanned Aerial Vehicles (UAVs) integrated with hyperspectral cameras included with a downwelling irradiance spectrometer, to detect the PVY virus in commercial growers’ fields.
A sizable section of India's rural population depends on agriculture for their livelihoods, while manual labor and disease control continue to be problems. The objective of this study is to enhance the Mask R-CNN architecture for precise detection and segmentation of potato plant leaf illnesses. This is of utmost importance in agriculture since diseases like as early blight and late blight profoundly affect crop productivity. Traditional illness detection techniques are characterized by their high labor requirements and susceptibility to human mistakes, thereby requiring the use of automated alternatives. By refining the feature extraction method, optimizing the Region Proposal Network (RPN), and enhancing segmentation via data augmentation and parameter tweaking, the suggested technique improves Mask R-CNN. Empirical findings indicate that the optimized Mask R-CNN outperforms other models, including YOLOv8 and EfficientNet, with an accuracy of 99.86%, precision of 99.82%, recall of 99.83%, and an F1-score of 99.84%. In conclusion, of work establishes that the optimized Mask R-CNN is a reliable instrument for early and accurate disease identification, thereby enhancing crop management and agricultural output.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から検出・セグメンテーションするMask R-CNNの改良と比較評価が研究の中心であり、植物病害状態の画像ベース表現型計測に該当する。
abstractThe objective of this study is to enhance the Mask R-CNN architecture for precise detection and segmentation of potato plant leaf illnesses.
The accurate classification of potato leaf diseases plays a pivotal role in ensuring the health and productivity of crops. This study presents a unified approach for addressing this challenge by leveraging the power of Explainable AI (XAI) and transfer learning within a deep Learning framework. In this research, we propose a transfer learning-based deep learning model that is tailored for potato leaf disease classification. Transfer learning enables the model to benefit from pre-trained neural network architectures and weights, enhancing its ability to learn meaningful representations from limited labeled data. Additionally, Explainable AI techniques are integrated into the model to provide interpretable insights into its decision-making process, contributing to its transparency and usability. We used a publicly available potato leaf disease dataset to train the model. The results obtained are 97% for validation accuracy and 98% for testing accuracy. This study applies gradient-weighted class activation mapping (Grad-CAM) to enhance model interpretability. This interpretability is vital for improving predictive performance, fostering trust, and ensuring seamless integration into agricultural practices.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から分類する深層学習・Grad-CAM手法が研究の中心であり、植物病害フェノタイピングに該当する。
abstractThis study presents a unified approach for addressing this challenge by leveraging the power of Explainable AI (XAI) and transfer learning within a deep Learning framework.
Reproduction assets foundThe paper's potato leaf disease classification uses the publicly available PlantVillage dataset from Kaggle, cited with an explicit URL in the references. No author analysis code or trained model is deposited.Dataset · publicily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
Al-Dabbagh A.
( 2022 ). PlantVillage Dataset. Available at: https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset (Accessed August 20, 2022).
Al-Sadi A. M.
( 2017 ).
Impact of plant diseases on human health
. Int. J. Nutr. Pharmacol. Neurol. Dis.
7 , 21 – 22 . doi:
10.4103/ijnpnd.ijnpnd_24_17
Anim-Ayeko A. O. Schillaci C. Lipani A.
( 2023 ).
Automatic blight disease detection in potato ( Solanum tuberosum L.) andOpen asset ↗Kaggle · plantvillage-datasetlines:245-327Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
In present day agriculture, early and accurate identification of plant diseases is essential for prompt response, which protects crop quality and output. This paper presents the Entangled Quantum-Inspired Deep learning model (EQID), a unique method that improves feature representation and classification in plant disease prediction by utilizing the concepts of quantum computing. Two different datasets with images of potatoes and tomatoes as leaves were used to test the EQID model, which performed better than traditional models. EQID obtained 98.96% accuracy, 98.98% precision, 98.96% recall, and 98.90% F1 score on images of potato leaves. For tomato leaves, comparable outcomes were noted, with accuracy, precision, recall, and F1 score all above 99.61%. The accuracy of disease prediction is greatly increased by the efficient and effective feature representation made possible by the EQID model's inclusion of quantum computing techniques. Additionally, the model outperformed other cutting-edge models such as DenseNet-121, VGGNet 16, and Xception Net, illustrating the potentially revolutionary effects of quantum-inspired models in agriculture. Future work will focus on applying the EQID model to a broader range of crops and plant diseases, as well as incorporating additional data sources to further enhance the model's predictive capabilities.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する深層学習モデルを開発・比較評価しており、病害フェノタイピング手法が研究の中心です。
abstractThis paper presents the Entangled Quantum-Inspired Deep learning model (EQID), a unique method that improves feature representation and classification in plant disease prediction
Fast and accurate identification of potato plant traits is essential for formulating effective cultivation strategies. The integration of spectral cameras on Unmanned Aerial Vehicles (UAVs) has demonstrated appealing potential, facilitating non-invasive investigations on a large scale by providing valuable features for construction of machine learning models. Nevertheless, interpreting these features, and those derived from them, remains a challenge, limiting confident utilization in real-world applications. In this study, the interpretability of machine learning models is addressed by employing SHAP (SHapley Additive exPlanations) and UMAP (Uniform Manifold Approximation and Projection) to better understand the modeling process. The XGBoost model was trained on a multispectral dataset of potato plants and evaluated on various tasks, i.e. variety classification, physiological measures estimation, and detection of early blight disease. To optimize its performance, nearly 100 vegetation indices and over 500 auto-generated features were utilized for training. The results indicate successful separation of plant varieties with up to 97.10% accuracy, estimation of physiological values with a maximum R² and rNRMSE of 0.57 and 0.129, respectively, and detection of early blight with an F1 score of 0.826. Furthermore, both UMAP and SHAP proved beneficial for comprehensive analysis. UMAP visual observations closely corresponded to computed metrics, enhancing confidence for variety differentiation. Concurrently, SHAP identified the most informative features – green, red edge, and NIR channels – for most tasks, aligning tightly with existing literature. This study highlights potential improvements in farming efficiency, crop yield, and sustainability, and promotes the development of interpretable machine learning models for remote sensing applications.
Why it matches plant phenotyping methodsUAVマルチスペクトル撮像と機械学習によるジャガイモ形質・生理値・病害状態の推定が研究の中心であり、特徴量設計、モデル評価、解釈性検証を含むため。
titleField-scale UAV-based multispectral phenomics: Leveraging machine learning, explainable AI, and hybrid feature engineering for enhancements in potato phenotyping
• We explore UAV-based multispectral imaging for phenotyping and disease detection in potatoes. • We auto-generate features with simple math and combine them with various vegetation indices. • This is the first study to integrate XGBoost, SHAP, and UMAP in potato phenotyping research. • We propose an analysis pipeline to enhance understanding of relevant agricultural traits. Fast and accurate identification of potato plant traits is essential for formulating effective cultivation strategies. The integration of spectral cameras on Unmanned Aerial Vehicles (UAVs) has demonstrated appealing potential, facilitating non-invasive investigations on a large scale by providing valuable features for construction of machine learning models. Nevertheless, interpreting these features, and those derived from them, remains a challenge, limiting confident utilization in real-world applications. In this study, the interpretability of machine learning models is addressed by employing SHAP (SHapley Additive exPlanations) and UMAP (Uniform Manifold Approximation and Projection) to better understand the modeling process. The XGBoost model was trained on a multispectral dataset of potato plants and evaluated on various tasks, i.e. variety classification, physiological measures estimation, and detection of early blight disease. To optimize its performance, nearly 100 vegetation indices and over 500 auto-generated features were utilized for training. The results indicate successful separation of plant varieties with up to 97.10% accuracy, estimation of physiological values with a maximum R 2 and rNRMSE of 0.57 and 0.129, respectively, and detection of early blight with an F1 score of 0.826. Furthermore, both UMAP and SHAP proved beneficial for comprehensive analysis. UMAP visual observations closely corresponded to computed metrics, enhancing confidence for variety differentiation. Concurrently, SHAP identified the most informative features – green, red edge, and NIR channels – for most tasks, aligning tightly with existing literature. This study highlights potential improvements in farming efficiency, crop yield, and sustainability, and promotes the development of interpretable machine learning models for remote sensing applications.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像と機械学習・特徴量設計・解釈手法を統合した、ジャガイモ形質・生理値・病害の推定パイプラインが研究の中心であり、技術的評価も行っている。
abstractWe explore UAV-based multispectral imaging for phenotyping and disease detection in potatoes.
Ensuring a sustainable global food security status which necessitated by achieving an equilibrium state between the anticipated and significant rise in the global population and the projected agricultural output which is essential for their food adequacy. The absence of such a harmonious balance may be a contributing factor to the emergence of food crises worldwide. Hence, it is imperative to proactively address and mitigate both direct and indirect factors that could potentially lead to this agricultural yield imbalance. Facilitating optimal plant growth and implementing effective measures against diseases play a fundamental role in meeting the global demand for food in terms of both quality and quantity. This article offered a hybrid model based on Deep learning called DENSE-NET-121 with 2D Gaussian elimination filters that can be effective deep learning tools to increase potato yield by early detection of the leaf. Three types of potato leaf classes called Early Blight, Healthy, and Late Blight are incorporated by Dataset which has been taken from the kaggle repository. Considering this proposed model, state-of-the-art DENSE-NET-121 has produced an unprecedented training and validation accuracy 0.9908, 0.9837 respectively furthermore model also produced extremely low training and validation loss 0.0683, 0.0796 and an error rate below then 0.1 as well. Furthermore model produced average Precision, and recall, 0.98, 0.96, and 0.97 respectively.
Why it matches plant phenotyping methodsジャガイモ葉の画像から病害状態を認識する深層学習手法を提案・評価しており、植物病害表現型の取得が研究の中心である。
Ensuring a sustainable global food security status which necessitated by achieving an equilibrium state between the anticipated and significant rise in the global population and the projected agricultural output which is essential for their food adequacy. The absence of such a harmonious balance may be a contributing factor to the emergence of food crises worldwide. Hence, it is imperative to proactively address and mitigate both direct and indirect factors that could potentially lead to this agricultural yield imbalance. Facilitating optimal plant growth and implementing effective measures against diseases play a fundamental role in meeting the global demand for food in terms of both quality and quantity. This article offered a hybrid model based on Deep learning called DENSE-NET-121 with 2D Gaussian elimination filters that can be effective deep learning tools to increase potato yield by early detection of the leaf. Three types of potato leaf classes called Early Blight, Healthy, and Late Blight are incorporated by Dataset which has been taken from the kaggle repository. Considering this proposed model, state-of-the-art DENSE-NET-121 has produced an unprecedented training and validation accuracy 0.9908, 0.9837 respectively furthermore model also produced extremely low training and validation loss 0.0683, 0.0796 and an error rate below then 0.1 as well. Furthermore model produced average Precision, and recall, 0.98, 0.96 , and 0.97 respectively.
Why it matches plant phenotyping methodsジャガイモ葉の病徴を画像から分類する深層学習手法の開発・評価が中心であり、植物病害状態の表現型推定に該当する。
abstractThis article offered a hybrid model based on Deep learning called DENSE-NET-121 with 2D Gaussian elimination filters that can be effective deep learning tools to increase potato yield by early detection of the leaf.
User-friendly handheld plant phenotyping devices, such as the MultispeQ, provide quick and easy measurements that effectively capture the dynamic nature of photosynthesis. This study demonstrates the added value of integrating measurements of such devices with both process-based and empirical modeling approaches for estimating the maximum leaf photosynthetic capacity ( A m a x ) and biomass production (DMP) of potato crops. Utilizing leaf fluorescence measurements, such as the efficiency of photosystem II ( ϕ 2 ) and the electron transport rate, gathered from two fields in the Netherlands from May to September 2019, we determined the A m a x to be 34 kg C O 2 ha −1 hr −1 with a standard deviation of 6.6 kg C O 2 ha −1 hr −1 . By incorporating dynamic photosynthetic parameters, leaf area index (LAI) retrieval, and crop modeling techniques to scale assimilation from the leaf to the canopy level, we successfully reduced the discrepancy between simulated and measured dry matter production in 16 out of 18 cases, offering significant advantages over fixed, literature-based photosynthetic parameter values.
Why it matches plant phenotyping methods携帯型蛍光センシングと作物モデルを統合し、葉の光合成能力とバイオマスを推定する測定・解析ワークフローが研究の中心であるため、植物表現型計測法の応用として採用する。
abstractThis study demonstrates the added value of integrating measurements of such devices with both process-based and empirical modeling approaches for estimating the maximum leaf photosynthetic capacity ( A m a x ) and biomass production (DMP) of potato crops.
Crop yields are severely impacted by plant diseases, leading to significant economic consequences. This study presents a plant disease prediction model that utilizes Convolutional Neural Networks (CNNs) and the Keras image augmentation technique. The CNN architecture includes multiple convolutional and pooling layers, as well as fully connected layers. Model training employs the Adam optimiser and categorical cross-entropy loss function, using a dataset of plant leaf images labelled with corresponding diseases for validation. After training the model with 10 epochs and a batch size of 32, an accuracy of 97% was achieved with a loss of 0.11. Validation accuracy and loss were 91% and 0.20, respectively. The Keras image augmentation technique was also evaluated for its effectiveness in generating new images from existing ones, which were used to test the model's ability to generalise when exposed to unseen data. The accuracy and loss on the test images were 95% and 0.25 and for augmented images were 94% and 0.22, respectively, demonstrating the model's potential for use in plant disease management as a diagnostic tool for farmers. This study is unique in combining CNN and Keras Image Generator for the detection of leaf diseases, and the results suggest that the proposed model could be useful for improving crop yields and farmers' income.
Why it matches plant phenotyping methodsCNNと画像拡張を用いたジャガイモ葉の病害状態推定が研究の中心であり、モデル性能も検証しているため、植物フェノタイピング手法として含める。
abstractThis study presents a plant disease prediction model that utilizes Convolutional Neural Networks (CNNs) and the Keras image augmentation technique.
Continuous information on plant traits such as plant height, leaf area index (LAI), and above-ground biomass (AGB) is important in the study of plant growth and such information can help farmers achieve better yields while reducing agricultural inputs, e.g. through more efficient water use. Knowledge on plant traits is also key to further test and develop crop and land surface models. Cosmic-ray neutron sensors (CRNS) have primarily been used to determine soil moisture. Recently, Jakobi et al. (2022) found that thermal neutrons can be used to monitor aboveground biomass (ABG) and that the variations in measured thermal neutron intensity may also depend on the vegetation biomass and structure. However, different soil properties of the test sites may have influenced the results (e.g. related to differences in soil chemistry). In this follow-up study, a single agricultural field was investigated over a long measurement period (2015-2023) to avoid site-specific effects on the CRNS measurements. This new dataset contains different crop rotations with repetitions of the same crop and continuous measurements of plant height instead of sporadic biomass measurements. Based on this data, we developed regression models that take into account plant structure to predict traits (i.e. plant height and LAI) from observed thermal neutron intensity.The annual regression models for plant height provided generally high R²-values (0.86 on average), with the highest values found for potato and winter wheat. An aggregation by crop type of the different seasons resulted in a slight reduction of the R² to 0.84 for winter wheat (3 seasons), 0.68 for sugar beet (2 seasons), and 0.75 for potato (2 seasons). The slope values of these regressions were distinctly different, thus supporting the assumption that the relationship between plant traits and thermal neutron intensity depends on vegetation structure. The root mean square error (RMSE) of the plant height predicted with thermal neutrons were 12 cm for winter wheat and 14 cm for both sugar beet and potato. In addition, we tested a prediction of LAI based on thermal neutrons. For this, we used a regression model that predicts LAI based on plant height (R²: 0.78). Using this model, we were able to predict the LAI for a period of 5 years with LAI observation data with an RMSE of 1.23 m/m, which is still within the uncertainty range of radiation-based LAI methods (Fang et al., 2019). Independent validation was performed also against spatio-temporal LiDAR-based plant height and multispectral-based LAI measurements, each averaged for the CRNS footprint area. Our results demonstrate the potential of cosmic-ray neutron sensing for continuous monitoring of plant traits at the field scale. LiteratureFang, H., F. Baret, S. Plummer and G. Schaepman‐Strub (2019): An overview of global leaf area index (LAI): Methods, products, validation, and applications. Reviews of Geophysics 57(3): 739-799. DOI: 10.1002/hyp.11274Jakobi, J., J.A. Huisman, H. Fuchs, H. Vereecken and H. Bogena (2022): Potential of Thermal Neutrons to Correct Cosmic-Ray Neutron Soil Moisture Content Measurements for Dynamic Biomass Effects. Water Resour. Res. 58(8): e2022WR031972. DOI: 10.1029/2022WR031972
Why it matches plant phenotyping methods熱中性子センサーを用いて草丈・LAI・地上部バイオマスを連続推定する手法を開発し、回帰モデルとLiDAR・マルチスペクトル測定で検証しており、植物形質の取得手法が中心である。
abstractBased on this data, we developed regression models that take into account plant structure to predict traits (i.e. plant height and LAI) from observed thermal neutron intensity.
