The genetic identity of coffee cultivars is fundamental to the specialty coffee sector, where premium prices are paid under the assumption that the purchased planting material corresponds to the declared variety. However, many producing countries lack the certification infrastructure necessary to guarantee this identity in their informal seed systems, exposing producers to undetected varietal non-conformity. In this study, we examine a case from a specialty coffee ( Coffea arabica L.) farm in southern Ecuador where seeds labeled as Sidra (USD 100/kg) and Gesha (USD 500/kg) were purchased without genetic or phytosanitary certification. Using a combination of SSR-based DNA fingerprinting and quantitative morphological characterization, including plant architecture, leaf functional traits, and fruit characteristics, we documented varietal identity and assessed the discriminant capacity of morphological traits across the four resulting morphotypes. Using eleven microsatellite markers for SSR fingerprinting, we found that two of the four morphotypes did not match their declared commercial identity. One plant sold as Sidra was identified as compatible with Batian, a composite variety of Kenyan origin that is genetically unrelated to Ethiopian landraces. The plants acquired as Gesha corresponded to a pure Ethiopian landrace that is genetically similar to, but not identical to, the Panamanian Geisha reference accession T.02722. Only two morphotypes were confirmed as Sidra. Furthermore, the placement of Sidra within the Core Ethiopia genetic group is consistent with prior population-level analyses and with its likely status as a selected Ethiopian landrace rather than a variety of hybrid origin. Morphological linear discriminant analysis achieved 82.4% overall classification accuracy under leave-one-out cross-validation (LOOCV), with internode length dominating the first discriminant function (LD1 = 66.6%). These results demonstrate that varietal nonconformity in the specialty coffee seed sector can extend to the inadvertent introduction of genetically unrelated material and underscore the urgent need for accessible seed certification.
Why it matches plant phenotyping methodsコーヒー品種識別のための形態形質測定と判別分析が研究の中心であり、形態形質の識別性能をLOOCVで検証しているため、植物フェノタイピング手法の適用・検証に該当する。
abstractquantitative morphological characterization, including plant architecture, leaf functional traits, and fruit characteristics
Reproduction assets foundThe paper's morphological/functional trait dataset (used for the phenotyping and LDA analysis) is explicitly stated to be publicly available on Figshare (10.6084/m9.figshare.32841344). No author analysis code repository is stated; other URLs in the text are generic libraries or cited prior work.Dataset · publicThe morphological and functional trait dataset generated and analyzed in this study is publicly available in the Figshare repository at 10.6084/m9.figshare.32841344 .Open asset ↗Figshare · 10.6084/m9.figshare.32841344lines:526-568Plant phenotyping relevance match · UnverifiedEurope PMC · checked 5 Sept 2026
Coffee is a major export earner for Uganda, raking in over USD 2 billion in 2025. The global price of coffee is tagged to the perceived quality in the cup which in turn is affected by the chemical composition of the green bean. Breeding for market-preferred Arabica coffee varieties is a major objective of coffee breeding programs. Determination of coffee bean chemical constituents is routinely done through expensive, slow and tedious laboratory procedures, making it unsustainable of resource-limited public sector coffee breeding programs. Here, we demonstrate the use of near-infrared spectroscopy (NIRS) and the machine learning algorithms partial least squares (PLS), random forest (RF) and support vector machine (SVM) for the prediction of caffeine, protein and trigonelline in Arabica coffee. NIRS provides a fast, accurate and reliable method of simultaneously predicting multiple sample constituents. Ripe coffee cherries were picked from 172 farmers' fields, air dried in the laboratory at room temperature and processed to green beans. NIRS spectra were taken on the milled green bean at 400-2500 nm, with a 0.5 nanometer (nm) step. Reference data for caffeine, protein and trigonelline were collected on the same sample scanned with NIRS. A set of 12 spectral pretreatments were applied prior to making calibrations with the PLS, RF and SVM algorithms and 70% of the data as a training set and 30% as a test set. Caffeine content of reference samples ranged from 1.94-3.0 g/100 g, protein content ranged from 11.16-15.94% while trigonelline ranged from 0.94-1.23 g/100 g. The best calibrations for all algorithms and analytes were obtained using raw (untreated) spectra, which gave the same results as the Savitzky-Golay (SG) pretreatment. For caffeine, the best model (R 2 p = 0.89, RMSEP = 0.007, RPD = 3.34) was obtained with the SVM algorithm, while for protein, the best model (R 2 p = 0.98, RMSEP = 0.14, RPD = 6.92) was obtained using the PLS algorithm. Finally, for trigonelline, all three models had very high prediction accuracies (R 2 p = 0.98-0.99, RMSEP = 0.007-0.009, RPD = 8.53-10.52). Collectively, these results demonstrate the potential of using NIRS for rapid and simultaneous prediction of coffee green bean constituents to aid selection decisions.
Why it matches plant phenotyping methodsコーヒー生豆の化学的形質を対象に、NIRSと機械学習による予測モデルを開発・検証しており、形質取得・推定法が研究の中心である。育種選抜への利用も明示されている。
abstractwe demonstrate the use of near-infrared spectroscopy (NIRS) and the machine learning algorithms partial least squares (PLS), random forest (RF) and support vector machine (SVM) for the prediction of caffeine, protein and trigonelline in Arabica coffee.
This study aims to improve the performance of the Convolutional Neural Network (CNN) algorithm in detecting coffee leaf diseases using the Inception V3 architecture. The main challenge of this classification is the subtle visual similarity in color, texture, and symptom patterns between diseases. To overcome this, Inception V3 is implemented because of its superiority in multi-scale feature extraction through convolution factorization which reduces parameters while increasing accuracy. The dataset used consists of 1,120 images, evenly distributed into four classes (three types of diseases and one healthy class, each with 280 images), with a training, validation, and test data split ratio of 896:112:112. As a comparison, a conventional basic CNN architecture consisting of 3 convolution layers (3 X 3, stride 1), 3 max-pooling, and 1 dense layer, trained with the same hyperparameters (Adam optimizer, learning rate 0.001, batch size 32) is used. The experimental results show a significant performance improvement; Model accuracy increased from 74.4% on a standard CNN to 97.0% after integrating Inception V3. The scientific contribution of this research lies in mapping overlapping visual characteristics of coffee diseases through multi-scale feature optimization, which demonstrates that computational efficiency can go hand in hand with accuracy improvements on complex agricultural image datasets. These findings confirm that the Inception V3 architecture provides a robust and efficient solution for automating plant disease diagnosis in the field.
Why it matches plant phenotyping methodsコーヒー葉の病徴を画像から分類するCNN手法の改善・比較が研究の中心であり、植物病害状態の画像ベース表現型推定に該当する。
abstractThis study aims to improve the performance of the Convolutional Neural Network (CNN) algorithm in detecting coffee leaf diseases using the Inception V3 architecture.
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 13 Sept 2026
Modern agriculture operates at an unprecedented crossroads, it must simultaneously accelerate crop yields to feed an expanding global population and adapt to the severe, fluctuating pressures of climate change, structural soil degradation, abiotic water deficits, and evolving biological threats. Historically, selecting resilient crop varieties and implementing field-scale management strategies relied extensively on destructive, labor-intensive, and fundamentally subjective visual metrics. This manual processing approach has long been recognized as the primary operational bottleneck in agricultural advancement.To bridge the gap between rapidly expanding genomic data and actual field performance, the systematic, non-destructive quantification of structural and functional plant traits, plant phenotyping, has emerged as a transformative frontier. By integrating high-throughput engineering, multi-scale remote sensing, deep learning, and advanced molecular biology, modern phenotyping transitions crop science away from qualitative estimation toward highly reproducible, multidimensional data frameworks. This Research Topic presents new advances in advanced 3D reconstruction and deep semantic segmentation at the seedling stage; amodal fruit segmentation, morphological extraction, and early water-stress diagnostics; high-throughput in-field seedling counting and dynamic density modeling; multimodal foundation models, network pruning, and intelligent phytoprotection; aerial and spaceborne remote sensing for canopy analysis and weed monitoring; plant physiology, functional spectroscopy, and functional genomics under abiotic stress; and automated diagnostics for real-time orchard scouting and vineyard management.Automating the characterization of complex spatial layouts under controlled or greenhouse environments is essential for early variety selection and early-stage structural evaluation. Several contributions within this volume provide key breakthroughs in navigating overlapping tissues, severe occlusions, and low-contrast edge regions. showcases how substituting standard convolutions with deformable convolutions enables deep neural networks to accurately isolate the main stem of mature, high-density crops like soybeans. This architecture overcomes the traditional challenges of color mimicry and severe occlusion by pods and leaves, achieving an outstanding mIoU of 90.58% and providing reliable indices for lodging resistance and structural yield modeling (R 2 = 0.9746).Accurately extracting fruit morphology under commercial greenhouse conditions remains heavily constrained by overlapping crop structures, foliage cover, and variable shadows. Simple semantic masks typically fail when a target fruit is partially blocked, leading to a loss of key volumetric data.To resolve the challenge of hidden boundaries, Li, Yin, et al. (2025) developed CGA-ASNet, a specialized RGB-D amodal segmentation network driven by a Contextual and Global Attention (CGA) module designed to restore occluded tomato regions. Trained on a high-fidelity synthetic greenhouse dataset (Tomato-sim) generated via NVIDIA Isaac Sim's Replicator Composer and optimized with a mean coordinate fusion algorithm for real-world validation, this architecture expands the network's receptive field to predict the complete, hidden circular forms of occluded tomatoes, achieving an F@0.75 score of 94.2 and an amodal mIoU of 82.4%. This proves that simulation-to-real (Sim2Real) domain pathways can successfully decode full physical volumes under dense commercial canopies.Complementing this structural restoration, Yang, Li, et al. (2025) designed an integrated diagnostic framework to identify early water stress dynamics in greenhouse tomatoes. Built upon an optimized YOLOv11n core, their system integrates adaptive kernel convolutions (AKConv) into the network backbone's C3k2 modules and implements a recalibration feature pyramid detection head based on the specialized P2 small-target layer. This combination achieved a 5.4% increase in mAP50-95 for identifying fine phenotypic parts. By applying automated geometric analysis to the extracted bounding boxes, the system extracts plant heights and petiole count with low relative errors, feeding these phenotypic parameters into a Random Forest classification routine that flags water-stressed plants with 98% accuracy to guide targeted, automated drip irrigation.Accurate plant stands during early vegetative stages represent the foundational metric required to establish true field emergence rates, validate seed vigor across diverse breeding blocks, and perform early yield predictions.To solve the challenges of small targets, extreme spatial density, and adjacent leaf overlap, Zang et al. (2025) designed DM_IOC_fpn, a wheat seedling counting framework that balances local and global contextual features. By structuring a point-annotated dataset and embedding a densityenhanced encoder module, their network balances micro-scale spatial limits with macro-scale canopy structures. Optimized through a combined loss function tracking counting, classification, and regression parameters, this architecture achieved low error scores (RMSE = 2.91; MAE = 2.23), outperforming standard object-detection benchmarks in complex field environments.At the same time, scaling up to real-time aerial monitoring required major reductions in model complexity to support resource-constrained edge computers on autonomous aerial platforms. Feng, Nie, and Li (2025) engineered an ultra-lightweight YOLOv8n variant tailored for real-time maize seedling counting from high-speed UAV RGB overflights. By reparametrizing RepConv with HGNetV2, they constructed a lean Rep_HGNetV2 backbone, integrated a Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature alignment, and implemented a Task Dynamically Aligned Detection Head (TDADH). This architecture compressed total model parameters by 47% and reduced weight sizes to 3.5 MB while maintaining a 96.5% detection accuracy and an ultra-fast processing speed of 146.3 FPS, paving the way for low-cost, real-time field scouting.Automated phytoprotection requires machine-vision architectures capable of generalizing across highly diverse species, complex field conditions, and varying computational boundaries. A significant subset of the published papers addresses these challenges through foundation model adaptation, multi-modal alignment, and efficient network compression.A major paradigm shift presented in this collection involves moving away from task-specific training and toward foundation model adaptation. Chen, Ruan, et al. (2026) introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation across diverse species (such as coffee and black gram). By incorporating a Spatial Prior Module (SPM), their approach surpassed standard benchmark networks by over 10.5% in IoU while reducing inference times by approximately 93.6%, demonstrating that highparameter foundation models can be highly optimized for resource-constrained edge devices in real-time scouting.To solve the perennial problem of limited training data for rare or emerging crop diseases, Cooper et al. ( 2026) developed an ingenious synthetic data generation pipeline. Combining 3D procedural leaf modeling in Blender with diffusion-based disease synthesis (Stable Diffusion fine-tuned with LoRA and ControlNet), they synthesized highly accurate plant disease images with perfect groundtruth annotation masks. When deployed in low-resource data settings, combining these synthetic pipelines with restricted real-world datasets consistently drives significant improvements in downstream segmentation tasks. To tackle specific, complex pathologies, Xu, Chang, et al. (2025) developed the TSSC deep learning model, which embeds three-neighbor channel attention paired with a complementary squeeze-and-excitation mechanism. This specific architecture minimizes structural degradation risks while pushing classification accuracy to 99.61% for highly complex pea leaf pathologies. Similarly, Feng, Liu, et al. (2025) tackled overlapping leaf occlusions and small lesion footprints in citrus groves with YOLO-Citrus, an optimized framework integrating C3K2-STA, ADown modules, and a Wise-Inner-MPDIoU loss function to strike a balance between edge computational constraints and field deployment.UAVs and high-resolution satellite imagery have expanded the operational scale of phenotyping from individual pots to vast breeding blocks and commercial fields, allowing researchers to capture macro-dynamic parameters over time.In complex canopy systems that defy standard top-down aerial sensing, such as single-staked white Guinea yams, Iseki et al. (2026) demonstrated the distinct advantage of utilizing multi-angle (combined nadir and oblique) UAV imaging configurations. When coupled with support vector regression, this method captures complementary canopy-structure information to model shoot biomass trajectories (R 2 = 0.79) across multiple years and management zones. These nondestructive, time-series datasets enabled the fitting of genotype-specific Richard's growth curves using Bayesian inference, isolating valuable genetic variations in early growth allocation.To capture full-season vertical physiological changes over large scales, Li, Yue, and Luo (2025) developed a hybrid CNN-LSTM-Attention (CLA) model designed to estimate the full-period Leaf Area Index (LAI) in rice using multi-temporal UAV multispectral imagery. By using the CNN layer to extract instantaneous spatial features, the LSTM block to process seasonal time-series intervals, and a self-attention mechanism to weight critical growth transitions, their platform achieved a high coefficient of determination (R 2 = 0.92) and kept relative root mean square errors (RRMSE) below 9%. This network minimized soil background noise during early vegetative stages (LAI values 1-
Why it matches plant phenotyping methods植物フェノタイピングの技術動向を扱うEditorialであり、画像解析、UAVセンシング、深層学習、形質抽出などの方法が中心的に整理されている。
Saudi Arabia is expanding its domestic coffee sector under Vision 2030, yet coffee farming remains vulnerable to leaf diseases and pest damage. Image-based artificial intelligence studies conducted under Saudi field conditions remain limited, particularly in relation to assessing image-based visible disease severity. This study designs a hierarchical deep learning framework for screening coffee leaf diseases using field-collected images of Saudi coffee leaves. Three tasks were addressed: binary health status classification, four-class disease or pest damage identification, and binary visible severity classification. A dataset of 550 RGB images was collected from Al-Dayer Governorate, Jazan, under natural field conditions. ResNet50, DenseNet121, and EfficientNet-B0 were evaluated via transfer learning in two phases: a Saudi-only phase and an integrated phase that combined Saudi data with selected JMuBEN and JMuBEN2 samples. In the Saudi-only phase, ResNet50 achieved 96.47% accuracy for binary classification, while DenseNet121 achieved 68.66% and 78.12% for disease and visible severity classification, respectively. In the integrated phase, performance improved to 99.74%, 97.76%, and 97.37%. These integrated-phase results are interpreted as evidence that dataset expansion and increased visual diversity can improve model performance, rather than as definitive estimates of field deployment performance. The results show that binary classification is feasible under limited local data, whereas fine-grained disease classification is more constrained by dataset size and class imbalance. Grad-CAM visualizations were used to support qualitative interpretability and should not be interpreted as biological validation of disease localization. The framework is positioned as a decision-support screening approach that requires further expert-validated, multi-farm, and multi-season evaluation before deployment.
Why it matches plant phenotyping methodsコーヒー葉の画像から健康状態、病害・害虫損傷、可視的重症度を推定する階層的深層学習フレームワークが研究の中心であり、植物病害状態の画像ベース表現型推定に該当する。
abstractThis study designs a hierarchical deep learning framework for screening coffee leaf diseases using field-collected images of Saudi coffee leaves.
In complex mountainous environments, the asynchronous development between external color turning and internal sugar accumulation (often termed "false maturity") in coffee cherries poses a severe challenge to post-harvest quality sorting and the consistency of final coffee products. To overcome the limitations of single-phenotype detection in raw material screening, this study proposed a multimodal quality discrimination framework integrating fruit hyperspectral imaging, micro-topography, and plant physiological characteristics. Taking typical mountain-grown fresh coffee cherries as the research object, and after comparing various spectral preprocessing and feature dimensionality reduction algorithms, the multimodal fusion efficacy of nine machine learning classifiers was systematically evaluated. The results demonstrated that: (1) Full-spectrum difference analysis quantitatively confirmed the limitations of visual harvesting; spectral reflectance differences between high- and low-sugar fruits were highly concentrated in the red and red-edge regions, with the maximum difference precisely located at 676 nm. (2) Compared to the single-spectrum model (mean accuracy of 75.93%), the fully fused Multilayer Perceptron (MLP) network effectively mitigated background noise induced by heterogeneous environments, improving the mean classification accuracy to 77.22% with a mean Area Under the Curve (AUC) of 0.827. (3) Correlation analysis clarified the quantitative association between topography and quality; micro-topographic slope (r = 0.346) was identified as the key environmental driver of spatial differentiation in fruit sugar content, while plant chlorophyll A content (r = 0.183) exhibited a corresponding physiological response trend. This study not only explains the root cause of visual assessment failure from a physical optics perspective but also reveals the spatial variation laws of quality driven by micro-topography, providing preliminary data support for the intelligent sorting of raw materials and ensuring post-harvest quality consistency of mountainous crops.
Why it matches plant phenotyping methodsコーヒー果実の糖含量という植物器官形質を、ハイパースペクトル画像・微地形・生理情報の融合で非破壊推定する方法が研究の中心であり、前処理、特徴削減、複数分類器の性能比較も行っている。
abstracta multimodal quality discrimination framework integrating fruit hyperspectral imaging, micro-topography, and plant physiological characteristics
Introduction Nutrient deficiencies in coffee plants significantly impact bean quality and yield, making timely detection crucial for successful cultivation. Current assessment methods rely on manual inspection, which is labor-intensive and time-consuming, posing challenges for large-scale field management. This approach often results in inconsistent evaluations and delayed interventions. Methods This study presents CoNutriNet, an automated deep learning architecture that integrates DenseNet121 with a novel Graph-Enhanced Attention Feature Network (GEAFNet) for classifying nutrient deficiencies in coffee leaves. DenseNet121 provides deep hierarchical and regional feature representation, while GEAFNet captures local, fine-grained spatial features through Inception, Ghost, and Efficient Channel Attention (ECA) modules. Furthermore, a Graph Convolutional Network (GCN) is included to model spatial dependencies and structural variations between leaf regions. Feature representations from both pathways are concatenated and refined using a Coordinate Attention (CA) module to enhance discriminative capability. Results Evaluation on the CoLeaf dataset demonstrates that CoNutriNet achieves an accuracy of 94.5%. The integration of lightweight attention mechanisms, dense connectivity, and graph-based modeling improves both performance and computational efficiency. Conclusion These results indicate that CoNutriNet achieves and efficient performance in nutrient deficiency detection in coffee crops, highlighting its potential for deployment in agricultural environments to support precision farming and optimize yield.
Why it matches plant phenotyping methodsコーヒー葉の栄養欠乏という植物状態を画像から分類する深層学習手法を開発し、データセットで性能評価しており、表現型取得・推定が研究の中心である。
abstractThis study presents CoNutriNet, an automated deep learning architecture that integrates DenseNet121 with a novel Graph-Enhanced Attention Feature Network (GEAFNet) for classifying nutrient deficiencies in coffee leaves.
Reproduction assets foundThe paper's phenotyping analysis (coffee nutrient deficiency classification) is performed on publicly available leaf image datasets. The data availability statement links a Mendeley Data repository containing the analyzed data, which is an allowed URL. No author analysis code or trained model checkpoints are explicitlyDataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://data.mendeley.com/datasets/brfgw46wzb/1Open asset ↗brfgw46wzb/1lines:866-910Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Plant disease is a serious threat to agricultural productivity and food security worldwide. Traditional diagnostic methods such as manual observation and laboratory testing are time-consuming, labor-intensive and error prone. The emergence of artificial intelligence (AI) and deep learning (DL) offer scalable solutions for precision agriculture in plant disease detection using advanced computational techniques to process large datasets. Hybrid deep learning architecture integrates Convolutional Neural Networks (CNNs) along with Artificial Neural Networks (ANNs) can leverage both visual and contextual data to improve detection performance. The hybrid CNN-ANN model was developed to analyze visual data (plant images) and contextual data (environmental and soil metrics). The CNN module extracted spatial and textural features from plant images, while the ANN module processed environmental parameters. These outputs were fused into a unified feature vector for disease classification. A total of 15 plant species and their associated diseases were analyzed using 200-270 training samples and 150-190 testing samples for each disease across a total of 1000 images. The model was judged by metrics such as detection accuracy, AUC, sensitivity etc. Data augmentation, pre-trained architectures (e.g., ResNet50) and early stopping techniques were utilized to improvise model performance. The hybrid model saliently achieved detection accuracy consistently above 87% with majority of diseases surpassing 90%. Highperforming cases like Rice Blast (92.5%), Tomato Early Blight (93.8%), and Coffee Rust (93.0%), with AUC values of 0.93 or higher, sensitivity exceeding 94% and specifically above 90%. Diseases of Sugarcane Red Rot and Tea Blister Blight exhibited sensitivities of 92.4% and 92.1% and specificities of 91.1% and 90.5% respectively. Moderate accuracy for Coconut Bud Rot (87.5%) and Mustard Alternaria Blight (87.8%) was due to smaller training sample sizes.
Why it matches plant phenotyping methods植物画像から病害状態を分類するハイブリッドCNN-ANN手法を開発し、精度・AUC・感度などで評価しており、病害フェノタイピング手法が研究の中心である。
abstractThe hybrid CNN-ANN model was developed to analyze visual data (plant images) and contextual data (environmental and soil metrics).
Reproduction assets foundThe paper's plant disease detection model was trained on public plant image datasets: the PlantSeg dataset (Zenodo record 13958858, DOI 10.5281/zenodo.13293891) and the UCI Machine Learning Repository Plants dataset. Both are cited in Materials and Methods as sources of the visual data used for the CNN module. No code,Dataset · publicebao (ZiranKexueBan)/Journal of
Huazhong University of Science and Technology
(Natural Science Edition). 2021;49(8).
