Precision agriculture is becoming more and more of a challenge that requires the use of intelligent systems that are able to predict stress and prevent yield loss before it is too late. Traditional methods of agricultural surveillance are predominantly reactive with irrigation demands being based on thresholds or individual yield forecasts models that do not represent the intricate spatio-temporal interactions that exist between crop physiology, soil status, and environmental stresses. Besides, the majority of the current practices do not have an autonomous decision-making approach to preventive intervention which leads to inefficient use of water and slows down the response to stress. This paper suggests a cognitive UAV-assisted agro-surveillance system to predict yield vulnerability caused by crop stress and optimize adaptive irrigation with the help of spatio-temporal deep and reinforcement learning. The framework combines UAV-obtained RGB and multispectral and thermal imagery with measurements of soil sensors and meteorological data obtained with the Crop Health and Environmental Stress Dataset. A new GeoSpatio-TRiNet model is used to acquire long-range spatial relationship, time stress development, and diffusion of stresses across agricultural regions. The model predicts the vulnerability trajectories of the stress instead of the direct yield regression, and this allows early detection of yield risk. Such predictions serve to generate a cognitive environmental state of a Soft ActorCritic (SAC) reinforcement learning agent that autonomously computes zone-based irrigation behaviors to reduce the recurrence of stress at the minimum water usage cost. As shown by the results of the experiment, the proposed framework has a stress forecasting accuracy of 96.3% and performs much better than the traditional machine learning, CNN-based, and transformer-based baselines. The system also decreases the predicted yield vulnerability by 46.6 and enhances water-use efficiency by 41.1 as compared to irrigation strategies based on rules. The results confirm the usefulness of spatio-temporal intelligence with predictive control in terms of effectiveness, and the proposed framework is a scalable and sustainable solution to precision agriculture of the next generation.
Why it matches plant phenotyping methodsUAV画像とセンサーデータから作物ストレスの時系列状態および収量脆弱性を推定する計算・センシング手法が研究の中心であり、灌漑制御への応用も技術評価の一部として記述されている。
abstractThe framework combines UAV-obtained RGB and multispectral and thermal imagery with measurements of soil sensors and meteorological data
Reproduction assets foundThe paper uses the public Kaggle Crop Health and Environmental Stress Dataset (UAV RGB/multispectral/thermal imagery plus soil/weather measurements and stress labels) as its phenotyping data source, and the authors provide an explicit public GitHub repository for the analysis code.Dataset · publicThe current research is based on the Crop Health and Environmental Stress Dataset, which is a publicly available
dataset on Kaggle, specially created to help perform a spatio-temporal analysis of crop health in response to changing
environmental and water-stress factors [26].Open asset ↗pdf-raw-page:10 lines:1-62Code · publicturn: Final zone-wise stress predictions 𝐶
𝑡
𝑧, Yield vulnerability trajectories 𝑉𝑡
𝑧, Optimal adaptive irrigation policy
𝜋∗
End Algorithm
Code availability:
The data used to support the findings of this study are included in the article.
Code availability:
The code used in this research work is available in the following link.
https://github.com/replyvenugopal/Cognitive-UAV-Driven-Agro-Surveillance
4. Result and Discussion
The architectural agro-surveillance solution, which is proposed to be executed by UAVs, is executed through a
modular and scalable software framework to guarantee reproducibility and extensibility. The experiments are all
performed in Python as a main programming languageOpen asset ↗github.com/replyvenugopal/Cognitive-UAV-Driven-Agro-Surveillancepdf-raw-page:24 lines:1-55Code / dataset availability confirmedOpenAlex · Europe PMC · bioRxiv · checked 14 Sept 2026
Abstract Background and aims Plant volatile organic compounds (VOCs) change dynamically with plant development and in response to environmental conditions. However, their potential as non-invasive indicators of phenological progression remains poorly explored. In this study, we developed a framework integrating automated VOC sampling, time-resolved VOC profiling, and machine-learning analysis for the non-invasive assessment of plant phenology. Using soybean ( Glycine max (L.) Merr.), we investigated whether development-associated temporal variation in VOC emissions could delineate and predict developmental phases. Methods We collected VOCs daily under controlled environmental conditions from 16 to 43 days after sowing, spanning the transition from vegetative to reproductive stages, using an automated sampling system coupled with thermal desorption-gas chromatograph-mass spectrometer (TD- GC-MS). To characterise temporal changes in VOC profiles associated with phenological progression, we analysed the daily VOC data using a multi-step pipeline combining statistical filtering and similarity-based network analysis. We defined VOC-derived developmental phases from similarity patterns in the VOC profiles, then developed and evaluated machine-learning models to predict these phases. Key results Seven VOCs exhibited distinct phase-dependent dynamics, including green leaf volatiles and monoterpenes showing characteristic temporal changes during phenological progression. Network-based clustering of VOC profiles resolved five developmental phases closely aligned with conventional developmental stages. A machine-learning model predicted these phases from the VOC profiles with high predictive accuracy on independent test data, demonstrating that phenological progression could be quantitatively inferred from VOC emission patterns. Conclusions Our findings support VOC profiling as a reliable and non-invasive approach for assessing phenological progression in soybean. By extracting temporally structured VOC signals, this framework captures developmental information that may be difficult to obtain through visual observation alone, particularly after canopy closure. VOC profiling offers a practical tool for monitoring crop developmental dynamics and has broader potential for plant phenotyping and precision crop management.
Why it matches plant phenotyping methods自動VOCサンプリング、時系列VOCプロファイリング、機械学習を統合し、VOCから植物の発育段階を非破壊推定する方法を開発・評価しており、フェノタイピング手法が中心である。
abstractwe developed a framework integrating automated VOC sampling, time-resolved VOC profiling, and machine-learning analysis for the non-invasive assessment of plant phenology.
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。Supplement · publicThe peak area matrix obtained from the MS- DIAL analysis (Supplementary Dataset S1) was filtered to remove unreliable features.Open asset ↗lines:66-69Code / dataset availability confirmedOpenAlex · Europe PMC · checked 5 Sept 2026
Thermal imaging enables non-invasive assessment of canopy temperature, an essential indicator of plant stress, yet the lack of color cues and strong shadow interference make plant segmentation in thermal images difficult. Recent advances in foundation models have demonstrated improved performance and generalizability across applications, showing promise for domain-specific applications with limited annotated datasets such as plant segmentation in thermal images. This study investigates large multimodal models (LMMs) for thermal image segmentation in plant phenotyping. Building upon the SAM-CLIP framework, we design a unified pipeline spanning zero-shot inference, few-shot and low-shot fine-tuning, and active learning to maximize accuracy with minimal supervision. Evaluations on two thermal datasets, LadyBird Brassica and UGA Brassica, demonstrate robust performance after minimal adaptation across both datasets and superior performance compared with baselines, achieving mIoU D values of 97.54% on the LadyBird dataset and 76.94 % on the UGA dataset. We also release the resulting thermal segmentation annotations to support community benchmarking and reproducible research, highlighting the potential of LMMs to enable scalable, high-quality dataset construction for field phenotyping. The released datasets can be found at: https://cornell.box.com/s/dh69xf84464yrc1vlws92l1tflx7qa89
Why it matches plant phenotyping methods熱画像から植物を分割する手法を開発・評価し、植物フェノタイピング用データセットとアノテーションも公開しているため、フェノタイピング手法が中心的である。
abstractThis study investigates large multimodal models (LMMs) for thermal image segmentation in plant phenotyping.