Abstract Understanding growth patterns and yield dynamics in potato cultivation is essential for optimizing agricultural practices and improving productivity. This study leverages machine-learning techniques to analyze and predict potato growth stages and yield outcomes based on environmental and physiological data. Various machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments. The models were evaluated for their accuracy in identifying growth stages and forecasting yield performance. Key physiological trends were identified during the tuber initiation, bulking, and maturation phases, correlating with specific environmental conditions. Predictions for tuber yield showed high accuracy, with models achieving R² values above 0.90 across validation datasets. Additionally, the study highlights the importance of integrating machine learning with precision agriculture systems to enhance decision-making and resource management. The proposed methodology demonstrates significant potential for advancing potato-farming practices by providing actionable insights into growth and yield optimization.
Why it matches plant phenotyping methods機械学習とマルチスペクトル画像を用いてジャガイモの生育段階と収量を推定し、検証しており、植物表現型の取得・推定手法が中心です。
abstractVarious machine-learning models were developed using multispectral imaging, soil parameters, and climatic factors collected across diverse cultivation environments.
Introduction Potatoes and tomatoes are important Solanaceae crops that require effective disease monitoring for optimal agricultural production. Traditional disease monitoring methods rely on manual visual inspection, which is inefficient and prone to subjective bias. The application of deep learning in image recognition has led to object detection models such as YOLO (You Only Look Once), which have shown high efficiency in disease identification. However, complex climatic conditions in real agricultural environments challenge model robustness, and current mainstream models struggle with accurate recognition of the same diseases across different plant species. Methods This paper proposes the SIS-YOLOv8 model, which enhances adaptability to complex agricultural climates by improving the YOLOv8 network structure. The research introduces three key modules: 1) a Fusion-Inception Conv module to improve feature extraction against complex backgrounds like rain and haze; 2) a C2f-SIS module incorporating Style Randomization to enhance generalization ability for different crop diseases and extract more detailed disease features; and 3) an SPPF-IS module to boost model robustness through feature fusion. To reduce the model's parameter size, this study employs the Dep Graph pruning method, significantly decreasing parameter volume by 19.9% and computational load while maintaining accuracy. Results Experimental results show that the SIS-YOLOv8 model outperforms the original YOLOv8n model in disease detection tasks for potatoes and tomatoes, with improvements of 8.2% in accuracy, 4% in recall rate, 5.9% in mAP50, and 6.3% in mAP50-95. Discussion Through these network structure optimizations, the SIS-YOLOv8 model demonstrates enhanced adaptability to complex agricultural environments, offering an effective solution for automatic crop disease detection. By improving model efficiency and robustness, our approach not only advances agricultural disease monitoring but also contributes to the broader adoption of AI-driven solutions for sustainable crop management in diverse climates.
Why it matches plant phenotyping methods植物の病徴を画像から検出する深層学習モデルを開発・評価しており、病害状態の表現型取得が研究の中心である。
abstractThe research introduces three key modules: 1) a Fusion-Inception Conv module to improve feature extraction against complex backgrounds like rain and haze; 2) a C2f-SIS module incorporating Style Randomization to enhance generalization ability for different crop diseases and extract more detailed disease features; and 3) an SPPF-IS module to boost model robustness through feature fusion.
Potato yield is an important metric for farmers to further optimize their cultivation practices. Potato yield can be estimated on a harvester using an RGB-D camera that can estimate the three-dimensional (3D) volume of individual potato tubers. A challenge, however, is that the 3D shape derived from RGB-D images is only partially completed, underestimating the actual volume. To address this issue, we developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images. CoRe++ is a deep learning network that consists of a convolutional encoder and a decoder. The encoder compresses RGB-D images into latent vectors that are used by the decoder to complete the 3D shape using the deep signed distance field network (DeepSDF). To evaluate our CoRe++ network, we collected partial and complete 3D point clouds of 339 potato tubers on an operational harvester in Japan. On the 1425 RGB-D images in the test set (representing 51 unique potato tubers), our network achieved a completion accuracy of 2.8 mm on average. For volumetric estimation, the root mean squared error (RMSE) was 22.6 ml, and this was better than the RMSE of the linear regression (31.1 ml) and the base model (36.9 ml). We found that the RMSE can be further reduced to 18.2 ml when performing the 3D shape completion in the center of the RGB-D image. With an average 3D shape completion time of 10 ms per tuber, we can conclude that CoRe++ is both fast and accurate enough to be implemented on an operational harvester for high-throughput potato yield estimation. CoRe++’s high-throughput and accurate processing allows it to be applied to other tuber, fruit and vegetable crops, thereby enabling versatile, accurate and real-time yield monitoring in precision agriculture. Our code, network weights and dataset are publicly available at https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git.
Why it matches plant phenotyping methodsRGB-D画像からジャガイモ塊茎の3D形状と体積を推定する手法を開発・検証し、収穫量フェノタイピングに適用した中心的な方法論研究。
abstractwe developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images.
Accurate determination of potato leaf protein content (Cp), carbon-based constituents (CBC), and leaf area index (LAI) are crucial for precise monitoring of potato growth. Dynamic monitoring of leaf Cp, CBC, and LAI can provide valuable insights for agricultural management, such as analyzing the impact of environment stress factors on potato growth throughout its lifecycle. Currently, the most commonly used method for estimating crop parameters is the vegetation spectral signature-statistical regression approach. However, leaf Cp and CBC estimation are greatly influenced by water absorptions, as they exhibited overlapping spectral features in the short-wave infrared (SWIR) region. Consequently, the accuracy of protein estimation using traditional vegetation spectral feature-statistical regression methods is limited. This study aims to propose a comprehensive approach called PCPNet (Potato Canopy and Leaf Parameter Network), which could jointly estimate potato canopy and leaf parameters including Cp, CBC, and LAI. The performance of the PCPNet was compared with traditional spectral feature-statistical regression methods in estimating Cp, CBC and LAI. A simulated dataset for pre-training was generated using the PROSPECT-PRO and SAIL radiative transfer models to represent various complex scenarios encountered in real-world potato cultivation practices. The designed PCPNet was initially pre-trained based on this simulated dataset and then re-trained using ground-based measurements from five potato growing seasons across two distinct regions in China through transfer learning techniques. The validation of potato canopy and leaf parameters was conducted based on the estimations provided by the PCPNet model, while assessing their accuracy. This study yields the following results: (1) The PCPNet-based deep learning model demonstrated markedly superior accuracy in estimating potato Cp, CBC, and LAI compared to traditional machine learning models. (2) The deep learning model pretrained with transfer learning exhibited greater estimation accuracy than the deep learning model trained from stratch. In future research, experiments should be conducted across multiple regions and crops to verify both accuracy and generalizability of this approach in remote sensing of leaf Cp, CBC, and LAI.
Why it matches plant phenotyping methodsジャガイモの葉タンパク質、炭素成分、LAIという植物形質を推定する深層学習・放射伝達モデル手法を開発し、従来法との比較と複数地域・季節での検証を行っており、フェノタイピング手法が中心である。
abstractThis study aims to propose a comprehensive approach called PCPNet (Potato Canopy and Leaf Parameter Network), which could jointly estimate potato canopy and leaf parameters including Cp, CBC, and LAI.
Breeding goals of potatoes for deep-frying purposes include high starch contents, good suitability for long-term storage, and low tendency to form reducing sugars as acrylamide precursors. Due to the extensive number of samples, an accurate analysis of acrylamide in French fries and its precursors in tubers is difficult to implement in the breeding process. Therefore, this study aimed to evaluate the suitability of NIRS measurements after minimal sample processing for the prediction of reducing sugar contents in the tubers or acrylamide contents in French fries. An external validation with more than 650 samples consisting of 194 potato genotypes resulted in a prediction accuracy of 51 % for acrylamide and 76 % for reducing sugar content. RPD values of less than 1.5 for acrylamide and between 1.64 and 2.23 for reducing sugar prediction rendered low medium to medium model quality. Nevertheless, acrylamide prediction models based on NIRS measurement of mashed tubers categorised over 80 % of unknown samples correctly as being below or above the European threshold value, indicating suitability as rapid test procedure in the breeding process.
Why it matches plant phenotyping methodsジャガイモ塊茎の還元糖および加工適性に関わるアクリルアミドをNIRSで推定する手法を、650超の試料で外部検証しており、育種用の迅速な表現型評価法として技術的検証が中心である。
abstractTherefore, this study aimed to evaluate the suitability of NIRS measurements after minimal sample processing for the prediction of reducing sugar contents in the tubers or acrylamide contents in French fries.
Potato late blight is a common disease affecting crops worldwide. To help detect this disease in complex environments, an improved YOLOv5 algorithm is proposed. First, ShuffleNetV2 is used as the backbone network to reduce the number of parameters and computational load, making the model more lightweight. Second, the coordinate attention mechanism is added to reduce missed detection for leaves that are overlapping, damaged, or hidden, thereby increasing detection accuracy under challenging conditions. Lastly, a bidirectional feature pyramid network is employed to fuse feature information of different scales. The study results show a significant improvement in the model's performance. The number of parameters was reduced from 7.02 to 3.87 M, and the floating point operations dropped from 15.94 to 8.4 G. These reductions make the model lighter and more efficient. The detection speed increased by 16 %, enabling faster detection of potato late blight leaves. Additionally, the average precision improved by 3.22 %, indicating better detection accuracy. Overall, the improved model provides a robust solution for detecting potato late blight in complex environments. The study's findings can be useful for applications and further research in controlling potato late blight in similar environments.
Why it matches plant phenotyping methodsジャガイモ葉の疫病検出を目的にYOLOv5を改良し、精度・速度・計算量を評価しており、植物病害状態の画像ベース推定が中心である。
titlePotato late blight leaf detection in complex environments.
In agriculture, plant disease detection at an early stage is significant. Plant leaves are an important factor in plant disease detection. Early disease prevention in-line harvest loss benefit is given to plant growers. The odd leaves can be visible after getting infected, and if the software can tell accurately the disease infestation result. Forecasting plant leaf disease works better for an early disease warning. The infected leaf needs to be permanently removed, or it will affect the plant. As leaves are a significant part and produce food from the sun, the infected leaves show different patterns. Many proposing such AI and ML models have forecasted the infected leaves of many plants. This document focuses on forecasting diseases in plant leaves mainly for four types of plants: tomato, potato, apple & grape. Diseases in plant leaves can cause significant damage to plants and can have a detrimental effect on both the quantity and quality of production whether we consider a lower scale kitchen gardening or a high scale agriculture farming. The research begins with an overview of the common plant leaf diseases found in each of these four plants, along with their symptoms and causes. It then discusses the importance of early detection and management of these diseases to ensure healthy growth. This helps a naïve gardener as well as an experienced farmer to prevent a plant or a whole field from getting infected or diseased. Plant disease detection approaches are crucial for prevention and management. Various techniques in plant disease detection using AI- based machine learning and deep learning methods are reviewed comprehensively. Keywords— Agriculture farming, Kitchen Garden, Plant leaf diseases, Forecasting diseases.
Why it matches plant phenotyping methods植物葉の病徴・病害をAI/機械学習で検出・予測する手法を包括的にレビューしており、植物の病害状態を観測・推定するフェノタイピング手法が中心です。
titleA Comprehensive Review of Research on Disease Prediction in Plant Leaves
Food is one of the most basic needs of living beings. It is very essential to grow a sufficient quantity of crops to cope with the growing population. With time, it is seen that plants are being affected by various kinds of diseases. Different plant diseases are a major influence on agricultural output limitations, and they are generally difficult to control. As a result, early detection of plant diseases is crucial for avoiding output losses and improving the quality of agricultural goods. This research paper proposes a method to detect and classify the disease on plant leaves with a severity measurement for the grading system. The paper describes a machine learning-based detection and classification of diseases like early blight and late blight on "potato leaf" using the KNN classifier. Our research focuses on a rigorous examination of potato plant disease segmentation approaches.
Why it matches plant phenotyping methods植物葉の病害を画像から検出・分類し、病害重症度を測定する手法が研究の中心であり、植物状態の表現型推定に該当する。
abstractThis research paper proposes a method to detect and classify the disease on plant leaves with a severity measurement for the grading system.
LiDAR sensors have great potential for enabling crop recognition (e.g., plant height, canopy area, plant spacing, and intra-row spacing measurements) and the recognition of agricultural working environments (e.g., field boundaries, ridges, and obstacles) using agricultural field machinery. The objective of this study was to review the use of LiDAR sensors in the agricultural field for the recognition of crops and agricultural working environments. This study also highlights LiDAR sensor testing procedures, focusing on critical parameters, industry standards, and accuracy benchmarks; it evaluates the specifications of various commercially available LiDAR sensors with applications for plant feature characterization and highlights the importance of mounting LiDAR technology on agricultural machinery for effective recognition of crops and working environments. Different studies have shown promising results of crop feature characterization using an airborne LiDAR, such as coefficient of determination (R2) and root-mean-square error (RMSE) values of 0.97 and 0.05 m for wheat, 0.88 and 5.2 cm for sugar beet, and 0.50 and 12 cm for potato plant height estimation, respectively. A relative error of 11.83% was observed between sensor and manual measurements, with the highest distribution correlation at 0.675 and an average relative error of 5.14% during soybean canopy estimation using LiDAR. An object detection accuracy of 100% was found for plant identification using three LiDAR scanning methods: center of the cluster, lowest point, and stem–ground intersection. LiDAR was also shown to effectively detect ridges, field boundaries, and obstacles, which is necessary for precision agriculture and autonomous agricultural machinery navigation. Future directions for LiDAR applications in agriculture emphasize the need for continuous advancements in sensor technology, along with the integration of complementary systems and algorithms, such as machine learning, to improve performance and accuracy in agricultural field applications. A strategic framework for implementing LiDAR technology in agriculture includes recommendations for precise testing, solutions for current limitations, and guidance on integrating LiDAR with other technologies to enhance digital agriculture.
Why it matches plant phenotyping methodsLiDARによる植物形質（草丈、樹冠面積、株間など）の取得・評価方法、試験手順、精度ベンチマークを中心にレビューしており、植物フェノタイピング手法が主要テーマである。
abstractThe objective of this study was to review the use of LiDAR sensors in the agricultural field for the recognition of crops and agricultural working environments.
Remote sensing is a valuable tool in precision agriculture due to its spatial and temporal coverage, non-destructive method of data collection, and cost-effectiveness. In this study, we measured the canopy reflectance of potato ( Solanum tuberosum L.) crops on a plant-by-plant basis with a handheld spectrometer instrument. Our study pursues two primary objectives: (1) determining the optimal temporal aggregation for measuring canopy signals related to potato yield and (2) identifying the best spectral bands in the 350-2500 nm domain and vegetation indices. The study was conducted over two consecutive years (2020 and 2021) with 60 plants per plot, encompassing six potato varieties and three replicates annually throughout the growth season. Employing correlation analysis and dimensionality reduction, we identified 23 independent features significantly correlated with tuber yield. We used multiple linear regression analysis to model the relationship between the selected features and yield and to compare their influence in the fitted model. We used the Leave-One-Out Cross-Validation (LOOCV) method to assess the validity of the model (RMSE = 702 g and %RMSE = 29.2%). The most significant features included the Gitelson2 and Vogelmann indices. The optimal time period for measurements was determined to be from 56 to 100 days after planting. These findings may contribute to the advancement of precision farming by proposing tailored sensor applications, paving the way for improved agricultural practices and enhanced food security.