37. Ma C, Mu X, Sha D. Multi-Layers Feature Fusion of
Convolutional Neural Network for Scene
Classification of Remote Sensing. IEEE Access.
2019;7.
38. Hämäläinen W.Plants Dataset[Internet]. 2024.
Available from:
https://archive.ics.uci.edu/dataset/180/plants
39. WeiT. PlantSeg: A Large-Scale In-the-wild Dataset
for Plant Disease Segmentation [Internet]. 2018.
Available from: https://zenodo.org/records/13958858Open asset ↗180pdf-raw-page:15 lines:1-48Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Objectives Nutritional deficiency in coffee is a major problem that compromises plant health, crop yield, and bean quality, directly threatening the economies of coffee-dependent regions. Traditional detection methods are primarily manual, time-consuming, and relied upon expert availability. Methods This study introduces a novel Deep Learning (DL)-based dual-track architecture designed for the efficient classification of nutritional deficiencies in coffee leaf. The first track utilizes a MobileNetV3 backbone integrated with a Multi-Convolutional Shape-Aware Kernel (MCSK) block to capture spatially adaptive features from leaf textures and vein patterns. The second track employs a Hierarchical Shuffled Group Attention Network (HSGAN), utilizing Efficient Channel Attention (ECA) and Local Group Attention (LGA) modules to balance fine-grained local variations with broad spatial dependencies. Finally, a Multidimensional Collaborative Attention (MCA) mechanism is applied to the fused features to enhance cross-channel interactions and feature extraction. Results The proposed model was evaluated using the CoLeaf dataset, where it achieved an accuracy score of 96.04%. This performance demonstrates an improvement over existing research and current state-of-the-art models, highlighting the architecture's ability to identify complex nutrient-related patterns in coffee leaves. Conclusion The performance of the proposed DL approach offer a solution for the automated monitoring of coffee plants. By providing a reliable alternative to manual inspection, this method presents the potential to help coffee production and support the agricultural regions worldwide.
Why it matches plant phenotyping methodsコーヒー葉の栄養欠乏という植物状態を画像から分類する深層学習手法を開発・評価しており、表現型取得・推定が研究の中心であるため。
abstractThis study introduces a novel Deep Learning (DL)-based dual-track architecture designed for the efficient classification of nutritional deficiencies in coffee leaf.
Reproduction assets foundThe paper's primary phenotyping asset is the CoLeaf coffee leaf nutrient-deficiency image dataset, which the authors state is publicly available via a Mendeley Data URL matching an allowed URL. No author analysis code or trained model checkpoints are disclosed.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://data.mendeley.com/datasets/brfgw46wzb/1 .Open asset ↗brfgw46wzb/1lines:733-764Plant phenotyping relevance match · UnverifiedCrossref · checked 5 Sept 2026
Efficient crop health monitoring is crucial for global food security. Supervised deep learning approaches are often impractical due to the scarcity of large, labeled datasets. To address this limitation, this study adapts EfficientAD, an unsupervised, label-free anomaly detection framework originally designed for industrial inspection, for agricultural imagery on small datasets. The method utilizes a Patch Description Network (PDN) for localized feature extraction, a student network for local anomalies, and an autoencoder for global structural constraints. Benchmarked against AnoGAN, Pix2Pix, InTra, and Teacher–Student models, the framework demonstrated superior performance on the MVTec AD, PlantVillage, Coffee Leaf, and a custom real-world Sweet Potato dataset. The model achieved perfect area under the receiver operating characteristic curve (AUROC) scores of up to 100% in categories like “Pongamia”, “Potato”, and “Coffee Leaf”. While image-level classification was exceptionally robust, pixel-level localization (AUPRO) proved sensitive to complex agricultural backgrounds. To overcome this, a background interference analysis was conducted using Background Removed (BGRM) and out-of-distribution Background Replaced-Green (BGRP-G) strategies on the custom dataset. Notably, the BGRP-G strategy remarkably improved the image-level AUROC from 88.9% to 99.5% and substantially boosted the pixel-level AUPRO from 47.1% to 61.9%, successfully preserving the boundary integrity of severe structural defects. Achieving millisecond-level latency without complex data augmentation, this adapted label-free framework offers a versatile, highly efficient solution for real-time crop health diagnostics on resource-constrained Edge AI devices.
Why it matches plant phenotyping methods農作物画像から異常・健康状態を抽出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・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 adapts EfficientAD, an unsupervised, label-free anomaly detection framework originally designed for industrial inspection, for agricultural imagery on small datasets.
CoffeeField / plotFruitObject detectionGrowth / development / phenology
Introduction Coffee cherry ripeness assessment is critical for harvesting efficiency and product quality, yet traditional manual inspection methods suffer from subjectivity and low efficiency. Methods To address the challenges of detecting small, occluded, and densely distributed coffee cherries in complex field environments, this study proposes an Occlusion and Density Aware Network (ODANet). Built upon the YOLOv8 framework, ODANet integrates three innovative modules: (1) Condition-Guided Windowed Attention (CGWA), which incorporates occlusion and density maps as auxiliary guidance signals for efficient feature enhancement; (2) Attention-guided Space-Preserving Convolution (ASPC), which employs space-to-depth transformation with cascaded attention to preserve spatial information during downsampling; and (3) Dual-Adaptive Dynamic Upsampling (DADU), which achieves content-adaptive feature reconstruction through dual-branch offset prediction with learnable fusion weights. Results Comprehensive evaluation on a publicly available dataset demonstrates that ODANet achieves state-of-the-art performance among 17 diverse detection architectures, attaining 76.7% mAP@0.5 with a 6.3 percentage point improvement over baseline YOLOv8, while maintaining computational efficiency (8.1 GFLOPs, 30.4M parameters) suitable for real-time deployment. Ablation studies validate the contributions of each module: ASPC improves performance by 2.2%, DADU by 0.6%, and CGWA by 3.5%. Discussion The model demonstrates robust performance across varying lighting conditions, occlusion levels, and growth stages, making it particularly suitable for practical agricultural deployment. This research provides an efficient solution for small object detection in precision agriculture.
Why it matches plant phenotyping methodsコーヒーチェリーの成熟度という植物器官の状態を画像から推定する検出手法を開発し、複数モデル比較・アブレーションで技術的に検証しているため、植物フェノタイピング手法が中心である。
abstractthis study proposes an Occlusion and Density Aware Network (ODANet)
Reproduction assets foundThe paper analyzes a publicly available coffee cherry dataset hosted on Kaggle, explicitly linked in the data availability statement. This is the paper-specific image dataset used for its coffee cherry ripeness detection experiments. No author code or model checkpoints are stated as available.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://www.kaggle.com/datasets/harisyunanda/dataset-coffee-cherry/data .Open asset ↗Kaggle · harisyunanda/dataset-coffee-cherrylines:682-758Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Precise detection of crop leaf damage is essential for real-time plant health monitoring and yield estimation. However, conventional deep learning models often exhibit poor generalization when deployed across varying species and complex, unstructured field environments. To address these limitations, we propose a new modeling paradigm that shifts from traditional task-specific training to foundation model adaptation. Specifically, we introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation. By incorporating a Spatial Prior Module (SPM) and a Projection Module, our approach effectively bridges the gap between general-purpose pre-training and domain-specific requirements. Experimental results on coffee and black gram datasets demonstrate that this paradigm consistently outperforms standard networks, including Unet, Unet++, and SwinUnet. On the coffee leaf dataset, the proposed model achieves an Intersection over Union (IoU) of 78.31% and a Pixel Accuracy of 88.00%, surpassing the baseline Unet by over 10.5% in IoU. Remarkably, the architecture reduces inference time by approximately 93.6% (from 63.41s to 4.07s), proving that high-parameter foundation models can be adapted for extreme computational efficiency in agricultural scenarios. To further validate scalability, we conduct additional experiments on a larger dataset, AMG HS . The proposed paradigm achieves the best overall detection performance while maintaining superior computational efficiency, confirming its robustness under increased data scale. Interpretability analysis reveals that the foundation model backbone effectively captures high-level semantic features of lesions, providing a clear explanation for its superior performance and cross-domain reliability. This research establishes a scalable, high-performance paradigm for intelligent crop protection, demonstrating that coupling customized encoders with foundation models is a superior strategy for cross-domain agricultural tasks.
Why it matches plant phenotyping methods植物葉の病変を画像からセグメンテーションし、葉の損傷状態を定量化する手法の開発・検証が研究の中心であるため。
abstractwe introduce a novel architecture integrating the DinoV3 foundation model with a Unet framework to achieve robust leaf lesion segmentation.
Reproduction assets foundThe paper analyzes two publicly available plant image datasets hosted on Mendeley Data: a coffee leaf rust/leaf miner dataset and a black gram leaf disease dataset, both explicitly linked in the Data Availability Statement. No author analysis code or trained model checkpoints are disclosed.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://data.mendeley.com/datasets/vfxf4trtcg/5; https://data.mendeley.com/datasets/45djgf3p96/1.Open asset ↗html-lines:473-493Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://data.mendeley.com/datasets/vfxf4trtcg/5; https://data.mendeley.com/datasets/45djgf3p96/1.Open asset ↗html-lines:473-493Plant phenotyping relevance match · UnverifiedCrossref · checked 5 Sept 2026
Crop monitoring over large land extensions represents a central challenge in precision agriculture, especially in polyculture contexts where species with different nutritional needs are combined. This study presents a methodology to manage and analyze large volumes of multispectral images captured by unmanned aerial vehicles (UAVs) in order to identify and monitor crops at the plant level. The images are efficiently stored and retrieved using a Hilbert Curve, which reduces the complexity of the search process from O(n2) to O(log(n)) where n represents the number of indexed data points). The system connects to a distributed Structured Query Language (SQL) database, allowing for fast image retrieval based on GPS coordinates and other metadata. Additionally, the Normalized Difference Vegetation Index (NDVI) is calculated using reflectance data from the red and near-infrared channels, adjusted by semantic segmentation masks generated with a U-Net model, which allows for species-specific evaluations. The methodology was evaluated on a 20,000 m2 polyculture farm with coffee, avocado, and plantain crops, using a dataset of 270 aerial images partitioned into 70% for training and 30% for validation. The results show improvements in retrieval speed and precision with the Hilbert Space-Filling Curve (HSFC) approach, and an accuracy of 82.3% and an the Mean Intersection over Union (MIoU) of 68.4% in species detection with the U-Net model. Overall, this integrated framework demonstrates a scalable potential for precision agriculture in complex polyculture systems, facilitating efficient data management and targeted crop interventions.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像、セマンティックセグメンテーション、NDVIを統合した植物レベルの健康状態評価手法が研究の中心であり、手法の構築と検証も行っている。
abstractThis study presents a methodology to manage and analyze large volumes of multispectral images captured by unmanned aerial vehicles (UAVs) in order to identify and monitor crops at the plant level.
The intricate process of coffee blossoming, pollination transfer, and successful development is crucial for creating every exquisite cup of coffee. During the flowering stage of coffee plants, delicate white flowers with a pleasant fragrance appear briefly, providing a limited opportunity for effective pollination. At this stage, the stigma of the flower, which is the female reproductive organ, becomes receptive and prepared to receive pollen. Existing research found methods such as machine learning and image analysis for monitoring crop pollination. Manual image annotation is conducted on pollen count disregarding spatial component of pollen collection which is essential for successful pollination. However, use of these strategies on coffee flowers by their complex structure and continuous changed in flowering stages. The paper represents novel methodologies by introducing methodological approach “IoU-AI” to monitor pollen transmission and success of pollination in coffee flower. IoU-AI utilize high resolution coffee flower image accurately track and detect floral organs by offering insight to pollen transfer. IoU-AI employs deep learning models to detect and observe floral components like stigma and anthers. Further computes overlap between structures and estimate pollen transmission. The flower detection accuracy was evaluated against ground truth measurements. The accuracy of coffee flower detection ranged from 94.77% to 85.34% for flower stages ranging from 20% to 100% blooming.
Why it matches plant phenotyping methodsコーヒー花の画像から柱頭・葯を検出し、重なりに基づいて花粉伝達と受粉成功を推定する画像解析手法を開発・精度評価しており、植物状態の取得が中心です。
abstractThe paper represents novel methodologies by introducing methodological approach “IoU-AI” to monitor pollen transmission and success of pollination in coffee flower.
Plant disease adversely impacts food production and quality. Alongside detecting the disease, estimating its severity is important in managing the disease. Artificial intelligence deep learning-based techniques for plant disease detection are emerging. Unlike most of these techniques, which focus on disease recognition, this study addresses various plant disease-related tasks, including annotation, severity classification, lesion detection, and leaf segmentation. We propose a novel approach that learns the disease symptoms, which are then used to segment disease lesions for severity estimation. To demonstrate the work, a dataset of barley images was used. We captured the images of barley plants inoculated with diseases on test-bed paddocks at various growth stages. The dataset was automatically annotated at a pixel level using a trained vision transformer to obtain the ground truth labels. The annotated dataset was applied to train salient object detection (SOD) methods. Two top-performing lightweight SOD models were used to segment the disease lesion areas. To evaluate the performance of the SODs, we have tested them on our dataset and several other datasets, including the Coffee dataset, which has expert pixel-level labels that were unseen during the training step. Several morphological and spectral disease symptoms, including those akin to the widely used ABCD rule for human skin-cancer detection, i.e., asymmetry (A), border irregularity (B), colour variance (C), and diameter (D), are learned. To the best of our knowledge, this is the first study to incorporate these ABCD features in plant disease detection. We further extract visual and texture features using the grey level co-occurrence matrix (GLCM) and fuse them with the ABCD features. For the coffee dataset, our method achieved 82 + % detection accuracy on the severity classification task. The results demonstrate the performance of the proposed method in detecting plant diseases and estimating their severity.
Why it matches plant phenotyping methods植物病斑の画素レベル分割と病害重症度推定という、植物状態を画像から定量化する手法が研究の中心であり、データセット構築・モデル評価も行っている。
abstractthis study addresses various plant disease-related tasks, including annotation, severity classification, lesion detection, and leaf segmentation
Purpose: Coffee farming plays an essential role in the global economy, making accurate productivity prediction methods indispensable for strategic decision-making in the sector. This study aimed to develop models for early prediction of coffee production per plant based on morphological indices.Methods:Two models were proposed using the following attributes: plant height, canopy width, and the number of fruits on the productive internodes of plagiotropic branches. In Model 1, fruit counts were manually conducted at the 4th and 5th productive nodes of the branches, while in Model 2, the average fruit count from the 1st to the 5th productive nodes was obtained automatically through branch image analysis using Detectron2, an open-source object detection library. Both models were developed using data collected at two distinct periods before harvest—the first five months prior and the second three months prior. The research was conducted in three coffee plots in Viçosa, Minas Gerais, Brazil, where 60 plants were selected to evaluate the production prediction model. During harvest, the production of each plant was individually recorded, enabling validation of the predictions. Results: The results revealed a strong correlation between the models and the field-observed production data, especially for the model based on data collected three months before harvest. Model 1 demonstrated a better fit (R² = 0.889; RMSE = 0.923 L/plant; MAE = 0.635 L/plant), while Model 2 had a lower absolute error (R² = 0.747; RMSE = 0.374 L/plant; MAE = 0.460 L/plant). Additionally, productivity maps were generated for each plot, showing good agreement with field-observed productivity data.Conclusions: It was concluded that the proposed models are promising for application in coffee farming, contributing to early production prediction.
Why it matches plant phenotyping methodsコーヒー果実数を枝画像から自動抽出し、個体あたり生産量を早期予測する手法を開発・検証しており、表現型取得と予測ワークフローが研究の中心である。
abstractBoth models were developed using data collected at two distinct periods before harvest—the first five months prior and the second three months prior.
Coffee has long promoted international trade and prosperity, employing millions of small-scale producers. The high demand for this crop has resulted in global supply networks. Young coffee seedlings are vulnerable to fungal diseases such as damping-off and root rot, which cause significant damage and substantially reduce plant productivity. Signs include wilting, root rot, and seedling death both before and after sprouting. Deep learning could allow automatic and scalable prediction of plant diseases. This study aims to enhance early detection of coffee seedling diseases, ensure model adaptability across samples, and optimize computational efficiency for practical implementation. The proposed Vision-based Heterogeneous Graph Neural Network (Vi-HGNN) model, which combines computer vision and graph neural networks (GNNs), provides information about disease transmission patterns over time and space. After training, the model can accurately detect early signs of infection, allowing farmers to intervene before the damage spreads. Experimental results show that Vi-HGNN achieves a 97.77 % detection accuracy, outperforming existing methods in precision, F1-score, and pathogen coverage. Future developments will aim to expand detection capabilities to include additional diseases, pests, and weeds, improving overall crop health monitoring.
Why it matches plant phenotyping methodsコーヒー苗の病徴を画像と深層学習で検出する手法が研究の中心であり、植物の病害状態を直接推定・評価しているため。
abstractDeep learning could allow automatic and scalable prediction of plant diseases.
Coffee is a vital agricultural commodity that sustains millions of farmers worldwide, yet its cultivation is increasingly threatened by devastating leaf diseases such as Leaf Rust, Phoma, Cercospora, and Leaf Miner. These diseases reduce photosynthetic efficiency, cause defoliation, and ultimately lower crop yield and quality. Traditional diagnostic methods, including visual inspection and laboratory-based tests such as PCR and ELISA, are often time-consuming, costly, and require expert intervention, making them impractical for large-scale use. To address these challenges, we propose EffResViT-SE FusionNet, a novel hybrid deep learning framework that integrates EfficientNetB3 and ResNet50 enhanced with Squeeze-and-Excitation (SE) blocks for adaptive local feature recalibration, along with a Vision Transformer (ViT) for modeling global contextual dependencies. This fusion design effectively combines CNN-based local feature extraction with transformer-based long-range attention in a unified architecture. The model was trained on a large-scale dataset comprising 58,555 coffee leaf images distributed across five classes: Healthy (18,984), Miner (16,983), Leaf Rust (8336), Cercospora (7681), and Phoma (6571). The dataset was split into 70%, 15%, and 15% testing. Key hyperparameters included the Adam optimizer, a learning rate of 0.001, a batch size of 32, and 80 training epochs, ensuring stable convergence. Experimental results demonstrate the superior capability of the proposed model, achieving an overall classification accuracy of 99%, with precision, recall, and F1-scores all ranging between 98% and 99% across all classes. Comparative analysis confirmed notable improvements over baseline models: ResNet50 (94% accuracy), EfficientNetB3 (95% accuracy), and standalone ViT (97% accuracy). Furthermore, ablation studies validated the critical role of SE blocks and feature fusion with the transformer in achieving optimal performance. These outcomes highlight EffResViT-SE FusionNet as a powerful, precise, and scalable solution for early detection and classification of coffee leaf diseases, supporting timely interventions and promoting sustainable agriculture.
Why it matches plant phenotyping methodsコーヒー葉画像から病害状態を分類する深層学習フレームワークの開発・比較検証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。
titleEffResViT-SE FusionNet: A Hybrid Deep Learning Framework for Accurate Classification of Coffee Leaf Diseases.
Reproduction assets foundThe paper's plant-phenotyping input is a public Kaggle coffee leaf image dataset (58,555 images across five classes) explicitly linked in the Data Availability Statement. No author analysis code or trained model checkpoints are disclosed.Dataset · publicInterest
The authors declare no conflicts of interest.
Acknowledgments
Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2025R238), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
Data Availability Statement
The dataset used in this study is publicly available on Kaggle: https://www.kaggle.com/datasets/noamaanabdulazeem/jmuben‐coffee‐dataset/data .
References
Adelaja , O.
, and
B.
Pranggono
. 2025 . “
Leveraging Deep Learning for Real‐Time Coffee Leaf Disease Identification
.” Aǧrı
7 , no. 1 : 13 .
10.3390/agriengineering7010013
.
Alirezazadeh , P.
,
M.
Schirrmann
, and
F.
Stolzenburg
. 2023 . “
Improving Deep Learning‐Based Plant DisOpen asset ↗Kaggle · jmuben‐coffee‐datasetlines:822-895Code / dataset availability confirmedCrossref · Europe PMC · checked 6 Sept 2026
Coffee, the world’s most traded tropical crop, is vital to the economies of many producing countries. However, coffee leaf diseases pose a serious threat to coffee quality and sustainable production. Deep learning has shown strong performance in plant disease identification through automatic image classification. Nevertheless, reliance on a single convolutional neural networks (CNNs) architecture restricts feature variability and real-world generalization. Moreover, limited work has systematically combined feature selection/reduction with CNNs, which constrains the advancement of hybrid models capable of capturing complementary features while ensuring computational efficiency without accuracy loss. This article presents an enhanced deep learning-based framework for coffee disease classification incorporating a hybrid strategy that integrates CNNs and advanced feature selection algorithms. GoogLeNet and ResNet18 are paired for complementary feature extraction, Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) are employed for dimensionality reduction, and ANOVA and Chi-square are applied to select the most informative features. An Adam optimizer (learning rate = 0.001, batch size = 20, epochs = 50) with early stopping is used for training. Experiments on the BRACOL dataset achieved 99.78% accuracy, with precision, recall, and F1-score all exceeding 99% across classes. To the best of our knowledge, this study systematically integrates GoogLeNet and ResNet18 with PCA/SVD dimensionality reduction and analysis of variance (ANOVA)/Chi-square feature selection, for coffee disease classification, thereby addressing a key gap in prior research.
Why it matches plant phenotyping methodsコーヒー葉の病害を画像から分類する深層学習フレームワークが研究の中心であり、植物の病害状態を直接推定する実質的な表現型解析手法である。
abstractThis article presents an enhanced deep learning-based framework for coffee disease classification incorporating a hybrid strategy that integrates CNNs and advanced feature selection algorithms.
Reproduction assets foundThe paper uses the public BRACOL/RoCoLe coffee leaf image dataset (Mendeley) and provides authors' analysis code publicly on GitHub and Zenodo, all explicitly linked in the text.Dataset · publicWe utilized the BRACOL dataset, a publicly available dataset of coffee leaf images. The dataset can be accessed at the following DOI: ( https://data.mendeley.com/datasets/c5yvn32dzg/2 ).Open asset ↗lines:30-49Code · publicAll implementation details, including preprocessing scripts, model training, and evaluation codes, are available in the following GitHub repository: ( https://github.com/DrMaherAlrahhal/coffe-code ).Open asset ↗GitHublines:30-49Code · publicThe code is available at GitHub and Zenodo:
- https://github.com/DrMaherAlrahhal/coffe-code .