Reproduction assets foundThe authors publicly released the paper-specific thermal segmentation annotations (20,538 LadyBird masks and 37,790 UGA masks) via a Cornell Box link stated in the abstract, results, and data availability statement. No author analysis code or trained model checkpoints are explicitly released; the mmsegmentation GitHub/Dataset · publicwe generated and publicly released segmentation annotations for the complete LadyBird and UGA thermal image datasets using the best-performing SAM-CLIP model. Specifically, the final model obtained through the multi-round training process was used to generate 20,538 masks for the LadyBird dataset and 37,790 masks for the UGA dataset. Details of the generated annotations are provided in Supplementary Fig. S1 , and both annotated datasets are publicly available at: https://cornell.box.com/s/dh69xf84464yrc1vlws92l1tflx7qa89Open asset ↗lines:220-232Code / dataset availability confirmedOpenAlex · checked 14 Sept 2026
PlantCV is an open-source Python project aimed at developing tools to address a range of image-based, plant phenotyping questions. PlantCV has been used for more than 10 years to automate trait collection from image data, and the newest release, PlantCV version 4, continues to lower the barrier to entry for users without substantial coding experience through extensive example use-case tutorials and simplified installation. In addition to usability, we document added functionality since the release of PlantCV v2, including support for more image types such as fluorescence, thermal, and hyperspectral data. Finally, we describe the development of a new subpackage focused on morphological trait measurements like leaf angle, and demonstrate its utility as compared to more manual methods of data collection.
Why it matches plant phenotyping methods植物フェノタイピング用の画像解析ソフトウェア開発と、形態形質測定機能の実証が中心である。
abstractPlantCV is an open-source Python project aimed at developing tools to address a range of image-based, plant phenotyping questions.
Reproduction assets foundThe paper's data availability statement explicitly says that scripts used for the analyses in this paper are publicly available on GitHub (danforthcenter/plantcv-4-paper), and PlantCV source code is available via the PlantCV homepage. This is a paper-specific, public, actionable analysis-code asset.Code · publicerest.
DATA AVA I L A B I L I T Y S TAT E M E N T
Links to code, tutorials, documentation, and other resources
are available on the PlantCV homepage at https://plantcv.org. PlantCV source code is available on GitHub at https://
github.com/danforthcenter/plantcv. Scripts used for analyses
in this paper are available on GitHub at https://github.com/danforthcenter/plantcv-4-paper.O RC I D
HaleySchuhl https://orcid.org/0000-0002-8825-8297
KeelyE. Brown https://orcid.org/0000-0002-5371-5830
ParagK. Bhatt https://orcid.org/0000-0002-0396-6412
DominikSchneider https://orcid.org/0000-0002-5846-5033
Anna L. Casto https://orcid.org/0000-0002-9597-0514
Lucia Acosta-Gamboa https://orcid.org/0000-0001-77Open asset ↗danforthcenter/plantcv-4-paperpdf-raw-page:15 lines:1-92Code / dataset availability confirmedCrossref · Europe PMC · checked 15 Sept 2026
Abstract Plant diseases are a serious danger to the world’s food security, because they lower agricultural output and increase economic losses. Due to subjectivity, fluctuating lighting, and environmental unpredictability, traditional visual examination techniques are frequently incorrect. The Excess Green (ExG) vegetation index and pseudo-thermal representations produced from RGB pictures are two synthetically developed complementary representations that are integrated with RGB imagery in this study’s lightweight multimodal deep learning system to address these issues. Histogram shifting and pseudo-infrared color mapping are used in a reproducible picture alteration pipeline to create the pseudo-thermal modality, which allows for extra visual signals without the need for specific thermal sensors. In order to classify plant diseases while preserving computational efficiency, the suggested framework uses MobileNetV3-Small backbones to extract modality-specific characteristics. This is followed by feature-level fusion. The publicly accessible Ginger Leaf Dataset, which includes RGB pictures of ginger leaves in four different conditions—Damage-Pest, Dehydrated, Healthy, and Leaf-blight—was used for the experiments. For training, validation, and testing, the dataset was split using a stratified 70:15:15 split. Python-based preprocessing procedures were used to create the extra modalities (ExG and pseudo-thermal representations) from the original RGB images. The experimental results show that the combination of the representations with RGB images can enhance the classification performance compared with the unimodal RGB-based models. Ablation experiments are also conducted to examine the contributions of different modalities to the overall categorization accuracy. The experimental results show that plant disease recognition can be improved with the help of efficient computing by combining lightweight convolutional neural networks with computationally generated visual representations.
Why it matches plant phenotyping methodsRGB画像からExG・疑似熱画像を生成し、植物葉の病害状態を分類するマルチモーダル手法が研究の中心であり、アブレーション評価も実施している。
titleHybrid deep learning-based multimodal framework for plant leaf disease classification using RGB, Excess Green (ExG), and pseudo-thermal representations with MobileNetV2
Reproduction assets foundThe paper's phenotyping experiments use the publicly available Ginger Leaf Dataset (RGB leaf images of four ginger leaf conditions), with a public GitHub repository and dataset website. The authors' derived ExG/pseudo-thermal representations and preprocessing scripts are only available upon request, so they do not yetDataset · publicor multispectral images
IEEE Geosci. Remote Sens. Lett. 2025
10.1109/LGRS.2025.XXXXXXX
Ulku, I., Tanriover, O. O. & Akagündüz, E. Cross-band correlation-aware interactive fusion for multispectral images. IEEE Geosci. Remote Sens. Lett.
10.1109/LGRS.2025.XXXXXXX
(2025).
10. Wong, J. Ginger Leaf Dataset. GitHub Repository (2023). https://github.com/wongjay1941/Ginger-Leaf-Dataset
11.
Bhakta I
A novel plant disease prediction model based on thermal images using modified deep convolutional neural network
Precis. Agric. 2023 24 23 39
10.1007/s11119-022-09927-x
Bhakta, I. et al. A novel plant disease prediction model based on thermal images using modified deep convolutional neural network. Precis.Open asset ↗https://github.com/wongjay1941/Ginger-Leaf-Datasetlines:580-681Code / dataset availability confirmedOpenAlex · Europe PMC · checked 15 Sept 2026
Accurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping, particularly in outdoor environments where low contrast between plants and weeds and frequent occlusions hinder performance. To address this, we present a framework that leverages synthetic RGB imagery, a limited set of real annotations, and GAN-based cross-modality alignment to enhance semantic segmentation in thermal images. We trained models on 1128 synthetic images containing complex mixtures of crop and weed plants in order to generate image segmentation masks for crop and weed plants. We additionally evaluated the benefit of integrating as few as 20 real, manually segmented field images within the training process using various sampling strategies. When combining all the synthetic images with a few labeled real images, we observed a maximum relative improvement of the mean IoU score of 25% compared to the synthetic-only baseline. Cross-modal alignment was enabled by translating RGB to thermal using CycleGAN-Turbo, allowing robust template matching without calibration. Results demonstrated that combining synthetic data with limited manual annotations and cross-domain translation via generative models can significantly boost segmentation performance in complex field environments for multi-model imagery.