Why it matches plant phenotyping methods携帯型分光計による植物体ごとのキャノピー反射測定、感度波長・植生指数の選定、収量推定モデルの検証が研究の中心であり、ジャガイモ収量という植物形質を推定する方法研究である。
abstractwe measured the canopy reflectance of potato ( Solanum tuberosum L.) crops on a plant-by-plant basis with a handheld spectrometer instrument.
PotatoLiDAR / point cloudLeafMorphology / geometry measurementObject detection2D/3D reconstructionGrowth / time-series analysisVisualization / data managementArchitecture / morphology / geometryLeaf traits
In modern agricultural science research, high-fidelity three-dimensional (3D) leaf models are crucial for crop growth analysis. However, reconstructing the complex morphology and texture of leaves from a single viewpoint under varying natural lighting conditions poses a significant challenge. To address the issues associated with this challenge, this paper presents a diffusion model-based method for single-view leaf reconstruction using potato leaves as the experimental subject. In the camera prediction process, the combination of an explicit point cloud generation technique and an implicit 3D Gaussian rendering technique enables the accurate prediction of camera parameters and the effective capture of leaf phenotypic features. In the synthesis of the 3D model of the leaf, a strategy for optimizing the coarse model UV texture is designed with the objective of achieving spatial consistency of texture details. Furthermore, the model was successfully applied to the reconstruction of other crop leaves and lamellar structural objects, and innovatively constructed a leaf reconstruction model with disease characteristics, aiming to provide a reference for the early 3D detection of crop diseases, as well as a reference for the 3D reconstruction and visualization of other lamellar objects. The results demonstrate that the method is effective in reconstructing the morphological structure and texture details of leaves, as well as thin sheet-like structured objects, achieving fast and high-fidelity single-view reconstruction.
Why it matches plant phenotyping methods単一画像から葉の形態・テクスチャを高精度に3D再構成する手法を開発しており、葉の表現型特徴抽出が中心的な技術貢献である。
abstractthis paper presents a diffusion model-based method for single-view leaf reconstruction using potato leaves as the experimental subject.
Plant phenotyping relevance match · UnverifiedCrossref · OpenAlex · Europe PMC · checked 13 Sept 2026
Ensuring plant health is a key factor to maximize crop yield. Despite that, the current field scouting and disease monitoring approaches often rely on visual evaluations and are, therefore, subjective and time demanding. New methods to assist in disease detection and severity assessment are required to allow better crop management and higher throughput in field phenotyping studies. With this objective, techniques involving the use of multi- and hyperspectral imagery for retrieval of plant traits and assessment of general crop health status are increasingly being proposed as alternatives to conventional disease monitoring approaches. Conversely, research focusing on specific pathogens are still lacking in many cases, in particular studies investigating multi-source sensing approaches, which have the potential to improve retrieval/classification accuracy. In this study, hyperspectral imagery and point clouds obtained with LiDAR or through Structure from Motion algorithm (SfM) applied to high resolution RGB images were evaluated as possible alternatives to detect Blackleg (caused by bacteria of the genera Pectobacterium and Dickeya ) in potato. It was demonstrated that all the different datasets have potential to discriminate healthy from diseased plants. The combination of Vegetation Indices (VIs) derived from hyperspectral images with structural features from LiDAR resulted in the best validation results (Balanced Accuracy – BA = 0.915). Small improvements were also achieved by combining VIs with SfM features (BA = 0.876) in comparison to VIs alone (BA = 0.846). Evaluation of feature importance for classification models derived from the different datasets indicated that after structural features derived from LiDAR or RGB imagery were added as predictor variables the relative importance of VIs for the predictions decreased, in particular for VIs related to LAI or other traits describing canopy properties. Finally, analysis of false negatives and positives indicated some limitations to the predictive potential of the different datasets, with diseased and healthy plants eventually presenting atypical structural and spectral characteristics in comparison to those expected for their classes. Therefore, multi-source sensing, including additional modalities (e.g., thermal or fluorescence), might be required to further improve detection of pathogens with complex symptoms, as those affecting roots, tubers and stems.
Why it matches plant phenotyping methodsUAVハイパースペクトル、LiDAR、SfMによる植物単位の病害状態判別を開発・比較検証しており、植物フェノタイピング手法が中心である。
abstractNew methods to assist in disease detection and severity assessment are required to allow better crop management and higher throughput in field phenotyping studies.
Ensuring plant health is a key factor to maximize crop yield. Despite that, the current field scouting and disease monitoring approaches often rely on visual evaluations and are, therefore, subjective and time demanding. New methods to assist in disease detection and severity assessment are required to allow better crop management and higher throughput in field phenotyping studies. With this objective, techniques involving the use of multi- and hyperspectral imagery for retrieval of plant traits and assessment of general crop health status are increasingly being proposed as alternatives to conventional disease monitoring approaches. Conversely, research focusing on specific pathogens are still lacking in many cases, in particular studies investigating multi-source sensing approaches, which have the potential to improve retrieval/classification accuracy. In this study, hyperspectral imagery and point clouds obtained with LiDAR or through Structure from Motion algorithm (SfM) applied to high resolution RGB images were evaluated as possible alternatives to detect Blackleg (caused by bacteria of the genera Pectobacterium and Dickeya) in potato. It was demonstrated that all the different datasets have potential to discriminate healthy from diseased plants. The combination of Vegetation Indices (VIs) derived from hyperspectral images with structural features from LiDAR resulted in the best validation results (Balanced Accuracy – BA = 0.915). Small improvements were also achieved by combining VIs with SfM features (BA = 0.876) in comparison to VIs alone (BA = 0.846). Evaluation of feature importance for classification models derived from the different datasets indicated that after structural features derived from LiDAR or RGB imagery were added as predictor variables the relative importance of VIs for the predictions decreased, in particular for VIs related to LAI or other traits describing canopy properties. Finally, analysis of false negatives and positives indicated some limitations to the predictive potential of the different datasets, with diseased and healthy plants eventually presenting atypical structural and spectral characteristics in comparison to those expected for their classes. Therefore, multi-source sensing, including additional modalities (e.g., thermal or fluorescence), might be required to further improve detection of pathogens with complex symptoms, as those affecting roots, tubers and stems.
Why it matches plant phenotyping methodsUAVハイパースペクトル、LiDAR、SfMを組み合わせ、ジャガイモ個体の健全・罹病状態を分類するセンシング手法を検証しており、植物病害状態の取得・評価が研究の中心です。
abstractNew methods to assist in disease detection and severity assessment are required to allow better crop management and higher throughput in field phenotyping studies.
Monitoring the aboveground biomass (AGB) is critical for assessing crop growth status, predicting yield, and making informed crop management decisions. This study aimed to develop an efficient and robust model for predicting potato AGB using data derived from unmanned aerial vehicle (UAV) RGB imagery, and to clarify the relationship between AGB and tuber biomass (TB). Remote sensing images of the potato canopy at multiple growth stages were acquired over two consecutive years (2022–2023), together with synchronous ground-based AGB and TB measurements. Sixty-four candidate variables encompassing spectral, color, structure, and texture features were extracted from the 2022 RGB images. We identified five single variables most sensitive to AGB through correlation analysis, which were then subjected to linear, polynomial, logarithmic, exponential, and power regressions. Recursive feature elimination (RFE) and variance inflation factor (VIF) analyses were used to select multivariate combinations as input parameters for Partial Least Squares (PLS) and Random Forest (RF) models. The optimal single-variable and multivariate regression models were selected based on the Bayesian information criterion (BIC), and subsequently applied to predict AGB in field trial plots for 2023. Additionally, we analyzed the dynamic relationship between AGB and TB, as well as the effects of genotype and nitrogen management on the accuracy of AGB predictions and its relationship with TB. The results showed that: (1) Structural indicators had the highest correlation with AGB among the four features. The linear regression using canopy volume (CVol) as an input parameter (Model 1) exhibited superior performance among the single-variable regression models (R² = 0.75, RMSE = 0.42 kg m⁻², BIC = −272.92). Meanwhile, the RF regression model with canopy cover (CC), maximum canopy height (CHₘₐₓ), and average canopy height (CHₘₑₐₙ) as input parameters (Model 2) had the lowest BIC value of −314.15 (R² = 0.82, RMSE = 0.36 kg m⁻²), and its predicted values for the new dataset were significantly correlated with the measured AGB values (correlation coefficient of 0.84). Furthermore, Model 2 showed a stronger predictive power for AGB in plots with the high-erectability genotype ('Zhongshu18', R² = 0.78, RMSE = 1.02 kg m⁻²) or those treated with ammonium nitrogen (NH₄⁺-N) (R² = 0.75, RMSE = 1.24 kg m⁻²). (2) A significant positive correlation was observed between TB and cumulative AGB, with R² values of 0.77 in 2022 and 0.76 in 2023 (p < 0.01). When the data were analyzed separately by genotype, the linear correlation between TB and cumulative AGB was further enhanced. Moreover, when analyzed by nitrogen form, the correlation under nitrate nitrogen and control treatments was significantly stronger than under NH₄⁺-N treatments. In conclusion, our results suggest that canopy structure indicators incorporating both horizontal and vertical dimensions, when combined with the RF algorithm, have the greatest potential for predicting AGB, and that the cumulative AGB over time can effectively estimate potato TB, although crop genotype and nitrogen management can affect the estimation accuracy of AGB as well as biomass allocation patterns. This study provides an efficient and cost-effective approach to accurately estimate the AGB of potato crops in the field, which is valuable for predicting yields of root and tuber crops and optimizing agronomic management practices.
Why it matches plant phenotyping methodsUAV RGB画像からジャガイモの地上部バイオマスを推定する画像解析・回帰モデルを開発し、別年の圃場データで予測性能を検証しており、表現型取得手法が研究の中心である。
abstractThis study aimed to develop an efficient and robust model for predicting potato AGB using data derived from unmanned aerial vehicle (UAV) RGB imagery
As climate changes, maintenance of yield stability requires efficient selection for drought tolerance. Drought-tolerant cultivars have been successfully but slowly bred by yield-based selection in arid environments. Marker-assisted selection accelerates breeding but is less effective for polygenic traits. Therefore, we investigated a selection based on phenotypic markers derived from automatic phenotyping systems. Our trial comprised 64 potato genotypes previously characterised for drought tolerance in ten trials representing Central European drought stress scenarios. In two trials, an automobile LIDAR system continuously monitored shoot development under optimal (C) and reduced (S) water supply. Six 3D images per day provided time courses of plant height (PH), leaf area (A3D), projected leaf area (A2D) and leaf angle (LA). The evaluation workflow employed logistic regression to estimate initial slope (k), inflection point (Tm) and maximum (Mx) for the growth curves of PH and A2D. Genotype × environment interaction affected all parameters significantly. Tm(A2D)ₛ and Mx(A2D)ₛ correlated significantly positive with drought tolerance, and Mx(PH)ₛ correlated negatively. Drought tolerance was not associated with LAc, but correlated significantly with the LAₛ during late night and at dawn. Drought-tolerant genotypes had a lower LAₛ than drought-sensitive genotypes, thus resembling unstressed plants. The decision tree model selected Tm(A2D)ₛ and Mx(PH)c as the most important parameters for tolerance class prediction. The model predicted sensitive genotypes more reliably than tolerant genotype and may thus complement the previously published model based on leaf metabolites/transcripts.
Why it matches plant phenotyping methods自動LIDARによる連続3D画像取得と、植物形態・成長形質の抽出および解析ワークフローが、乾燥耐性評価の中心的手法として用いられている。
abstractwe investigated a selection based on phenotypic markers derived from automatic phenotyping systems.
Reproduction assets foundThe paper's LIDAR phenotyping and yield data are deposited publicly in E!DAL (Köhl et al. 2022, doi 10.5447/ipk/2022/12). The SAS analysis scripts are only available from the corresponding author (request_only).Dataset · publicData availability All data are available at E!DAL (Köhl et al. 2022). Material and SAS scripts used for
evaluation are available from the corresponding author.Open asset ↗E!DALpdf-page:27 lines:1-62Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Dec 2024Computers and Electronics in Agriculture.
Agriculture is the backbone of the country’s economy. People depend on agriculture for food and exporting to generate income. However, agriculture faces various diseases that affect the quantity and quality of vegetables. Therefore, it is important to propose a model for detecting vegetable diseases. This study proposed a sustainable smart system for vegetable disease detection and classification. This system detects early vegetable diseases in common vegetables such as tomato, potato, lettuce, and cucumber. The study employed deep learning (DL) models to detect and classify vegetable diseases. Convolutional neural networks (CNN) are a type of DL model used for image classification. This study utilizes CNN and other extensions, such as VGG16 and MobileNet, for plant image classification. Three DL models were trained on four datasets for tomato disease classification, potato disease classification, lettuce disease classification, and cucumber disease classification. The results show that the three models achieved 84.49% accuracy on the tomato disease dataset, 97.65% accuracy on the cucumber disease dataset, 97% accuracy on the potato disease dataset, and 99.9% accuracy on the lettuce disease dataset. The proposed system can assist farmers in the early detection of vegetable diseases before they spread, and it can enhance agriculture by improving both the quality and quantity of products.
Why it matches plant phenotyping methods植物画像から病害状態を推定する深層学習手法が研究の中心であり、植物フェノタイピング手法として適格です。
abstractThis study proposed a sustainable smart system for vegetable disease detection and classification.
The application of hyperspectral imaging (HSI) has gained significant importance in the past decade, particulary in the context of food analysis, including potatoes. However, the current literature lacks a comprehensive systematic review of the application of this technique in potato cultivation. Therefore, the aim of this work was to conduct a systematized review by analysing the most relevant compounds, diseases and stress factors in potatoes using hyperspectral imaging. For this purpose, scientific studies were retrieved through a systematic keyword search in Web of Science and Scopus databases. Studies were only included in the review if they provided at least one set of quantitative data. As a result, a total of 52 unique studies were included in the review. Eligible studies were assigned an in-house developed quality scale identifying them as high, medium or low risk. In most cases the studies were rated as low risk. Finally, a comprehensive overview of the HSI applications in potatoes was performed. It has been observed that most of the selected studies obtained better results using linear methods. In addition, a meta-analysis of studies based on regression and classification was attempted but was not possible as not enough studies were found for a specific variable.
Why it matches plant phenotyping methodsジャガイモの化合物・病害・ストレスをHSIで定量・分類する研究を体系的にレビューしており、植物状態の画像計測手法が中心です。
abstractFinally, a comprehensive overview of the HSI applications in potatoes was performed.
Timely and accurate monitoring of above-ground biomass (AGB) is of great significance for indicating crop growth status, predicting yield, and assessing carbon dynamics. Compared with the traditional time-consuming and laborious method through destructive sampling, UAV remote sensing provides a timely and efficient strategy for estimating biomass. However, the universality of remote sensing retrieval models with multi-feature fusion under different management practices and cultivars are unknown. The spectral, textural, and structural features extracted by UAV multispectral and RGB imaging, coupled with agricultural meteorological parameters, were integrated to estimate the AGB in potato during the whole growth period. Six advanced modeling algorithms, including random forest (RF), partial least squares regression (PLSR), multiple linear regression (MLR), simple linear regression (SLR), ridge regression (RR), and lasso regression (LR) models, were adopted to evaluate the ability of estimating AGB by single feature and multi-feature information fusion. The results indicate the following: (1) The newly proposed variety-dependent indicator growth process ratio (GPR) can improve the model accuracy by over 20%. (2) The fusion of vegetation indices, canopy cover, growing degree days, and GPR achieved higher accuracy to estimate AGB at all growth stages compared with single feature model. (3) RF model performed best for the estimation of AGB during the whole growth period with R 2 0.79 and rRMSE 0.24 ton/ha. The study demonstrated that the fusion of multi-feature coupled with the machine learning algorithm achieved the best performance for estimating potato AGB under different management practices and cultivars, which can be a potential and useful phenotyping strategy for estimating AGB at refined plot scale during the whole growth period.
Why it matches plant phenotyping methodsUAV画像から特徴量を抽出し、機械学習でジャガイモの地上部バイオマスを推定する手法を開発・評価しており、植物形質取得が研究の中心です。
abstractThe spectral, textural, and structural features extracted by UAV multispectral and RGB imaging, coupled with agricultural meteorological parameters, were integrated to estimate the AGB in potato during the whole growth period.