- w. (2025). coffee code. Zenodo. https://doi.org/10.5281/zenodo.17470672 .Open asset ↗Zenodo · 10.5281/zenodo.17470672lines:2688-2696Code / dataset availability confirmedCrossref · checked 6 Sept 2026
CoffeeMultispectral / hyperspectralLeafClassificationPhysiological trait estimationWater status / transpiration
Water potential is an important indicator used to study water relations in plants, as it reflects the level of hydration in their tissues. There are different numerical variables that describe plant properties and can be acquired from leaf reflectance. The objective of this study was to estimate water potential in coffee plants using spectral variables. For this, a range of wavelengths that provided analytical flexibility was used. After this, machine learning techniques were employed to build data-driven models. The dataset used presents spectral characteristics (wavelength) of coffee plants, collected through the CI-710 Mini-Leaf Spectrometer equipment and also the water potential of each coffee plant, measured by the Scholander Chamber equipment. The dataset was divided into two crop management groups: irrigated and rainfed. Four machine learning techniques were implemented: Multi-Layer Perceptron (MLP), Decision Tree, Random Forest and K-Nearest Neighbor (KNN). The implementation of machine learning techniques followed two distinct strategies: regression and classification. The results indicate that the decision tree-based model demonstrated superior performance under irrigated conditions for regression tasks. In contrast, the KNN technique achieved the best performance for classification. Under rainfed conditions, the MLP model outperformed the other techniques for regression, while the Random Forest method exhibited the highest accuracy in classification tasks. While no hardware prototype was developed, the machine learning-based methods presented here suggest a possible pathway toward future intelligent, user-friendly, and accessible sensing technologies for coffee plantations.
Why it matches plant phenotyping methodsコーヒー植物の葉スペクトルから水ポテンシャルという生理形質を機械学習で推定・分類する手法が研究の中心であり、植物フェノタイピング手法の開発・評価に該当する。
abstractThe objective of this study was to estimate water potential in coffee plants using spectral variables.
Reproduction assets foundThe paper's Data Availability Statement explicitly states that the study's datasets (coffee leaf spectral reflectance and water potential measurements) and the MATLAB analysis codes are publicly available at the authors' UFLA repository, which is an allowed URL. This is a paper-specific, public, actionable asset.Dataset · publicData Availability Statement: The datasets and MATLAB codes used in this study are available at
http://www.aia.ufla.br/home/filesdatasets/, accessed on 27 November 2025.Open asset ↗aia.ufla.brpdf-page:18 lines:1-54Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 Dec 2025Computers and Electronics in Agriculture.
Accurate identification of plant diseases is critical for maximizing agricultural productivity, particularly in high-value crops like Peruvian coffee, where traditional manual diagnostics remain error-prone and inefficient. While numerous studies have explored convolutional neural networks (CNNs) for disease classification, achieving optimal performance hinges on the precise tuning of hyperparameters a process often relegated to suboptimal trial-and-error methods. Using metaheuristic optimization algorithms to detect such hyperparameters would be a correct approach. For this reason, with the artificial bee colony (ABC) optimization method was goal to determine the hyper-parameters of the proposed CNN architecture in the study. In accordance with this goal, both Peruvian Coffea Dataset (CoLeaf-DB), which is an up-to-date dataset, and Arabica Coffee Leaf Dataset (AcLeaf-DB) which is a reliable dataset with which many studies have been conducted on this subject and which can be benchmarked, were used. On CoLeaf-DB, which is a current dataset used in the study, values of 0.94, 0.94, 0.94, 0.95 were obtained in terms of precision, recall, F1 score, accuracy performance metrics, respectively. Same to order, the values of 0.95, 0.95, 0.95, and 0.97 were obtained from the AcLeaf-DB. When the obtained values are compared with state-of-the-art (SOTA) studies, it is revealed that the determination of hyperparameters with the proposed optimization method and the CNN-based architecture developed on this basis have an extremely important effect on disease detection.
Why it matches plant phenotyping methodsコーヒー葉の病徴を画像から分類するCNNと、ABCによるハイパーパラメータ最適化を開発し、複数データセットで性能比較しているため、病害フェノタイピング手法が中心である。
abstractwith the artificial bee colony (ABC) optimization method was goal to determine the hyper-parameters of the proposed CNN architecture in the study.
Precision agriculture technologies based on satellite remote sensing remain largely inaccessible to smallholder farmers in developing countries due to technical complexity, cost barriers, and infrastructure demands. This study presents the design and implementation of an open-source, web-based platform for processing Sentinel-2 Level-2A imagery tailored to the specific needs of family farming systems. The platform integrates a FastAPI backend for geospatial data processing with a Next.js frontend providing simplified tools for spectral index computation (NDVI, EVI, SAVI, NDWI, NDBI), crop classification using supervised and unsupervised machine learning, and interactive 2D/3D visualization. A laboratory module implements thirteen digital image processing techniques—including Gaussian filtering, edge detection, morphological operations, and thresholding—for educational and comparative analysis. The browser-based system eliminates installation requirements and automates key workflows such as coordinate reprojection, JP2 band extraction, and statistical evaluation. Validation using ground-truth data from coffee and soybean fields in the Brazilian Cerrado achieved classification accuracies above 85% and correlation coefficients exceeding 0.90 for biomass estimation based on NDVI-derived metrics. The platform contributes to the democratization of remote sensing technologies and enhances accessibility of precision agriculture tools for smallholder farmers.
Why it matches plant phenotyping methods植物圃場の衛星画像を処理し、NDVI等からバイオマスを推定するオープンソース基盤の設計・実装・検証が中心であり、植物形質推定ワークフローとして収録対象。
titleAn Open-Source Web Platform for Sentinel-2 Multispectral Analysis in Smallholder Agriculture: Design, Implementation and Validation
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the authors' complete source code, documentation, and example datasets for the Sentinel-2 phenotyping/analysis platform on a public GitHub repository under MIT license. Sentinel-2 imagery is from the public Copernicus browser, but that is a generic data sourceCode · publicresearch received no external funding
Institutional Review Board Statement: Not applicable. This study did not involve humans or animals.
Informed Consent Statement: Not applicable. This study did not involve humans.
Data Availability Statement: Complete source code, documentation, and example datasets are publicly available
at https://github.com/rexionmars/icev-remote-sensing under MIT license. The platform can be deployed locally
or accessed via hosted instance for testing purposes. Sentinel-2 satellite imagery used in this study was obtained
from the Copernicus Open Access Hub (https://browser.dataspace.copernicus.eu/) and is freely available.
Acknowledgments: The authors thank the iCEV IOpen asset ↗https://github.com/rexionmars/icev-remote-sensing · icev-remote-sensingpdf-layout-page:11 lines:1-70Code / dataset availability confirmedCrossref · Europe PMC · checked 15 Sept 2026
Abstract The growth and productivity of banana crops are critically affected by micronutrient deficiencies, which are often difficult to detect at early stages. Lightweight deep learning models, optimized through neural architecture search (NAS) and attention mechanisms, are hypothesized to provide accurate and efficient classification of such deficiencies for real-time agricultural applications. In this study, multiple convolutional neural networks (CNNs) and mobile-friendly architectures, including ResNet50, VGG16, NASNetMobile, and MobileNet variants (V1, V2, V3), were evaluated using transfer learning on a curated banana leaf deficiency dataset. To improve robustness and prediction accuracy, modified classification layers and ensemble strategies–initially average ensembling and later a NAS-guided dynamic attention weighting mechanism were employed. This optimization resulted in a novel lightweight model, NASMobV2 (NASNetMobile + MobileNetV2), capable of both classifying nutrient deficiencies and assessing their severity levels. The proposed model achieved a validation accuracy of 98.57%, outperforming baseline and state-of-the-art counterparts in precision, recall, and F1 score. To improve generalization, banana crop diseases along with an additional Coffee crop dataset were included for evaluation. Finally, the practical utility of the model was demonstrated by deploying the trained system in both mobile and web applications, enabling farmers and agronomists to perform fast and accurate diagnostics directly in the field.
Why it matches plant phenotyping methodsバナナ葉画像から栄養欠乏と重症度を推定する軽量深層学習モデルを開発・評価し、実運用アプリにも展開しており、植物状態の取得・推定手法が中心である。
titleA neural architecture search optimized lightweight attention ensemble model for nutrient deficiency and severity assessment in diverse crop leaves.
Reproduction assets foundThe paper's banana leaf nutrient-deficiency image dataset is publicly available on Mendeley Data and was directly used for the phenotyping/classification measurements. No author analysis code or trained model checkpoints are explicitly deposited; the GitHub/Streamlit links are deployment apps rather than deposited codeDataset · publiclidation and editing in addition to overall supervision.
Funding
Open access funding provided by Vellore Institute of Technology. We thank our Management “Vellore Institute of Technology, Vellore” for open access funding support.
Data availability
An openly available repository (Mendeley dataset) was used to perform this study;(https://data.mendeley.com/datasets/7vpdrbdkd4/1), Request for any data or materials shall be addressed to the author(sudhakar.m2020@vitstudent.ac.in).
Declarations
Competing interests
The authors declare that they have no competing interests.
References
1.
Sherefu A Zewide I
Review paper on effect of micronutrients for crop production
J. Nutr. Food Process. 2021
10.31Open asset ↗Mendeley · 7vpdrbdkd4lines:1245-1307Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
This study evaluated the integration of non-invasive remote sensing and colorimetry to classify the maturity stages of Coffea arabica fruits across four varieties: Caturra Amarillo, Excelencia, Milenio, and Típica. Multispectral signatures were captured using a Parrot Sequoia camera at wavelengths of 550 nm, 660 nm, 735 nm, and 790 nm, while colorimetric parameters L*, a*, and b* were measured with a high-precision colorimeter. We conducted multivariate analyses, including Principal Component Analysis (PCA) and multiple linear regression (MLR), to identify color patterns and develop predictors for fruit maturity. Spectral curve analysis revealed consistent changes related to ripening: a decrease in reflectance in the green band (550 nm), a progressive increase in the red band (660 nm), and relative stability in the RedEdge and near-infrared regions (735-790 nm). Colorimetric analysis confirmed systematic trends, indicating that the a* component (green to red) was the most reliable indicator of ripeness. Additionally, L* (lightness) decreased with maturity, and the b* component (yellowness to blue) showed varying importance depending on the variety. PCA accounted for over 98% of the variability across all varieties, demonstrating that these three parameters effectively characterize maturity. MLR models exhibited strong predictive performance, with adjusted R 2 values ranging between 0.789 and 0.877. Excelencia achieved the highest predictive accuracy, while Milenio demonstrated the lowest, highlighting varietal differences in pigmentation dynamics. These findings show that combining multispectral imaging, colorimetry, and statistical modeling offers a non-destructive, accessible, and cost-effective method for objectively classifying coffee maturity. Integrating this approach into computer vision or remote sensing systems could enhance harvest planning, reduce variability in specialty coffee lots, and improve competitiveness by ensuring greater consistency in cup quality.
Why it matches plant phenotyping methodsコーヒー果実の成熟度という植物形質を、マルチスペクトル画像・色彩計測・統計モデルで非破壊推定する方法が研究の中心であり、予測性能も評価している。
abstractThis study evaluated the integration of non-invasive remote sensing and colorimetry to classify the maturity stages of Coffea arabica fruits across four varieties
Coffee is one of the most popular beverages consumed worldwide and is also an important economic driver in agricultural economies. However, nutritional deficiencies in coffee plants have a major effect on the quality and yield of the crop. Detection of these deficiencies early and accurately is critical for effective intervention and management. In this work, we introduce a novel deep-learning framework for detection and classification of nutritional deficiencies in coffee plants. DenseNet-201, AlexNet, and MobileNet-V2 are integrated to extract discriminative features from coffee leaf images, and an attention-based feature fusion mechanism is proposed using squeeze-and-excitation blocks to improve feature representation. A differential evolution algorithm is used to optimize a Kernel extreme learning machine for learning efficiency and generalization to classify the extracted features. A benchmark dataset is used for the evaluation of the proposed model and its performance is assessed against multiple performance metrics such as accuracy, precision, recall, specificity, F1-score, and the Matthews correlation coefficient. The proposed method is compared with existing deep learning models, and it is found that the proposed method outperforms the other models with a classification accuracy of 99.50%, precision of 99.22%, recall of 99.24%, specificity of 0.9947, F1-score of 0.9957, and M correlation coefficient of 0.9908. The model is able to identify nutritional deficiencies accurately, and these results confirm the model’s effectiveness as a practical and scalable solution for precision agriculture and sustainable coffee cultivation.
Why it matches plant phenotyping methodsコーヒー葉画像から栄養欠乏という植物状態を検出・分類する深層学習手法を開発し、ベンチマークデータセットと比較評価しており、植物フェノタイピング手法が中心です。
abstractwe introduce a novel deep-learning framework for detection and classification of nutritional deficiencies in coffee plants.
Plant phenotyping relevance match · UnverifiedOpenAlex · Crossref · Europe PMC · checked 6 Sept 2026
C. canephora exhibits high genetic variability, and to estimate this variability, morphological descriptors associated with coffee quality are used. Bean size is a physical trait of great importance for coffee classification. Manual classification is known to be inaccurate and time-consuming, which is why researchers have adopted digital imaging techniques to improve classification efficiency. The objective of this study was to quantify the genetic diversity in 43 C. canephora clones using the Ward-MLM strategy and to estimate genetic parameters and correlations from digital phenotyping of beans and cherries. The experiment was conducted on a crop consisting of 43 C. canephora genotypes, where the cherries were manually pulped and dried until they reached 12% moisture content. Using GroundEye® equipment, four replicates of 50 beans and cherries were evaluated for each treatment, and the software generated spreadsheets with the results of the geometric traits. To determine the existence of genetic variability among the genotypes, the data obtained were subjected to analysis of variance, estimation of genetic parameters, Ward-MLM analysis, and Pearson correlation. The genotypic variance was higher than the environmental variance for all variables analyzed, both for beans and cherries, indicating that the genotypes evaluated have high genetic variability. The greatest genetic distance was observed between groups I and IV, suggesting favorable conditions for crosses between the genotypes of these groups. Phenotypic correlation analysis revealed significant positive and negative correlations between the variables. Digital seed analysis successfully detected genetic divergence among the 43 C. canephora clones. The variables ‘area’, ‘maximum diameter’, and ‘minimum diameter’ are the most suitable for selecting genotypes with larger beans.
Why it matches plant phenotyping methodsGroundEye®によるデジタル画像計測でコーヒー豆・果実の幾何形質を抽出し、遺伝的多様性評価に用いる方法が研究の中心的なデータ取得手段となっている。
abstractManual classification is known to be inaccurate and time-consuming, which is why researchers have adopted digital imaging techniques to improve classification efficiency.
Integrating multispectral imaging and artificial intelligence in coffee production is a promising approach to optimize farming practices and improve crop management. This systematic literature review analyzes the current status, challenges, and future directions for combining these technologies in the coffee sector. Following the PRISMA protocol, 455 papers were reviewed in six scientific databases, identifying 27 primary studies that met the inclusion and exclusion criteria. The analysis reveals a significant increase in research activity since 2020, with a relationship between time and frequency of publication. Machine learning techniques, particularly regression analysis and random forests, emerged as the predominant artificial intelligence approaches for multispectral data processing. The review identified several key applications, such as coffee quality assessment, disease detection, and yield prediction. However, significant challenges remain, such as limited biometric variability within coffee plants, the influence of environmental factors, and the need for high-quality training data. The effectiveness of these technologies varies across geographic regions and soil and climatic conditions, underscoring the importance of application in specific contexts. Future research points toward the development of more robust artificial intelligence models, the integration of multiple data sources, and the need to employ hybrid artificial intelligence approaches. This review provides an understanding of the current landscape and valuable information for researchers, industry professionals, and stakeholders interested in creating more efficient and sustainable coffee farming practices using these technologies.
Why it matches plant phenotyping methodsコーヒー生産におけるマルチスペクトル画像とAIの植物状態・形質推定を扱う系統的レビューであり、フェノタイピング関連手法のレビューが中心である。
titleArtificial intelligence and multispectral imaging in coffee production: A systematic literature review
CoffeeMultispectral / hyperspectralLeafClassificationPhysiological trait estimationWater status / transpiration
Water potential is an important indicator used to study water relations in plants, as it reflects the level of hydration in their tissues. There are different numerical variables that describe plant properties and can be acquired from leaf reflectance. The objective of this study is to estimate water potential in coffee plants using spectral variables. For this, a range of wavelengths is used that provides analytical flexibility. After this, machine learning techniques are employed to build data-driven models. The dataset used presents spectral characteristics (wavelength) of coffee plants, collected through the CI-710 Mini-Leaf Spectrometer equipment and also the water potential of each coffee plant, measured by the Scholander Chamber equipment. The dataset is divided into two crop management groups: irrigated and rainfed. Four machine learning techniques were implemented: Multi-Layer Perceptron (MLP), Decision Tree, Random Forest and K-Nearest Neighbor (KNN). The implementation of machine learning techniques followed two distinct strategies: regression and classification. The results indicate that the decision tree-based model demonstrated superior performance under irrigated conditions for regression tasks. In contrast, the KNN technique achieved the best performance for classification. Under rainfed conditions, the MLP model outperformed the other techniques for regression, while the Random Forest method exhibited the highest accuracy in classification tasks. The developed machine learning-based methods can enable the creation of intelligent, user-friendly, and accessible sensors (smart sensors) for coffee plantations.
Why it matches plant phenotyping methodsコーヒー植物の水ポテンシャルという生理形質をスペクトル反射と機械学習で推定・分類する手法が研究の中心であり、植物フェノタイピング手法に該当する。
abstractThe objective of this study is to estimate water potential in coffee plants using spectral variables.
Coffee berry disease (CBD), caused by Colletotrichum kahawae, significantly threatens global Coffee arabica production, leading to major yield losses. Traditional detection methods are often subjective and inefficient, particularly in resource-limited settings. While deep learning has advanced plant disease detection, most existing research targets leaf diseases, with limited focus on berry-specific infections like CBD. This study proposes a lightweight and accurate solution using a Compact Convolutional Transformer (CCT) for classifying healthy and CBD-affected coffee berries. The CCT model combines parallel convolutional branches for hierarchical feature extraction with a transformer encoder to capture long-range dependencies, enabling high performance on limited data. A dataset of 1737 coffee berry images was enhanced using bilateral filtering and color segmentation. The CCT model, integrated with a Multilayer Perceptron (MLP) classifier and optimized through early stopping and regularization, achieved a validation accuracy of 97.70% and a sensitivity of 100% for CBD detection. Additionally, CCT-extracted features performed well with traditional classifiers, including Support Vector Machine (SVM) (82.47% accuracy; AUC 0.91) and Decision Tree (82.76% accuracy; AUC 0.86). Compared to pretrained models, the proposed system delivered superior accuracy (97.5%) with only 0.408 million parameters and faster training (2.3 s/epoch), highlighting its potential for real-time, low-resource deployment in sustainable coffee production systems.
Why it matches plant phenotyping methodsコーヒー果実の画像から病徴を分類する深層学習手法の開発・検証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。
abstractThis study proposes a lightweight and accurate solution using a Compact Convolutional Transformer (CCT) for classifying healthy and CBD-affected coffee berries.
Precision agriculture is an approach that uses information technologies to improve and optimize agricultural production. It is based on the collection and analysis of agricultural data to support decision making in agricultural processes. In recent years, Artificial Neural Networks (ANNs) have demonstrated significant benefits in addressing precision agriculture needs, such as pest detection, disease classification, crop state assessment, and soil quality evaluation. This article aims to perform a systematic literature review on how ANNs with an emphasis on image processing can assess if fruits such as mango, apple, lemon, and coffee are ready for harvest. These specific crops were selected due to their diversity in color and size, providing a representative sample for analyzing the most commonly employed ANN methods in agriculture, especially for fruit ripening, damage, pest detection, and harvest prediction. This review identifies Convolutional Neural Networks (CNNs), including commonly employed architectures such as VGG16 and ResNet50, as highly effective, achieving accuracies ranging between 83% and 99%. Additionally, it discusses the integration of hardware and software, image preprocessing methods, and evaluation metrics commonly employed. The results reveal the notable underuse of vegetation indices and infrared imaging techniques for detailed fruit quality assessment, indicating valuable opportunities for future research.
Why it matches plant phenotyping methods果実の成熟・損傷・病害などを画像処理とANNで評価する方法を体系的にレビューしており、植物表現型取得・推定手法が中心である。
abstractThis article aims to perform a systematic literature review on how ANNs with an emphasis on image processing can assess if fruits such as mango, apple, lemon, and coffee are ready for harvest.
Citizen science is an effective approach for collecting extensive data scalable for deep learning, although data quality is debatable. However, few studies have determined the factors associated with data collection that affect model performance and potential sampling bias. This study aims to identify the factors that significantly influence the performance of a deep learning object detection model in agricultural prediction tasks. To do so, we analyzed errors in a You Only Look Once (YOLO v8) model trained for counting the number of coffee cherries in mobile pictures. The model was trained with 436 images taken in Colombia and Peru collected by local farmers as a citizen science approach. We analyzed the prediction errors of the model using 637 additional pictures. We then applied a linear mixed model (LMM) and a decision tree machine learning model to regress the model’s error against predictor variables related to the following categories: photographer influence, geographic location, mobile phone characteristics, picture characteristics, and coffee varieties. Our results show the strong influence of photographer identity and adherence (whether the image collection protocol was followed or not) on model prediction error. Following the protocol can increase model performance from an R2 of 0.48 to 0.73. Additionally, model performance varied significantly depending on photographer identity, with R2 ranging from 0.45 to 0.93. In contrast, factors such as mobile phone characteristics (e.g., frontal camera resolution, flash type, and screen size), using the screen behind the branch to obscure other cherries, coffee varieties, and geographic location did not significantly affect prediction error. These findings demonstrate that data quality in citizen science–based data collection for enhancing model prediction can be achieved through straightforward and comprehensive protocols, customized volunteer training, and regular feedback from experts. Such measures collectively support the robust application of deep learning models in agriculture. Furthermore, this study demonstrated that any mobile device with a camera can contribute to citizen science initiatives, underscoring the potential and scalability of this approach in agricultural research.
Why it matches plant phenotyping methodsコーヒーチェリー数という植物器官の形質を画像から推定する深層学習モデルを対象に、予測誤差、撮影者、プロトコル遵守などを分析して技術性能を検証しており、フェノタイピング手法が中心である。
abstractWe analyzed the prediction errors of the model using 637 additional pictures.