Why it matches plant phenotyping methods熱画像における作物・雑草の分割を対象とし、合成データ、少数の実画像、GANによるモダリティ間整合を用いた高スループット圃場フェノタイピング手法を開発・評価しているため。
abstractAccurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping
Reproduction assets foundThe paper's real annotated cowpea segmentation images and its synthetic Helios-generated training imagery are both publicly available on Hugging Face per the Data Availability statement. No author analysis code repository with explicit deposit language is provided (Helios and AgML are generic third-party tools, not theDataset · publicendix A
Supplementary data to this article can be found online at https://doi.org/10.1016/j.plaphe.2026.100214 .
Appendix A.
Supplementary data
The following is the Supplementary data to this article:
Multimedia component 1
Data availability
Data can currently be accessed through Huggingface [ 75 ]. The real data is found here: https://huggingface.co/datasets/earlranario/cowpea-segmentation . The synthetic data is found here: https://huggingface.co/datasets/earlranario/cowpea-synthetic-segmentation .Open asset ↗earlranario/cowpea-segmentationlines:341-366Code / dataset availability confirmedOpenAlex · checked 5 Sept 2026
Unmanned aerial vehicles (UAVs) have become indispensable tools in precision agriculture and plant phenotyping, enabling the rapid, non-destructive assessment of crop traits across space and time. Equipped with RGB, multispectral, thermal, and other sensors, UAVs provide detailed information on canopy structure, physiology, and stress responses that can guide management decisions and accelerate breeding programs. Despite these advances, the downstream processing of UAV imagery remains technically demanding. Converting orthomosaics into standardized, biologically meaningful data often requires a combination of photogrammetry, geospatial analysis, and custom scripting, which can limit reproducibility and accessibility across research groups. We present drone2report, an open-source python-based software that processes orthomosaics from UAV flights to generate vegetation indices, summary statistics, derived subimages, and text (html) reports, supporting both research and applied crop breeding needs. Alongside the basic structure and functioning of drone2report, we also present five case studies that illustrate practical applications common in UAV-/drone-phenotyping of plants: (i) thresholding to remove background noise and highlight regions of interest; (ii) monitoring plant phenotypes over time; (iii) extracting information on plant height to detect events like lodging or the falling over of spikes; (iv) integrating multiple sensors (cameras) to construct and optimize new synthetic indices; (v) integrate a trained deep learning network to implement a classification task. These examples demonstrate the tool’s ability to automate analysis, integrate heterogeneous data and models, and support reproducible computation of agronomically relevant traits. drone2report streamlines orthorectified UAV-image processing for precision agriculture by linking orthomosaics to standardized, plot-level outputs. Its modular, configuration-driven design allows transparent workflows, easy customization, and integration of multiple sensors within a unified analytical framework. By facilitating reproducible, multi-modal image analysis, drone2report lowers technical barriers to UAV-based phenotyping and opens the way to robust, data-driven crop monitoring and breeding applications.
Why it matches plant phenotyping methods植物表現型取得のためのUAV画像処理ソフトウェアを開発し、植物高・倒伏などの形質抽出、マルチセンサー統合、再現可能な解析ワークフローを中心的に提示している。
abstractWe present drone2report, an open-source python-based software that processes orthomosaics from UAV flights to generate vegetation indices, summary statistics, derived subimages, and text (html) reports
Reproduction assets foundThe paper explicitly states that the code and data to reproduce its five case studies (thresholding, temporal vegetation indices, height analysis, multi-sensor index optimization, deep learning classification) are publicly available in the authors' GitHub repository, and the DRONE2REPORT software itself is released as Code · publicThe code and data to reproduce these case studies
can be found at https://github.com/ne1s0n/paper-drone2report (accessed on 13 April
2026).Open asset ↗ne1s0n/paper-drone2reportpdf-page:6 lines:1-59Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
This article describes a multi-sensor dataset collected during the TIRAMISU (Thermal InfraRed Anisotropy Measurements in India and Southern eUrope) campaign at the Nawagam research site in Gujarat, India, during the 2023 monsoon season. The objective was to acquire continuous ground-based optical and thermal measurements over a homogeneous rice canopy across different crop growth stages. The dataset integrates several complementary components. Thermal data were acquired with an Optris longwave infrared camera (8-14 µm) at high temporal resolution, capturing canopy temperature dynamics throughout the diurnal cycle. Optical data were obtained with a Micasense RedEdge-M multispectral sensor, providing imagery in Blue, Green, Red, RedEdge, and Near-Infrared bands with radiometric corrections. An Apogee radiometer supplied reference radiometric temperature. Meteorological measurements included air temperature, humidity, wind speed and direction, and net radiation. Ancillary field measurements comprised Leaf Area Index (LAI), plant height, emissivity sampling, hyperspectral observations, and crop stage information. The datasets are provided with metadata and processing workflows, including calibration procedures for optical reflectance and thermal radiance. Together, these components form a comprehensive record of canopy-atmosphere interactions over a homogeneous rice field. The datasets can support research on optical and thermal directional anisotropy, canopy radiative transfer, emissivity characterization, and crop biophysical parameter estimation. In addition, they are relevant for applications in vegetation monitoring, agricultural water stress assessment, and surface energy balance studies. By combining optical, thermal, and meteorological observations, the resource is suited for multidisciplinary investigations in remote sensing, agronomy, and environmental sciences.
Why it matches plant phenotyping methods光学・熱画像、校正手順、処理ワークフロー、LAIや草丈などの植物形質を含む再利用可能な作物キャノピーデータセットが研究の中心であり、植物表現型取得基盤として適格。
abstractThe dataset integrates several complementary components.
Reproduction assets foundThe paper is a Data in Brief describing the TIRAMISU rice-canopy dataset (thermal/multispectral images, meteorological, ancillary LAI/height, hyperspectral, emissivity) publicly deposited at doi.org/10.6096/1028, including processing scripts (Thermal_CSV_to_Image.py, MicaSense notebook) for reproducibility.Dataset · publicRepository name: Optical, Thermal Infrared, and Meteorological Dataset from the Thermal InfraRed Anisotropy Measurements in India and Southern eUrope (TIRAMISU) Rice Canopy Experiment
Data identification number: doi.org/10.6096/1028
Direct URL to data: https://doi.org/10.6096/1028
Instructions for access: Publicly accessible repository; representative subsets provided with metadata and processing scripts.