Potato yield is an important metric for farmers to further optimize their cultivation practices. Potato yield can be estimated on a harvester using an RGB-D camera that can estimate the three-dimensional (3D) volume of individual potato tubers. A challenge, however, is that the 3D shape derived from RGB-D images is only partially completed, underestimating the actual volume. To address this issue, we developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images. CoRe++ is a deep learning network that consists of a convolutional encoder and a decoder. The encoder compresses RGB-D images into latent vectors that are used by the decoder to complete the 3D shape using the deep signed distance field network (DeepSDF). To evaluate our CoRe++ network, we collected partial and complete 3D point clouds of 339 potato tubers on an operational harvester in Japan. On the 1425 RGB-D images in the test set (representing 51 unique potato tubers), our network achieved a completion accuracy of 2.8 mm on average. For volumetric estimation, the root mean squared error (RMSE) was 22.6 ml, and this was better than the RMSE of the linear regression (31.1 ml) and the base model (36.9 ml). We found that the RMSE can be further reduced to 18.2 ml when performing the 3D shape completion in the center of the RGB-D image. With an average 3D shape completion time of 10 ms per tuber, we can conclude that CoRe++ is both fast and accurate enough to be implemented on an operational harvester for high-throughput potato yield estimation. CoRe++’s high-throughput and accurate processing allows it to be applied to other tuber, fruit and vegetable crops, thereby enabling versatile, accurate and real-time yield monitoring in precision agriculture. Our code, network weights and dataset are publicly available at https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git . • CoRe++ is a high-throughput 3D shape completion network for RGB-D images. • CoRe++ uses a convolutional encoder and DeepSDF decoder to complete the 3D shape. • Testing on 1425 RGB-D images, CoRe++ achieved a completion accuracy of 2.8 mm. • The average 3D shape completion time was 10 ms per potato tuber.
Why it matches plant phenotyping methodsRGB-D画像からジャガイモ塊茎の3D形状と体積を推定する手法を開発・評価しており、植物形質取得が研究の中心である。
abstractwe developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images.
Introduction Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants under water deficit. Sensor-based imaging data serves as a rich source of information for machine learning and deep learning algorithms, facilitating further analysis that aims to identify drought stress. While these approaches yield favorable results, real-time field applications require algorithms specifically designed for the complexities of natural agricultural conditions. Methods Our work proposes a novel deep learning framework for classifying drought stress in potato crops captured by unmanned aerial vehicles (UAV) in natural settings. The novelty lies in the synergistic combination of a pre-trained network with carefully designed custom layers. This architecture leverages the pre-trained network's feature extraction capabilities while the custom layers enable targeted dimensionality reduction and enhanced regularization, ultimately leading to improved performance. A key innovation of our work is the integration of gradient-based visualization inspired by Gradient-Class Activation Mapping (Grad-CAM), an explainability technique. This visualization approach sheds light on the internal workings of the deep learning model, often regarded as a "black box". By revealing the model's focus areas within the images, it enhances interpretability and fosters trust in the model's decision-making process. Results and discussion Our proposed framework achieves superior performance, particularly with the DenseNet121 pre-trained network, reaching a precision of 97% to identify the stressed class with an overall accuracy of 91%. Comparative analysis of existing state-of-the-art object detection algorithms reveals the superiority of our approach in achieving higher precision and accuracy. Thus, our explainable deep learning framework offers a powerful approach to drought stress identification with high accuracy and actionable insights.
Why it matches plant phenotyping methodsUAV画像からジャガイモの干ばつストレス状態を推定する深層学習・可視化パイプラインが研究の中心であり、植物状態の取得・分類手法を開発および評価している。
abstractOur work proposes a novel deep learning framework for classifying drought stress in potato crops captured by unmanned aerial vehicles (UAV) in natural settings.
Potatoes are one of the horticultural commodities with significant trade value both domestically and internationally. To produce high-quality potatoes, healthy and disease-free potato plants are essential. The most common diseases affecting potato plants are late blight and early blight. These diseases appear randomly in different positions and sizes on potato leaves, resulting in numerous combinations of infected leaves. This study proposes an architecture focused on a similarity-based approach, namely the Siamese Neural Network (SNN). SNN can recognize images by comparing two or more images and categorizing the test image accordingly. Thus, SNN has an advantage over classification-based approaches as it can identify various combinations of disease spots on potato plants using a similarity-based approach. This study is divided into two main scenarios: testing with data categories which were previously seen during the training process (traditional testing) and testing with the addition of new data categories that were not seen during training. In the first scenario, SNN showed better accuracy with an accuracy rate of 98.4%, while in the second scenario, SNN achieved an accuracy of 97.1%. That result suggests that SNN can categorize data very well, even recognizing data which never seen during training. These results offer hope that SNN can recognize more disease spots/patterns on potato plants or even identify new diseases by adding these new diseases to the SNN support set without retraining.
Why it matches plant phenotyping methodsジャガイモ葉の病斑パターンを画像から分類するSiamese Neural Networkを提案・評価しており、植物の病害状態を直接推定する画像ベース表現型解析手法が研究の中心です。
abstractThis study proposes an architecture focused on a similarity-based approach, namely the Siamese Neural Network (SNN).
The Leaf Area Index (LAI) is a crucial parameter for evaluating crop growth and informing fertilization management in agricultural fields. Compared to traditional methods, UAV-based hyperspectral imaging technology offers significant advantages for non-destructive, rapid monitoring of crop LAI by simultaneously capturing both spectral information and two-dimensional images of the crop canopy, which reflect changes in its structure. While numerous studies have demonstrated that various texture features, such as the Gray-Level Co-occurrence Matrix (GLCM), can be used independently or in combination with crop canopy spectral data for LAI estimation, limited research exists on the application of Haralick textures for evaluating crop LAI across multiple growth stages. In this study, experiments were conducted on two early-maturing potato varieties, subjected to different treatments (e.g., planting density and nitrogen levels) at the Xiaotangshan base in Beijing, during three key growth stages. Crop canopy spectral reflectance and Haralick textures were extracted from ultra-low-altitude UAV hyperspectral imagery, while LAI was measured using ground-based methods. Three types of spectral data-original spectral reflectance (OSR), first-order differential spectral reflectance (FDSR), and vegetation indices (VIs)-along with three types of Haralick textures-simple, advanced, and higher-order-were analyzed for their correlation with LAI across multiple growth stages. A model for LAI estimation in potato at multiple growth stages based on spectral and textural features screened by the successive projection algorithm (SPA) was constructed using partial least squares regression (PLSR), random forest regression (RFR) and gaussian process regression (GPR) machine learning methods. The results indicated that: (1) Spectral data demonstrate greater sensitivity to LAI than Haralick textures, with sensitivity decreasing in the order of VIs, FDSR and OSR; (2) spectral data alone provide more accurate LAI estimates than Haralick textures, with VIs achieving an accuracy of R² = 0.63, RMSE = 0.38, NRMSE = 28.36%; and (3) although Haralick textures alone were not effective for LAI estimation, they can enhance LAI prediction when combined with spectral data, with the GPR method achieving R ² = 0.70, RMSE = 0.30, NRMSE = 20.28%. These findings offer a valuable reference for large-scale, accurate monitoring of potato LAI.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像からスペクトル・テクスチャ特徴を抽出し、ジャガイモのLAIを推定する手法を開発・評価しており、表現型取得と推定ワークフローが中心である。
abstractUAV-based hyperspectral imaging technology offers significant advantages for non-destructive, rapid monitoring of crop LAI
The plant disease is a significant concern in the agriculture field. Many diseases destroy the crop badly. Optimized Convolutional neural network (CNN) model having seven convolutional layer with weight pruning is used for detecting disease on potato leaves. Further transfer learning is used to compare the results of the proposed model. Plant Village dataset which contains potato disease-Early blight and late blight is used. Both the diseases are fungaldiseases. Used transfer learning models are Resnet50, VGG16 and VGG19.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から検出するCNN手法を開発・比較しており、植物病害フェノタイピングが中心である。
abstractOptimized Convolutional neural network (CNN) model having seven convolutional layer with weight pruning is used for detecting disease on potato leaves.
Plant phenotyping relevance match · UnverifiedOpenAlex · Europe PMC · bioRxiv · checked 13 Sept 2026
Abstract Phenotypes, defining an organism’s behaviour and physical attributes, arise from the complex, dynamic interplay of genetics, development, and environment, whose interactions make it enormously challenging to forecast future phenotypic traits of a plant at a given moment. This work reports AMULET, a modular approach that uses imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible. AMULET streamlines the phenotyping process by integrating plant detection, prediction, segmentation, and data analysis, enhancing workflow efficiency and reducing time. The machine learning models used data from over 30,000 plants, using the Arabidopsis thaliana-Pseudomonas syringae pathosystem. AMULET also demonstrated its adaptability by accurately detecting and predicting phenotypes of in vitro potato plants after minimal fine-tuning with a small dataset. The general approach implemented through AMULET streamlines phenotyping and will improve breeding programs and agricultural management by enabling pre-emptive interventions optimising plant health and productivity.
Why it matches plant phenotyping methods画像ベース高スループット表現型解析と機械学習による植物形態・生理形質の予測基盤AMULETを開発しており、表現型取得・抽出ワークフローが研究の中心である。
abstractThis work reports AMULET, a modular approach that uses imaging-based high-throughput phenotyping and machine learning to predict morphological and physiological plant traits hours to days before they are visible.
The agricultural sector faces significant losses due to plant diseases, particularly in major crops such as potatoes, tomatoes, and bell peppers. This paper presents a machine learning-based approach to classify diseases in these crops using leaf images. A Convolutional Neural Network (CNN) model was constructed and trained on datasets of healthy leaf images and diseased leaf images from potato, tomato, and bell pepper plants. The model successfully classifies diseases such as Bacterial Spot (for bell peppers), Early Blight, Late Blight, Mosaic Virus, Leaf Mold (for tomatoes), and with a classification accuracy of 93%, this system provides early detection, helping farmers take timely action to reduce disease impact and increase crop yield.
Why it matches plant phenotyping methods葉画像から植物病害を分類するCNN手法が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採用する。
abstractThis paper presents a machine learning-based approach to classify diseases in these crops using leaf images.
The epidermal leaf patterns of plants exhibit remarkable diversity in cell shapes, sizes, and arrangements, driven by environmental interactions that lead to significant adaptive changes even among closely related species. The Solanaceae family, known for its high diversity of adaptive epidermal structures, has traditionally been studied using qualitative phenotypic descriptions. To advance this, we developed a workflow combining multi-scale computer vision, image processing, and data analysis to extract digital descriptors for leaf epidermal cell morphology. Applied to nine wild potato species, this workflow quantified key morphological parameters, identifying descriptors for trichomes, stomata, and pavement cells, and revealing interdependencies among these traits. Principal component analysis (PCA) highlighted two main axes, accounting for 45% and 21% of variance, corresponding to features such as guard cell shape, trichome length, stomatal density, and trichome density. These axes aligned well with the historical and geographical origins of the species, separating southern from Central American species, and forming distinct clusters for monophyletic groups. This workflow thus establishes a quantitative foundation for investigating leaf epidermal cell morphology within phylogenetic and geographic contexts.
Why it matches plant phenotyping methods葉表皮細胞の形態形質を画像から抽出・定量するコンピュータビジョン／画像処理ワークフローの開発と適用が研究の中心であるため、植物フェノタイピング手法として収載する。
abstractwe developed a workflow combining multi-scale computer vision, image processing, and data analysis to extract digital descriptors for leaf epidermal cell morphology.
Reproduction assets foundThe paper's quantitative phenotyping measurements (trichome types and morphometric parameters of leaf epidermal cells for nine wild potato species) are publicly available as Supplementary Tables S1 and S2 at the MDPI supplementary URL. Microscopy images are not publicly deposited and are available only upon request; noSupplement · publicObjects of the Institute of Cytology and Genetics SB RAS.
Abbreviations
The following abbreviations are used in this manuscript:
LSM
Laser scanning microscopy
PI
Propidium iodide
DAPI
4′,6-diamidino-2-phenylindole
PCA
Principal component analysis
Supplementary Materials
The following supporting information can be downloaded at https://www.mdpi.com/article/10.3390/plants13213084/s1 , Table S1: Trichome types for the studied wild potato species; Table S2: Morphometric parameters for leaf epidermal cells of the studied wild potato species, including Area, Length, Width, Elongation, Circularity, Rectangularity, Perimeter, Convex Hull Area, Convex Hull Perimeter, and Convex Hull Coverage.
Author Open asset ↗lines:139-176Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
The use of remote sensing technologies to monitor the nitrogen nutrient status of crops is gradually becoming a more sensible choice, as traditional methods are time-consuming, labor-intensive, and destructive. However, most predictive models utilizing remote sensing data are statistical rather than mechanistic, making them difficult to extend at interannual and regional scales. This study explored the interannual and regional transferability of the potato plant nitrogen content (PNC) prediction models, which combined environmental variables (EVs, e.g. temperature, precipitation, etc.) with proximal hyperspectral vegetation indices (VIs). Two methodologies were implemented to fuse EVs and VIs. The first involved a multiple regression analysis utilizing a multivariate linear model and a random forest approach, with VIs and EVs treated as independent variables, respectively. The second, a hierarchical linear model (HLM), employed EVs to dynamically adjust the relationship between VIs and PNC for different experimental sites. The predictive outcomes demonstrated that (i) the conventional method relying solely on optical VIs exhibited limited accuracy and stability in interannual and regional PNC forecasting; (ii) albeit the multivariate regression approach significantly enhanced model accuracy within the calibration set, its scalability across years and regions remained suboptimal; (iii) the HLM method exhibited high precision and scalability across years and regions, with R², RMSE, and NRMSE values of 0.68, 0.50 %, and 19.68 % in the validation set, respectively. Those findings corroborate that using a two-tier HLM method can automatically adjust for discrepancies in VIs response to PNC through EVs, thereby enhancing the model's stability. Provided that remote sensing data and EVs are sustainably acquired over the potato growth cycle, it will provide a particularly promising approach to potato nitrogen diagnostics as a decision-making tool for regional application of nitrogen fertilizer.
Why it matches plant phenotyping methodsジャガイモ植物の窒素含有量という植物形質を近接ハイパースペクトルデータから推定するモデルについて、年次・地域間の移植性を比較・検証しており、形質取得・推定手法が研究の中心である。
abstractThis study explored the interannual and regional transferability of the potato plant nitrogen content (PNC) prediction models, which combined environmental variables (EVs, e.g. temperature, precipitation, etc.) with proximal hyperspectral vegetation indices (VIs).
Accurate disease recognition through computer vision is crucial for the intelligent management of potato production. Popular data-driven classification methods face challenges including limited labelled data and poor model portability. Unsupervised Domain Adaptation (UDA) addresses these challenges with a novel learning strategy. However, the complex field environment introduces a significant domain shift problem due to varying conditions. Existing UDA methods usually concentrate on aligning global data distribution and employ a single structure for disease feature extraction, thereby limiting their efficacy in true field environment. To tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented. MRSAN effectively aligns feature distributions across diverse data by minimising distribution differences among relevant subdomains. Simultaneously, the multi-representation extraction method captures finer details from various perspectives in the disease images. The combination of these two approaches efficiently mitigates the adverse effects caused by various interference factors in field environment. Based on the acquisition conditions of light variation and disease progression, two field potato disease image datasets are created, containing five and six kinds of potato leaf disease, respectively. Extensive transfer experiments are conducted on the two datasets. MRSAN achieves average classification accuracies of 87.03% and 80.06% on the datasets for the corresponding transfer tasks, outperforming the other compared methods. This not only validates the effectiveness of MRSAN but also demonstrates its robust ability to generalise across changes in regard to light variation and disease progression.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から認識する手法を開発し、異なる圃場条件で検証しているため、植物表現型取得・抽出法が中心である。
abstractTo tackle this challenge of potato disease recognition, the Multi-Representation Adaptive Network (MRSAN) based on subdomain alignment is presented.