In deep learning, Semi-Supervised Learning is a highly effective technique to enhances neural network training by leveraging both labeled and unlabeled data. This process involves using a trained model to generate pseudo labels to the unlabeled samples, which are then incorporated to further train the original model, resulting in a new model. However, if these pseudo labels contain substantial errors, the resulting model's accuracy may drop, potentially falling below the performance of the initial model. To tackle the problem, we propose an Ambiguity-Aware Semi-Supervised Learning method for Leaf Disease Classification. Specifically, we present a per-disease ambiguity rejection algorithm that eliminates ambiguous results, thereby enhancing the precision of pseudo labels for the subsequent semi-supervised training step and improving the precision of the final classifier. The proposed method is evaluated on two public leaf disease datasets of coffee and banana across various data scenarios, including supervised and semi-supervised settings, with varying proportions of labeled data. The results indicate that our semi-supervised method reduces the reliance for fully labeled datasets while preserving high accuracy by utilizing the ambiguity rejection algorithm. Additionally, the rejection algorithm significantly boosts precision of final classifier on both coffee and banana datasets, achieving rates of 99.46% and 100.0%, respectively, while using only 50% labeled data. The study also presents a thorough set of experiments and analyses to validate the effectiveness of the proposed method, comparing its performance against state-of-the-art supervised approaches. The results demonstrate that our method, despite using only 50% of the labeled data, achieves competitive performance compared to fully supervised models that use 100% of the labeled data.
Why it matches plant phenotyping methods葉画像から植物病害状態を分類する半教師あり学習法と曖昧性除去アルゴリズムを開発し、コーヒー・バナナの公開データセットで評価しており、病害表現型の抽出手法が研究の中心である。
abstractwe propose an Ambiguity-Aware Semi-Supervised Learning method for Leaf Disease Classification.
Remotely Piloted Aircraft (RPA) as sensor-carrying airborne platforms for indirect measurement of plant physical parameters has been discussed in the scientific community. The utilization of RGB sensors with photogrammetric data processing based on Structure-from-Motion (SfM) and Light Detection and Ranging (LiDAR) sensors for point cloud construction are applicable in this context and can yield high-quality results. In this sense, this study aimed to compare coffee plant height data obtained from RGB/SfM and LiDAR point clouds and to estimate soil compaction through penetration resistance in a coffee plantation located in Minas Gerais, Brazil. A Matrice 300 RTK RPA equipped with a Zenmuse L1 sensor was used, with RGB data processed in PIX4D software (version 4.5.6) and LiDAR data in DJI Terra software (version V4.4.6). Canopy Height Model (CHM) analysis and cross-sectional profile, together with correlation and statistical difference studies between the height data from the two sensors, were conducted to evaluate the RGB sensor’s capability to estimate coffee plant height compared to LiDAR data considered as reference. Based on the height data obtained by the two sensors, soil compaction in the coffee plantation was estimated through soil penetration resistance. The results demonstrated that both sensors provided dense point clouds from which plant height (R2 = 0.72, R = 0.85, and RMSE = 0.44) and soil penetration resistance (R2 = 0.87, R = 0.8346, and RMSE = 0.14 m) were accurately estimated, with no statistically significant differences determined between the analyzed sensor data. It is concluded, therefore, that the use of remote sensing technologies can be employed for accurate estimation of coffee plantation heights and soil compaction, emphasizing a potential pathway for reducing laborious manual field measurements.
Why it matches plant phenotyping methodsRGB/SfMとLiDARによるコーヒー樹高推定を比較・検証することが研究の中心であり、植物形質取得手法の技術評価に該当する。土壌硬度推定も扱うが、樹高計測法の検証が明確である。
abstractthis study aimed to compare coffee plant height data obtained from RGB/SfM and LiDAR point clouds
Spectral indices such as NDRE (Normalized Difference Red Edge Index), CCCI (Canopy Chlorophyll Content Index), and IRECI (Inverted Red Edge Chlorophyll Index), based on the Red Edge band of MSI/Sentinel-2 (B05, B06, B07 images), are essential tools in coffee monitoring. These indices require resampling the Red Edge band (20 m resolution) to match the NIR (10 m resolution) using methods such as nearest neighbor, bilinear, cubic, and Lanczos. In this technical note, we evaluated these resampling methods using two original B05 images, selected on November 24, 2023, and September 21, 2023, with reference points from the farms "Ouro Verde" (15 hectares) in Barra do Choça (BA) and "Canto do Rio" (45 hectares) in Luís Eduardo Magalhães (BA), respectively. A total of 500 random points were generated and analyzed using PSF, linear models, and cross-validation with metrics such as R², MAE, and RMSE. The PSF analysis indicated the integrity of the data for further analysis. The cubic method showed the best performance (R² = 0.996, MAE = 20.87, RMSE = 32.67). The validation results of the resampling methods suggest that this procedure is crucial for accurate digital processing in remote sensing for coffee cultivation and should be aligned with the study objectives.
Why it matches plant phenotyping methodsコーヒー栽培における植物キャノピーのスペクトル指標算出を対象に、Sentinel-2赤縁バンドのリサンプリング手法を比較・検証しており、植物状態推定の技術的手法が中心である。
abstractSpectral indices such as NDRE (Normalized Difference Red Edge Index), CCCI (Canopy Chlorophyll Content Index), and IRECI (Inverted Red Edge Chlorophyll Index), based on the Red Edge band of MSI/Sentinel-2 (B05, B06, B07 images), are essential tools in coffee monitoring.
In this work, a unique database of 6726 multispectral images of coffee leaves is presented. These images were captured in JPG format for the RGB photos and in TIF format for the five multispectral bands: blue, green, red, NIR and red edge, providing a detailed view of different wavelengths of the electromagnetic spectrum. Images in TIF format have a color depth of 16 bits per pixel, ensuring good quality. The blue band (Band 1) captures light in the blue region of the spectrum, approximately 450 to 500 nm. The green band (Band 2) records light in the green region, approximately between 500 and 620 nm. The red band (Band 3) captures light in the red region, between 620 and 750 nm. The red-edge band (Band 4) lies between the red band and the NIR, and is sensitive to the transition between green vegetation and non-vegetation, around 840 nm. Finally, the near infrared band (Band 5) captures light in the near infrared region, between 750 and 900 nm. For ease of identification, images are labeled as follows: if the image name ends in 0, it is an RGB image; if it ends in 1, it corresponds to the blue band; if it ends in 2, to the green band; if it ends in 3, to the red band; if it ends in 4, to the red-edge band; and if it ends in 5, to the near-infrared band. The images show coffee leaves with and without lesions caused by the Hemileia vastatrix fungus, known as coffee rust. These samples were collected from Colombian coffee farms and the images were captured under controlled lighting conditions to ensure quality and consistency. This database is an invaluable resource for precision agriculture research and early detection of crop diseases. With these 6726 images, researchers can use advanced image processing and machine learning techniques to identify differences between healthy leaves and those affected by rust. This can lead to the development of effective predictive models, enabling early detection and more efficient management of diseases in coffee plantations, optimizing production and reducing economic losses for farmers.
Why it matches plant phenotyping methodsコーヒー葉の病斑という植物の病害状態を対象としたマルチスペクトル画像データセットであり、再利用可能なフェノタイピング用データセットの提供が中心です。
abstractIn this work, a unique database of 6726 multispectral images of coffee leaves is presented.
Reproduction assets foundThe paper is a data descriptor whose own multispectral coffee leaf image dataset is publicly deposited on Kaggle with an explicit direct URL and DOI, matching an allowed URL.Dataset · publicth of 16 bits per pixel .
Data source location
Institution: Escuela Colombiana de Ingeniería Julio Garavito University
City/Town/Region: Bogotá D.C.
Country: Colombia Latitude: 4.5983° * Longitude: 74.0051°.
Data accessibility
Repository name: Coffe Rust
Data identification number: 10.34740/kaggle/ds/5644659
Direct URL to data: https://www.kaggle.com/ds/5644659
Instructions for accessing these data: Data available free of charge to anyone with access to the Internet and the web server address provided.
Related research article
[ 1 ] Jorge Luis Aroca Trujillo, Alexander Pérez-Ruiz. “Technologies Applied in the Field of Early Detection of Coffee Rust Fungus Diseases: A Review.” Nongye JOpen asset ↗Kaggle · 10.34740/kaggle/ds/5644659lines:1-53Plant phenotyping relevance match · UnverifiedEurope PMC · checked 6 Sept 2026
Coffee is one of the most popular and widely used drinks worldwide. At present, how to judge the maturity of coffee fruit mainly depends on the visual inspection of human eyes, which is both time-consuming and labor-intensive. Moreover, the occlusion between leaves and fruits is also one of the challenges. In order to improve the detection efficiency of coffee fruit maturity, this paper proposes an improved detection method based on YOLOV7 to efficiently identify the maturity of coffee fruits, called ASD-YOLO. Firstly, a new dot product attention mechanism (L-Norm Attention) is designed to embed attention into the head structure, which enhances the ability of the model to extract coffee fruit features. In addition, we introduce SPD-Conv into backbone and head to enhance the detection of occluded small objects and low-resolution images. Finally, we replaced upsampling in our model with DySample, which requires less computational resources and is able to achieve image resolution improvements without additional burden. We tested our approach on the coffee dataset provided by Roboflow. The results show that ASD-YOLO has a good detection ability for coffee fruits with dense distribution and mutual occlusion under complex background, with a recall rate of 78.4%, a precision rate of 69.8%, and a mAP rate of 80.1%. Compared with the recall rate, accuracy rate and mAP of YOLOv7 model, these results are increased by 2.0%, 1.1% and 2.1%, respectively. The enhanced model can identify coffee fruits at all stages more efficiently and accurately, and provide technical reference for intelligent coffee fruit harvesting.
Why it matches plant phenotyping methodsコーヒー果実の成熟状態を画像から推定するYOLOベース手法を開発し、複雑背景・遮蔽下で性能評価している。収穫対象の単なる位置検出を超え、果実の成熟状態という植物器官の形質を中心的に扱うため含める。
abstractthis paper proposes an improved detection method based on YOLOV7 to efficiently identify the maturity of coffee fruits, called ASD-YOLO.
The portable X-ray fluorescence (pXRF) spectrometry has been very useful for the characterization of different earth materials, and its application for foliar analysis is really promising. The performance of pXRF for foliar analysis depends on several factors such as concentration of the elements, fluorescence yield which is influenced by atomic number, spectral interference, and water content. Mn is one of the elements that present a prominent fluorescence peak. In this sense, it was hypothesized that pXRF can directly determine the Mn concentration on foliar samples, even when used on intact leaves (fresh or dry) being a useful tool for agronomic and environmental purposes. Thus, the objective was to assess the performance of a pXRF to determine Mn concentration in two different foliar datasets from Brazil/South America and Mali/Africa. In the Brazilian dataset, leaves from eight crops (common bean, castor plant, coffee, eucalyptus, guava tree, maize, mango, and soybean) were scanned via pXRF at the following conditions: intact and fresh leaves, intact and dry leaves, and powdered samples). In the Malian dataset, powdered samples from cotton and maize were analyzed via pXRF. For comparison, Mn concentration was also determined after nitro-perchloric digestion followed by quantification via inductively coupled plasma optical emission spectroscopy (ICP-OES). After descriptive statistics, linear regressions were performed for all sample preparation conditions in both datasets, using Mn concentrations obtained through pXRF and the acid digestion method. The data quality level of all linear regressions was considered quantitative with high R (0.93 to 0.98) and R 2 (0.87 to 0.96) values. The direct analysis of Mn via pXRF on intact and fresh leaves yielded R of 0.93, R 2 of 0.87, and a low relative standard deviation (< 10%). The manufactured pXRF calibration used in this work allowed an accurate direct Mn determination in plant leaves. Considering the importance of Mn as a plant micronutrient and its potential toxicity depending on soil redox conditions, the fast, in situ, non-destructive, and eco-friendly determination via pXRF has a tremendous agronomic and environmental application worldwide.
Why it matches plant phenotyping methods植物葉のMn濃度という生理・元素形質を、携帯型XRFで非破壊測定する方法の性能評価と検証が中心であり、単なる生物学的実験での routine 測定ではない。
abstractThe direct analysis of Mn via pXRF on intact and fresh leaves yielded R of 0.93, R 2 of 0.87, and a low relative standard deviation (< 10%).
Global warming and extreme climate conditions caused by unsuitable temperature and humidity lead to coffee leaf rust ( Hemileia vastatrix ) diseases in coffee plantations. Coffee leaf rust is a severe problem that reduces productivity. Currently, pesticide spraying is considered the most effective solution for mitigating coffee leaf rust. However, the application of pesticide spray is still not efficient for most farmers worldwide. In these cases, pruning the most infected leaves with leaf rust at coffee plantations is important to help pesticide spraying to be more efficient by creating a more targeted, accessible treatment. Therefore, detecting coffee leaf rust is important to support the decision on pruning infected leaves. The dataset was acquired from a coffee farm in Majalengka Regency, Indonesia. Only images with clearly visible spots of coffee leaf rust were selected. Data collection was performed via two devices, a digital mirrorless camera and a phone camera, to diversify the dataset and test it with different datasets. The dataset, comprising a total of 2024 images, was divided into three sets with a ratio of 70% for training (1417 images), 20% for validation (405 images), and 10% for testing (202 images). Images with leaves infected by coffee leaf rust were labeled via LabelImg ® with the label "CLR". All labeled images were used to train the YOLOv5 and YOLOv8 algorithms through the convolutional neural network (CNN). The trained model was tested with a test dataset, a digital mirrorless camera image dataset (100 images), a phone camera dataset (100 images), and real-time detection with a coffee leaf rust image dataset. After the model was trained, coffee leaf rust was detected in each frame. The mean average precision (mAP) and recall for the trained YOLOv5 model were 69% and 63.4%, respectively. For YOLOv8, the mAP and recall were approximately 70.2% and 65.9%, respectively. To evaluate the performance of the two trained models in detecting coffee leaf rust on trees, 202 original images were used for testing with the best-trained weight from each model. Compared to YOLOv5, YOLOv8 demonstrated superior accuracy in detecting coffee leaf rust. With a mAP of 73.2%, YOLOv8 outperformed YOLOv5, which achieved a mAP of 70.5%. An edge device was utilized to deploy real-time detection of CLR with the best-trained model. The detection was successfully executed with high confidence in detecting CLR. The system was further integrated into pruning solutions for Arabica coffee farms. A pruning device was designed using Autodesk Fusion 360 ® and fabricated for testing on a coffee plantation in Indonesia.
Why it matches plant phenotyping methodsコーヒー葉のさび病症状を画像から検出・推定するYOLOモデルを開発し、複数データセットで性能評価してエッジデバイスへ実装しており、植物病害状態の取得方法が中心である。
abstractTherefore, detecting coffee leaf rust is important to support the decision on pruning infected leaves.
The accurate and fast assessment of plant diseases and fruits is important for sustainable and productive agriculture. However, typically manual methods are adopted for the assessment of plant diseases and fruit, which is a time-consuming, resource-intensive, and error-prone approach. A few artificial intelligence (AI)-based methods have been introduced to automate this process, but they show limitations in attaining high performance in challenging imaging conditions such as occlusions, poor lighting, noise, indistinctive boundaries, and excessive morphological variations. Moreover, current approaches also lack in providing computationally efficient solutions. To overcome these issues, two novel architectures are developed to segment plant diseases and fruits with higher segmentation performance and less computational requirements. The efficient feature fusion segmentation network (EFFS-Net) is the base network, and a multi-scale dilated feature fusion segmentation network (MDFS-Net) is the final network of this study. EFFS-Net uses an identity skip path-based feature fusion mechanism with an efficient grouped convolutional depth (EGCD) to provide satisfactory segmentation performance with high computational efficiency. MDFS-Net uses a multi-scale feature fusion mechanism and fuses low-level information in the EGCD and other sections of the network to learn detailed input features for delivering promising performance even in challenging imaging conditions. MDFS-Net also applies multiple receptive fields to the low-level information in the effective receptive field processing (ERFP) block for fusion near the pixel classification stage for further performance enhancement. Both networks are evaluated using a Brazilian Arabica coffee leaf (BRACOL) image dataset, an Australian Center for Field Robotics orchard fruit (apple) dataset, and a necrotized cassava root cross-section image dataset. The proposed method provides a promising segmentation performance, achieving dice similarity coefficients of 88.81 %, 95.01 %, and 86.04 % with performance improvement of 3.5 %, 2.6 %, and 1.07 % on the three datasets, respectively, with approximately ten times less number of required trainable parameters compared with the state-of-the-art methods. • Architectures (EFFS-Net and MDFS-Net) for plant disease and fruit segmentation. • EFFS-Net uses efficient grouped convolutional depth. • MDFS-Net uses multi-scale and multi-receptive field-based feature fusion mechanisms. • Our trained models and codes are publicly available via Github site.
Why it matches plant phenotyping methods植物病害および果実を画像からセグメンテーションする新規ネットワークを開発・評価しており、植物の病害状態や器官の抽出が中心的な方法論的貢献である。
abstracttwo novel architectures are developed to segment plant diseases and fruits with higher segmentation performance and less computational requirements
Spectral characterization of coffee cultivars after pruning may help predict the crop’s diverse phytotechnical behaviors. Therefore, this study aimed to differentiate coffee genotypes based on leaf reflectance following pruning and to develop models capable of estimating the agronomic parameters of vegetative growth. This study included eight coffee cultivars. The biochemical and leaf structure parameters were quantified for the spectral characterization of each genotype and adopted as the basis for the application of vegetation indices and to generate models that can estimate agronomic parameters after pruning. The cultivar Topázio MG-1190 proved to be the most efficient at absorbing electromagnetic radiation in the blue (220–510 nm), green (520–590 nm), and red (690–730 nm) spectral ranges among all other cultivars after pruning. The regression models could estimate the following vegetative growth parameters of the coffee cultivars: height using the normalized difference water index (root mean square error (RMSE) = 5.78%), crown diameter and plagiotropic branch length using the enhanced vegetation index (RMSE = 10.21% and 12.69%, respectively), the number of nodes using the chlorophyll b index (RMSE = 14.47%), chlorophyll a content using the photochemical reflectance index (RMSE = 2.39%), and leaf water potential using the leaf water vegetation index-1 (40.72%). The hyperspectral characterization of coffee cultivars with respect to the phytotechnical development of the genotypes after pruning was successfully accomplished. This tool can assist coffee growers to enhance their competitiveness and productivity through the development of management strategies such as the early detection of plant growth issues.
Why it matches plant phenotyping methodsコーヒー葉のハイパースペクトル計測と回帰モデルにより、草高・樹冠径・枝長・節数・葉緑素量・水ポテンシャルなどの植物形質を推定する方法が研究の中心である。
abstractto develop models capable of estimating the agronomic parameters of vegetative growth
Plant diseases threaten agricultural sustainability by reducing crop yields. Rapid and accurate disease identification is crucial for effective management. Recent advancements in artificial intelligence (AI) have facilitated the development of automated systems for disease detection. This study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images. To do so, we propose a novel approach as the preprocessing step for the classification in which enhanced multivariance product representation (EMPR) is used to decompose the considered image into components, a new image is constructed using some of those components, and the contrast of the new image is enhanced by applying high-dimensional model representation (HDMR) to highlight the diseased parts of the leaves. Popular convolutional neural network (CNN) architectures, including AlexNet, VGG16, and ResNet50, are evaluated. Results show that VGG16 achieves the highest classification accuracy of approximately 96%, while all models perform well in predicting disease severity levels, with accuracies exceeding 85%. Notably, the ResNet50 model achieves accuracy levels surpassing 90%. This research contributes to the advancement of automated crop health management systems.
Why it matches plant phenotyping methodsコーヒー葉画像から病害の種類と重症度を推定する画像・深層学習手法が研究の中心であり、植物状態の表現型評価に該当する。
abstractThis study focuses on enhancing the classification of diseases and estimating their severity in coffee leaf images.
Reproduction assets foundThe authors explicitly state that the data, algorithms, and code for the DeepEMPR coffee leaf disease detection study are publicly available on GitHub and Zenodo, and the leaf image dataset (LeafData.zip) is deposited on Figshare. These are paper-specific, publicly actionable assets directly supporting the study's phenCode · publicd the experiments, analyzed the data, performed the computation work, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft.
Data Availability
The following information was supplied regarding data availability:
The data, algorithms and code are available at GitHub and Zenodo:
- https://github.com/ArticleCodeHub/DeepEMPR
- Topal, A. (2024). DeepEMPR. Zenodo. https://doi.org/10.5281/zenodo.13823450 .
The code is available in the Supplemental File .
The data is also available at Figshare: Topal, Ahmet (2024). LeafData.zip. figshare. Dataset. https://doi.org/10.6084/m9.figshare.26060464.v1 .
References
Agarwal et al. (2020)
Agarwal M
Singh A
ArjOpen asset ↗ArticleCodeHub/DeepEMPRlines:660-763Code · publicgures and/or tables, authored or reviewed drafts of the article, and approved the final draft.
Data Availability
The following information was supplied regarding data availability:
The data, algorithms and code are available at GitHub and Zenodo:
- https://github.com/ArticleCodeHub/DeepEMPR
- Topal, A. (2024). DeepEMPR. Zenodo. https://doi.org/10.5281/zenodo.13823450 .
The code is available in the Supplemental File .
The data is also available at Figshare: Topal, Ahmet (2024). LeafData.zip. figshare. Dataset. https://doi.org/10.6084/m9.figshare.26060464.v1 .
References
Agarwal et al. (2020)
Agarwal M
Singh A
Arjaria S
Sinha A
Gupta S
2020
ToLeD: tomato leaf disease detection using convolutiOpen asset ↗10.5281/zenodo.13823450lines:660-763Dataset · publicdata, algorithms and code are available at GitHub and Zenodo:
- https://github.com/ArticleCodeHub/DeepEMPR
- Topal, A. (2024). DeepEMPR. Zenodo. https://doi.org/10.5281/zenodo.13823450 .
The code is available in the Supplemental File .
The data is also available at Figshare: Topal, Ahmet (2024). LeafData.zip. figshare. Dataset. https://doi.org/10.6084/m9.figshare.26060464.v1 .
References
Agarwal et al. (2020)
Agarwal M
Singh A
Arjaria S
Sinha A
Gupta S
2020
ToLeD: tomato leaf disease detection using convolution neural network
Procedia Computer Science 167 293 301
10.1016/j.procs.2020.03.225
Ahmed et al. (2019)
Ahmed K
Shahidi TR
Alam SMI
Momen S
2019
Rice leaf disease detection using machineOpen asset ↗10.6084/m9.figshare.26060464.v1lines:660-763Plant phenotyping relevance match · UnverifiedCrossref · checked 7 Sept 2026
Published4 Nov 2024ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesCited by 1 · OpenAlex ↗
Abstract. Brazil plays a crucial role in the global economy due to its significant contribution to the agricultural sector, particularly in coffee production, where it stands out as the largest producer and exporter of processed coffee. Various disturbances can influence coffee plants, causing abnormalities that can hinder their successful growth. Parameters such as plant height and canopy diameter play an essential role in assessing the health and productivity of the plants, reflecting their growth, development, and ability to capture sunlight. Additionally, height is also related to the balanced distribution of nutrients and water, providing valuable information about overall performance and the capacity for healthy production. In this regard, the application of methodologies involving remote sensing and machine learning algorithms has shown promising results in the rapid and safe acquisition of information about agricultural systems. This study evaluates different machine learning algorithms, using radiometric values from multispectral images obtained by remote sensing platforms as input datasets for estimating plant height and canopy diameter in coffee cultivation. The best performance was observed for architectures that showed lower RMSE and RMSE% values. For the plant height parameter (m), the RGB sensor exhibited the best performance using the Random Tree algorithm, with an RMSE (0.27) and RMSE% (8.80). For the canopy diameter (m), the sensor showed the best performance using the Random Forest algorithm, with an RMSE (0.15) and RMSE% (8.16).