Related research article
Pinnepalli, C., Roujean, J.-L., Irvine, M., et al. [ 1 ]. Measuring and modelling directional effects in the frame of TIRAMISU. ISPRS Annals, X–3–2024 , 325–330. https://doi.orgOpen asset ↗doi.org · 10.6096/1028lines:49-77Code / dataset availability confirmedCrossref · OpenAlex · Europe PMC · checked 5 Sept 2026
Developing climate-resilient wheat varieties requires combining high yield with stability across diverse environments, especially under increasingly variable precipitation and rising temperatures. This study evaluated 64 post-Green Revolution durum wheat cultivars under irrigated and rainfed conditions at two contrasting Mediterranean sites in Spain. A classification framework was developed to support genotype selection based on yield and yield stability, estimated using linear mixed models and yield slopes across environments. Genotypes were classified by interquartile thresholds, and those showing either low yield or low stability were considered undesirable for selection. High-throughput phenotyping was conducted throughout the season using ground-sensor Red-Green-Blue (RGB) and multispectral (MS) vegetation indices (VIs), along with UAV-derived RGB, MS, and thermal-infrared (TIR) data. VIs and TIR at anthesis and grain filling, and their differences (senescence proxies), were used to train Random Forests for yield and stability estimation including sequential feature selection. Environmental covariates (water input, reference evapotranspiration) were integrated in yield models, with strong outcomes (R 2 > 0.74; MAPE <23.6%). Stability predictions were based on VI stability and, though moderate (R 2 up to 0.56; MAPE <17.75%), outperformed previous studies. Selected features were used to evaluate seasonal reflectance phenotypes: “keep” genotypes (intermediate/high yield or/and stability) exhibited early-vigor but lower green retention by the end of grain filling, while “discard” genotypes (low yield or/and stability) showed reduced early vigor and “stay-green” behavior. This study highlights early-vigor and earlier senescence over “stay-green” for wheat selection, offering a cost-effective approach shifting the breeding focus from yield maximization to joint yield-stability evaluation, promoting sustainability.
Why it matches plant phenotyping methods高スループットの地上・UAVセンサーによる表現型取得と、機械学習による収量・安定性推定が研究の中心であり、育種選抜に用いる手法を実質的に評価・適用している。
abstractHigh-throughput phenotyping was conducted throughout the season using ground-sensor Red-Green-Blue (RGB) and multispectral (MS) vegetation indices (VIs), along with UAV-derived RGB, MS, and thermal-infrared (TIR) data.
Reproduction assets foundThe authors explicitly state that the datasets and analysis scripts for all analyses (yield/stability modeling, VI extraction, Random Forest workflows) are publicly available in their Zenodo repository (DOI 10.5281/zenodo.17435708), referenced both in the statistical analysis section and the Data Availability statementCode · publicThe datasets and scripts for all the analyses conducted are available in our repository ( https://doi.org/10.5281/zenodo.17435708 ).Open asset ↗zenodo · 10.5281/zenodo.17435708lines:222-237Code / dataset availability confirmedOpenAlex · Crossref · checked 15 Sept 2026
Abstract PlantCV is an open‐source Python project aimed at developing tools to address a range of image‐based, plant phenotyping questions. PlantCV has been used for more than 10 years to automate trait collection from image data, and the newest release, PlantCV version 4, continues to lower the barrier to entry for users without substantial coding experience through extensive example use‐case tutorials and simplified installation. In addition to usability, we document added functionality since the release of PlantCV v2, including support for more image types such as fluorescence, thermal, and hyperspectral data. Finally, we describe the development of a new subpackage focused on morphological trait measurements like leaf angle, and demonstrate its utility as compared to more manual methods of data collection.
Why it matches plant phenotyping methodsPlantCV v4は、画像から植物形質を自動抽出するオープンソースソフトウェアの開発・機能拡張・比較評価を主題としており、植物フェノタイピング手法が中心である。
abstractPlantCV is an open‐source Python project aimed at developing tools to address a range of image‐based, plant phenotyping questions.
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the authors' analysis scripts on GitHub (danforthcenter/plantcv-4-paper), which directly reproduces this paper's phenotyping analyses.Code · publicerest.
DATA AVA I L A B I L I T Y S TAT E M E N T
Links to code, tutorials, documentation, and other resources
are available on the PlantCV homepage at https://plantcv.org. PlantCV source code is available on GitHub at https://
github.com/danforthcenter/plantcv. Scripts used for analyses
in this paper are available on GitHub at https://github.com/danforthcenter/plantcv-4-paper.O RC I D
HaleySchuhl https://orcid.org/0000-0002-8825-8297
KeelyE. Brown https://orcid.org/0000-0002-5371-5830
ParagK. Bhatt https://orcid.org/0000-0002-0396-6412
DominikSchneider https://orcid.org/0000-0002-5846-5033
Anna L. Casto https://orcid.org/0000-0002-9597-0514
Lucia Acosta-Gamboa https://orcid.org/0000-0001-77Open asset ↗danforthcenter/plantcv-4-paperpdf-raw-page:15 lines:1-97Code / dataset availability confirmedEurope PMC · checked 5 Sept 2026
Effective pest and disease detection plays a crucial role in minimizing crop losses and improving decision-making in precision agriculture. Among the most destructive pests affecting maize crops globally is the Fall Army Worm (FAW), known for its rapid spread and high impact on yield. Existing detection practices often rely on manual scouting, which can be inefficient, labour intensive and prone to human error. This study proposes a novel deep learning based framework for the automatic classification of FAW infested and healthy maize crops by integrating RGB and thermal image modalities. The core objective is to enhance detection accuracy through multimodal image fusion. A hybrid DNN-ViT model is introduced, combining two complimentary pipelines: (i) feature-level fusion, where CNN extracted features from RGB and thermal images are fused and classified using a Deep Neural Network (DNN) and (ii) image-level fusion, where a 6 channel RGB-thermal image is directly processed using a modified Vision Transformer (ViT). Experimental results demonstrate that the fused model achieved superior performance with an accuracy of 0.98, precision, recall and F1-score of 0.98 and AUC-ROC of 0.98 on the test set, outperforming models trained on RGB-only, thermal-only and unfused data. The ablation study confirms the effectiveness of multimodal fusion, with the no-fusion model showing significantly lower performance (accuracy-0.60 and AUC-ROC-0.67). This work highlights the benefits of integrating complementary data sources for robust crop health monitoring. Future research will explore enhanced fusion strategies, environmental robustness and field level deployment to validate the model's practical applicability.
Why it matches plant phenotyping methodsRGB・熱画像融合によるFAW被害・健全状態の画像判定モデルを開発し、融合方式や性能を比較検証しているため、植物の健康状態を取得する方法が中心である。
abstractThis study proposes a novel deep learning based framework for the automatic classification of FAW infested and healthy maize crops by integrating RGB and thermal image modalities.