In sweet potato and potato, sensory traits are critical for acceptance by consumers, growers, and traders, hence underpinning the success or failure of a new cultivar. A quick analytical method for the sensory traits could expedite the selection process in breeding programs. In this paper, the relationship between sensory panel and instrumental color plus texture features was evaluated. Results have shown a high correlation between the sensory panel and instrumental color in both sweet potato (up to r = 0.84) and potato ( r > 0.78), implying that imaging is a potential alternative to the sensory panel for color scoring. High correlations between sensory panel aroma and flavor with instrumental color were detected (up to r = 0.66), although the validity of these correlations needs to be tested. With instrumental color and texture parameters as predictors, low to moderate accuracy was detected in the machine learning models developed to predict sensory panel traits. Overall, the performance of the eXtreme Gradient Boosting (XGboost) was comparable to the radial-based support vector machine (NL-SVM) algorithm, and these could be used for the initial selection of genotypes for aromas and flavors ( r 2 = 0.64-0.72) and texture attributes like moisture or mealiness ( r 2 > 50). Among the chemical properties screened in sweet potato, only starch showed a moderate correlation with sensory features like mealiness ( r = 0.54) and instrumental color ( r = 0.65). From the results, we can conclude that the instrumental scores of color are equivalent to those scored by the sensory panel, and the former could be adopted for quick analysis. Further investigations may be required to understand the association between color and aroma or flavor.
Why it matches plant phenotyping methods育種選抜を目的に、画像由来の色・テクスチャ特徴と機械学習でサツマイモ・ジャガイモの感覚形質を推定し、官能評価との相関・予測精度を検証しているため、表現型取得・推定法が中心である。
abstractA quick analytical method for the sensory traits could expedite the selection process in breeding programs.
Detecting potato plant leaf diseases using convolutional neural networks (CNNs) is a significant step towards sustainable agriculture. Computer vision-based automated disease detection in agriculture is essential for the early detection and treatment of plant diseases, assisting farmers in minimizing crop losses, maximizing yields, and guaranteeing food security. This study proposes a novel method for detecting potato leaf disease using a customized 5-layer Convolutional Neural Network (CNN). The model’s performance is compared with MobileNet and a 4-layer CNN as the backbone architectures. Based on experimental results, the 5-layer customized CNN achieves an accuracy rate of 97.16%, which is significantly higher than that of the 4-layer CNN (73.21%) and MobileNet (78.43%). Additionally, the 5-layer CNN model shows promising results for other evaluation metrics, including F1 score (97.18%), recall (97.16%), and precision (97.24%). Furthermore, out of all the models that were tested, the 5-layer CNN model shows the least amount of loss. Using a threshold of 0.6, and the custom CNN as backbone architecture to Faster R-CNN (FRCNN) the model achieved an Intersection over Union (IoU) of 0.76 for disease detection. Additionally, a comparative study of various optimizers (Adam, SGD, Adadelta, and AdamW) and loss functions is done; the Adam optimizer and the unique 5-layer CNN model yielded the best results. This study advances automated methods for detecting potato leaf diseases, offering a dependable and effective way to identify diseases early in agricultural settings.
Why it matches plant phenotyping methodsジャガイモ葉の病害状態を画像から検出・分類するCNN/Faster R-CNN手法を開発し、複数モデル・指標で性能比較しており、植物表現型取得が中心である。
abstractThis study proposes a novel method for detecting potato leaf disease using a customized 5-layer Convolutional Neural Network (CNN).
Plant diseases represent a serious threat to national productivity and global food security. Effective therapy for multiple diseases requires a precise and useful differentiation of them. In this work, a computerized system for the identification and categorization of diseases in potato and maize crops is developed using convolutional neural networks. The demonstration was created with the ResNet50V2 model and tested on a combined collection of images of leaves. The system achieved an astounding accuracy of 85.19. Enhancing model execution through exchange learning, fine-tuning, and information augmentation were all part of the process. With the use of another dataset, the trained model was verified and produced positive results, almost exactly differentiating between the disease-causing leaf type (potato or maize). This technology helps ranchers adopt sustainable and knowledgeable disease management methods by promoting timely mediations, which in turn advances disease discovery.
Why it matches plant phenotyping methods葉画像から植物病害を識別・分類するCNN手法の開発と別データセットでの検証が中心であり、植物の病害状態を直接推定するため。
abstracta computerized system for the identification and categorization of diseases in potato and maize crops is developed using convolutional neural networks.
Agriculture is one of the most important sectors in nutrition and economy worldwide. One of the most effective ways to combat the contraction of agricultural activities is the management of crop diseases, which impact food security and the earnings of many people. This study deals with applying a variety of ML techniques that are used in the disease diagnosis of plant leaves based on the dataset PlantVillage, especially corn, apples, and potatoes. Feature extraction was performed by Histogram of Oriented Gradients(HOG), and traditional models: Support Vector Machine, Random Forest, Logistic Regression, and Multilayer Perceptron were used for training. The ensemble techniques of bagging, XGBoost, stacking, and voting classifiers brought more improvement in the model performance. Separation of diseases with very close features is still a challenging task. The results seem quite promising for identifying leaf diseases through machine learning techniques, but because the conditions are indistinguishable, further research becomes obligatory.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定する機械学習手法の比較・性能分析が中心であり、植物フェノタイピング手法として収録対象。
titlePerformance Analysis of Machine Learning Techniques in Plant Leaf Disease Detection
Potato is an important agricultural product that is consumed extensively throughout the world, but it is a plant that is sensitive to various diseases. Detecting diseases in potato plants at an early stage both prevents outbreaks of plant diseases and increases crop yield. For this purpose, 3 deep learning-based models were used in this study to detect and classify potato plant diseases. These models are 5-layer Convolutional Neural Network (CNN), EfficientNetB2 and ConvNeXtSmall transfer learning models, respectively. These models were trained and tested on the publicly available and widely used PlantVillage dataset. In this dataset, there are three classes: healthy (152), early blight disease (1000) and late blight disease (1000) and a total of 2152 images. The models were first trained on this dataset, and 5-layer CNN gave the best performance, with an average classification accuracy of 98.54% over 10 tests. Afterwards, data augmentation was performed to equalize the number of samples in the classes, and the EfficientNetB2 model gave the best performance on the augmented data with 99.89% accuracy. 99.33% performance was achieved with 5-layer CNN. CNN, designed as 5-layer, and other proposed methods classify potato plant diseases with high performances, and the results obtained are comparable to the literature.
Why it matches plant phenotyping methodsジャガイモ葉画像から病害状態を推定・分類する深層学習手法が研究の中心であり、植物病害表現型の画像ベース推定に該当する。
abstract3 deep learning-based models were used in this study to detect and classify potato plant diseases.
Early blight and ladybug beetle infestation are important factors threatening potato yields. The current research on disease classification using the spectral differences between the healthy and disease-stressed leaves of plants has achieved good progress in a variety of crops, but less research has been conducted on early blight in potato. This paper proposes a CARS-SPA-GA feature selection method. First, the raw spectral data of potato leaves in the visible/near-infrared light region were preprocessed. Then, the feature wavelengths were selected via competitive adaptive reweighted sampling (CARS) and the successive projection algorithm (SPA), respectively. Then, the two sets of wavelengths were reorganized and duplicates were removed, and secondary feature selection was conducted with genetic algorithm (GA). Finally, the feature wavelengths were fed into different classifiers and the parameters were optimized using a real-coded genetic algorithm (RCGA). The experimental results show that the feature wavelengths selected by the CARS-SPA-GA method accounted only for 9% of the full band, and the classification accuracy of the RCGA-optimized support vector machine (SVM) classification model reached 98.366%. These results show that it is feasible to classify early blight and ladybug beetle infestation in potato using visible/near-infrared spectral data, and the CARS-SPA-GA method can substantially improve the accuracy and detection efficiency of potato pest and disease classification.
Why it matches plant phenotyping methodsジャガイモ葉の病害・食害状態を可視近赤外スペクトルから推定する特徴波長選択と分類手法が研究の中心であり、植物の病害状態を直接評価するため。
abstractThis paper proposes a CARS-SPA-GA feature selection method.
Accurate identification of potato diseases is crucial for reducing yield losses. To address the issue of low recognition accuracy caused by the mismatch between target domain and source domain due to insufficient samples, the effectiveness of Multi-Source Unsupervised Domain Adaptation (MUDA) method in disease identification is explored. A Multi-Source Domain Feature Adaptation Network (MDFAN) is proposed, employing a two-stage alignment strategy. This method first aligns the distribution of each source-target domain pair within multiple specific feature spaces. In this process, multi-representation extraction and subdomain alignment techniques are utilized to further improve alignment performance. Secondly, classifier outputs are aligned by leveraging decision boundaries within specific domains. Taking into account variations in lighting during image acquisition, a dataset comprising field potato disease images with five distinct disease types is created, followed by comprehensive transfer experiments. In the corresponding transfer tasks, MDFAN achieves an average classification accuracy of 92.11% with two source domains and 93.02% with three source domains, outperforming all other methods. These results not only demonstrate the effectiveness of MUDA but also highlight the robustness of MDFAN to changes in lighting conditions.
Why it matches plant phenotyping methodsジャガイモ病害を画像から認識するドメイン適応ネットワークを開発し、圃場画像データセットと転移実験で性能を検証しており、植物の病害状態の表現型取得が中心である。
abstractA Multi-Source Domain Feature Adaptation Network (MDFAN) is proposed, employing a two-stage alignment strategy.
Accurate real-time estimation of nutrient concentrations in potato (Solanum tuberosum L.) canopies is crucial for advanced decision support systems in site-specific nutrient management. This study investigated the effectiveness of unmanned aerial vehicle (UAV) based hyperspectral imaging in predicting nitrogen (N), phosphorus (P), potassium (K), and sulfur (S) concentrations in potato plants comparing two sampling types such as petiole/leaves and above-ground biomass (AGB) sampling. Furthermore, this study also investigates the prediction of AGB, total, and marketable yield of two potato cultivars, 'Atlantic' (chipping) and 'Red La Soda' (tablestock). Four UAV flights over experimental sites were made, and hyperspectral imaging sensors (393–995 nm, 273 bands) were conducted, which coincided with the in-field sample collection as ground truth. Data were analyzed using the partial least square regression model after preprocessing and extracting spectra from images. The model showed high accuracy in estimating plant N concentration from petiole/leaf samples (external validation R² = 0.58; [external validation RMSE = 0.31 × 10⁴ mg kg⁻¹]), as well as for P (0.75 [0.05 × 10⁴ mg kg⁻¹]) and S (0.58 [0.03 × 10⁴ mg kg⁻¹]). Potassium estimation accuracy improved with biomass sampling (0.47 [1.19 × 10⁴ mg kg⁻¹]). Above-ground biomass estimation had higher accuracy for 'Atlantic' (0.75 [1.29 Mg ha⁻¹]) than for 'Red La Soda' (0.57 [1.38 Mg ha⁻¹]). The model accurately estimated total and marketable tuber yields for both cultivars, with variations noted based on flight timing related to the crop stage. Cultivar ‘Red La Soda’ achieved the highest total yield accuracy on the first (0.76 [3.31 Mg ha⁻¹]) and fourth flights (0.76 [3.31]), while the ‘Atlantic’ had the highest accuracy on the third flight (0.50 [4.11]). Model outputs, including standardized coefficients and variable importance in prediction, visualizing band contributions to measured parameter predictions are presented. This study concludes that hyperspectral imaging successfully estimates the potato nutrient concentration and predicts the in-season potato yield, which can contribute significantly to the potato management decision support system. However, it underscores the importance of multiyear high temporal data acquisition with variable potato varieties to establish a reliable AGB and yield estimation model to improve performance.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像からジャガイモの栄養状態、バイオマス、収量を推定する取得・解析手法を開発および検証しており、植物表現型の測定が研究の中心である。
abstractThis study investigated the effectiveness of unmanned aerial vehicle (UAV) based hyperspectral imaging in predicting nitrogen (N), phosphorus (P), potassium (K), and sulfur (S) concentrations in potato plants
In potato breeding, maturity class (MC) is a crucial selection criterion because this is a critical aspect of commercial potato production. Currently, the classification of potato genotypes into MCs is done visually, which is time- and labor-consuming. The objective of this research was to use vegetation indices (VIs) derived from unmanned aerial vehicle (UAV) imagery to remotely assign MCs to potato plants grown in trials, representing three different early stages within a multi-year breeding program. The relationships between VIs (GOSAVI – Green Optimized Soil Adjusted Vegetation Index, MCARI2 – Modified Chlorophyll Absorption Index-Improved, NDRE – Normalized Difference Red Edge, NDVI – Normalized Difference Vegetation Index, and OSAVI – Optimized Soil Adjusted Vegetation Index and WDVI – Weighted Difference Vegetation Index) and visual potato canopy status were determined. Further, this study aimed to identify factors that could improve the accuracy (decrease Mean Absolute Error – MAE) of potato MC estimation remotely. Results show that VIs derived from UAV imagery can be effectively used to remotely assign MCs to potato breeding lines, with higher accuracy for the potato B-clones (20 plants per plot) than the A-clones (6 plants per plot). Among the tested VIs, the NDRE allowed for potato MC evaluation with the lowest MAE. Applying NDRE for remote MC estimation using a validation dataset of potato B-clones (100 plants per plot), resulted in an MC estimate with a 0.81 MAE. However, the accuracy of potato MC estimation using UAV image-based methods should be improved by reducing the potato canopy’s variability (increasing uniformity) within the plot. This could be achieved by minimizing 1) potato vines bending over the neighboring row, causing vine overlap between plots, and 2) plants damaged by tractor wheels during field operations.
Why it matches plant phenotyping methodsUAV画像から植生指数を抽出し、ジャガイモの成熟クラスという植物状態を推定・検証する手法が研究の中心です。
abstractThe objective of this research was to use vegetation indices (VIs) derived from unmanned aerial vehicle (UAV) imagery to remotely assign MCs to potato plants grown in trials
Agricultural productivity is one of the critical factors towards ensuring food security across the globe. However, some of the main crops, such as potato, tomato, and mango, are usually infested by leaf diseases, which considerably lower yield and quality. The traditional practice of diagnosing disease through visual inspection is labor-intensive, time-consuming, and can lead to numerous errors. To address these challenges, this study evokes the AgirLeafNet model, a deep learning-based solution with a hybrid of NASNetMobile for feature extraction and Few-Shot Learning (FSL) for classification. The Excess Green Index (ExG) is a novel approach that is a specified vegetation index that can further the ability of the model to distinguish and detect vegetative properties even in scenarios with minimal labeled data, demonstrating the tremendous potential for this application. AgirLeafNet demonstrates outstanding accuracy, with 100% accuracy for potato detection, 92% for tomato, and 99.8% for mango leaves, producing incredibly accurate results compared to the models already in use, as described in the literature. By demonstrating the viability of a deep learning/IoT system architecture, this study goes beyond the current state of multi-crop disease detection. It provides practical, effective, and efficient deep-learning solutions for sustainable agricultural production systems. The innovation of the model emphasizes its multi-crop capability, precision in results, and the suggested use of ExG to generate additional robust disease detection methods for new findings. The AgirLeafNet model is setting an entirely new standard for future research endeavors.
Why it matches plant phenotyping methods葉画像から植物病害状態を推定する深層学習手法の開発・比較が中心であり、植物表現型計測法として採用する。
abstractthis study evokes the AgirLeafNet model, a deep learning-based solution with a hybrid of NASNetMobile for feature extraction and Few-Shot Learning (FSL) for classification.
Reproduction assets foundThe paper's Data Availability Statement explicitly lists three public Kaggle leaf-image datasets (potato, tomato, mango) that constitute the phenotyping image inputs used for the study's disease-detection experiments. No author analysis code or trained model checkpoints are reported.Dataset · publicAgronomy 2024, 14, 2230 32 of 33
Data Availability Statement: These data were derived from the following resources available in
the public domain: Potato Plant Diseases Data (https://www.kaggle.com/datasets/hafiznouman
786/potato-plant-diseases-data) (accessed on 22 September 2024), Tomato Leaf Diseases Dataset
(https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf) (accessed on 22 September 2024),
Mango Leaf Disease Dataset (https://www.kaggle.com/datasets/aryashah2k/mango-leaf-disease-dataset) (accessed on 22 September 2024).
Conflicts ofOpen asset ↗Kagglepdf-raw-page:32 lines:1-53Dataset · publicAgronomy 2024, 14, 2230 32 of 33
Data Availability Statement: These data were derived from the following resources available in
the public domain: Potato Plant Diseases Data (https://www.kaggle.com/datasets/hafiznouman
786/potato-plant-diseases-data) (accessed on 22 September 2024), Tomato Leaf Diseases Dataset
(https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf) (accessed on 22 September 2024),
Mango Leaf Disease Dataset (https://www.kaggle.com/datasets/aryashah2k/mango-leaf-disease-dataset) (accessed on 22 September 2024).