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コーヒーの草丈・樹冠径を推定し、アルゴリズム性能をRMSEで比較評価しているため、植物表現型取得法が中心です。
abstractThis study evaluates different machine learning algorithms, using radiometric values from multispectral images obtained by remote sensing platforms as input datasets for estimating plant height and canopy diameter in coffee cultivation.
Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像とYOLOv9、二重チャネルNMSを用いてコーヒー植物の検出・セグメンテーション・個体数推定手法を開発し、精度評価しているため、植物フェノタイピング手法が中心である。
titleA Coffee Plant Counting Method Based on Dual-Channel NMS and YOLOv9 Leveraging UAV Multispectral Imaging
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 will publish all the codes and datasets in this study after the article is accepted
https://github.com/legend2588/Coffee-plant-counting.gitOpen asset ↗https://github.com/legend2588/Coffee-plant-counting.gitpdf-page:19 lines:1-58Plant phenotyping relevance match · UnverifiedEurope PMC · checked 14 Sept 2026
Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.
Why it matches plant phenotyping methodsRGB画像のセグメンテーション、YOLOv5、OpenCVによる果実検出・計数を開発し、コーヒー生産量推定という植物の収量関連形質を評価しており、画像ベースの表現型取得が中心である。
abstractThis study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images.
Plant 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).
Deep learning and computer vision, using remote sensing and drones, are 2 promising nondestructive methods for plant monitoring and phenotyping. However, their applications are infeasible for many crop systems under tree canopies, such as coffee crops, making it challenging to perform plant monitoring and phenotyping at a large spatial scale at a low cost. This study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach. The approach uses basic smartphones to take a few pictures of coffee trees; 2,968 trees were investigated with 8,904 pictures in Junín and Piura (Peru), Cauca, and Quindío (Colombia) in 2022, with the help of nearly 1,000 smallholder coffee farmers. Then, we trained and validated YOLO (You Only Look Once) v8 for detecting cherries in the dataset in Peru. An average number of cherries per picture was multiplied by the number of branches to estimate the total number of cherries per tree. The model's performance in Peru showed an R 2 of 0.59. When the model was tested in Colombia, where different varieties are grown in different biogeoclimatic conditions, the model showed an R 2 of 0.71. The overall performance in both countries reached an R 2 of 0.72. The results suggest that the method can be applied to much broader scales and is transferable to other varieties, countries, and regions. To our knowledge, this is the first AI-powered method for counting coffee cherries and has the potential for a geographic-scale, multiyear, photo-based phenotypic monitoring for coffee crops in low-income countries worldwide.
Why it matches plant phenotyping methodsスマートフォン画像と深層学習でコーヒー果実数を推定する方法を開発・検証しており、植物形質の取得が研究の中心です。
abstractThis study aims to develop a geographic-scale monitoring method for coffee cherry counting, supported by an artificial intelligence (AI)-powered citizen science approach.
Reproduction assets foundThe paper's Data Availability statement explicitly deposits representative coffee cherry pictures (phenotyping image data) and the authors' Python analysis script in a public GitHub repository, matching the paper's smartphone-image cherry counting analysis. Other URLs (FAOSTAT, SENAMHI, IDEAM, Label Studio, YOLOv5 docsCode · publicSome representative pictures and the Python script used for the study are available at the GitHub repository: https://github.com/j-river1/Croppie .Open asset ↗j-river1/Croppielines:207-221Code / dataset availability confirmedCrossref · checked 15 Sept 2026
In an effort to advance Digital Agriculture, this paper provides a comparative assessment of Artificial Neural Networks for intelligent detection of a major biotic stress factors in coffee cultivation. Through a multi-class Computer Vision task, the superior performance of Convolutional Neural Networks, notably the ShuffleNet architecture, was discerned, further substantiated by statistical analyses. This model's performance, akin to state-of-the-art solutions, was achieved with reduced training data and parameter requirements. Robustness was affirmed through external validation using alternative datasets. This contribution directly enhances coffee plantations' quality and supports the development of Edge Computing devices for Agricultural IoT.
Why it matches plant phenotyping methodsコーヒー葉の病害状態を画像から検出するコンピュータビジョン手法を比較・評価し、外部データセットで検証しているため、植物病害フェノタイピング手法が中心です。
abstractThrough a multi-class Computer Vision task, the superior performance of Convolutional Neural Networks, notably the ShuffleNet architecture, was discerned
Reproduction assets foundThe paper's Declarations section explicitly states that the datasets generated and/or analysed during the study are available at the authors' public GitHub repository (https://github.com/elloa/jis-2023), which is an allowed URL. This repository is the paper-specific asset covering the coffee leaf disease image datasetsDataset · publicent Systems (LSI) at the Amazonas State University (UEA).
Authors’ Contributions
Both authors have contributed equally to this manuscript.
Competing interests
The authors declare they do not have competing interests.
Availability of data and materials
The datasets generated and/or analysed during the current study are
available https://github.com/elloa/jis-2023
References
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z.,
Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Is-
ard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M.,
Levenberg, J., Mané, D., Monga, R., Moore, S., Mur-
ray, D., Olah, C., Schuster, M., ShOpen asset ↗github.com/elloa/jis-2023pdf-raw-page:12 lines:1-91Plant phenotyping relevance match · UnverifiedCrossref · checked 7 Sept 2026
Brazil stands out among coffee-growing countries worldwide. The use of precision agriculture to monitor coffee plants after transplantation has become an important step in the coffee production chain. The objective of this study was to assess how coffee plants respond after transplanting seedlings grown in different containers, based on multispectral images acquired by Unmanned Aerial Vehicles (UAV). The study was conducted in Santo Antônio do Amparo, Minas Gerais, Brazil. The coffee plants were imaged by UAV, and their height, crown diameter, and chlorophyll content were measured in the field. The vegetation indices were compared to the field measurements through graphical and correlation analysis. According to the results, no significant differences were found between the studied variables. However, the area transplanted with seedlings grown in perforated bags showed a lower percentage of mortality than the treatment with root trainers (6.4% vs. 11.7%). Additionally, the vegetation indices, including normalized difference red-edge, normalized difference vegetation index, and canopy planar area calculated by vectorization (cm2), were strongly correlated with biophysical parameters. Linear models were successfully developed to predict biophysical parameters, such as the leaf area index. Moreover, UAV proved to be an effective tool for monitoring coffee using this approach.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像から植生指数・樹冠面積を抽出し、コーヒーの生物物理形質を推定・検証する手法が研究の中心である。
abstractThe objective of this study was to assess how coffee plants respond after transplanting seedlings grown in different containers, based on multispectral images acquired by Unmanned Aerial Vehicles (UAV).
Why it matches plant phenotyping methodsコーヒー葉の病害状態（brown-eye spotの発生・重症度）を機械学習で予測する手法が研究の中心であり、複数モデルの較正・比較と精度評価を行っているため、病害表現型の計算的推定として含める。
abstractThis study focuses on forecasting coffee brown-eye spot using various models that incorporate agrometeorological data, allowing for predictions at least 1 week prior to the occurrence of disease.
Coffee Leaf Rust (CLR), caused by the fungus Hemileia vastatrix, poses a severe threat to global coffee production. Timely detection is critical for effective control measures. This study employs Convolutional Neural Networks (CNNs) to enhance CLR detection accuracy. Traditionally, this task relies on expert assessment. DL emerges as a promising approach, capable of autonomously extracting salient features. Our model, trained on a diverse dataset, accurately identifies CLR. Using 1365 meticulously curated images, the model undergoes rigorous preprocessing and augmentation. The DL-based approach achieves remarkable accuracy (98.89%), precision (99.00%), recall (98.07%), and an F1 score of (98.55%). These outcomes establish the CNN model as a proficient system for precise, real-time CLR diagnosis. This study contributes to the creation of an efficient system, safeguarding coffee orchard vitality and productivity.
Why it matches plant phenotyping methodsコーヒー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、植物フェノタイピング手法として採用。
abstractThis study employs Convolutional Neural Networks (CNNs) to enhance CLR detection accuracy.
Abstract—Coffee plants are woody evergreens that can reach a height of up to ten meter’s in the wild with the fruit of coffee beans, which are the seeds that produce the majority of the world’s coffee. This study focuses on a variety of Arabica Coffee leaf diseases that occurs frequently in Ethiopia. The diseases which occurred primarily are Miner coffee leaf disease (MCLD), Rust coffee leaf disease (RCLD), Cercospora coffee leaf disease (CCLD), and Phoma coffee leaf disease (PCLD). The study focuses on the identification of those four a variety of diseases through image processing as well as machine learning mechanisms through Transfer learning and convolution neural network (CNN) architectures through the feed-forward model, resnet50 model, inceptionV3 model, and deep learning model through tenser flow, which are the most popular models to detect various plant diseases with high Accuracy. All the pictures used for this study were captured from the whole state of Ethiopia in every place where coffee plant exists. The total number of data sets currently used is 58,546 with 80 percent being put to use for training, while the rest 20 percent were employed for testing, with a 99.9%, 98.5%, 99%, and 99% respectively with a total success rate in classification accuracy and 99.8%, 98%, 99% and 99.7% respectively with total success rate in confusion matrix accuracy. So there is excellent performance in inferences.
Why it matches plant phenotyping methodsコーヒー葉の病害状態を画像処理と機械学習で直接分類する方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。
abstractThe total number of data sets currently used is 58,546 with 80 percent being put to use for training, while the rest 20 percent were employed for testing
The early identification of plant diseases is crucial for preventing the loss of crop production. Recently, the advancement of deep learning has significantly improved the identification of plant leaf diseases. However, most approaches depend on a single convolutional neural network (CNN) to extract the leaf features, ignoring the opportunity to take full advantage of the feature richness available in the images. This paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases. DFNet aims to increase the diversity of extracted features in order to improve discrimination. Instead of using a single‐CNN model, DFNet relies on a double‐pretrained CNN model, MobileNetV2 and NASNetMobile, as the feature extractor. The features extracted from each CNN are fused in the fusion layer using a fully connected network. The proposed method was evaluated using corn (Zea mays L.) and coffee (Coffea canephora) leaf disease datasets and compared to the existing models. The experiment showed that DFNet is superior and consistent to other CNN methods by achieving an accuracy of 97.53% for corn leaf diseases and 94.65% for coffee leaf diseases.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類するCNN手法の開発・比較評価が中心であり、植物病害状態の画像ベース表現型推定に該当する。
abstractThis paper explores a novel CNN model with multiple automated feature extractors, namely, dense fusion CNN (DFNet), for classifying plant leaf diseases.
In Indonesia, coffee is one of the plantation products with a relatively high level of productivity and is a source of foreign exchange income for the country. However, unfortunately, certain factors can threaten productivity and quality in cultivating coffee plants, one of which is rust leaf disease. This disease causes disturbances in photosynthesis, thereby reducing plant yields. Therefore, to maintain and control productivity in coffee cultivation, this research carried out the process of observing coffee leaf images through segmentation using the Otsu Thresholding and Mean Denoising methods. The entire series of processes in this research was carried out using the Python programming language and succeeded in providing output in the form of image comparisons showing areas affected by Rust Leaf disease using the Otsu thresholding method alone and the Otsu thresholding method combined with a non-local means denoising algorithm. The test results prove that the Otsu thresholding method with the non-local means denoising algorithm has a smaller MSE value. It is the most optimal method for handling coffee leaf disease image segmentation with an accuracy level of 88%. It is hoped that this research can support farmers in providing insight into early detection of coffee plant diseases and increasing productivity through visual analysis.
Why it matches plant phenotyping methodsコーヒー葉の病斑領域を画像セグメンテーションで抽出し、植物の病害状態を推定する手法の開発・比較が中心であるため。
abstractresearch carried out the process of observing coffee leaf images through segmentation using the Otsu Thresholding and Mean Denoising methods
Coffee leaf disease is a problem that needs attention because it affects the quality and productivity of the coffee harvest and is detrimental to farmers. Therefore, a system is needed to identify types of coffee leaf diseases using artificial intelligence. There are four types of coffee leaf diseases, namely Miner leaf, Phoma leaf, Rust leaf, and Nodisease leaf. The research used the EfficientNet Architecture Convolutional Neural Network (CNN) method to detect types of disease on coffee leaves. This method was chosen because it is capable and reliable in processing digital images for pattern recognition. The dataset used is 1,464 images with dimensions of 2048 x 1024 pixels with RGB type which are divided into 1,264 training data and 400 testing data. Several architectures used in EfficientNet are EfficientNet B0, EfficientNet B1, EfficientNet B2, EfficientNet B3, EfficientNet B4. Parameters used are Lanczos resampling, Epoch 25, Learning Rate 0.0001, Loss Function Sparse Categorical Cross Entropy, Optimizer Adam. The results of training data testing, namely the CNN EfficientNet B1 Architecture Model method, got the best accuracy of 97% and a loss of 0.1328 and testing data testing got an accuracy of 0.97% and a loss of 0.1328. The architecture of the EfficientNet B1 model is better than other architectural models, namely VGG16, ResNet50, MobileNetv2, EfficientNet B0, EfficientNet B2, EfficientNet B3, EfficientNet B4, EfficientNet B5, EfficientNet B6, EfficientNet B7.
Why it matches plant phenotyping methodsコーヒー葉画像から病害状態を分類するCNN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。
abstractThe research used the EfficientNet Architecture Convolutional Neural Network (CNN) method to detect types of disease on coffee leaves.
Reproduction assets foundThe paper's coffee leaf disease image dataset (1,464 RGB images of Miner, Phoma, Rust, and healthy leaves) is a public Kaggle dataset explicitly linked by the authors. No author analysis code or trained model checkpoints are reported as available.Dataset · publicIICS SEMNASTIK 2023 E-ISSN: 2774-5899 | P-ISSN: 2774-5880 ■ 61
pixels with RGB color mode, and the total number of images is 1.464, as detailed in Table 3. This dataset
can be accessed via the following link:
https://www.kaggle.com/datasets/gauravduttakiit/coffee-leaf-diseases.
Rust Phoma
Nodisease Miner
Figure 4. Types of Coffee Leaf Diseases
Table 3. Dataset details
Type Training Testing
Miner 332 128
No Disease 284 116
Phoma 388 96
Rust 260 60
Total 1.264 400
2.3 Evaluation
Evaluation is a critical step to obtain performance from model results [27][28]. This evaluation
process utilizes a matrix, aOpen asset ↗Kaggle · gauravduttakiit/coffee-leaf-diseasespdf-layout-page:4 lines:1-52Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Conventional methods of crop yield estimation are costly, inefficient, and prone to error resulting in poor yield estimates. This affects the ability of farmers to appropriately plan and manage their crop production pipelines and market processes. There is therefore a need to develop automated methods of crop yield estimation. However, the development of accurate machine-learning methods for crop yield estimation depends on the availability of appropriate datasets. There is a lack of such datasets, especially in sub-Saharan Africa. We present curated image datasets of coffee and cashew nuts acquired in Uganda during two crop harvest seasons. The datasets were collected over nine months, from September 2022 to May 2023. The data was collected using a high-resolution camera mounted on an Unmanned Aerial Vehicle . The datasets contain 3000 coffee and 3086 cashew nut images, constituting 6086 images. Annotated objects of interest in the coffee dataset consist of five classes namely: unripe, ripening, ripe, spoilt, and coffee_tree. Annotated objects of interest in the cashew nut dataset consist of six classes namely: tree, flower, premature, unripe, ripe, and spoilt. The datasets may be used for various machine-learning tasks including flowering intensity estimation, fruit maturity stage analysis, disease diagnosis, crop variety identification, and yield estimation.
Why it matches plant phenotyping methodsコーヒーとカシューナッツの画像データセットを構築し、開花強度、成熟段階、収量などの植物形質・状態推定に利用する方法基盤を提供しており、表現型取得用データセットが研究の中心である。
abstractWe present curated image datasets of coffee and cashew nuts acquired in Uganda during two crop harvest seasons.
Reproduction assets foundThe paper's own UAV coffee and cashew image datasets with YOLO annotations are publicly deposited on Mendeley Data (DOI 10.17632/r46c6bpfpf.1), directly reproducing the paper's phenotyping measurements. Annotation tools (Makesense AI, VGG Image Annotator) are generic third-party tools, not paper-specific assets.Dataset · publicre of f/1.7 and focus range of 1 m to ∞, shutter speed of 2-1/8000s and ISO range of 100-6400 (Auto and Manual)
Data source location
Institution: Makerere University
City: Kampala
Country: Uganda
Data accessibility
Repository name: Mendely Data
Data identification number: http://doi.org/10.17632/r46c6bpfpf.1
Direct URL to data:
https://data.mendeley.com/datasets/r46c6bpfpf/1
1.
Value of the Data
•
Flowering intensity estimation. Flowering represents an important stage in coffee and cashew farming since it affects crop yield. It has a significant impact on yield in that flowering intensity is positively correlated with the amount of crop yield. Therefore, flowering intensity could be an imporOpen asset ↗10.17632/r46c6bpfpf.1lines:1-51Plant phenotyping relevance match · UnverifiedCrossref · checked 7 Sept 2026
Published5 Dec 2023ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesCited by 0 · OpenAlex ↗
Abstract. Leaf Water Potential (LWP) is an indicator widely used to understand water relations in a coffee tree. Monitoring water potential is a challenge for remote sensing using low-cost multispectral cameras, with images taken by remotely piloted aircraft. The objective of this work was to evaluate the potential of a low-cost camera to discriminate different water treatments in the coffee tree. In addition, the accuracy of models to estimate LWP in the coffee crop was evaluated. The results showed that the NDVI (Normalized Difference Vegetation Index) vegetation index was able to discriminate 61.6 % more plots in a drought regime than the Near-InfraRed (NIR) band in the rainfall regime. For LWP, the architecture that presented the best performance in the detection of water stress was for the first flight (SMOreg algorithm using as predictor variables all bands, Red, Green, and NIR, and the NDVI vegetation index) with RMSE value of 0.1880 and RMSE% of 34.18. For the second flight (Random Tree algorithm, using as predictor variables all bands and NDVI) with RMSE (0.0520) and RMSE% (32.00) values.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からコーヒー樹の葉水ポテンシャルと水ストレスを推定し、モデル精度を評価することが中心であり、植物生理状態の取得・推定手法を技術的に検証している。
abstractMonitoring water potential is a challenge for remote sensing using low-cost multispectral cameras, with images taken by remotely piloted aircraft.
CoffeeRaman / spectroscopyLeafPhysiological trait estimationWater status / transpiration
In this work, we present a practical approach combining experimental and theoretical analyses to assess water evaporation in Arabica coffee leaves. We examine continuously the changing water content of leaves through optical reflectance spectroscopy and mass loss measurements, beginning from a fully saturated stage and extending beyond the turgor loss point. We establish a relationship between the current water content and the dielectric function, based on the changing of the molecular water dipoles inside the leaf due to evaporation.
Why it matches plant phenotyping methods葉の含水量を光学反射分光と質量減少で連続測定し、誘電関数との関係を構築する手法が研究の中心であり、植物の水分状態を評価する生理 phenotyping に該当する。
abstractWe examine continuously the changing water content of leaves through optical reflectance spectroscopy and mass loss measurements
Due to the constraints of agricultural computing resources and the diversity of plant diseases, it is challenging to achieve the desired accuracy rate while keeping the network lightweight. In this paper, we proposed a computationally efficient deep learning architecture based on the mobile vision transformer (MobileViT) for real-time detection of plant diseases, which we called plant-based MobileViT (PMVT). Our proposed model was designed to be highly accurate and low-cost, making it suitable for deployment on mobile devices with limited resources. Specifically, we replaced the convolution block in MobileViT with an inverted residual structure that employs a 7×7 convolution kernel to effectively model long-distance dependencies between different leaves in plant disease images. Furthermore, inspired by the concept of multi-level attention in computer vision tasks, we integrated a convolutional block attention module (CBAM) into the standard ViT encoder. This integration allows the network to effectively avoid irrelevant information and focus on essential features. The PMVT network achieves reduced parameter counts compared to alternative networks on various mobile devices while maintaining high accuracy across different vision tasks. Extensive experiments on multiple agricultural datasets, including wheat, coffee, and rice, demonstrate that the proposed method outperforms the current best lightweight and heavyweight models. On the wheat dataset, PMVT achieves the highest accuracy of 93.6% using approximately 0.98 million (M) parameters. This accuracy is 1.6% higher than that of MobileNetV3. Under the same parameters, PMVT achieved an accuracy of 85.4% on the coffee dataset, surpassing SqueezeNet by 2.3%. Furthermore, out method achieved an accuracy of 93.1% on the rice dataset, surpassing MobileNetV3 by 3.4%. Additionally, we developed a plant disease diagnosis app and successfully used the trained PMVT model to identify plant disease in different scenarios.
Why it matches plant phenotyping methods植物画像から病害状態を推定する軽量な深層学習モデルを開発・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。
abstractwe proposed a computationally efficient deep learning architecture based on the mobile vision transformer (MobileViT) for real-time detection of plant diseases
The Segment Anything Model (SAM) is a versatile image segmentation model that enables zero-shot segmentation of various objects in any image using prompts, including bounding boxes, points, texts, and more. However, studies have shown that the SAM performs poorly in agricultural tasks like crop disease segmentation and pest segmentation. To address this issue, the agricultural SAM adapter (ASA) is proposed, which incorporates agricultural domain expertise into the segmentation model through a simple but effective adapter technique. By leveraging the distinctive characteristics of agricultural image segmentation and suitable user prompts, the model enables zero-shot segmentation, providing a new approach for zero-sample image segmentation in the agricultural domain. Comprehensive experiments are conducted to assess the efficacy of the ASA compared to the default SAM. The results show that the proposed model achieves significant improvements on all 12 agricultural segmentation tasks. Notably, the average Dice score improved by 41.48% on two coffee-leaf-disease segmentation tasks.
Why it matches plant phenotyping methods農業画像から作物病害を分割・推定するモデルアダプターを開発し、複数タスクで性能検証しているため、植物病害状態の画像ベース表現型計測が中心である。
abstractthe agricultural SAM adapter (ASA) is proposed, which incorporates agricultural domain expertise into the segmentation model through a simple but effective adapter technique.