Reproduction assets foundThe paper's paired RGB/thermal maize FAW image dataset is publicly deposited on Figshare (part of a peer-reviewed data publication), and the authors' custom Python analysis code is released as a public supplementary file (Supplementary Code.zip) with explicit availability language. The Figshare URL matches an allowed, Dataset · publicThe dataset has been made publicly available in the Figshare Data repository as a part of a peer reviewed data publication54. Detailed information on data acquisition, sensor specifications, environmental conditions and annotation protocols is provided in the associated data article. The dataset can be accessed at: https://figshare.com/s/677d2384ba6e02db9230 (10.6084/m9.figshare.28388018).Open asset ↗Figshare · 10.6084/m9.figshare.28388018html-lines:324-345Code · publicThe custom python code developed for this study is available as supplementary file (“Supplementary Code.zip”) and includes all scripts necessary to reproduce the multimodal feature fusion, image-level fusion and ablation experiments described in the manuscript. The dataset used is publicly available on Figshare. All dependencies are listed within the code file. Readers can execute the python script to reproduce the reported results.Open asset ↗html-lines:324-345Code / dataset availability confirmedCrossref · Europe PMC · checked 6 Sept 2026
Background: Quantitatively detecting whether plants exhibit measurable bioelectric differences in the presence of nearby human movement remains challenging, in part because plant signals are low-amplitude, slow, and easily confounded by environmental factors. Methods: We recorded bioelectric activity from 2978 plant samples across three species (basil, salad, tomato) using differential electrode pairs (leaf and soil electrodes) sampling at 142 Hz. Two trained performers executed three specific eurythmic gestures near experimental plants while control plants remained isolated. Random Forest and Convolutional Neural Network classifiers were applied to distinguish the control from treatment conditions using engineered features including spectral, temporal, wavelet, and frequency domain characteristics. Results: Random Forest classification achieved 62.7% accuracy (AUC = 0.67) distinguishing differences in recordings collected near a moving human from control conditions, representing a statistically significant 12.7 percentage point improvement over chance. Individual performer signatures were detectable with 68.2% accuracy, while plant species classification achieved only 44.5% accuracy, indicating minimal species-specific artifacts. Temporal analysis revealed that the plants with repeated exposure exhibited consistently less negative bioelectric amplitudes compared to single-exposure plants. Innovation: We introduce a data-driven approach that pairs standardized, short-window bioelectric recordings with machine-learning classifiers (Random Forest, CNN) to test, in an exploratory manner, whether plant signals differ between human-moving-nearby and isolation conditions. Conclusions: Plants exhibit modest but statistically detectable bioelectric differences in the presence of nearby human movement. Rather than attributing these differences to eurythmic movement itself, the present design can only demonstrate that plant recordings collected within ~1 m of a moving human differ, modestly but statistically, from recordings taken ≥3 m away. The underlying biophysical pathways and specific contributing factors (airflow, VOCs, thermal plumes, vibration, electromagnetic fields) remain unknown. These results should therefore be interpreted as exploratory correlations, not mechanistic evidence of gesture-specific plant sensing.
Why it matches plant phenotyping methods植物の生体電気記録をセンサーで取得し、特徴抽出と機械学習によって植物の状態差を判別する方法が研究の中心であり、単なる生理測定ではない。
abstractWe introduce a data-driven approach that pairs standardized, short-window bioelectric recordings with machine-learning classifiers (Random Forest, CNN) to test, in an exploratory manner, whether plant signals differ between human-moving-nearby and isolation conditions.
Reproduction assets foundThe paper's plant bioelectric recordings (wav sensor data from basil, salad, tomato with/without nearby human movement) are publicly deposited on figshare, with an explicit Data Availability Statement and URL matching an allowed URL.Dataset · publicThe datasets generated and analyzed during the current study are available from figshare https://figshare.com/articles/dataset/Machine_Learning_Detection_of_Plant_Bioelectric_Responses_to_Human_Eurythmic_Gestures_/30227083?file=58324288 (accessed 25 October 2025).Open asset ↗figshare · 30227083lines:172-191Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
We investigate the potential of phenomic prediction (PP) in remote-sensing-based phenotyping for genetic studies. Rather than relying on a single vegetation index, we utilize all available data collectively to predict the human-assigned visual score (VS). The conceptual motivation is that when a trained model is available, these predictions may provide a more accurate assessment of disease symptoms than the use of a specific vegetation index (VI). To evaluate the PP approach, we employ the predicted VS in a genome-wide association study (GWAS) and consider strength and position of the detected genetic signal. We use two different sets of predictor variables: i) the five basic wavelengths captured by a multispectral and a thermal camera (basic traits model, BT) or ii) all traits (AT), consisting of the five basic wavelengths plus ten vegetation indices. As statistical methods, we compare a) (linear) ordinary least squares regression (OLS), b) (linear) ridge regression (RR), c) (linear) least absolute shrinkage and selection operator (LASSO) d) an artificial neural network (ANN) and e) a gradient boosted regression tree method (GBRT). Our results indicate that the simple linear OLS regression on the five basic wavelengths (BT-OLS) performs on a level comparable to the best individual vegetation index G. The use of all traits in the OLS regression (AT-OLS) leads to overfitting, which was prevented by the regularization in AT-RR and AT-LASSO. The non-linear ANN approach seems to improve the results further, but the differences between the methods were not statistically significant. The strongest improvement for the purification of the genetic signal was observed when genomic estimated breeding values (GEBVs) for the different traits (VS, basic wavelengths, vegetation indices) instead of their adjusted phenotypes were used. Across all approaches, the combination of GEBVs with Ridge Regression or the non-linear ANN provided the best results.
Why it matches plant phenotyping methodsリモートセンシング画像・センサーデータからトウモロコシさび病の視覚的症状スコアを推定する複数の統計・機械学習手法を比較評価しており、表現型取得・抽出法が研究の中心である。
abstractWe investigate the potential of phenomic prediction (PP) in remote-sensing-based phenotyping for genetic studies.
Reproduction assets foundThe paper's phenotypic (visual scores, adjusted phenotypes) and remote-sensing (multispectral/thermal) data, plus genomic marker data, are publicly deposited in the CIMMYT Research Data repository. No authors' analysis code or trained model checkpoints are deposited; R packages cited are generic libraries.Dataset · publicWe use the data previously published by Loldaze et al. [ 21 , 22 ], which is available on the CIMMYT Research Data repository at https://hdl.handle.net/11529/10548898 .Open asset ↗CIMMYT Research Data repository · 11529/10548898lines:35-47Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Large-scale rainfed cropping systems (broadacre agriculture) face intensifying climate and resource stresses that undermine yield stability and farm livelihoods. Remote sensing (RS) offers critical tools for improving resilience by monitoring crop performance—productivity, phenology, and environmental stress—across large areas and timeframes. This review aims to synthesize methodological advances over the past two decades in applying RS for broadacre crop monitoring and to identify key challenges and integration opportunities. Peer-reviewed studies across diverse crops and regions were systematically examined to evaluate the strengths, limitations, and emerging trends across the three RS application themes. The review finds that (1) RS enables spatially explicit yield estimation from regional to paddock scales, with vegetation indices (VIs) and phenology-adjusted metrics closely correlated with yield. (2) Time-series analyses of RS data effectively capture phenological transitions critical for forecasting, supported by advances in curve fitting, sensor fusion, and machine learning. (3) Thermal and multispectral indices support early detection of abiotic (drought, heat, salinity) and biotic (pests, disease) stresses, though specificity remains limited. Across themes, methodological silos and sensor integration barriers hinder holistic application. Emerging approaches—such as multi-sensor/scale fusion, RS–crop model data assimilation, and operational and big data integration—provide promising pathways toward resilience-focused decision support. Future research should define quantifiable resilience metrics and cross-theme predictive integration to guide climate adaptation.
Why it matches plant phenotyping methods作物の生産性、フェノロジー、環境ストレスをリモートセンシングで測定・推定する方法論レビューであり、植物形質・状態の取得手法が中心である。
abstractThis review aims to synthesize methodological advances over the past two decades in applying RS for broadacre crop monitoring
Reproduction assets foundThis methodological review includes a case study (Figure 2) using MODIS NDVI composites, SILO gridded climate data, and ABARES historical winter crop yield data. The authors explicitly state the case-study datasets are publicly accessible via official portals; the SILO and ABARES portals are paper-specific public data-Dataset · publiclies, and observed productivity. Note: This figure is derived from
the authors’ ongoing study. The monthly NDVI composites (MOD13C2) were generated post-season, which limits their
utility for in-season forecasting. The gridded Climate data were obtained from the Australian Scientific Information for
Land Owners (SILO) database (https://www.longpaddock.qld.gov.au/silo/), and historical winter crop yield data were
sourced from the Australian Bureau of Agricultural and Resource Economics and Sciences (ABARES)
(https://www.agriculture.gov.au/abares/data).