Conflicts of Interest: The authors declare that there are no conflicts of interest regarding the publica-
tion of this study.
References
1. Mohanty, S.P.; Hughes,Open asset ↗Kagglepdf-raw-page:32 lines:1-53Dataset · publicng resources available in
the public domain: Potato Plant Diseases Data (https://www.kaggle.com/datasets/hafiznouman
786/potato-plant-diseases-data) (accessed on 22 September 2024), Tomato Leaf Diseases Dataset
(https://www.kaggle.com/datasets/kaustubhb999/tomatoleaf) (accessed on 22 September 2024),
Mango Leaf Disease Dataset (https://www.kaggle.com/datasets/aryashah2k/mango-leaf-disease-dataset) (accessed on 22 September 2024).
Conflicts of Interest: The authors declare that there are no conflicts of interest regarding the publica-
tion of this study.
References
1. Mohanty, S.P.; Hughes, D.P.; Salathé, M. Using Deep Learning for Image-Based Plant Disease Detection. Front. Plant Sci. 2016,
Open asset ↗Kagglepdf-raw-page:32 lines:1-53Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Plant disease identification is a crucial issue in agriculture, and with the advancement of deep learning techniques, early and accurate identification of plant diseases has become increasingly critical. In recent years, the rise of vision transformers has attracted significant attention from researchers in various vision-based application areas. We designed a model with an encoder–decoder architecture to efficiently classify plant diseases using a transfer learning approach, which effectively recognizes a large number of plant diseases in multiple crops. The model was tested on the “PlantVillage”, “FGVC8”, and “EMBRAPA” datasets, which contain leaf information from crops such as apples, soybeans, tomatoes, and potatoes. These datasets cover diseases caused by fungi, including rust, spot, and scab, as well as viral diseases such as leaf curl. The model’s performance was rigorously evaluated on datasets, and the results demonstrated its high accuracy. The model achieved 99.9% accuracy on the “PlantVillage” dataset, 97.4% on the “EMBRAPA” dataset, and 91.5% on the “FGVC8” dataset, showcasing its competitiveness with other state-of-the-art models. This study provides a robust and reliable solution for plant disease classification and contributes to the advancement of precision agriculture.
Why it matches plant phenotyping methods葉画像から植物病害を分類するエンコーダ・デコーダ法を開発し、複数データセットで性能評価しており、植物状態の取得・推定手法が研究の中心である。
abstractWe designed a model with an encoder–decoder architecture to efficiently classify plant diseases using a transfer learning approach
Published20 Sept 20242024 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems (SPICES)Cited by 0 · OpenAlex ↗
Agriculture is a major economic driver of both the high and low income countries across the globe. Hence it is important to modernize agricultural practices by incorporating modern technological developments as a continuous process. Among the various challenges, plant leaf diseases pose a significant threat, leading to reduced agricultural yields and economic losses. Early detection of these diseases is crucial for timely intervention, yet traditional methods relying on human visual inspection are often delayed, incomplete, and unreliable. To address this, our study employs a Convolutional Neural Network (CNN) to analyze plant leaf images taken from New plant dataset, resulting in a highly accurate model for detecting various leaf diseases of Apple, Potato, Strawberry and Tomato. The developed CNN model achieved an accuracy of 90.91%, offering a promising tool for improving agricultural productivity by minimizing disease-induced crop damage.
Why it matches plant phenotyping methods植物葉画像から病害状態をCNNで推定する手法が研究の中心であり、植物の病徴に基づくフェノタイピング手法の開発・評価に該当する。
abstractour study employs a Convolutional Neural Network (CNN) to analyze plant leaf images taken from New plant dataset, resulting in a highly accurate model for detecting various leaf diseases of Apple, Potato, Strawberry and Tomato.
Magnetic resonance imaging (MRI) is a versatile technique in the biomedical field, but its application to the study of plant metabolism in vivo remains challenging because of magnetic susceptibility problems. In this study, we report the establishment of chemical exchange saturation transfer (CEST) for plant MRI. This method enables noninvasive access to the metabolism of sugars and amino acids in complex sink organs (seeds, fruits, taproots, and tubers) of major crops (maize, barley, pea, potato, sugar beet, and sugarcane). Because of its high signal detection sensitivity and low susceptibility to magnetic field inhomogeneities, CEST analyzes heterogeneous botanical samples inaccessible to conventional magnetic resonance spectroscopy. The approach provides unprecedented insight into the dynamics and distribution of sugars and amino acids in intact, living plant tissue. The method is validated by chemical shift imaging, infrared microscopy, chromatography, and mass spectrometry. CEST is a versatile and promising tool for studying plant metabolism in vivo, with many applications in plant science and crop improvement.
Why it matches plant phenotyping methods植物の生体内代謝を非侵襲的に測定するCEST-MRI法を確立し、複数手法で検証しており、植物表現型取得法が研究の中心である。
abstractIn this study, we report the establishment of chemical exchange saturation transfer (CEST) for plant MRI.
Genetic gain in potato breeding is limited by the heterozygous tetraploid genome of cultivated potato. Recent efforts to breed potato at the diploid level promise to improve genetic gain and allow more straightforward genetics and introgression breeding. Diploid F1 hybrid potato breeding relies on the ability to create diploid inbred lines via repeated self-fertilization. However, self-fertilization of diploid potato is hampered by a gametophytic self-incompatibility system encoded by the S-locus that prevents fertilization by self-pollen. Nonetheless, self-compatible diploid potato genotypes exist and have been used to create inbred lines. The S-locus inhibitor ( Sli ) gene is a dominant gene that provides strong self-compatibility in diploid potato and was previously mapped to Chromosome 12. While the Sli gene has already been identified and characterized, the most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene. To this end, we developed an effective phenotyping protocol to identify suitable parents and create diploid populations segregating for Sli . We show that an accurate phenotyping method is crucial to discriminate between confounding fertility factors and self-compatibility. In addition, we found that the Sli locus shows extreme segregation distortion on Chromosome 12. Finally, we used these insights to develop three F1 populations that segregate for Sli , which we later used for the identification of the Sli gene. Supplementary information The online version contains supplementary material available at 10.1007/s11540-024-09792-3.
Why it matches plant phenotyping methodsSli遺伝子探索に先立ち、自己適合性を他の稔性要因と識別するための表現型判定プロトコルを開発し、その有効性を集団作製に適用しており、植物表現型取得法が研究の中心である。
abstractthe most tedious challenge was to develop the optimal phenotyping methods and genetic populations preceding the cloning of this gene.
Abstract. Nitrogen is a plant growth limiting nutrient in natural ecosystems, however, many agricultural systems are saturated due to high fertilizer applications. This can lead to higher costs, nitrogen leakage into the environment and unnecessary GHG emissions that contribute to climate change. To avoid this, Neilson (2021) has proposed an approach based on minimal input agricultural systems (MIAS). MIAS seeks to grow crops with limited fertilizer inputs. This is accomplished through targeted/precision fertilizer placement, managing plant physiology to operate at higher efficiencies and adopting new varieties. To work optimally MIAS requires methods to quickly assess plant nutrient status and adjust fertilizer applications accordingly. This study tested remote sensing for detecting stress in potato plants, based on two separate and independent laboratory remote sensing experiments. The goal is to determine minimal input levels applied to a starvation agricultural system that provide yields equivalent (or perhaps even improving upon) those obtained using current excessive inputs, both in terms of yield and, importantly, quality. This research is at the front-end of a proposed paradigm shifting new approach to agriculture. We are being careful to start at first principles in this work; thus the study presented here is based on multiple trials and independent tests. Results testing experimental approaches and N deprivation assessment determined the optimal leaf density and timing of measurements and demonstrated a capability to detect vegetation stress and N deprivation in three potato varieties. These results will inform next steps for future RPAS/UAV/airborne/satellite studies and be used to develop other plant physiology assessment methods.
Why it matches plant phenotyping methodsジャガイモの窒素欠乏・植生ストレスを高分解能分光リモートセンシングで検出し、測定条件を検証・最適化しており、植物状態の取得法が中心である。
abstractThis study tested remote sensing for detecting stress in potato plants, based on two separate and independent laboratory remote sensing experiments.
Reductive and oxidative signals transmitted from the photosynthetic electron chain to target proteins through the redox signaling network are key regulators of carbon assimilation and downstream metabolism. However, despite their crucial role in activating and inhibiting photosynthetic activity, their relation to photosynthetic efficiency is hardly quantified due to the methodological gap between traditional spectroscopic approaches for investigating photosynthesis and biochemical analyses used in the redox regulation field. Here, we simultaneously quantified redox signals and photosynthetic activity by exploring time and wavelength-resolved fluorescence spectra that capture biosensor and chlorophyll fluorescence signals. Using a set of potato plants expressing genetically encoded redox biosensors, we demonstrated how reductive and oxidative signals are amplified with elevated light intensities and revealed the tight connection between electron transport rate (ETR) and the generation of peroxiredoxin-related oxidative signals. These results demonstrate how full spectrum analysis can pave the way for the integration of genetically encoded biosensors in photosynthesis research and demonstrate light-dependent activation of inhibitory oxidative signals in major crop plants.
Why it matches plant phenotyping methods時間・波長分解蛍光スペクトルを用いて、植物のレドックスシグナルと光合成活性を同時定量する測定法を開発・実証しており、植物生理状態の取得が研究の中心です。
abstractHere, we simultaneously quantified redox signals and photosynthetic activity by exploring time and wavelength-resolved fluorescence spectra that capture biosensor and chlorophyll fluorescence signals.
Breeding goals of potatoes for deep-frying purposes include high starch contents, good suitability for long-term storage, and low tendency to form reducing sugars as acrylamide precursors. Due to the extensive number of samples, an accurate analysis of acrylamide in French fries and its precursors in tubers is difficult to implement in the breeding process. Therefore, this study aimed to evaluate the suitability of NIRS measurements after minimal sample processing for the prediction of reducing sugar contents in the tubers or acrylamide contents in French fries. An external validation with more than 650 samples consisting of 194 potato genotypes resulted in a prediction accuracy of 51 % for acrylamide and 76 % for reducing sugar content. RPD values of less than 1.5 for acrylamide and between 1.64 and 2.23 for reducing sugar prediction rendered low medium to medium model quality. Nevertheless, acrylamide prediction models based on NIRS measurement of mashed tubers categorised over 80 % of unknown samples correctly as being below or above the European threshold value, indicating suitability as rapid test procedure in the breeding process.
Why it matches plant phenotyping methodsジャガイモ塊茎の還元糖含量をNIRSで推定する手法を外部検証し、育種選抜向けの迅速測定法として評価しており、植物形質の取得が研究の中心です。
abstractthis study aimed to evaluate the suitability of NIRS measurements after minimal sample processing for the prediction of reducing sugar contents in the tubers or acrylamide contents in French fries
Potato (Solanum tuberosum L.) is the most widely grown vegetable in the world. Consumers and processors evaluate potatoes based on quality traits such as shape and skin color, making these traits important targets for breeders. Achieving and evaluating genetic gain is facilitated by precise and accurate trait measures. Historically, quality traits have been measured using visual rating scales, which are subject to human error and necessarily lump individuals with distinct characteristics into categories. Image analysis offers a method of generating quantitative measures of quality traits. In this study, we use TubAR, an image-analysis R package, to generate quantitative measures of shape and skin color traits for use in genomic prediction. We developed and compared different genomic models based on additive and additive plus non-additive relationship matrices for two aspects of skin color, redness, and lightness, and two aspects of shape, roundness, and length-to-width ratio for fresh market red and yellow potatoes grown in Minnesota between 2020 and 2022. Similarly, we used the much larger chipping potato population grown during the same time to develop a multi-trait selection index including roundness, specific gravity, and yield. Traits ranged in heritability with shape traits falling between 0.23 and 0.85, and color traits falling between 0.34 and 0.91. Genetic effects were primarily additive with color traits showing the strongest effect (0.47), while shape traits varied based on market class. Modeling non-additive effects did not significantly improve prediction models for quality traits. The combination of image analysis and genomic prediction presents a promising avenue for improving potato quality traits.
Why it matches plant phenotyping methodsTubARによる画像解析でジャガイモの形状・皮色を定量化する手法が、ゲノム予測への主要な入力として明示されており、単なる routine 測定ではない。
abstractImage analysis offers a method of generating quantitative measures of quality traits.
Reproduction assets foundThe paper's data availability statement points to a public GitHub repository containing all data and scripts used for the phenotyping and genomic prediction analysis.Code · publicAll data and scripts used for this work are available at: https://github.com/shannonlabumn/GSQualityTraits .Open asset ↗shannonlabumn/GSQualityTraitslines:1105-1109Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published6 Sept 20242024 3rd International Conference for Advancement in Technology (ICONAT)Cited by 11 · OpenAlex ↗
Agriculture plays a pivotal role in our lives and holds significant importance in our economy. Proper management of agricultural practices is essential for maximizing profits in agricultural production. However, many farmers lack expertise in identifying and managing plant leaf diseases, leading to reduced crop yields. Since agricultural productivity directly impacts the profitability of farming, efficient disease detection and management are crucial. To address this issue, Convolutional Neural Networks (CNN) emerge as a viable solution for leaf disease detection and classification. The primary objective of this research is to develop a robust CNN-based system capable of detecting and classifying leaf diseases in various crops such as apple, grape, corn, potato, tomato, and more. In this research, the CNN algorithm was utilised, and the accuracy was $\mathbf{9 7. 5 8 \%}$. The system’s application will enable farmers to monitor large fields of crops, facilitating early detection and treatment of diseases. The significance of plant leaf disease detection spans across multiple sectors, including Biological Research and Agriculture Institutes. Detecting diseases promptly can help implement timely medical treatments, thereby mitigating the negative impacts on crop health and productivity. Moreover, such a system can assist in monitoring crop health on a larger scale, benefiting the agricultural sector as a whole.
Why it matches plant phenotyping methods植物葉の病害状態を画像からCNNで検出・分類する手法開発が研究の中心であり、植物表現型の測定に該当します。
abstractThe primary objective of this research is to develop a robust CNN-based system capable of detecting and classifying leaf diseases in various crops such as apple, grape, corn, potato, tomato, and more.
Abstract Grapes and potato, both a crucial component of the global agricultural economy, are susceptible to various diseases that can adversely affect crop quality and yield. Recently, the use of Deep Learning (DL) techniques in agriculture has shown potential for predicting and detecting diseases early. This study explores the effectiveness of Convolutional Neural Networks (CNN), Efficient Net, and Residual Networks (ResNet) in identifying diseases in grape and potata leavess. It employs a database containing high-resolution images of healthy and diseased grape leaves, including conditions like leaf blight, and grape and potata leaves browny mildew. Data pre-processing methods are used to standardize and enhance the datasets for model training and evaluation. The study implements and fine-tunes three DL classifiers—CNN, Efficient Net, and ResNet—using transfer learning. To assess the models' performance in disease classification, the dataset is divided into training and validation subsets. Metrics such as accuracy, recall, precision, and F1-score are used to evaluate the models' predictive capabilities. The experimental results show that CNN achieved 94% accuracy, ResNet attained the highest efficiency with 96% accuracy, and Efficient Net reached 97% accuracy.
Why it matches plant phenotyping methodsブドウ・ジャガイモ葉の病害状態を画像から分類する深層学習手法を比較・評価しており、植物病害フェノタイピングが中心的な技術課題である。
titleComparative Analysis of CNN, EFFICIENTNET and RESNET for Grape and Potato leaves Disease Prediction: A Deep Learning Approach.
The agricultural sector in Bangladesh is a cornerstone of the nation's economy, with key crops such as rice, corn, wheat, potato, and tomato playing vital roles. However, these crops are highly vulnerable to various leaf diseases, which pose significant threats to crop yields and food security if not promptly addressed. Consequently, there is an urgent need for an automated system that can accurately identify and categorize leaf diseases, enabling early intervention and management. This study explores the efficacy of the latest state-of-the-art object detection model, YOLOv8 (You Only Look Once), in surpassing previous models for the automated detection and categorization of leaf diseases in these five major crops. By leveraging modern computer vision techniques, the goal is to enhance the efficiency of disease detection and management. A dataset comprising 19 classes, each with 150 images, totaling 2850 images, was meticulously curated and annotated for training and evaluation. The YOLOv8 framework, known for its capability to detect multiple objects simultaneously, was employed to train a deep neural network. The system's performance was evaluated using standard metrics such as mean Average Precision (mAP) and F1 score. The findings demonstrate that the YOLOv8 framework successfully identifies leaf diseases, achieving a high mAP of 98% and an F1 score of 97%. These results underscore the significant potential of this approach to enhance crop disease management, thereby improving food security and promoting agricultural sustainability in Bangladesh.