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2件を確認しました。Dataset · publicThese data can be
downloaded from https://doi.org/10.17632/yy2k5y8mxg.1Open asset ↗10.17632/yy2k5y8mxg.1pdf-page:15 lines:1-59Dataset · publicdownloaded from https://doi.org/10.17632/yy2k5y8mxg.1 and https://data.mendeley.com/datasetsOpen asset ↗pdf-page:15 lines:1-59Plant phenotyping relevance match · UnverifiedCrossref · checked 8 Sept 2026
Rwandan coffee holds significant importance and immense value within the realm of agriculture, serving as a vital and valuable commodity. Additionally, coffee plays a pivotal role in generating foreign exchange for numerous developing nations. However, the coffee plant is vulnerable to pests and diseases weakening production. Farmers in cooperation with experts use manual methods to detect diseases resulting in human errors. With the rapid improvements in deep learning methods, it is possible to detect and recognize plan diseases to support crop yield improvement. Therefore, it is an essential task to develop an efficient method for intelligently detecting, identifying, and predicting coffee leaf diseases. This study aims to build the Rwandan coffee plant dataset, with the occurrence of coffee rust, miner, and red spider mites identified to be the most popular due to their geographical situations. From the collected coffee leaves dataset of 37,939 images, the preprocessing, along with modeling used five deep learning models such as InceptionV3, ResNet50, Xception, VGG16, and DenseNet. The training, validation, and testing ratio is 80%, 10%, and 10%, respectively, with a maximum of 10 epochs. The comparative analysis of the models’ performances was investigated to select the best for future portable use. The experiment proved the DenseNet model to be the best with an accuracy of 99.57%. The efficiency of the suggested method is validated through an unbiased evaluation when compared to existing approaches with different metrics.
Why it matches plant phenotyping methodsコーヒー葉の病害状態を画像から認識・分類する深層学習手法とデータセットを中心に開発・比較・検証しており、植物病害フェノタイプの取得が中心である。
abstractThis study aims to build the Rwandan coffee plant dataset
The assessment of the nutritional status of plants is traditionally performed by wet-digestion methods using oven-dried and ground samples. This process requires sampling, takes time, and it is non-environmentally friendly. Agricultural and environmental science have been greatly benefited by in-field, ecofriendly methods, and real-time element measurements. This work employed the portable X-ray fluorescence spectrometry (pXRF) to analyze intact and fresh leaves of crops aiming to assess the effect of water content and leaf surface (adaxial and abaxial) on pXRF results. Also, pXRF data were used to predict the real concentration of macro- and micronutrients. Eight crops (bean, castor plant, coffee, eucalyptus, guava tree, maize, mango, and soybean) with contrasting water contents were used. Intact leaf fragments (∼2 × 2 cm), fresh or oven-dried (60 °C) were obtained to be analyzed via pXRF on both adaxial and abaxial surface. Conventional wet-digestion method was also performed on powdered material to obtain the concentration of macro- and micronutrients via ICP-OES. The data were subjected to descriptive statistics, principal component analysis (PCA) and random forest (RF) algorithm regression. RF was used to predict the real concentration of macro- and micronutrients based on pXRF measurements obtained directly on intact leaves. Water content had a significant effect on pXRF results. However, a positive correlation between the concentration of macro- and micronutrients obtained via pXRF directly on intact leaves and conventional analysis performed on powdered samples was obtained. PCA analysis allowed a clear differentiation of crops based on elemental composition. The concentrations of macro- and micronutrients were very accurately predicted via RF. Even elements not detected by pXRF (N and B) were satisfactory predicted. From this pilot study, it is possible to concluded that pXRF is feasible for in-field assessment of nutritional status of plants. Further studies are needed to obtain specific and robust calibrations for each crop.
Why it matches plant phenotyping methods携帯型XRFによる生葉の栄養元素濃度・栄養状態推定法を開発・検証しており、植物表現型の取得手法が研究の中心である。
abstractThis work employed the portable X-ray fluorescence spectrometry (pXRF) to analyze intact and fresh leaves of crops aiming to assess the effect of water content and leaf surface (adaxial and abaxial) on pXRF results.
The current methods of classifying plant disease images are mainly affected by the training phase and the characteristics of the target dataset. Collecting plant samples during different leaf life cycle infection stages is time-consuming. However, these samples may have multiple symptoms that share the same features but with different densities. The manual labelling of such samples demands exhaustive labour work that may contain errors and corrupt the training phase. Furthermore, the labelling and the annotation consider the dominant disease and neglect the minor disease, leading to misclassification. This paper proposes a fully automated leaf disease diagnosis framework that extracts the region of interest based on a modified colour process, according to which syndrome is self-clustered using an extended Gaussian kernel density estimation and the probability of the nearest shared neighbourhood. Each group of symptoms is presented to the classifier independently. The objective is to cluster symptoms using a nonparametric method, decrease the classification error, and reduce the need for a large-scale dataset to train the classifier. To evaluate the efficiency of the proposed framework, coffee leaf datasets were selected to assess the framework performance due to a wide variety of feature demonstrations at different levels of infections. Several kernels with their appropriate bandwidth selector were compared. The best probabilities were achieved by the proposed extended Gaussian kernel, which connects the neighbouring lesions in one symptom cluster, where there is no need for any influencing set that guides toward the correct cluster. Clusters are presented with an equal priority to a ResNet50 classifier, so misclassification is reduced with an accuracy of up to 98%.
Why it matches plant phenotyping methodsコーヒー葉の病斑・症状領域を画像から自動抽出・クラスタリングし、病害状態を分類する手法が研究の中心であるため、植物病害フェノタイピング手法として含める。
abstractThis paper proposes a fully automated leaf disease diagnosis framework that extracts the region of interest based on a modified colour process, according to which syndrome is self-clustered using an extended Gaussian kernel density estimation and the probability of the nearest shared neighbourhood.
Coffea canephora (C. canephora) has two botanical varieties, Robusta and Conilon. Intraspecific variability was hypothesized and projected for the selection of C. canephora plants able to maintain production in the context of global climate changes. For that, architectural, C-assimilation and biomass analyses were performed on 17-month-old Robusta (clones 'A1' and '3 V') and Conilon (clones '14' and '19') varieties grown in non-limiting soil, water and mineral nutrient conditions. Nondestructive coffee plant architecture coding, reconstruction and plant photosynthesis estimations were performed using a functional-structural plant modeling platform OpenAlea. 3D reconstructions and inclusion of parameters calculated and estimated from light response curves, such as dark respiration (Rd), maximum rate of carboxylation of RuBisCO and photosynthetic electron transport allowed the estimation of instantaneous and daily plant photosynthesis. The virtual orchard leaf area index was low, and light was not a limiting factor in early C. canephora development stages. Under such conditions, Robusta assimilated more CO2 at the plant and orchard scale and produced higher total biomass than Conilon. Lower plant daily photosynthesis and total biomass were correlated to higher Rd in Conilon than in Robusta. Among the architectural traits, leaf inclination, size and allometry were most highly correlated with plant assimilation and biomass. Relative allocation in leaf biomass was higher in '19' Conilon than in young Robusta plants, indicating intraspecific biomass partitioning. Similarly, variation in relative distribution of the root biomass and the root volume reflected clonal variation in soil occupation, indicating intraspecific variability in space occupation competitiveness. Coffea canephora denoted high root allocation in both Conilon and Robusta clones. However, relevant differences at subspecific levels were found, indicating the high potential of C. canephora to cope with drought events, which are expected to occur more frequently in the future, because of climate changes. The methodology developed here has the potential to be used for other crops and tree species. Highlights Functional-structural plant model was used to estimate photosynthesis on a plant and daily scales in Coffea canephora (C. canephora). Among the architectural traits, leaf shape and inclination had the most impact on photosynthesis and biomass. Under non-limiting conditions, Robusta had higher plant photosynthesis and biomass than Conilon. A higher leaf biomass allocation in Conilon clone '19' than in Robusta suggested variety-specific partitioning. Variation in the relative distribution of the root biomass indicated C. canephora intraspecific soil occupation variability.
Why it matches plant phenotyping methodsOpenAleaを用いた非破壊的な植物体アーキテクチャの3D再構成と光合成推定が研究の中心的手法であり、再利用可能な機能構造モデルとして植物形質を抽出している。
abstractNondestructive coffee plant architecture coding, reconstruction and plant photosynthesis estimations were performed using a functional-structural plant modeling platform OpenAlea.
The coffee plant is one of the main crops grown in Brazil. However, strategies to estimate its yield are questionable given the characteristics of this crop; in this context, robust techniques, such as those based on machine learning, may be an alternative. Thus, the aim of the present study was to estimate the yield of a coffee crop using multispectral images and machine learning algorithms. Yield data from a same study area in 2017, 2018 and 2019, Sentinel 2 images, Random Forest (RF) algorithms, Support Vector Machine (SVM), Neural Network (NN) and Linear Regression (LR) were used. Statistical analysis was performed to assess the absolute Pearson correlation and coefficient of determination values. The Sentinel 2 satellite images proved to be favorable in estimating coffee yield. Despite the low spatial resolution in estimating agricultural variables below the canopy, the presence of specific bands such as the red edge, mid infrared and the derived vegetation indices, act as a countermeasure. The results show that the blue band and green normalized difference vegetation index (GNDVI) exhibit greater correlation with yield. The NN algorithm performed best and was capable of estimating yield with 23% RMSE, 20% MAPE and R² 0.82 using 85% of the training and 15% of the validation data of the algorithm. The NN algorithm was also more accurate (27% RMSE) in predicting yield.
Why it matches plant phenotyping methodsマルチスペクトル画像と機械学習によりコーヒーの収量という植物形質を推定し、複数モデルの性能を検証しているため、フェノタイピング手法の応用・技術評価が中心である。
abstractthe aim of the present study was to estimate the yield of a coffee crop using multispectral images and machine learning algorithms.
Coffee leaf rust (CLR) is one of the most devastating leaf diseases in coffee plantations. By knowing the symptoms, severity, and spatial distribution of CLR, farmers can improve disease management procedures and reduce losses associated with it. Recently, Unmanned Aerial Vehicles (UAVs)-based images, in conjunction with machine learning (ML) techniques, helped solve multiple agriculture-related problems. In this sense, vegetation indices processed with ML algorithms are a promising strategy. It is still a challenge to map severity levels of CLR using remote sensing data and an ML approach. Here we propose a framework to detect CLR severity with only vegetation indices extracted from UAV imagery. For that, we based our approach on decision tree models, as they demonstrated important results in related works. We evaluated a coffee field with different infestation classes of CLR: class 1 (from 2% to 5% rust); class 2 (from 5% to 10% rust); class 3 (from 10% to 20% rust), and; class 4 (from 20% to 40% rust). We acquired data with a Sequoia camera, producing images with a spatial resolution of 10.6 cm, in four spectral bands: green (530–570 nm), red (640–680 nm), red-edge (730–740 nm), and near-infrared (770–810 nm). A total of 63 vegetation indices was extracted from the images, and the following learners were evaluated in a cross-validation method with 10 folders: Logistic Model Tree (LMT); J48; ExtraTree; REPTree; Functional Trees (FT); Random Tree (RT), and; Random Forest (RF). The results indicated that the LMT method contributed the most to the accurate prediction of early and several infestation classes. For these classes, LMT returned F-measure values of 0.915 and 0.875, thus being a good indicator of early CLR (2 to 5% of rust) and later stages of CLR (20 to 40% of rust). We demonstrated a valid approach to model rust in coffee plants using only vegetation indices and ML algorithms, specifically for the disease's early and later stages. We concluded that the proposed framework allows inferring the predicted classes in remaining plants within the sampled area, thus helping the identification of potential CLR in non-sampled plants. We corroborate that the decision tree-based model may assist in precision agriculture practices, including mapping rust in coffee plantations, providing both an efficient non-invasive and spatially continuous monitoring of the disease.
Why it matches plant phenotyping methodsUAV画像から植生指数を抽出し、機械学習でコーヒー葉さび病の重症度を推定する枠組みが研究の中心であり、植物病害状態のフェノタイプ取得・推定に該当する。
abstractHere we propose a framework to detect CLR severity with only vegetation indices extracted from UAV imagery.
Monitoring the spatial variability of agricultural variables is a main step in implementing precision agriculture practices. Active optical sensors (AOS), with their instrumentation directly on agricultural machines, are suitable and make it possible to obtain high-frequency data. This study aimed to evaluate the potential of AOS to map the spatial and temporal variability of coffee crop yields, as well as to establish guidelines for the acquisition of AOS data for sensing the sides of a coffee plant, allowing the evaluation of large commercial fields. The study was conducted in a commercial coffee area of 10.24 ha, cultivated with the Catuaí 144 variety. Data collection was performed with six Crop Circle ACS 430 sensors (Holland Scientific, Lincoln, NE, USA) and two N-Sensor NG sensors (Yara International, Dülmen, Germany). Seven field expeditions were made to collect data using the optical sensors during 2019 and 2021, obtaining data during the flowering, fruit-filling and fruit maturation phases (pre-harvest), and post-harvest. The results showed that the different faces of the same plant present a different Pearson’s correlation coefficient (r) to its yield, obtained with a yield monitor on the harvester. The face with the highest exposure to solar radiation presented a slightly higher correlation to yield (−0.34 ≤ r ≤ −0.17) when compared with the face with less exposure (−0.27 ≤ r ≤ −0.15). In addition, it was observed that the vegetation indices measured at the beginning of the coffee cycle (before the rainy season that starts in October) present a positive correlation to the coffee yield of that same year (0.73 ≤ r ≤ 0.91). On the other hand, this relationship is changed after the beginning of the rain season, at which time the vegetation index increases abruptly, inverting the correlation with the yield after that (−0.93 ≤ r ≤ −0.77). Furthermore, it was observed that, due to the biennial nature of coffee production, the vegetation index acquired at a specific time has an inverted relationship when compared with the yield of that year and to the yield of the following (or previous) year.
Why it matches plant phenotyping methodsコーヒー樹体の収量という植物形質をアクティブ光学センサーで推定・マッピングし、センサー取得条件や植生指数と収量の関係を評価しているため、測定手法の応用・検証が中心である。
abstractThis study aimed to evaluate the potential of AOS to map the spatial and temporal variability of coffee crop yields, as well as to establish guidelines for the acquisition of AOS data for sensing the sides of a coffee plant
Abstract This study mainly focused on the detection of Coffee Arabica nutrient deficiency by using image processing techniques. Coffee nutrition deficiency techniques are very traditional and time taking which means the agronomists simply detect deficiencies by observing the leaves of the coffee and decide by guessing. The study employed experimental research design which involves dataset preparation, designing classification model and evaluation. In addition, Python programming languages were used. The researcher has 422 total nutritional deficient Coffee plant leaves image data set, from this data first the researcher split 20 percent for testing which is 84 images and 338 training image data, and further from the remaining training data, the researcher again split20 percent validation data which is 10 images. The three pre-trained deep learning models were used to evaluate the experiments. The evaluation of the system indicated the performance of Mobile Net (0.9882), VGG16 Net (0.6471) and Inception_V3 (0.8095). Therefore, testing and training value of Mobile Net model was more accurate than the rest of two models. Finally, the prototype for detection of Coffee nutrient deficiency developed by using Mobile Net deep learning model. For the feature the researchers suggest doing more researchers by using others CNN architectures and more datasets.
Why it matches plant phenotyping methodsコーヒー葉画像から栄養欠乏という植物状態を推定する画像処理・深層学習モデルを開発し、複数モデルで性能評価しているため、フェノタイピング手法が中心である。
abstractThis study mainly focused on the detection of Coffee Arabica nutrient deficiency by using image processing techniques.
Genomic prediction has revolutionized crop breeding despite remaining issues of transferability of models to unseen environmental conditions and environments. Usage of endophenotypes rather than genomic markers leads to the possibility of building phenomic prediction models that can account, in part, for this challenge. Here, we compare and contrast genomic prediction and phenomic prediction models for 3 growth-related traits, namely, leaf count, tree height, and trunk diameter, from 2 coffee 3-way hybrid populations exposed to a series of treatment-inducing environmental conditions. The models are based on 7 different statistical methods built with genomic markers and ChlF data used as predictors. This comparative analysis demonstrates that the best-performing phenomic prediction models show higher predictability than the best genomic prediction models for the considered traits and environments in the vast majority of comparisons within 3-way hybrid populations. In addition, we show that phenomic prediction models are transferrable between conditions but to a lower extent between populations and we conclude that chlorophyll a fluorescence data can serve as alternative predictors in statistical models of coffee hybrid performance. Future directions will explore their combination with other endophenotypes to further improve the prediction of growth-related traits for crops.
Why it matches plant phenotyping methodsクロロフィル蛍光データを用いたフェノミック予測モデルを構築・比較し、成長形質の予測性能と条件間・集団間の転移性を評価しているため、植物フェノタイピング手法が中心である。
abstractThe models are based on 7 different statistical methods built with genomic markers and ChlF data used as predictors.
Reproduction assets foundThe paper's Data availability statement explicitly states that all code and datasets (including the ChlF phenomic data and growth-trait phenotypes used for GP/PP modeling) are freely available at the authors' public GitHub repository https://github.com/alainmbebi/GP-PP, which matches an allowed URL. Other URLs (BGLR CRCode · publicr and is an excellent proxy for photosynthesis in coffee, making it a tool of choice for assessing the vigor of a genotype, which the present study tends to prove.
Data availability
We implemented all statistical models using R programming language; the codes and all data sets used in the current study are freely available from https://github.com/alainmbebi/GP-PP .
Supplemental material is available at G3 online.
Supplementary Material
jkac170_Supplementary_Data_File_S1
Click here for additional data file.
jkac170_Supplementary_Data_File_S2
Click here for additional data file.
Acknowledgments
We would like to thank the 2 anonymous reviewers for their suggestions and comments.
Funding
ThOpen asset ↗alainmbebi/GP-PPlines:876-910Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Published1 May 2022Computers and Electronics in Agriculture.
With the continuing changes in the structure of plant and cultivation patterns, new diseases are constantly appearing on the leaves of plant, exacerbating the threat to food security and agricultural production in many areas of the world. Thus, a rapid and accurate recognition of various diseases in plant will not only significantly reduce unnecessary planting costs, but also alleviate the economic losses and environmental pollution caused by incorrect disease diagnosis. Recent advances in deep learning have improved the performance in recognizing plant leaf diseases. In this paper, we present a general framework for recognizing plant diseases. Firstly, we propose a deep feature descriptor based on transfer learning to obtain a high-level latent feature representation. Then, we integrate the deep features with traditional handcrafted features by feature fusion to capture the local texture information in plant leaf images. In addition, centre loss is incorporated to further enhance the discriminative ability of the fused feature. The centre loss simultaneously minimizes intra-class distance and maximizes inter-class distance to learn both compact and separate features. Extensive experiments have been conducted on three publicly available datasets (two Apple Leaf datasets and one Coffee Leaf dataset) to validate the effectiveness of proposed method. The propose method achieves 99.79%, 92.59% and 97.12% classification accuracies on the three datasets, respectively. The experiment results demonstrate that the proposed method effectively captures the discriminative feature representation for distinguishing plant leaf diseases.
Why it matches plant phenotyping methods植物葉画像から病害状態を推定する画像解析手法を提案し、複数データセットで性能検証しており、フェノタイピング手法が中心である。
abstractwe present a general framework for recognizing plant diseases.
Plant cells use different structural mechanisms, either constitutive or inducible, to defend themselves from fungal infection. Encapsulation is an efficient inducible mechanism to isolate the fungal haustoria from the plant cell protoplast. Conversely, pectin, one of the polymeric components of the cell wall, is a target of several pectolytic enzymes in necrotrophic interactions. Here, a protocol to detect pectin and fungal hyphae through optical microscopy is presented. The pectin-rich encapsulation in the cells of coffee leaves infected by the rust fungus Hemileia vastatrix and the mesophyll cell wall modification induced by Cercospora coffeicola are investigated. Lesioned leaf samples were fixed with the Karnovsky solution, dehydrated, and embedded in glycol methacrylate for 2-4 days. All steps were followed by vacuum-pumping to remove air in the intercellular spaces and improve the embedding process. The embedded blocks were sectioned into 5-7 µm thick sections, which were deposited on a glass slide covered with water and subsequently heated at 40 °C for 30 min. Next, the slides were double-stained with 5% cotton blue in lactophenol to detect the fungus and 0.05% ruthenium red in water to detect pectin (acidic groups of polyuronic acids of pectin). Fungal haustoria of Hemileia vastatrix were found to be encapsulated by pectin. In coffee cercosporiosis, mesophyll cells exhibited dissolution of cell walls, and intercellular hyphae and conidiophores were observed. The method presented here is effective to detect a pectin-associated response in the plant-fungi interaction.
Why it matches plant phenotyping methods植物組織中のペクチンと真菌菌糸を光学顕微鏡で検出する二重染色プロトコルが研究の中心であり、感染植物の細胞壁応答・病徴状態を測定する方法として提示されている。
abstractHere, a protocol to detect pectin and fungal hyphae through optical microscopy is presented.
Abstract Manual measurements of quantitative traits are time consuming and error prone. Therefore, high‐throughput phenotyping methods that allow a rapid and accurate assessment are vital to a growing range of researchers such as agronomists, breeders, phytopathologists, geneticists, ecologists and biologists. Here, I describe the pliman R package, a collection of functions designed (but not limited) to conduct plant image analysis. The package will help researchers to (a) manipulate, segment and compute image indexes based on Red, Green, Blue, Red‐Edge and Near‐Infrared bands; (b) measure leaf area and shape; (c) quantify plant disease severity; (d) count and extract features (e.g. area, perimeter, radius, circularity and eccentricity) of objects such as grains, leaves, pods, pollen and cells; and (e) compute RGB indexes for each object in an image. In this paper, I describe the main features implemented in the package, guiding the user along a gentle learning curve with practical and reproducible examples. The results of validation studies implemented to count objects in different scenarios (combination of seed sizes, background colour and image resolution), measure leaf area, and quantify plant disease severity have shown that pliman measurements are highly concordant with existing ‘gold standard’ tools. The pliman package offers a flexible, intuitive and richly documented working environment for image‐based phenotyping, being an interesting alternative to free and commercial ‘point‐and‐click’ solutions. R users will find the package fairly easy to use and will be surprised at how the setting of a few arguments will allow processing thousands of images while they enjoy a cup of coffee.
Why it matches plant phenotyping methods植物画像解析用Rパッケージを開発し、葉面積・形状・病害重症度などの表現型抽出機能と検証結果を中核として扱っているため。
abstractHere, I describe the pliman R package, a collection of functions designed (but not limited) to conduct plant image analysis.
Brazil is the largest coffee producer in the world, and then there are many challenges to maintain the high quality and purity of the beans. Thus, it is important to study coffee plants, and help agronomists to detect diseases, such as rust, with resources of computer science. In this work, it is described experiments using image segmentation algorithm JSEG, which is capable to segment images in multi-scale. Using a coffee tree image database RoCoLe (Robusta Coffee Leaf Images), the JSEG algorithm is used to segment these images in four scales. It is selected typical segments in each scale and they are grouped using similarity of normalized color histograms. In this way the several scales segmentations are compared. It is concluded that the segments in scales 1 and 2, in which the colors are more homogeneous then in scales 3 and 4, are adequate to use as training samples for the detection of rust diseases.