However, Figure 2 also illustrates key limitations of NDVI-based monitoring. First, the complete
seasonal NDVI composite becomes available onlOpen asset ↗SILOpdf-layout-page:8 lines:1-53Dataset · publiclity for in-season forecasting. The gridded Climate data were obtained from the Australian Scientific Information for
Land Owners (SILO) database (https://www.longpaddock.qld.gov.au/silo/), and historical winter crop yield data were
sourced from the Australian Bureau of Agricultural and Resource Economics and Sciences (ABARES)
(https://www.agriculture.gov.au/abares/data).
However, Figure 2 also illustrates key limitations of NDVI-based monitoring. First, the complete
seasonal NDVI composite becomes available only after crop harvest, limiting its usefulness for in-
season yield forecasting or early drought warning. In other words, detailed phenological curves and
productivity metrics can onlyOpen asset ↗ABARESpdf-layout-page:8 lines:1-53Code / dataset availability confirmedEurope PMC · bioRxiv · Crossref · checked 14 Sept 2026
ABSTRACT The development of remote sensing methods to estimate plant functional diversity is limited by mismatches between ecology and remote sensing sampling schemes, and the limited representativeness of local field campaigns. The Biodiversity Observing System Simulation Experiment (BOSSE) provides a modeling framework for benchmarking new methodologies. We used BOSSE to simulate 180 different synthetic “Scenes” encompassing a two-year-long time series of plant trait maps and imagery of hyperspectral reflectance factors, spectral indices, sun-induced chlorophyll fluorescence, land surface temperature, and estimates of plant traits (optical traits). We used these simulations to answer five fundamental, yet unsolved, questions: Q1. How should remote sensing characterize functional diversity in large surfaces (sites)? Diversity metric values saturate with the number of pixels involved, hampering comparisons between plant traits and remote sensing estimates in large areas. The average value of metrics computed over small samples should be used instead. Q2. Which sources of spectral information (or combinations thereof) can best capture plant functional diversity at the site scale? Accounting for background effects is the key. Optical traits (remote sensing estimates of plant traits) are the best estimators for plant functional diversity. Other variables succeed when filtered out of the soil pixels; their combination did not yield additional advantages. Q3. How should remote sensing estimates be validated/compared with plant functional diversity measurements? Leaf area index (LAI) is a better proxy of abundance than the pixel for Q Rao, but not for variance-based partitioning. It is more sensitive to sample size, but also more resistant to suboptimal spatial resolution. Q4. When (in the phenological year) can remote sensing best capture site-scale plant functional diversity? The estimation error decreased with LAI and stabilized at values above 1 m²/m². Q5. Which approaches and remote sensing variables are more resistant to the effects of suboptimal spatial resolution? Optical traits, fluorescence, and reflectance factors were the most robust variables. Still, field data resolution needs to be degraded to match the sensor’s resolution. We found a relative spatial resolution threshold of ∼30 % (where the pixel is around three times larger than the plants). Simulation frameworks like BOSSE enable testing methodologies beyond local contexts and address the current shortage of suitable global datasets, supporting the application and development of methods for assessing plant functional diversity with remote sensing. In the future, BOSSE could contribute to understanding observational results, refining and pre-testing new methodologies, and supporting the development of comparable experimental datasets.
Why it matches plant phenotyping methodsBOSSEを用いてリモートセンシングによる植物形質・機能多様性推定手法をシミュレーションベンチマークし、検証・比較する研究であり、植物フェノタイピング手法が中心である。
abstractThe Biodiversity Observing System Simulation Experiment (BOSSE) provides a modeling framework for benchmarking new methodologies.
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 · publicvariables, we used the “pyGNDiv” package (https://github.com/JavierPachecoLabrador/pyGNDiv-Open asset ↗JavierPachecoLabrador/pyGNDiv- · pyGNDivpdf-page:11 lines:1-60Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 6 Sept 2026
Developing crop varieties that maintain productivity under drought is essential for future food security. Here, we investigated the potential of time-resolved high-throughput phenotyping to predict harvest-related traits and identify drought-stressed plants. Six barley lines ( Hordeum vulgare ) were grown in a greenhouse environment with well-watered and drought treatments, and dynamically phenotyped using RGB, thermal infrared, chlorophyll fluorescence, and hyperspectral imaging sensors. A temporal phenomic classification model accurately distinguished between drought-treated and control plants, achieving high accuracy (classification accuracy ≥0.97) even when relying solely on predictors from the early drought response phase. Canopy temperature depression at the early stage and RGB-derived plant size estimates at the late stage emerged as key classification features. A temporal phenomic prediction model of harvest-related traits achieved particularly high mean R 2 values for total biomass dry weight (0.97) and total spike weight (0.93), with RGB plant size estimators emerging as important predictors. Importantly, prediction accuracy for these traits remained high (R 2 ≥ 0.84) even when restricted to early developmental phase data, including the stem elongation stage. Models trained on pooled drought and control data outperformed single-treatment models and maintained high predictive power across treatments. Together, these findings highlight the value of integrating high-throughput phenotyping with temporal modeling to enable earlier, more cost-effective selection of drought-resilient genotypes and demonstrate the broader potential of phenomics-driven strategies for accelerating crop improvement under stress-prone environments.
Why it matches plant phenotyping methodsRGB・熱赤外・蛍光・ハイパースペクトルによる時系列表現型取得と、収穫形質予測モデルの構築・評価が研究の中心であるため。
abstractdynamically phenotyped using RGB, thermal infrared, chlorophyll fluorescence, and hyperspectral imaging sensors
Reproduction assets foundThe authors explicitly state that the data and analysis pipeline code for this barley phenotyping study is publicly available on GitHub at https://github.com/hatiez/barley-TPP-pipeline. This is a paper-specific computational asset (the temporal phenomic classification/prediction pipeline) with an authors' public URL. DCode · publicThe data and analysis pipeline code is available on https://github.com/hatiez/barley-TPP-pipeline .Open asset ↗https://github.com/hatiez/barley-TPP-pipelinelines:390-415Code / dataset availability confirmedOpenAlex · arXiv · checked 6 Sept 2026
Accurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping, particularly in outdoor environments where low contrast between plants and weeds and frequent occlusions hinder performance. To address this, we present a framework that leverages synthetic RGB imagery, a limited set of real annotations, and GAN-based cross-modality alignment to enhance semantic segmentation in thermal images. We trained models on 1,128 synthetic images containing complex mixtures of crop and weed plants in order to generate image segmentation masks for crop and weed plants. We additionally evaluated the benefit of integrating as few as five real, manually segmented field images within the training process using various sampling strategies. When combining all the synthetic images with a few labeled real images, we observed a maximum relative improvement of 22% for the weed class and 17% for the plant class compared to the full real-data baseline. Cross-modal alignment was enabled by translating RGB to thermal using CycleGAN-turbo, allowing robust template matching without calibration. Results demonstrated that combining synthetic data with limited manual annotations and cross-domain translation via generative models can significantly boost segmentation performance in complex field environments for multi-model imagery.