Why it matches plant phenotyping methods植物葉の病害状態を画像から推定するYOLOv8手法の開発・評価が研究の中心であり、植物表現型（病害状態）の計測に該当する。
abstractThis study explores the efficacy of the latest state-of-the-art object detection model, YOLOv8 (You Only Look Once), in surpassing previous models for the automated detection and categorization of leaf diseases in these five major crops.
In this research, plant pathogens are considered as big data because of the numerical counts for high intensity pixels in the images. The research presents an automated approach for early detection of plant diseases using image processing techniques. By analyzing the color features of leaf areas, the k-means algorithm for color segmentation and the Gray-Level Co-Occurrence Matrix (GLCM) are used for disease classification. A novelty of this research is that it illustrates four categories of plants to analyze and compare: (1.) Grain, represented by Rice Plant Leaf Data; (2.) Fruit, represented by banana plant leaf data, (3.) Flower, represented by sunflower plant leaf data; and (4.) Vegetable, represented by potato plant leaf data. Six stages of image processing are applied to real data for diseases of leaf smut for rice, black sigatoka for banana, leaf scars for sunflower, and late blight for potato. Finally, a comparison of the image processing for each of the four plant types, conclusions, and future research directions are presented.
Why it matches plant phenotyping methods葉画像から植物病害を自動検出・分類する画像処理手法が研究の中心であり、植物の病害状態を直接推定しているため、植物フェノタイピング手法として含める。
abstractThe research presents an automated approach for early detection of plant diseases using image processing techniques.
Abstract Agriculture is one of the fundamental components of human civilization, contributing not only to food production but also to economic growth. Early identification of diseases in plants presents a significant challenge, as timely detection is crucial to increasing agricultural production. Incorporating the latest technology, such as artificial intelligence (AI) techniques, in fields can reduce major losses for farmers and also improve productivity. In this paper, we have proposed a Deep Vision transformer and an Explainable AI-based technique to overcome the various diseases in plants. Here, we have used the dataset "Plant Village," as a case study that focuses on two majorly grown crops like: potatoes and tomatoes. Further, we have analyzed nine diseases that affect these crops around the globe, with tomatoes showing six different conditions and potatoes affected by three bacterial diseases. The proposed DVTXAI framework incorporates the Deep vision transforms to detect plant diseases at an early stage. In the experiments, the proposed model achieves an accuracy of 93. 56% for tomatoes and 99.95% for potatoes. Additionally, the model is Explainable AI (XAI), which reveals the transparency mechanism that helps the farmer to make the right decision at an early stage of the crop.
Why it matches plant phenotyping methods植物画像から病害を推定する深層学習・説明可能AIフレームワークが研究の中心であり、植物病害状態の表現型推定手法として評価されている。
abstractwe have proposed a Deep Vision transformer and an Explainable AI-based technique to overcome the various diseases in plants.
An open-source software for field-based plant phenotyping, Precision Plots Analyzer (PREPs), was developed using Window.NET. The software runs on 64-bit Windows computers. This software allows the extraction of phenotypic traits on a per-microplot basis from orthomosaic and digital surface model (DSM) images generated by Structure-from-Motion/Multi-View-Stereo (SfM-MVS) tools. Moreover, there is no need to acquire skills in geographical information system (GIS) or programming languages for image analysis. Three use cases illustrated the software's functionality. The first involved monitoring the growth of sugar beet varieties in an experimental field using an unmanned aerial vehicle (UAV), where differences among varieties were detected through estimates of crop height, coverage, and volume index. Second, mixed varieties of potato crops were estimated using a UAV and varietal differences were observed from the estimated phenotypic traits. A strong correlation was observed between the manually measured crop height and UAV-estimated crop height. Finally, using a multicamera array attached to a tractor, the height, coverage, and volume index of the 3 potato varieties were precisely estimated. PREPs software is poised to be a useful tool that allows anyone without prior knowledge of programming to extract crop traits for phenotyping.
Why it matches plant phenotyping methods植物形質抽出ソフトウェアの開発と複数センサーによる検証が中心であり、圃場画像から草丈・被覆率・体積指標を推定する再利用可能な表現型解析手法である。
abstractAn open-source software for field-based plant phenotyping, Precision Plots Analyzer (PREPs), was developed using Window.NET.
If damaged potatoes are detected promptly during harvest, the spread of potato decay in potato storage warehouses is reduced and timely loss control is achieved. Therefore, damaged potatoes must be identified and removed during harvest. A field collaborative recognition method for thermal infrared imaging of damaged potatoes is proposed in this work. An experimental device was developed to detect and identify three commonly damaged potatoes using this method. First, a heat transfer model for damaged potatoes based on the field synergy theory was established and heat transfer analysis was conducted. The reason for the temperature difference between the damaged and intact parts of potatoes was the difference in convective heat transfer intensity between the two and the hot air, as well as the thermal properties of the potato skin and flesh. Then, the surface temperature distribution of the damaged potato under various hot air inlet angles was obtained using finite element simulation tests. According to the imaging effect of the thermal image, the optimal inlet angle was determined to be 90° vertically. Finally, the operating parameters of the potato-screening device were optimized and analyzed. The optimal parameter combination obtained is as follows: The conveyor belt speed was 0.37 m/s, the hot air speed was 3.5 m/s, and the hot air temperature was 45 °C. Actual experiments were conducted on this device. The experimental results indicated that the accuracy, precision, recall, and F-score evaluation values of detecting damaged potatoes were 96%, 94.6%, 97.6%, and 0.961 respectively. The potato thermal infrared damage detection method can meet the technical requirements of grading detection during potato harvest.
Why it matches plant phenotyping methods熱赤外画像を用いてジャガイモの損傷状態を検出する装置・手法を開発し、実験で性能評価しており、植物状態の取得が中心的です。
abstractA field collaborative recognition method for thermal infrared imaging of damaged potatoes is proposed in this work.
Timely monitoring of potato yield status is crucial for guiding field management and ensuring the sustainability of food trade. In recent years, non-destructive remote sensing techniques have emerged as one of the most promising methods for crop yield monitoring. However, most existing potato yield estimation models have primarily been tested at specific growth stages within a single ecosystem, highlighting the urgent need for a model that can be applied across different ecological environments. In this study, we developed a semi-physical model based on hierarchical linear modeling (HLM) to automatically correct yield estimation based on remotely sensed vegetation indices using environmentally relevant variables such as net solar radiation at the surface (ssr), air temperature at 2 m above the surface (t2m), and soil water content in the root zone (swvl). The accuracy and transferability of the model were further evaluated by comparing it with aboveground destructive sampling methods, conventional empirical models, and machine learning approaches. The results demonstrated that site-specific relationships exist between aboveground agronomic traits parameters like biomass and leaf area index (LAI) with respect to yield estimation. Conventional linear statistical and machine learning methods faced challenges in transferring their constructed yield estimation models across regions and years. However, the HLM approach exhibited excellent generalization ability across all trial samples. In the middle and later stages of potato growth, the standardized LAI determining index proved to be the most effective vegetation for predicting yield, while ssr, sktₘₐₓ, and shallow swvl were identified as key environmental variables affecting yield. By integrating these variables using HLM modeling techniques, we achieved optimal generalization performance (R² = 0.57, RMSE = 7.65 t/ha, NRMSE = 25.02 % during tuber growth stage; R² = 0.60, RMSE = 7.37 t/ha, NRMSE = 24.13 % during starch accumulation stage). This study underscores the importance of considering environmental factors when constructing a reliable model for estimating potato yield at different spatial and temporal scales using remote sensing technology.
Why it matches plant phenotyping methodsリモートセンシングによるジャガイモ収量推定モデルを開発し、異なる地域・年で精度と転移性を比較評価しており、植物形質の取得・推定手法が研究の中心である。
abstractwe developed a semi-physical model based on hierarchical linear modeling (HLM) to automatically correct yield estimation based on remotely sensed vegetation indices
Potato yield is an important metric for farmers to further optimize their cultivation practices. Potato yield can be estimated on a harvester using an RGB-D camera that can estimate the three-dimensional (3D) volume of individual potato tubers. A challenge, however, is that the 3D shape derived from RGB-D images is only partially completed, underestimating the actual volume. To address this issue, we developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images. CoRe++ is a deep learning network that consists of a convolutional encoder and a decoder. The encoder compresses RGB-D images into latent vectors that are used by the decoder to complete the 3D shape using the deep signed distance field network (DeepSDF). To evaluate our CoRe++ network, we collected partial and complete 3D point clouds of 339 potato tubers on an operational harvester in Japan. On the 1425 RGB-D images in the test set (representing 51 unique potato tubers), our network achieved a completion accuracy of 2.8 mm on average. For volumetric estimation, the root mean squared error (RMSE) was 22.6 ml, and this was better than the RMSE of the linear regression (31.1 ml) and the base model (36.9 ml). We found that the RMSE can be further reduced to 18.2 ml when performing the 3D shape completion in the center of the RGB-D image. With an average 3D shape completion time of 10 milliseconds per tuber, we can conclude that CoRe++ is both fast and accurate enough to be implemented on an operational harvester for high-throughput potato yield estimation. CoRe++'s high-throughput and accurate processing allows it to be applied to other tuber, fruit and vegetable crops, thereby enabling versatile, accurate and real-time yield monitoring in precision agriculture. Our code, network weights and dataset are publicly available at https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git.
Why it matches plant phenotyping methodsRGB-D画像からジャガイモ塊茎の3D形状を補完し、体積・収量を推定する手法を開発・検証しており、植物フェノタイピング手法が研究の中心である。
abstractwe developed a 3D shape completion network, called CoRe++, which can complete the 3D shape from RGB-D images.
Reproduction assets foundThe paper's abstract explicitly states that the authors' code, network weights, and the potato tuber RGB-D/3D point cloud dataset are publicly available at the authors' GitHub repository (UTokyo-FieldPhenomics-Lab/corepp), which is a paper-specific, public, actionable asset for the CoRe++ phenotyping analysis.Code · publicOur code, network weights and dataset are publicly available at https://github.com/UTokyo-FieldPhenomics-Lab/corepp.git .Open asset ↗UTokyo-FieldPhenomics-Lab/corepplines:1-93Plant phenotyping relevance match · UnverifiedCrossref · checked 7 Sept 2026
Spatial information about plant health and productivity are essential when assessing the progress towards Sustainable Development Goals such as life on land and zero hunger. Plant health and productivity are strongly linked to a plant’s phenological progress. Remote sensing, and since the launch of Sentinel-1 (S1), specifically, radar-based frameworks have been studied for the purpose of monitoring phenological development. This study produces insights into how crop phenology shapes S1 signatures of PolSAR features and InSAR coherence of wheat, canola, sugar beet. and potato across multiple years and orbits. Hereby, differently smoothed time series and a base line of growing degree days are stacked to estimate the patterns of occurrence of extreme values and break points. These patterns are then linked to in situ observations of phenological developments. The comparison of patterns across multiple orbits and years reveals that a single optimized fit hampers the tracking capacities of an entire season monitoring framework, as does the sole reliance on extreme values. VV and VH backscatter intensities outperform all other features, but certain combinations of phenological stage and crop type are better covered by a complementary set of PolSAR features and coherence. With regard to PolSAR features, alpha and entropy can be replaced by the cross-polarization ratio for tracking certain stages. Moreover, a range of moderate incidence angles is better suited for monitoring crop phenology. Also, wheat and canola are favored by a late afternoon overpass. In sum, this study provides insights into phenological developments at the landscape level that can be of further use when investigating spatial and temporal variations within the landscape.
Why it matches plant phenotyping methodsSentinel-1レーダー特徴量とInSARコヒーレンスを用いて作物のフェノロジーを追跡し、複数年・軌道・特徴量間で性能を比較しており、植物状態の取得・推定方法が中心である。
abstractThis study produces insights into how crop phenology shapes S1 signatures of PolSAR features and InSAR coherence of wheat, canola, sugar beet. and potato across multiple years and orbits.
Agriculture plays a vital role in Bangladesh's economy. It is essential to ensure the proper growth and health of crops for the development of the agricultural sector. In the context of Bangladesh, crop diseases pose a significant threat to agricultural output and, consequently, food security. This necessitates the timely and precise identification of such diseases to ensure the sustainability of food production. This study focuses on building a hybrid deep learning model for the identification of three specific diseases affecting three major crops: late blight in potatoes, brown spot in rice, and common rust in corn. The proposed model leverages EfficientNetB0's feature extraction capabilities, known for achieving rapid high learning rates, coupled with the classification proficiency of SVMs, a well-established machine learning algorithm. This unified approach streamlines data processing and feature extraction, potentially improving model generalizability across diverse crops and diseases. It also aims to address the challenges of computational efficiency and accuracy that are often encountered in precision agriculture applications. The proposed hybrid model achieved 97.29% accuracy. A comparative analysis with other models, CNN, VGG16, ResNet50, Xception, Mobilenet V2, Autoencoders, Inception v3, and EfficientNetB0 each achieving an accuracy of 86.57%, 83.29%, 68.79%, 94.07%, 90.71%, 87.90%, 94.14%, and 96.14% respectively, demonstrated the superior performance of our proposed model.
Why it matches plant phenotyping methods植物病害を画像等の観察から識別する深層学習・SVM手法の構築と性能比較が研究の中心であり、植物の病害状態を推定するフェノタイピング手法に該当します。
abstractThis study focuses on building a hybrid deep learning model for the identification of three specific diseases affecting three major crops: late blight in potatoes, brown spot in rice, and common rust in corn.
Reproduction assets foundThe paper's crop disease image dataset is publicly available on Kaggle (Bangladeshi Crops Disease Dataset), explicitly cited as the open-source image source used for the study's phenotyping/classification experiments. The authors' additionally collected 1334 field images and their analysis code/trained model are not公开;Dataset · publicung-EffNet: Lung Cancer Classification Using EfficientNet from CT-Scan Images
Eng. Appl. Artif. Intell. 2023 126 106902
10.1016/j.engappai.2023.106902
23.
Huang Z.
Su L.
Wu J.
Chen Y.
Rock Image Classification Based on EfficientNet and Triplet Attention Mechanism
Appl. Sci. 2023 13 3180
10.3390/app13053180
24. Available online: https://www.kaggle.com/datasets/nafishamoin/bangladeshi-crops-disease-dataset (accessed on 11 June 2023)
25.
Atila U.
Uçar M.
Akyol K.
Uçar E.
Plant leaf disease classification using EfficientNet deep learning model
Ecol. Inform. 2021 61 101182
10.1016/j.ecoinf.2020.101182
26.
Padol P.B.
Yadav A.A.
SVM classifier-based grape leaf disease detection
Proceedings of the 2Open asset ↗Kaggle · bangladeshi-crops-disease-datasetlines:139-314Plant phenotyping relevance match · UnverifiedOpenAlex · checked 14 Sept 2026
Segment Anything Model (SAM) is a new “foundation model” that can be used as a zero-shot object segmentation method with the use of either guide prompts such as bounding boxes, polygons, or points. Alternatively, additional post processing steps can be used to identify objects of interest after segmenting everything in an image. Here a method is presented using segment anything together with a series of post processing steps to segment potato leaves, called Leaf Only SAM. The advantage of this proposed method is that it does not require any training data to produce its results so has many applications across the field of plant phenotyping where there is limited high quality annotated data available. The performance of Leaf Only SAM is compared to a Mask R-CNN model which has been fine-tuned on a small novel potato leaf dataset. On the evaluation dataset, Leaf Only SAM finds an average recall of 73.1 and an average precision of 73.9, compared to recall of 87.6 and precision of 84.4 for Mask R-CNN. Leaf Only SAM does not perform better than the fine-tuned Mask R-CNN model on the potato leaf dataset, but the SAM based model does not require any extra training or annotation. This shows there is potential to use SAM as a zero-shot classifier with the addition of post processing steps.