Why it matches plant phenotyping methodsコーヒー葉画像のセグメンテーションを開発・評価し、さび病検出用の学習サンプル生成に用いる方法研究であり、植物病害状態の画像取得・抽出が中心です。
abstractthe JSEG algorithm is used to segment these images in four scales
Colour-thresholding digital imaging methods are generally accurate for measuring the percentage of foliar area affected by disease or pests (severity), but they perform poorly when scene illumination and background are not uniform. In this study, six convolutional neural network (CNN) architectures were trained for semantic segmentation in images of individual leaves exhibiting necrotic lesions and/or yellowing, caused by the insect pest coffee leaf miner (CLM), and two fungal diseases: soybean rust (SBR) and wheat tan spot (WTS). All images were manually annotated for three classes: leaf background (B), healthy leaf (H) and injured leaf (I). Precision, recall, and Intersection over Union (IoU) metrics in the test image set were the highest for B, followed by H and I classes, regardless of the architecture. When the pixel-level predictions were used to calculate percent severity, Feature Pyramid Network (FPN), Unet and DeepLabv3+ (Xception) performed the best among the architectures: concordance coefficients were greater than 0.95, 0.96 and 0.98 for CLM, SBR and WTS datasets, respectively, when confronting predictions with the annotated severity. The other three architectures tended to misclassify healthy pixels as injured, leading to overestimation of severity. Results highlight the value of a CNN-based automatic segmentation method to determine the severity on images of foliar diseases obtained under challenging conditions of brightness and background. The accuracy levels of the severity estimated by the FPN, Unet and DeepLabv3 + (Xception) were similar to those obtained by a standard commercial software, which requires adjustment of segmentation parameters and removal of the complex background of the images, tasks that slow down the process.
Why it matches plant phenotyping methodsCNNによる葉の病害・食害症状のセマンティックセグメンテーションと重症度推定手法を開発・比較検証しており、植物表現型の取得が中心である。
abstractsix convolutional neural network (CNN) architectures were trained for semantic segmentation in images of individual leaves exhibiting necrotic lesions and/or yellowing
The automated diagnosis of pests and diseases that affect coffee crops is an important issue for coffee farmers. Conventional methods of computer vision and pattern recognition present limitations to tackle such challenging problems. However, in the last few years, there is a growing interest in deep learning, especially in the detection/recognition of biotic stresses from in-field images of plants acquired by smartphones, since they are affected by lighting variations, complex backgrounds, image noise, and so on. In this work, we propose an integrated framework by using different convolutional neural networks (CNN) to automate detection/recognition of lesions from in-field images collected via smartphone containing part of the coffee tree. In the first stage, we use a Mask R-CNN network for instance segmentation; in the second stage the UNet and PSPNet networks for semantic segmentation and finally, in the third stage, a ResNet for classification. For the Mask R-CNN network, we obtained a precision of 73.90% and a recall of 71.90% in the instance segmentation task. For the UNet and PSPNet networks, we obtained a mean intersection over union of 94.25% and 93.54%, respectively. The results are promising and indicate suitability to implement the entire framework in an embedded mobile platform to be used in the real world.
Why it matches plant phenotyping methodsコーヒー葉の病変を圃場画像からセグメンテーション・分類する統合画像解析手法を開発し、性能評価しているため、植物病害状態のフェノタイピング手法が中心である。
abstractwe propose an integrated framework by using different convolutional neural networks (CNN) to automate detection/recognition of lesions from in-field images collected via smartphone
CoffeeLeafClassificationVisualization / data managementDisease symptoms / severity
Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to trust the model that it truly identifies the region of the disease in the image; it may simply use unrelated surroundings for classification. Visualization techniques can help determine important areas for the model by highlighting the region responsible for the classification. In this study, we present a methodology for visualizing coffee diseases using different visualization approaches. Our goal is to visualize aspects of a coffee disease to obtain insight into what the model "sees" as it learns to classify healthy and non-healthy images. In addition, visualization helped us identify misclassifications and led us to propose a guided approach for coffee disease classification. The guided approach achieved a classification accuracy of 98% compared to the 77% of naïve approach on the Robusta coffee leaf image dataset. The visualization methods considered in this study were Grad-CAM, Grad-CAM++, and Score-CAM. We also provided a visual comparison of the visualization methods.
Why it matches plant phenotyping methodsコーヒー葉の病害領域を画像から可視化・分類する手法が研究の中心であり、Grad-CAM系手法の比較と分類精度の評価を行っているため、植物病害状態の画像ベース表現型解析に該当する。
abstractIn this study, we present a methodology for visualizing coffee diseases using different visualization approaches.
Reproduction assets foundThe paper's plant-phenotyping input data (the Robusta coffee leaf image dataset, RoCoLe, used for disease classification and visualization experiments) is explicitly declared openly available in Mendeley Data. No author analysis code or trained model checkpoints are stated as publicly available. The only allowed URL isDataset · publicThe data presented in this study are openly available in Mendeley Data at doi:10.17632/c5yvn32dzg.2, reference number 36.Mendeley Data · doi:10.17632/c5yvn32dzg.2lines:198-232Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
This article introduces Arabica coffee leaf datasets known as JMuBEN and JMuBEN2. Image acquisition was done in Mutira coffee plantation in Kirinyaga county-Kenya under real-world conditions using a digital camera and with the help of a pathologist. JMuBEN dataset contains three compressed folders with images inside. The first file contains 7682 images of Cerscospora, the second contains 8337 images of rust and the last one contains 6572 images of Phoma. JMuBEN2 contains two compressed files where the first file contains 16,979 images of Miner while the other contains 18,985 images of healthy leaves. In total, the dataset contains 58,555 leaf images spread across five classes (Phoma, Cescospora, Rust, Healthy, Miner,) with annotations regarding the state of the leaves and the disease names. The Arabica datasets contain images that facilitates training and validation during the utilization of deep learning algorithms for coffee plant leaf disease recognition and classification. The dataset is publicly and freely available at https://data.mendeley.com/datasets/tgv3zb82nd/1 and https://data.mendeley.com/datasets/t2r6rszp5c/1 respectively.
Why it matches plant phenotyping methodsコーヒー葉の病害・健全状態を画像と注釈で体系化した公開データセットであり、植物表現型（病害状態）の取得・分類基盤が研究の中心である。
abstractThis article introduces Arabica coffee leaf datasets known as JMuBEN and JMuBEN2.
Reproduction assets foundThe paper is a data descriptor for the JMuBEN and JMuBEN2 Arabica coffee leaf image datasets, which are the paper's own phenotyping assets (58,555 annotated leaf images across five classes) and are publicly available on Mendeley Data.Dataset · publicHealthy, Miner,) with annotations regarding the state of the leaves and the disease names. The Arabica datasets contain images that facilitates training and validation during the utilization of deep learning algorithms for coffee plant leaf disease recognition and classification. The dataset is publicly and freely available at https://data.mendeley.com/datasets/tgv3zb82nd/1 and https://data.mendeley.com/datasets/t2r6rszp5c/1 respectively.
Keywords
Arabica coffee Image datasets Machine learning Deep learning Disease diagnosis pmc-status-qastatus 0 pmc-status-live yes pmc-status-embargo no pmc-status-released yes pmc-prop-open-access yes pmc-prop-olf no pmc-prop-manuscript no pmc-prop-legally-Open asset ↗lines:1-54Dataset · publicte of the leaves and the disease names. The Arabica datasets contain images that facilitates training and validation during the utilization of deep learning algorithms for coffee plant leaf disease recognition and classification. The dataset is publicly and freely available at https://data.mendeley.com/datasets/tgv3zb82nd/1 and https://data.mendeley.com/datasets/t2r6rszp5c/1 respectively.
Keywords
Arabica coffee Image datasets Machine learning Deep learning Disease diagnosis pmc-status-qastatus 0 pmc-status-live yes pmc-status-embargo no pmc-status-released yes pmc-prop-open-access yes pmc-prop-olf no pmc-prop-manuscript no pmc-prop-legally-suppressed no pmc-prop-has-pdf yes pmc-prop-has-supOpen asset ↗lines:1-54Plant phenotyping relevance match · UnverifiedEurope PMC · checked 9 Sept 2026
CoffeeField / plotLeafPhysiological trait estimationWater status / transpiration
The prediction of leaf wetness duration (LWD) is an issue of interest for disease prevention in coffee plantations, forests, and other crops. This study analyzed different LWD prediction approaches using machine learning and meteorological and temporal variables as the models' input. The information was collected through meteorological stations placed in coffee plantations in six different regions of Costa Rica, and the leaf wetness duration was measured by sensors installed in the same regions. The best prediction models had a mean absolute error of around 60 min per day. Our results demonstrate that for LWD modeling, it is not convenient to aggregate records at a daily level. The model performance was better when the records were collected at intervals of 15 min instead of 30 min.
Why it matches plant phenotyping methods葉面濡れ時間という植物の状態をセンサーで測定し、機械学習による推定手法と時間分解能・性能を比較評価しており、表現型取得・推定法が研究の中心である。
abstractThe prediction of leaf wetness duration (LWD) is an issue of interest for disease prevention in coffee plantations, forests, and other crops.
The development of approaches to determine the spatial variability of nitrogen (N) into coffee leaves is essential to increase productivity and reduce production costs and environmental impacts associated with excessive N applications. Thus, this study aimed to assess the potential of the Random Forest (RF) machine learning method applied to vegetation indices (VI) obtained from Remotely Piloted Aircraft (RPA) images to measure the N content in coffee plants. A total of 10 VI were obtained from multispectral images by a camera attached to a rotary-wing RPA. The RGB orthomosaic was used to determine sampling points at the crop area, which were ranked by N levels in the plants as deficient, critical, or sufficient. The chemical analysis of N content in the coffee leaves, as well as the VI values in sample points, were used as input parameters for the image training and its classification by the RF. The suggested model has shown global accuracy and a kappa coefficient of up to 0.91 and 0.86, respectively. The best results were achieved using the Green Normalized Difference Vegetation (GNDVI) and Green Optimized Soil Adjusted Vegetation Index (GOSAVI). In addition, the model enabled the evaluation of the spatial distribution of N in the coffee trees, as well as quantification of N deficiency in the crop for the whole area. The GNDVI and GOSAVI allowed the verification that 22% of the entire crop area had plants with N deficiency symptoms, which would result in a reduction of 78% in the amount of N applied by the producer.
Why it matches plant phenotyping methodsRPA画像と植生指数、Random Forestを用いてコーヒー植物の葉内窒素状態を推定する手法を開発・評価しており、植物形質推定が研究の中心である。
abstractthis study aimed to assess the potential of the Random Forest (RF) machine learning method applied to vegetation indices (VI) obtained from Remotely Piloted Aircraft (RPA) images to measure the N content in coffee plants.
CoffeeField / plotFruitClassificationObject detectionVisualization / data management
In this study, an algorithm is implemented with a computer vision model to detect and classify coffee fruits and map the fruits maturation stage during harvest. The main contribution of this study is with respect to the assignment of geographic coordinates to each frame, which enables the mapping of detection summaries across coffee rows. The model used to detect and classify coffee fruits was implemented using the Darknet, an open source framework for neural networks written in C. The coffee fruits detection and classification were performed using the object detection system named YOLOv3-tiny. For this study, 90 videos were recorded at the end of the discharge conveyor of a coffee harvester during the 2020 harvest of arabica coffee (Catuaí 144) at a commercial area in the region of Patos de Minas, in the state of Minas Gerais, Brazil. The model performance peaked around the ~3300th iteration when considering an image input resolution of 800 × 800 pixels. The model presented an mAP of 84%, F1-Score of 82%, precision of 83%, and recall of 82% for the validation set. The average precision for the classes of unripe, ripe, and overripe coffee fruits was 86%, 85%, and 80%, respectively. As the algorithm enabled the detection and classification in videos collected during the harvest, it was possible to map the qualitative attributes regarding the coffee maturation stage along the crop lines. These attribute maps provide managers important spatial information for the application of precision agriculture techniques in crop management. Additionally, this study should incentive future research to customize the deep learning model for certain tasks in agriculture and precision agriculture.
Why it matches plant phenotyping methodsコーヒー果実の成熟段階という植物器官の状態を、コンピュータビジョンで検出・分類・マッピングする手法が研究の中心であり、性能評価も行っている。単なる収穫対象の位置検出を超えて成熟状態を推定しているため、植物フェノタイピング手法に該当する。
abstractan algorithm is implemented with a computer vision model to detect and classify coffee fruits and map the fruits maturation stage during harvest.
The advance of digital agriculture combined with computational tools and Unmanned Aerial Vehicles (UAVs) has enabled the collection of data for reliably extracting vegetation indices and biophysical parameters derived from the Structure from Motion (SfM) algorithm. This work aimed to evaluate the accuracy of the photogrammetry technique using an SfM point cloud for the estimation of the height (h) and crown diameter (d) of coffee trees from aerial images obtained by UAV with an RGB (Red, Green, Blue) camera and compared the results with data measured in situ for 12 months. The experiment was carried out in a coffee plantation, Lavras, Minas Gerais, Brazil. A rotary-wing UAV was used in autonomous flight mode and coupled to a conventional camera, flying at a height of 30 m with an image overlap of 80% and a speed of 3 m/s. The images were processed using PhotoScan software, and the analyses were performed in Qgis. A correlation of 87% was obtained between the h values in the field and h values obtained by the UAV, and there was a 95% correlation between the d values obtained in the field and the values obtained by the UAV. It was possible to obtain significant estimates of the attributes, such as the h and d of coffee trees, using UAV–SfM images acquired with an RGB digital camera.
Why it matches plant phenotyping methodsUAV-RGB画像とSfM点群によるコーヒー樹の樹高・樹冠径推定手法を開発・精度評価しており、形質取得法が研究の中心です。
abstractThis work aimed to evaluate the accuracy of the photogrammetry technique using an SfM point cloud for the estimation of the height (h) and crown diameter (d) of coffee trees from aerial images obtained by UAV with an RGB (Red, Green, Blue) camera and compared the results with data measured in situ for 12 months.
Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5° angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.
Why it matches plant phenotyping methodsコーヒー花を画像から抽出・分類するCNNと二値化手法を開発・比較評価しており、植物器官の画像ベース計測が中心である。
abstractThe main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images).
Plant phenotyping relevance match · UnverifiedCrossref · Europe PMC · checked 9 Sept 2026
Abstract Background and Aims Using internal trophic pressure as a regulating variable to model the complex interaction loops between organogenesis, production of assimilates and partitioning in functional–structural models of plant growth has attracted increasing interest in recent years. However, this approach is hampered by the fact that internal trophic pressure is a non-measurable quantity that can be assessed only through model parametric estimation, for which the methodology is not straightforward, especially when the model is stochastic. Methods A stochastic GreenLab model of plant growth (called ‘GL4’) is developed with a feedback effect of internal trophic competition, represented by the ratio of biomass supply to demand (Q/D), on organogenesis. A methodology for its parameter estimation is presented and applied to a dataset of 15 two-year-old Coffea canephora trees. Based on the fitting results, variations in Q/D are reconstructed and analysed in relation to the estimated variations in organogenesis parameters. Key Results Our stochastic retroactive model was able to simulate realistically the progressive set-up of young plant architecture and the branch pruning effect. Parameter estimation using real data for Coffea trees provided access to the internal trophic dynamics. These dynamics correlated with the organogenesis probabilities during the establishment phase. Conclusions The model can satisfactorily reproduce the measured data, thus opening up promising avenues for further applying this original procedure to other experimental data. The framework developed can serve as a model-based toolkit to reconstruct the hidden internal trophic dynamics of plant growth.
Why it matches plant phenotyping methodsコーヒー樹の器官形成・樹形を対象に、確率的機能構造モデルとパラメータ推定法を開発し、観測データから内部栄養動態を再構成することが中心であり、植物形態・成長状態の計算的推定手法に該当する。
abstractA stochastic GreenLab model of plant growth (called ‘GL4’) is developed with a feedback effect of internal trophic competition, represented by the ratio of biomass supply to demand (Q/D), on organogenesis.
Color photographs represent the symptoms of the disease as observed in the field, favoring the visual estimation of severity. In order to increase the accuracy, repeatability and reproducibility of Coffea canephora L. rust severity estimates, this study was carried out to elaborate and validate a standard area diagram (SAD) constructed with color photographs (SADcp). To do so, we collected leaves with different intensities of symptoms in crops, and the actual severity was determined with the aid of the software QUANT. The intermediate levels of the scale were determined based on the frequency distribution of severity values. The validation of the diagram was performed by 13 raters who estimated disease severity in 50 leaves of C. canephora with different intensity of symptoms. One assessment without the standard area diagram and two assessments with the diagram were performed at intervals of seven days. Data were analyzed by linear regression and Lin's concordance correlation coefficient. The accuracy, precision, repeatability and reproducibility of the estimates were evaluated. To compare the efficiency of SADcp with the existing scale constructed with two-color diagram (SAD2col), these procedures were performed with both scales. Without the scale and with the SAD2col diagram, the raters overestimated the severity of the disease. With the use of SADcp, the raters presented better levels of accuracy, precision, reproducibility and repeatability in the estimates, compared to when they did not use SAD, or when they used SAD2col. Therefore, SADcp was suitable for estimating the severity of coffee leaf rust in C. canephora.
Why it matches plant phenotyping methodsコーヒー葉さび病の病徴重症度という植物状態を対象に、カラー写真による標準面積図を開発し、精度・再現性・反復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ある。
abstractthis study was carried out to elaborate and validate a standard area diagram (SAD) constructed with color photographs (SADcp).
CoffeeField / plotMultispectral / hyperspectralLeafPhysiological trait estimationWater status / transpiration
Traditionally, water conditions of coffee areas are monitored by measuring the leaf water potential (ΨW) throughout a pressure pump. However, there is a demand for the development of technologies that can estimate large areas or regions. In this context, the objective of this study was to estimate the ΨW by surface reflectance values and vegetation indices obtained from the Landsat-8/OLI sensor in Minas Gerais-Brazil Several algorithms using OLI bands and vegetation indexes were evaluated and from the correlation analysis, a quadratic algorithm that uses the Normalized Difference Vegetation Index (NDVI) performed better, with a correlation coefficient (R2) of 0.82. Leave-One-Out Cross-Validation (LOOCV) was performed to validate the models and the best results were for NDVI quadratic algorithm, presenting a Mean Absolute Percentage Error (MAPE) of 27.09% and an R2 of 0.85. Subsequently, the NDVI quadratic algorithm was applied to Landsat-8 images, aiming to spatialize the ΨW estimated in a representative area of regional coffee planting between September 2014 to July 2015. From the proposed algorithm, it was possible to estimate ΨW from Landsat-8/OLI imagery, contributing to drought monitoring in the coffee area leading to cost reduction to the producers.
Why it matches plant phenotyping methodsLandsat-8反射率・植生指数からコーヒー葉の水ポテンシャルという植物生理形質を推定するアルゴリズムを開発し、交差検証および空間適用を行っており、フェノタイピング手法が中心である。
abstractthe objective of this study was to estimate the ΨW by surface reflectance values and vegetation indices obtained from the Landsat-8/OLI sensor
Biotic stress consists of damage to plants through other living organisms. The efficient control of biotic agents such as pests and pathogens (viruses, fungi, bacteria, etc.) is closely related to the concept of agricultural sustainability. Agricultural sustainability promotes the development of new technologies that allow the reduction of environmental impacts, greater accessibility to farmers and, consequently, increased productivity. The use of computer vision with deep learning methods allows the early and correct identification of the stress-causing agent. So, corrective measures can be applied as soon as possible to mitigate the problem. The objective of this work is to design an effective and practical system capable of identifying and estimating the stress severity caused by biotic agents on coffee leaves. The proposed approach consists of a multi-task system based on convolutional neural networks. In addition, we have explored the use of data augmentation techniques to make the system more robust and accurate. Computational experiments performed with the proposed system using the ResNet50 architecture obtained an accuracy of 95.24% for the biotic stress classification and 86.51% for severity estimation. Moreover, it was found that by classifying only the symptoms, the results were greater than 97%. The experimental results indicate that the proposed system might be a suitable tool to assist both experts and farmers in the identification and quantification of biotic stresses in coffee plantations.
Why it matches plant phenotyping methodsコーヒー葉の症状を画像から分類し、植物の生物的ストレス重症度を推定する深層学習手法が研究の中心であるため、植物病害・症状フェノタイピングとして収録する。
abstractThe objective of this work is to design an effective and practical system capable of identifying and estimating the stress severity caused by biotic agents on coffee leaves.
Leaf area is a component of crop growth and yield prediction models. Few studies have used the structure from motion (SfM) algorithm, which is based on the principles of traditional stereophotogrammetry, to obtain the leaf area index (LAI). Thus, the objective of this study was to follow the evolution of the LAI and percentage of land cover (%COV) in coffee plants, using pre-established equations and plant measurements obtained from generated 3-D point clouds, combined with the application of the SfM algorithm to digital images recorded by a camera coupled to an unmanned aerial vehicle (UAV). The experiment was conducted in a coffee plantation located in southeastern Brazil. A rotary wing UAV containing a conventional camera was used. The images were collected once per month for 12 months. Image processing was performed using PhotoScan software. Regression analysis and spatial analysis were performed using R and GeoDa software, respectively. The resulting %COV data had R2and RMSE values of 89% and 3.41, respectively, while those for LAI had R2and RMSE of 88% and 0.47, respectively. Significant %COV results were obtained in the months of January, February, and March of 2018. There was significant autocorrelation for the LAI values from January to May 2018, with most blocks in the central and center-west regions presenting LAI values > 3.0. It was possible to monitor the temporal and spatial behavior of the LAI and %COV, allowing for the conclusion that this methodology generated results that are consistent with the literature.
Why it matches plant phenotyping methodsUAV RGB画像とSfMによる3D点群からコーヒーのLAIおよび被覆率を推定し、精度指標で検証しており、植物形質の取得手法が研究の中心です。
abstractusing pre-established equations and plant measurements obtained from generated 3-D point clouds, combined with the application of the SfM algorithm to digital images recorded by a camera coupled to an unmanned aerial vehicle (UAV)
Nitrogen is an essential element for coffee production. However, when fertilization do not consider the spatial variability of the agricultural parameters, it can generate economic losses, such as low productivity, and environmental impacts, such as pollution of air and eutrophication of water bodies. Thus, the monitoring of the nitrogen during different phases of the production is a key factor for the fertilization management, and remote sensing based on unmanned aerial vehicles imagery has been evaluated for this task. Thus, this work aimed to evaluate the potential of visible vegetation indices obtained from such images to monitor the spatial variability of the leaf nitrogen content in a coffee farm located in Divisa Nova Municipality, Minas Gerais. Therefore, we performed a leaf analysis using the Kjeldahl method to determine leaf nitrogen, and to process the images and produce the vegetation indices, we use Geographic Information Systems and photogrammetry software. As analyze methods, we used the Random Forest classification algorithm as an estimator and performed ordinary kriging to visualize the spatial variability as nitrogen content. Lastly, the Pearson correlation coefficient was employed to evaluate the relationship between the variables. However, the Random Forest models were unable to explain nitrogen variability, and we did not find any significant correlations between the tested vegetation indices and nitrogen content. Therefore, it is indicated the replication of the study in the vegetative phase of the coffee plants, with the establishment of different fertilization treatments, as well as the use of multispectral sensors and radiometric calibration techniques. Keys words: Vegetation indices; RGB; machine learning; Coffea arabica.