Why it matches plant phenotyping methods熱画像による作物・雑草の分割を対象とし、合成データ、少数の実画像、GANによるモダリティ変換を組み合わせた高スループット表現型取得手法を開発・評価している。
abstractAccurate plant segmentation in thermal imagery remains a significant challenge for high throughput field phenotyping
Reproduction assets foundThe paper states its synthetic and real phenotyping image datasets (cowpea/weed RGB and thermal imagery with segmentation masks) are publicly available through the AgML framework, with an explicit authors' URL. Helios is a general simulation tool, not a paper-specific asset.Dataset · publicSynthetic and real datasets are available through AgML 1 1
1
https://github.com/Project-AgML/AgML [ 50 ] , a centralized framework for agricultural machine learning.Open asset ↗Project-AgML/AgMLlines:339-434Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
Summary Thermal imaging is a key plant phenotyping and monitoring technique but faces major bottlenecks in accurately and efficiently inferring stomatal conductance (gsw) from leaf temperature. The conductance index (Ig) was previously proposed to estimate gsw from thermography by linking temperature differences between real and artificial leaves (ALs) based on the leaf energy balance. However, Ig is highly sensitive to environmental fluctuations, hampering interpretation and reducing reproducibility. We developed a simple and novel correction factor (named DynG) for Ig that accounts for environmental fluctuations when scaling Ig to gsw. This was achieved by capturing temperature variations in a set of ALs with a range of known constant pore conductances. This approach provided the Ig–conductance relationship, using ALs as a reference, to infer gsw of real leaves from their measured Ig. In fluctuating environments, gsw estimated using DynG showed greater accuracy and stability than gsw calculated from Ig alone, and was in good agreement with gsw determined using lysimetric and gas exchange methods. DynG's power was further showcased in distinguishing gsw of Arabidopsis genotypes differing in stomatal traits (Col‐0, epf1epf2, and EPF2OE). We conclude that Ig corrected with DynG can reliably estimate gsw in fluctuating environments without complex modeling, opening new avenues for gsw phenotyping and monitoring.
Why it matches plant phenotyping methods熱画像から気孔コンダクタンスを推定する補正係数を開発し、変動環境下で既存法と比較検証した、植物フェノタイピング手法の中心的研究である。
abstractWe developed a simple and novel correction factor (named DynG) for Ig that accounts for environmental fluctuations when scaling Ig to gsw.
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 · publicRelated codes are available on GitHub ( https://github.com/jiayu0903/dynamic‐conductance‐index.git ).Open asset ↗https://github.com/jiayu0903/dynamic‐conductance‐index.gitlines:805-819Code / dataset availability confirmedCrossref · Europe PMC · checked 13 Sept 2026
GreenhouseThermalLeafPhysiological trait estimationStress response / tolerancePlant / canopy temperature
ABSTRACT Extreme heat can push plants beyond their thermal safety margin ( TSM ) if maximum leaf temperature ( T leaf_max ) exceeds leaf critical temperature ( T crit ). The TSM is potentially useful for assessing heat vulnerability across species but needs further validation, so we exposed 50 tree/shrub species in controlled glasshouses to a 6‐day heatwave (peak air temperature = 41°C). Many species increased their mean T crit during the heatwave (42%), with Δ T crit ranging from +1°C to 4°C, but other species did not acclimate or were impaired by heat stress (58%). Species T leaf_max explained ~55% of the variation in species T crit and was a key correlate of the plasticity of T crit among species. Species with high Δ T crit also had higher Δ T leaf_max , with leaves being 7°‒12°C hotter during the heatwave than under baseline conditions. Both T leaf_max and TSMs were correlated with heatwave damage across diverse species from contrasting climate zones. Species differences in TSMs were stable across measurement temperatures, correctly identified the most vulnerable species, and were strongly associated with T leaf_max . Our results suggest that (1) T leaf_max alone is more informative than T crit for ranking species heat tolerance, and (2) species vulnerability to heatwaves is most reliably assessed by using TSMs that integrate T leaf_max with T crit across species.
Why it matches plant phenotyping methods葉温・熱安全余裕度（TSM）を用いた植物の熱脆弱性評価手法を、多種の植物で検証し、損傷予測性能や種間比較の妥当性を評価しているため、方法的役割が中心である。
abstractThe TSM is potentially useful for assessing heat vulnerability across species but needs further validation
Reproduction assets foundThe article's Data Availability Statement explicitly states the supporting data (phenotype measurements: Tcrit, Tleaf_max, TSM, damage indicators for 50 species) are openly available on Figshare at the authors' public DOI, which is an allowed URL.Dataset · publicData Availability Statement
The data that support the findings of this study are openly available in Figshare at https://doi.org/10.6084/m9.figshare.29345549.v1 .Open asset ↗Figshare · 10.6084/m9.figshare.29345549.v1lines:721-817Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
The aboveground biomass (AGB) of crops is an essential metric for monitoring crop growth, making timely and accurate AGB forecasting critical for effective agricultural management. The introduction of Unmanned Aerial Vehicles (UAVs) and advanced sensor technologies has revolutionized traditional AGB prediction techniques. Currently, machine learning (ML) combined with UAV data are commonly utilized, along with the Vegetation Index Weighted Canopy Volume Model (CVM VI ) for AGB prediction. Nevertheless, there is limited investigation into how these methods perform across different agricultural conditions. This study aims to fill this gap by creating specific methodologies for estimating corn AGB under diverse fertilization and irrigation treatments. We utilized LiDAR, multispectral (MS), thermal infrared (TIR), along with measured AGB and Leaf Area Index (LAI) data from various growth stages to develop a stacking ensemble learning model. This model effectively integrates data from multiple sources, resulting in a strong prediction performance with R 2 of 0.86, Mean Absolute Error (MAE) of 1.54 t/ha, and Root Mean Square Error (RMSE) of 2.06 t/ha. Meanwhile, the analysis of the accuracy of CVM VI revealed its efficacy during the early-stage when corn is short, with its predictive capability diminishing as AGB increases. Consequently, we recommend the CVM VI for early-stage AGB prediction, which can streamline data collection and computational efforts. In contrast, the ML approach, which benefits from data fusion, is more appropriate for predicting AGB during the mid to late growth stages. This study enhances AGB prediction accuracy and speed, providing critical understanding of regional AGB dynamics and supporting better agricultural decision-making.
Why it matches plant phenotyping methodsUAVのLiDAR・マルチスペクトル・熱赤外データを統合し、トウモロコシの地上部バイオマスを推定するモデルを開発・比較・評価しており、植物形質取得手法が中心である。
abstractThis study aims to fill this gap by creating specific methodologies for estimating corn AGB under diverse fertilization and irrigation treatments.