Why it matches plant phenotyping methodsジャガイモ葉の画像セグメンテーション手法を開発し、Mask R-CNNと性能比較しており、植物表現型取得法が研究の中心である。
abstractHere a method is presented using segment anything together with a series of post processing steps to segment potato leaves, called Leaf Only SAM.
Why it matches plant phenotyping methods植物病害を画像から識別する深層学習手法について、圃場・実験室条件、モデル構成、パラメータ規模、作物別モデルを比較評価しており、病害状態の推定手法の技術評価が中心である。
abstractIn this study, we aimed to evaluate disease identification accuracy under Lab, Field, and Mixed (Lab and Field) conditions using an assembled data set encompassing 14 diseases of apple ( Malus × domestica Borkh.), potato ( Solanum tuberosum L.), and tomato ( Solanum lycopersicum L.).
Agriculture is a crucial industry to humankind's continued existence. Simultaneously, digitalization's pervasive influence made it simpler to accomplish previously challenging jobs in a wide range of disciplines. The agriculture industry, for both the farmer and the consumer, would greatly benefit from technological and digital adaptation. Through the use of technology and consistent monitoring, illnesses can be detected early on and removed, resulting in a higher yield. The economic, social, and political lives of farmers and the entire agricultural industry are profoundly impacted by the health and productivity of their crops. Therefore, in order to detect the illnesses at the proper moment, it is essential to conduct careful monitoring at different phases of crop growth. However, humans may require more than their natural attire, and there may be situations when doing so would be deceiving. Accurate identification requires a system that can automatically recognise and categorise the numerous illnesses that can affect a given crop. The current proposed framework was inspired by this train of thought. The suggested framework is primarily concerned with the transfer learning phenomena based on VGG16, and the "Plant Village" dataset, which contains both damaged and healthy potato and tomato leaves, is being explored for implementation. Keywords: Transfer learning, VGG16, Plant Village.
Why it matches plant phenotyping methods植物葉の病害状態を画像から分類する計算機手法が研究の中心であり、VGG16転移学習による提案フレームワークを扱っているため。
abstractAccurate identification requires a system that can automatically recognise and categorise the numerous illnesses that can affect a given crop.
Hyperspectral imaging has emerged as a pivotal technology in agricultural research, offering a powerful means to non-invasively monitor stress factors, such as drought, in crops like potato plants. In this context, the integration of attention-based deep learning models presents a promising avenue for enhancing the efficiency of stress detection, by enabling the identification of meaningful spectral channels. This study assesses the performance of deep learning models on two potato plant cultivars exposed to water-deficient conditions. It explores how various sampling strategies and biases impact the classification metrics by using a dual-sensor hyperspectral imaging systems (VNIR -Visible and Near-Infrared and SWIR—Short-Wave Infrared). Moreover, it focuses on pinpointing crucial wavelengths within the concatenated images indicative of water-deficient conditions. The proposed deep learning model yields encouraging results. In the context of binary classification, it achieved an area under the receiver operating characteristic curve (AUC-ROC—Area Under the Receiver Operating Characteristic Curve) of 0.74 (95% CI: 0.70, 0.78) and 0.64 (95% CI: 0.56, 0.69) for the KIS Krka and KIS Savinja varieties, respectively. Moreover, the corresponding F1 scores were 0.67 (95% CI: 0.64, 0.71) and 0.63 (95% CI: 0.56, 0.68). An evaluation of the performance of the datasets with deliberately introduced biases consistently demonstrated superior results in comparison to their non-biased equivalents. Notably, the ROC-AUC values exhibited significant improvements, registering a maximum increase of 10.8% for KIS Krka and 18.9% for KIS Savinja. The wavelengths of greatest significance were observed in the ranges of 475–580 nm, 660–730 nm, 940–970 nm, 1420–1510 nm, 1875–2040 nm, and 2350–2480 nm. These findings suggest that discerning between the two treatments is attainable, despite the absence of prominently manifested symptoms of drought stress in either cultivar through visual observation. The research outcomes carry significant implications for both precision agriculture and potato breeding. In precision agriculture, precise water monitoring enhances resource allocation, irrigation, yield, and loss prevention. Hyperspectral imaging holds potential to expedite drought-tolerant cultivar selection, thereby streamlining breeding for resilient potatoes adaptable to shifting climates.
Why it matches plant phenotyping methodsジャガイモの水欠乏状態をハイパースペクトル画像と深層学習で識別し、性能評価および重要波長の同定を行っており、植物ストレス表現型の取得・抽出手法が中心である。
abstractHyperspectral imaging has emerged as a pivotal technology in agricultural research, offering a powerful means to non-invasively monitor stress factors, such as drought, in crops like potato plants.
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the pre-processed hyperspectral dataset on Zenodo and the authors' analysis code on GitHub, both with public URLs matching allowed_urls. The SiaPy Zenodo record is a generic open-source library, not a paper-specific asset.Code · publicand code at https://github.com/janezlapajne/manuscripts (accessed on 8 July 2024)Open asset ↗github · janezlapajne/manuscriptslines:104-424Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 7 Sept 2026
Abstract Crop yield production could be enhanced for agricultural growth if various plant nutrition deficiencies, and diseases are identified and detected at early stages. Hence, continuous health monitoring of plant is very crucial for handling plant stress. The deep learning methods have proven its superior performances in the automated detection of plant diseases and nutrition deficiencies from visual symptoms in leaves. This article proposes a new deep learning method for plant nutrition deficiencies and disease classification using a graph convolutional network (GNN), added upon a base convolutional neural network (CNN). Sometimes, a global feature descriptor might fail to capture the vital region of a diseased leaf, which causes inaccurate classification of disease. To address this issue, regional feature learning is crucial for a holistic feature aggregation. In this work, region-based feature summarization at multi-scales is explored using spatial pyramidal pooling for discriminative feature representation. Furthermore, a GCN is developed to capacitate learning of finer details for classifying plant diseases and insufficiency of nutrients. The proposed method, called P lant N utrition Deficiency and D isease Net work (PND-Net), has been evaluated on two public datasets for nutrition deficiency, and two for disease classification using four backbone CNNs. The best classification performances of the proposed PND-Net are as follows: (a) 90.00% Banana and 90.54% Coffee nutrition deficiency; and (b) 96.18% Potato diseases and 84.30% on PlantDoc datasets using Xception backbone. Furthermore, additional experiments have been carried out for generalization, and the proposed method has achieved state-of-the-art performances on two public datasets, namely the Breast Cancer Histopathology Image Classification (BreakHis 40 $$\times $$ × : 95.50%, and BreakHis 100 $$\times $$ × : 96.79% accuracy) and Single cells in Pap smear images for cervical cancer classification (SIPaKMeD: 99.18% accuracy). Also, the proposed method has been evaluated using five-fold cross validation and achieved improved performances on these datasets. Clearly, the proposed PND-Net effectively boosts the performances of automated health analysis of various plants in real and intricate field environments, implying PND-Net’s aptness for agricultural growth as well as human cancer classification.
Why it matches plant phenotyping methods葉の視覚症状から植物の栄養欠乏・病害状態を分類する画像解析手法を新規開発し、複数データセットで評価しており、植物フェノタイピング手法が中心である。
abstractThis article proposes a new deep learning method for plant nutrition deficiencies and disease classification using a graph convolutional network (GNN), added upon a base convolutional neural network (CNN).
The color potato has the function of both a food and vegetable. The color potato not only contains various amino acids and trace elements needed by the human body but also contains anthocyanins. Anthocyanins have many functions, such as antioxidation, inflammation inhibition, vision improvement, and cancer prevention, so colored potatoes are deeply loved by consumers and have good market prospects. However, at present, the detection of anthocyanin content in color potatoes mainly depends on chemical methods, which are time-consuming and laborious, so it is necessary to study a fast and accurate detection method. In this study, microscopic hyperspectral equipment was used to collect the spectral information of the outer skin and inner skin of potatoes. The original spectrum, pretreatment spectrum, and characteristic spectrum variables of the outer skin and inner skin were predicted by the convolution neural network (CNN) algorithm and partial least squares regression (PLS) algorithm, respectively, and the performance of the model was evaluated by the prediction set correlation coefficient (Rp), prediction set root mean square error (RMSEP), correction set correlation coefficient (Rc), correction set root mean square error (RMSEC), and residual prediction deviation (RPD). The results revealed that the inner skin Raw + CNN model constructed under raw spectral data is optimal with Rc = 0.9508, RMSEC = 0.0374%, Rp = 0.9461, RMSEP = 0.2361% and RPD = 4.4933. The inner skin Savitzky-Golay (SG) + Detrend (DET) + CNN model constructed from pre-processed spectral data is optimal with Rc = 0.9499, RMSEC = 0.0359%, Rp = 0.9439, RMSEP = 0.2384%, RPD = 4.6516. The inner skin DET + competitive adaptive reweighted sampling (CARS) +CNN model constructed from the feature-based spectral data was optimal with Rc = 0.9527, RMSEC = 0.0708%, Rp = 0.9457, RMSEP = 0.2711%, and RPD = 4.1623. It can be seen that the Rp, RMSEP, Rc, RMSEC, and RPD values for modeling the spectral information of the inner skin were higher than those of the outer skin under the three different spectral data. The prediction accuracy of the model built by the CNN algorithm was better than the conventional algorithm PLS, the application of the CNN algorithm in inner skin can achieve accurate prediction of anthocyanin content in potato.
Why it matches plant phenotyping methodsジャガイモ組織のマイクロハイパースペクトル画像からアントシアニン含量という植物器官形質をCNN等で推定する測定法を開発・評価しており、表現型取得が中心である。
abstractit is necessary to study a fast and accurate detection method
This paper proposes a study conducted on various techniques that can be employed for the early detection of plant diseases. With exponential growth in the global population, there is a dire need for the detection and prevention of various types of plant diseases such as Mosaic virus in Solanum Lycopersicon (tomato), bacterial spot in Fragaria Ananassa (strawberry), late and early blight in Solanum Tuberosum (potato), huanglongbing in Citrus sinensis (orange), and Isariopsis leaf spot in Vitis vinifera (grapes). These diseases generally lead to lower yields and hence less profit. In the last two decades, there has been rapid development in the fields of image processing and deep learning. Various models of deep learning can be used for plant disease detection. The main objective is that as soon as plant leaf disease appears, there should be one device to monitor the symptoms and detect them over a large field with as much accuracy as possible. This study compares the deep learning models Resnet, MobileNet, and inceptionV3 that are implemented on a large dataset taken from the Kaggle repository. We implemented the models using Google Colaboratory tools, which provide us with Python’s Jupyter notebook that runs on the Google cloud server. The GPU “Tesla T4” and CPU “Intel Xenon” were used during training, validation, and testing respectively. The training and validation accuracy of the InceptionV3 model was 98.78% and 93.94%, respectively. MobileNet classified various plant diseases with training and validation accuracies of 99.57% and 97.31. Similarly, for ResNet, the training accuracy was found to be around 99.62% and the validation accuracy was 97.16%. We hope that this work will provide a helpful resource for other researchers working in the field of agriculture to detect various types of crop diseases. Future work and some challenges still faced are also discussed in this study.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類する深層学習手法を比較評価しており、病害状態の表現型推定と手法検証が研究の中心である。
abstractThis paper proposes a study conducted on various techniques that can be employed for the early detection of plant diseases.
Reproduction assets foundThe paper's plant-disease classification experiments are built entirely on two public leaf-image datasets: the augmented New Plant Diseases Dataset from Kaggle (87.9k RGB leaf images, 38 classes) and the original PlantVillage-Dataset on GitHub. Both are explicitly cited with public URLs and directly constitute the phenDataset · publicWe used the New Plant Disease Dataset (augmented) [18],
which can be found in the Kaggle repository.Open asset ↗Kagglepdf-raw-page:3 lines:1-117Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Jul 2024Computers and Electronics in Agriculture.
Above-ground biomass (AGB) is an important agronomic indicator that reflects crop growth and estimates yield. The AGB estimation using remote sensing becomes a non-destructive, rapid, and alternative method to post-harvest laboratory measurements. However, most of the AGB estimation models constructed based on remote sensing data are difficult to expand regionally, which limits the applicability of the models. This study combined ground-based hyperspectral and meteorological data by using a hierarchical linear modeling (HLM) to construct an AGB estimation model that was generalized across different regions. Experimental data from both regions were acquired and validated, namely from Xiaotangshan Experimental Base, Beijing, 2019 (North China) and Keshan Farm, Qiqihar Branch, Heilongjiang General Bureau of Reclamation, 2022 (Northeast China). Compared to OLS, RFR and GRU, the HLM method was better for estimating potato AGB in different regions with R² = 0.54, RMSE = 429.62 kg/hm², NRMSE = 28.20 %. The results of this study demonstrated that HLM could be used as a powerful method to improve the transferability of AGB estimation at different regions.
Why it matches plant phenotyping methodsリモートセンシングのハイパースペクトルデータからジャガイモの地上部バイオマスを推定するモデルを開発・検証し、地域間の性能と転移性を比較しているため、植物形質推定手法が中心です。
abstractThe AGB estimation using remote sensing becomes a non-destructive, rapid, and alternative method to post-harvest laboratory measurements.
Potatoes (Solanum tuberosum L.) are one of the world's major staple crops. In stored potatoes, Pectobacterium carotovorum subsp carotovorum causes soft rot. As a result of the rapid spread of the disease during post-harvest storage, potato production suffers huge losses. By detecting disease early and controlling it promptly, losses can be minimized. The profile of volatiles of plants can be altered by phytopathogens. Identifying unique volatile organic compounds (VOCs) as biomarkers for early disease detection has attracted considerable research attention. This study compared the VOC profiles of healthy and soft rot inoculated potatoes (cv. "Kufri Pukhraj") over a time course using gas chromatography-mass spectrometry (GC-MS). It was found that there was a differential emission of 27 VOCs between healthy non-inoculated potatoes and soft rot inoculated potatoes. Among 27 VOCs, only five (1-octen-3-ol, 2-methylisoborneol, 3-octanone, 1,4-dimethyladamantane, and 2-methyl-2-bornene) were found exclusively in soft rot inoculated potatoes, suggesting them potential biomarker for non-destructive prediction of soft rot disease in potatoes. Reactive oxygen species (H 2 O 2 ) and phytohormone methyl-jasmonate (MeJa) levels increased transiently on infection with soft rot. The analysis of the primary metabolism of soft rot infected tubers at three different stages suggests metabolic reprogramming that occurs at the early stage of infection, possibly leading to biomarker volatile emission. Based on these results, it appears that the initial potato-soft rot bacteria interaction initiates metabolic reprogramming mainly through H 2 O 2 and the MeJa signalling pathway. In asymptomatic potatoes, these biomarkers may be promising candidates for non-destructive detection of soft rot at an early stage. These biomarkers can be used to develop an e-nose sensor to predict soft rot in the future.
Why it matches plant phenotyping methods植物体の揮発性成分を用いて、無症状のジャガイモ塊茎における軟腐病状態を非破壊推定するバイオマーカー手法が研究の中心であり、病害表現型の取得・予測に該当する。
titleEarly asymptomatic prediction of potato soft rot disease using phytohormone-induced volatile biomarkers.
Plant diseases are a serious threat to crop production worldwide, causing economic losses and food insecurity. Early and accurate detection of these diseases is important for appropriate intervention and better product health. In this paper, we present the development of a mobile application for the detection of plant diseases aimed at three major crops: potato, tomato and corn. This application uses a convolutional neural network (CNN) trained on a complete set of images to classify plant leaves into healthy and dead leaves. This model was developed using the Teachable Machine friendly platform and then converted to the TensorFlow Lite model for optimal deployment on Android devices. The Android Studio app allows users to capture images directly or select them from the gallery. The captured images are analyzed by a pre-trained CNN model to provide real-time classification results. If a leaf dies, the application will display the name of the disease and specific symptoms, recommended fertilizers for treatment and possible treatment methods. This study demonstrates the potential of using CNN approaches for plant disease detection in mobile application settings. This application has the potential to empower farmers and agricultural officers with easy-to-use tools to identify early diseases, allowing them to act in time to improve crop health and yields.
Why it matches plant phenotyping methods植物葉画像から健全・枯死および病害を分類するCNNとモバイルアプリの開発が研究の中心であり、植物の病徴状態を直接推定するフェノタイピング手法に該当する。
abstractIn this paper, we present the development of a mobile application for the detection of plant diseases aimed at three major crops: potato, tomato and corn.