Why it matches plant phenotyping methodsUAV画像と機械学習を用いてコーヒー葉の窒素含量という植物形質を推定・評価する手法が研究の中心であり、手法適用および技術評価に該当する。
abstractthis work aimed to evaluate the potential of visible vegetation indices obtained from such images to monitor the spatial variability of the leaf nitrogen content in a coffee farm
The implementation of image recognition in agriculture to detect symptoms of plant disease using deep learning Convolutional Neural Network (CNN) models are proven to be highly effective. The computational efficiency by using CNN, made possible to run the application on mobile device. To optimize the utilization of mobile device and choosing the most effective CNN model to run as detection system in mobile device with the highest accuracy and low resource consumption is proposed in this paper. In this study, PlantVillage dataset which extended to coffee leaf, were tested and compared using three CNN models, two models which specifically designed for mobile, MobileNet and Mobile Nasnet (MNasNet), and one model that recognized for its accuracy on personal computer (PC), InceptionV3. The experiment executed on both mobile and PC found a slightly degradation on accuracy when the application is running on mobile. InceptionV3 experienced the most persistence model compares to MNasNet and MobileNet. Yet, InceptionV3 had biggest latency time. The final result on mobile device recorded InceptionV3 achieved highest accuracy of 95.79%, MNasNet 94.87%, and MobileNet 92.83%, while for time latency MobileNet achieved the lowest with 394.70 ms, MNasnet 430.20 ms, and InceptionV3 2236.10 ms respectively. It is expected that the outcome of this study will be of great benefit to farmers as mobile image recognition would help them analyze the condition of their plants on site simply by taking a picture of the leaf and running the experiment on their mobile device.
Why it matches plant phenotyping methods植物葉の病徴を画像から分類するCNN手法をモバイル端末向けに比較・評価しており、植物状態の取得・推定方法が研究の中心である。
abstractdetect symptoms of plant disease using deep learning Convolutional Neural Network (CNN) models
CoffeePeaSpinachLeafClassificationPhysiological trait estimationWater status / transpiration
Abstract Background The demand for effective use of water resources has increased because of ongoing global climate transformations in the agriculture science sector. Cost-effective and timely distributions of the appropriate amount of water are vital not only to maintain a healthy status of plants leaves but to drive the productivity of the crops and achieve economic benefits. In this regard, employing a terahertz (THz) technology can be more reliable and progressive technique due to its distinctive features. This paper presents a novel, and non-invasive machine learning (ML) driven approach using terahertz waves with a swissto12 material characterization kit (MCK) in the frequency range of 0.75 to 1.1 THz in real-life digital agriculture interventions, aiming to develop a feasible and viable technique for the precise estimation of water content (WC) in plants leaves for 4 days. For this purpose, using measurements observations data, multi-domain features are extracted from frequency, time, time–frequency domains to incorporate three different machine learning algorithms such as support vector machine (SVM), K-nearest neighbour (KNN) and decision-tree (D-Tree). Results The results demonstrated SVM outperformed other classifiers using tenfold and leave-one-observations-out cross-validation for different days classification with an overall accuracy of 98.8%, 97.15%, and 96.82% for Coffee, pea shoot, and baby spinach leaves respectively. In addition, using SFS technique, coffee leaf showed a significant improvement of 15%, 11.9%, 6.5% in computational time for SVM, KNN and D-tree. For pea-shoot, 21.28%, 10.01%, and 8.53% of improvement was noticed in operating time for SVM, KNN and D-Tree classifiers, respectively. Lastly, baby spinach leaf exhibited a further improvement of 21.28% in SVM, 10.01% in KNN, and 8.53% in D-tree in overall operating time for classifiers. These improvements in classifiers produced significant advancements in classification accuracy, indicating a more precise quantification of WC in leaves. Conclusion Thus, the proposed method incorporating ML using terahertz waves can be beneficial for precise estimation of WC in leaves and can provide prolific recommendations and insights for growers to take proactive actions in relations to plants health monitoring.
Why it matches plant phenotyping methods植物葉の含水量という生理形質を、テラヘルツ計測と機械学習で非侵襲推定する手法の開発・評価が中心である。
abstractThis paper presents a novel, and non-invasive machine learning (ML) driven approach using terahertz waves
Robust monitoring techniques for perennial crops have become increasingly possible due to technological advances in the area of Remote Sensing (RS), and the products are available through the European Space Agency (ESA) initiative. RS data provides valuable opportunities for detailed assessments of crop conditions at plot level using high spatial, spectral, and temporal resolution. This study addresses the monitoring of coffee at the plot level using RS, analyzing the relationship between the spatio-temporal variability of the Leaf Area Index (LAI) and the crop coefficient (Kc); the Kc being a biophysical variable that integrates the potential hydrological characteristics of an agroecosystem compared to the reference crop. Daily and one-year Kc were estimated using the relation of crop evapotranspiration and reference. ESA Sentinel-2 images were pre-analyzed and atmospherically corrected, and Top-of-the-Atmosphere (TOA) reflections converted to Top-of-the-Canopy (TOC) reflectance. The TOCs resampled at the 10m resolution, and with the angles corresponding to the directional information at the time of the acquisition, the LAI was estimated using the trained neural network available in the Sentinel Application Platform (SNAP). During 75% of the monitored days, Kc ranged between 1.2 and 1.3 and, the LAI analyzed showed high spatial and temporal variability at the plot level. Based on the relationship between the biophysical variables, the LAI variable can substitute the Kc and be used to monitor the water conditions at the production area as well as analyze spatial variability inside that area. Sentinel-2 products could be more useful in monitoring coffee in the farm production area.
Why it matches plant phenotyping methods圃場レベルのコーヒー葉面積指数（LAI）をSentinel-2リモートセンシングとニューラルネットワークで推定する手法を中心に適用しており、植物形質の取得・抽出が水分状態モニタリングの主要要素である。
abstractThis study addresses the monitoring of coffee at the plot level using RS
The potencial of Coffea arabica leaves as bioindicators of atmospheric carbon dioxide (CO 2 ) was evaluated in a free-air carbon dioxide enrichment (FACE) experiment by using near-infrared reflectance (NIR) spectroscopy for direct analysis and partial least squares discriminant analysis (PLS-DA). A supervised classification model was built and validated from the spectra of coffee leaves grown under elevated and current CO 2 levels. PLS-DA allowed correct test set classification of 92% of the elevated-CO 2 level leaves and 100% of the current-CO 2 level leaves. The spectral bands accounting for the discrimination of the elevated-CO 2 leaves were at 1657 and 1698 nm, as indicated by the variable importance in the projection (VIP) score together with the regression coefficients. Seven months after suspension of enriched CO 2 , returning to current-CO 2 levels, new spectral measurements were made and subjected to PLS-DA analysis. The predictive model correctly classified all leaves as grown under current-CO 2 levels. The fingerprints suggest that after suspension of elevated-CO 2 , the spectral changes observed previously disappeared. The recovery could be triggered by two reasons: the relief of the stress stimulus or the perception of a return of favorable conditions. In addition, the results demonstrate that NIR spectroscopy can provide a rapid, nondestructive, and environmentally friendly method for biomonitoring leaves suffering environmental modification. Finally, C. arabica leaves associated with NIR and mathematical models have the potential to become a good biomonitoring system.
Why it matches plant phenotyping methodsコーヒー葉の環境状態をNIR分光とPLS-DAで非破壊的に識別する手法の構築・検証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。
abstractA supervised classification model was built and validated from the spectra of coffee leaves grown under elevated and current CO 2 levels.
In this article we introduce a robusta coffee leaf images dataset called RoCoLe. The dataset contains 1560 leaf images with visible red mites and spots (denoting coffee leaf rust presence) for infection cases and images without such structures for healthy cases. In addition, the data set includes annotations regarding objects (leaves), state (healthy and unhealthy) and the severity of disease (leaf area with spots). Images were all obtained in real-world conditions in the same coffee plants field using a smartphone camera. RoCoLe data set facilitates the evaluation of the performance of machine learning algorithms used in image segmentation and classification problems related to plant diseases recognition. The current dataset is freely and publicly available at https://doi.org/10.17632/c5yvn32dzg.2.
Why it matches plant phenotyping methodsコーヒー葉の病害状態と重症度を画像・アノテーションとして収録し、植物病害認識手法の評価用データセットとして提供することが中心であるため、植物フェノタイピング手法文献に含める。
abstractwe introduce a robusta coffee leaf images dataset called RoCoLe
Reproduction assets foundThe paper is a Data in Brief article introducing the RoCoLe dataset of 1560 annotated robusta coffee leaf images, explicitly stated as freely and publicly available on Mendeley Data with DOI 10.17632/c5yvn32dzg.2.Dataset · publicThe current dataset is freely and publicly available at https://doi.org/10.17632/c5yvn32dzg.2 .Open asset ↗10.17632/c5yvn32dzg.2lines:1-55Plant phenotyping relevance match · UnverifiedEurope PMC · checked 15 Sept 2026
Statistical analysis of Coffea arabica L. progeny production has been a great challenge. In this species, genotypes may present differential biennial behaviors due to different physiological responses to the environmental conditions, indicating a mixture of two subpopulations in the tested progenies. Previously proposed statistical methods are unable to handle data overdispersion and/or bimodality because they assume the same stochastic process generating different phenotypes. This study proposes a finite mixture mixed model for modeling the biennial patterns. Production data for 21 S₀:₁ progenies, evaluated through eight harvests, were used. Individual (per harvest) and repeated measures analyses were performed using conventional mixed models and Gaussian mixture mixed models. The proposed methodology is also illustrated in a simulation study. On a real dataset, the approximated prediction error variance, CV, and residual variance were drastically reduced using mixture mixed models, resulting in a higher estimated heritability and expected gain from selection. Residual dependence across years was lower for the mixture model, but no differences were observed in genetic correlations. The posterior probability matrix captured the biennial pattern, which indicates the probability of a progeny's physiological stage. The Spearman correlation coefficient (0.87) indicates that selection based on grouped means may not be efficient. In general, the proposed model was more efficient for higher subpopulations means differences. The results suggest that for analysis of C. arabica progenies exhibiting different biennial patterns, mixture mixed models are superior to traditional mixed models and to models that structure biennial effects using covariance matrices.
Why it matches plant phenotyping methodsコーヒー progeny の生産データから二年結果性という植物の生理状態・表現型を推定する混合モデルを提案し、従来法と比較・シミュレーション検証している。統計モデル自体が中心的な方法論的貢献である。
abstractThis study proposes a finite mixture mixed model for modeling the biennial patterns.
CoffeeMultispectral / hyperspectralSeed / grainPhysiological trait estimationSegmentationWater status / transpiration
Hyperspectral imaging (1000-2500 nm) was used for rapid prediction of moisture and total lipid content in intact green coffee beans on a single bean basis. Arabica and Robusta samples from several growing locations were scanned using a "push-broom" system. Hypercubes were segmented to select single beans, and average spectra were measured for each bean. Partial Least Squares regression was used to build quantitative prediction models on single beans (n = 320-350). The models exhibited good performance and acceptable prediction errors of ∼0.28% for moisture and ∼0.89% for lipids. This study represents the first time that HSI-based quantitative prediction models have been developed for coffee, and specifically green coffee beans. In addition, this is the first attempt to build such models using single intact coffee beans. The composition variability between beans was studied, and fat and moisture distribution were visualized within individual coffee beans. This rapid, non-destructive approach could have important applications for research laboratories, breeding programmes, and for rapid screening for industry.
Why it matches plant phenotyping methods単一の緑色コーヒー豆（種子）における水分・脂質という植物器官形質を、ハイパースペクトル画像と定量予測モデルで非破壊推定する方法の開発・性能評価が中心である。
abstractHyperspectral imaging (1000-2500 nm) was used for rapid prediction of moisture and total lipid content in intact green coffee beans on a single bean basis.
Hyperspectral imaging (HSI) is a novel technology for the food sector that enables rapid non-contact analysis of food materials. HSI was applied for the first time to whole green coffee beans, at a single seed level, for quantitative prediction of sucrose, caffeine and trigonelline content. In addition, the intra-bean distribution of coffee constituents was analysed in Arabica and Robusta coffees on a large sample set from 12 countries, using a total of 260 samples. Individual green coffee beans were scanned by reflectance HSI (980-2500nm) and then the concentration of sucrose, caffeine and trigonelline analysed with a reference method (HPLC-MS). Quantitative prediction models were subsequently built using Partial Least Squares (PLS) regression. Large variations in sucrose, caffeine and trigonelline were found between different species and origin, but also within beans from the same batch. It was shown that estimation of sucrose content is possible for screening purposes (R 2 =0.65; prediction error of ~0.7% w/w coffee, with observed range of ~6.5%), while the performance of the PLS model was better for caffeine and trigonelline prediction (R 2 =0.85 and R 2 =0.82, respectively; prediction errors of 0.2 and 0.1%, on a range of 2.3 and 1.1% w/w coffee, respectively). The prediction error is acceptable mainly for laboratory applications, with the potential application to breeding programmes and for screening purposes for the food industry. The spatial distribution of coffee constituents was also successfully visualised for single beans and this enabled mapping of the analytes across the bean structure at single pixel level.
Why it matches plant phenotyping methods単一コーヒー種子の化学的形質をHSIで非破壊推定・可視化する手法を開発し、HPLC-MSとの比較およびPLS予測モデルで技術検証している。食品分析を主目的とするが、種子形質の育種・スクリーニングへの応用も明示され、表現型取得法が中心である。
abstractHSI was applied for the first time to whole green coffee beans, at a single seed level, for quantitative prediction of sucrose, caffeine and trigonelline content.
Stomatal regulation is a key process in the physiology of Coffea arabica (C. arabica). Intrinsically linked to photosynthesis and water relations, it provides insights into the plant's adaptive capacity, survival and growth. The ability to rapidly quantify this parameter for C. arabica under different agroecological systems would be an indispensable tool. Using a Flir E6 MIR Camera, an index that is equivalent to stomatal conductance (I g ) was compared with stomatal conductance measurements (g s ) in a mature coffee plantation. In order to account for varying meteorological conditions between days, the methods were also compared under stable meteorological conditions in a laboratory and I g was also converted to absolute stomatal conductance values (g 1 ). In contrast to typical plant-thermography methods which measure indices once per day over an extended time period, we used high resolution hourly measurements over daily time series with 9 sun and 9 shade replicates. Eight daily time series showed a strong correlation between methods, while the remaining 10 were not significant. Including several other meteorological parameters in the calculation of g 1 did not contribute to any stronger correlation between methods. Total pooled data (combined daily series) resulted in a correlation of ρ=0.66 (P≤2.2e-16), indicating that our approach is particularly useful for situations where absolute values of stomatal conductance are not required, such as for comparative purposes, screening or trend analysis. We use the findings to advance the protocol for a more accurate methodology which may assist in quantifying advantageous microenvironment designs for coffee, considering the current and future climates of coffee growing regions.
Why it matches plant phenotyping methods熱画像による気孔コンダクタンス推定を実測値と比較・検証し、測定プロトコルを改良する研究であり、植物生理形質の取得法が中心である。
abstractUsing a Flir E6 MIR Camera, an index that is equivalent to stomatal conductance (I g ) was compared with stomatal conductance measurements (g s )
In this article, a non-destructive method is proposed to count the number of fruits on a coffee branch by using information from digital images of a single side of the branch and its growing fruits. In order to do this, 1018 coffee branches at different ripening stages. They had different numbers of fruits, harvest dates, were of different varieties, and were at different stages of coffee tree’s life. A Machine Vision System (MVS) was constructed, which was capable of counting and identifying harvestable and not harvestable fruits in a set of images corresponding to a specific coffee branch was constructed. This MVS consists of an image acquisition system, based on mobile devices (it does not require to control of the environmental conditions), and an image processing algorithm to classify and detect each one of the fruits in the acquired images. After obtaining information regarding the number of fruits identified by the MVS, linear estimation models were constructed between the detected fruits automatically and the ones observed on the coffee branch. These models were calculated for fruits in three categories: harvestable, not harvestable, and fruits whose maturation stage were disregarded. These models link the fruits that are counted automatically to the ones actually observed with an R2 higher than 0.93 one-to-one. Not only is the MVS used to estimate the number of fruits on the branch but also to estimate their maturation percentage and weight. The MVS was validated in four Variedad Castillo® coffee plots, in different stages of development and with different densities. We found that MVS neither overestimates nor underestimates the number of fruits and that it shows a correlation higher than 0.90 at early stages of crop development, when tree fruits are still not harvestable. The information obtained in this research will spawn a new generation of tools for coffee growers to use. It is an efficient, non-destructive, and low-cost method which offers useful information for them to plan agricultural work and obtain economic benefits from the correct administration of resources.
Why it matches plant phenotyping methodsコーヒー枝上の果実数、成熟度、重量を画像から推定する機械視覚システムを開発し、複数圃場で検証しており、植物形質取得法が研究の中心である。
abstracta non-destructive method is proposed to count the number of fruits on a coffee branch by using information from digital images
CoffeeLaboratory / benchtopSeed / grainClassificationGrowth / development / phenology
Seeds age during storage, resulting in a decline in germination and seedling quality. Seed quality tests are important to monitor this decline. However, such tests are usually destructive and require large seed numbers and long time. For coffee seeds the standard germination test and assessment of seedling quality takes 30 days. Biospeckle has been used previously as a non‐destructive optical tool to monitor biological activity in a range of tissues. Biospeckle was applied 3–6 days after imbibition (DAI) to investigate an association with coffee seedling quality after 30 days. Two distinct areas of biospeckle activity were demonstrated, concurring with the locations of the embryonic axis and the cotyledons in the apical and central seed parts, respectively. Moisture content analysis revealed that embryos of imbibed seeds contained more water than endosperm. Different areas within the endosperm did not differ in moisture content, while the moisture content of the axis was higher than that of the cotyledons, and this did not change from 4 DAI. Therefore, it was concluded that high biospeckle activity was not the result of increased water content in any seed part, but more likely of growth and metabolism in the axis and cotyledons, which had been described previously. A threshold biospeckle ratio apical : central of 1.02 after 6 days distinguished between seeds that produced dead and viable seedlings after 30 days and provided similar results as a tetrazolium test, a widely acknowledged but destructive test for seed quality. Thus, biospeckle data provided a non‐destructive early parameter for seedling quality, based on embryo growth during germination.
Why it matches plant phenotyping methodsコーヒー種子の生理活性を非破壊的に測定し、発芽後の生存・幼苗品質を早期推定するバイオスペックル法が研究の中心であり、閾値判定とテトラゾリウム試験との比較検証も行っている。
abstractBiospeckle was applied 3–6 days after imbibition (DAI) to investigate an association with coffee seedling quality after 30 days.
CoffeeGrapevineLeafMorphology / geometry measurementPhysiological trait estimationLeaf traitsWater status / transpiration
Fresh water is a key natural resource for food production, sanitation and industrial uses and has a high environmental value. The largest water use worldwide (~70%) corresponds to irrigation in agriculture, where use of water is becoming essential to maintain productivity. Efficient irrigation control largely depends on having access to reliable information about the actual plant water needs. Therefore, fast, portable and non-invasive sensing techniques able to measure water requirements directly on the plant are essential to face the huge challenge posed by the extensive water use in agriculture, the increasing water shortage and the impact of climate change. Non-contact resonant ultrasonic spectroscopy (NC-RUS) in the frequency range 0.1-1.2 MHz has revealed as an efficient and powerful non-destructive, non-invasive and in vivo sensing technique for leaves of different plant species. In particular, NC-RUS allows determining surface mass, thickness and elastic modulus of the leaves. Hence, valuable information can be obtained about water content and turgor pressure. This work analyzes and reviews the main requirements for sensors, electronics, signal processing and data analysis in order to develop a fast, portable, robust and non-invasive NC-RUS system to monitor variations in leaves water content or turgor pressure. A sensing prototype is proposed, described and, as application example, used to study two different species: Vitis vinifera and Coffea arabica, whose leaves present thickness resonances in two different frequency bands (400-900 kHz and 200-400 kHz, respectively), These species are representative of two different climates and are related to two high-added value agricultural products where efficient irrigation management can be critical. Moreover, the technique can also be applied to other species and similar results can be obtained.
Why it matches plant phenotyping methods植物葉の水分量・膨圧を非接触超音波で測定するセンサー方式の要件分析、試作、応用を中心に扱っており、植物表現型取得法が明確に中心的である。
abstractThis work analyzes and reviews the main requirements for sensors, electronics, signal processing and data analysis in order to develop a fast, portable, robust and non-invasive NC-RUS system to monitor variations in leaves water content or turgor pressure.
Reproduction assets foundThe paper's inverse-problem analysis code for extracting leaf parameters (thickness, density, ultrasound velocity, attenuation) from measured resonance spectra is explicitly stated to be publicly available via the authors' GitHub repository and the US-BIOMAT resource page. No phenotype dataset deposit is mentioned.Code · publicUS-BIOMAT
Available online: https://us-biomat.com/resources/code-2/ or https://github.com/usbiomat/ultrasonic-thickness-resonance (accessed on 12 July 2016)Open asset ↗usbiomat/ultrasonic-thickness-resonancelines:327-413Plant phenotyping relevance match · UnverifiedCrossref · checked 15 Sept 2026
Published30 Apr 2016International Journal of Database Theory and ApplicationCited by 41 · OpenAlex ↗
Coffee plant is a plant whose seeds called coffee beans are grown in all over the world particularly in Ethiopia. The research focuses on three major type of coffee disease which occurs on the leave part of a coffee plant, these are Coffee Leaf Rust (CLR), Coffee Berry Disease (CBD), and Coffee Wilt Disease (CWD). The aim of this paper is recognition of the three types of coffee disease using imaging and machine learning techniques. The image of Coffee plant diseases were taken from the regions of Ethiopia where more coffee is produced i.e. Southern Nations, Nationalities, and Peoples, Jimma and Zegie. In this paper artificial neural network (ANN), k-Nearest Neighbours (KNN), Naive and a hybrid of self organizing map (SOM) and Radial basis function (RBF) are used. We conduct experiment for each group of feature set in order to get a highly correlated and the more representing features. The total number of data sets is 9100. From the total of 9100, 70% were used for training and the remaining 30% were used for testing. . In general, the overall result showed that color features represents more than texture features regarding recognition of coffee plant diseases and the performance of combination of RBF (Radial basis function) and SOM (Self organizing map) is 90.07%.
Why it matches plant phenotyping methodsコーヒー葉・果実の病徴を画像から認識し、機械学習手法と特徴量を比較評価することが中心であり、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 aim of this paper is recognition of the three types of coffee disease using imaging and machine learning techniques.