Reproduction assets foundThe paper's Data Availability statement explicitly deposits authors' model training code and test data at a public GitHub repository, which qualifies as a paper-specific public code asset for the AGB prediction analysis.Code · publicCode and test data for model training are available at https://github.com/Joker1xuan/model_training .Open asset ↗Joker1xuan/model_traininglines:323-356Code / dataset availability confirmedEurope PMC · checked 6 Sept 2026
In complex farmland environments, wheat canopy coverage is insufficient at the tillering stage, posing a considerable challenge to the accurate extraction of its canopy using UAV(unmanned air vehicle) remote sensing images. In this paper, an end-to-end semantic segmentation method based on visible light (RGB) and thermal infrared (TIR) images, Tiff-SegFormer, which fused spectral features and temperature features effectively, is proposed for accurate pixel-level classification of winter wheat at the tillering stage images taken by UAV to segment the wheat canopy and background. Tiff-SegFormer utilizes hierarchical feature representation and efficient self-attention in the encoder stage to extract features of detail contours of RGB images and temperature changes of TIFF images, respectively. In the decoder stage, the features are concatenated and then the channel and spatial attention mechanisms are superimposed, aiming to further improve the segmentation accuracy and efficiency of winter wheat at the tillering stage in UAV remote sensing images. The results show that Tiff-SegFormer can achieve accurate segmentation of wheat canopy and background from UAV images of winter wheat at the tillering stage (mIoU = 84.28%, mPA = 88.97%, accuracy = 94.55%). In order to verify the efficiency of the proposed method, Tiff-SegFormer is compared with four widely used semantic segmentation methods, all of which show better performance. The four methods are UNet, DeepLabv3+, HRNet, SegFormer and four-channel (RGB + TIFF) Segformer. The generalization test shows that the proposed Tiff-SegFormer also achieves better performance than other comparison methods (mIoU = 84.94%, mPA = 91.46%, accuracy = 94.71%). Tiff-SegFormer provides a robust and efficient tool for segmenting winter wheat canopy from UAV remote sensing images of winter wheat at the tillering stage, and has great potential in applications (model implementation and results can be found at https://github.com/wylSUGAR/Tiff-SegFormer ).
Why it matches plant phenotyping methodsUAVのRGB・熱赤外画像から冬コムギのキャノピーを抽出するセマンティックセグメンテーション手法を開発し、複数手法との比較および汎化性能検証を行っており、植物状態の取得方法が中心である。
abstractan end-to-end semantic segmentation method based on visible light (RGB) and thermal infrared (TIR) images, Tiff-SegFormer, which fused spectral features and temperature features effectively, is proposed for accurate pixel-level classification of winter wheat at the tillering stage images taken by UAV to segment the wheat canopy and background.
Reproduction assets foundThe paper publicly releases the UAV RGB/TIR winter wheat tillering-stage image dataset and the TIR-to-TIFF conversion code via two author GitHub repositories. The Tiff-SegFormer model repository is referenced but its URL is not among the allowed URLs, and labelme is a generic third-party tool, so neither is included.Dataset · publicThe image can be found at
https://github.com/wylSUGAR/wheat_tillering_stage.Open asset ↗wylSUGAR/wheat_tillering_stagepdf-page:2 lines:56-74Code · publicthe TIR image was
converted into a TIFF image (the code can be found at https://github.com/wylSUGAR/TIR_DJ_tiff)Open asset ↗wylSUGAR/TIR_DJ_tiffpdf-page:2 lines:56-74Code / dataset availability confirmedOpenAlex · Crossref · checked 14 Sept 2026
Alfalfa is a deep-rooted perennial forage crop with diverse drought-tolerant traits. This study evaluated 250 alfalfa half-sib populations over three growing seasons (2021–2023) under irrigated and rainfed conditions in the Mediterranean drought-prone region of Central Chile (Cauquenes), aiming to identify high-yielding, drought-tolerant populations using remote sensing. Specifically, we assessed RGB-derived indices and canopy temperature difference (CTD; Tc − Ta) as proxies for forage yield (FY). The results showed considerable variation in FY across populations. Under rainfed conditions, winter FY ranged from 1.4 to 6.1 Mg ha−1 and total FY from 3.7 to 14.7 Mg ha−1. Under irrigation, winter FY reached up to 8.2 Mg ha−1 and total FY up to 25.1 Mg ha−1. The AlfaL4-5 (SARDI7), AlfaL57-7 (WL903), and AlfaL62-9 (Baldrich350) populations consistently produced the highest yields across regimes. RGB indices such as hue, saturation, b*, v*, GA, and GGA positively correlated with FY, while intensity, lightness, a*, and u* correlated negatively. CTD showed a significant negative correlation with FY across all seasons and water regimes. These findings highlight the potential of RGB imaging and CTD as effective, high-throughput field phenotyping tools for selecting drought-resilient alfalfa genotypes in Mediterranean environments.
Why it matches plant phenotyping methodsRGB画像指標と冠層温度差を用いた高スループット表現型解析を、アルファルファ集団の収量・干ばつ耐性選抜に実質的に適用しており、表現型取得手法が中心的である。
titleSelecting High Forage-Yielding Alfalfa Populations in a Mediterranean Drought-Prone Environment Using High-Throughput Phenotyping
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 · publicthe Mosaic tool software and Cereal-Scanner plugin,
developed by Shawn Kefauver from the University of Barcelona, were utilized for further
analysis (available at https://gitlab.com/sckefauver/cerealscanner (accessed on 6 March
2025)).Open asset ↗gitlab.com/sckefauver/cerealscannerpdf-page:7 lines:1-55Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Published1 Mar 2025The Plant journal : for cell and molecular biologyCited by 6 · OpenAlex ↗
High lipid producing (HLP) tobacco (Nicotiana tabacum) is a potential biofuel crop that produces an excess of 30% dry weight as lipid bodies in the form of triacylglycerol. While using HLP tobacco as a sustainable fuel source is promising, it has not yet been tested for its tolerance to warmer environments that are expected in the near future as a result of climate change. We found that HLP tobacco had reduced stomatal conductance, which results in increased leaf temperatures up to 1.5°C higher under control and high temperature (38°C day/28°C night) conditions, reduced transpiration, and reduced CO 2 assimilation. We hypothesize this reduction in stomatal conductance is due to the presence of excessive, large lipid droplets in HLP guard cells imaged using confocal microscopy. High temperatures also significantly reduced total fatty acid levels by 55% in HLP plants; thus, additional engineering may be needed to maintain high titers of leaf oil under future climate conditions. High-throughput image analysis techniques using open-source image analysis platform PlantCV for thermal image analysis (plant temperature), stomata microscopy image analysis (stomatal conductance), and fluorescence image analysis (photosynthetic efficiency) were developed and applied in this study. A corresponding set of PlantCV tutorials are provided to enable similar studies focused on phenotyping future crops under adverse conditions.
Why it matches plant phenotyping methodsPlantCVを用いた熱画像・気孔顕微鏡画像・蛍光画像の高スループット解析手法を開発・適用し、植物温度、気孔関連指標、光合成効率を推定しているため、表現型取得手法が中心的です。
abstractHigh-throughput image analysis techniques using open-source image analysis platform PlantCV for thermal image analysis (plant temperature), stomata microscopy image analysis (stomatal conductance), and fluorescence image analysis (photosynthetic efficiency) were developed and applied in this study.
Reproduction assets foundThe paper's raw phenotyping image data (thermal, fluorescence, stomata, confocal microscopy) are deposited on Zenodo, and the authors' PlantCV analysis workflows and R scripts are on GitHub, including three PlantCV tutorials for thermal, stomata, and photosynthesis analysis.Dataset · publicaxial side of the leaf rather than a cross section. While small lipid droplets were present in the WT stomatal guard cells and epidermis, large lipid droplets were present in the HLP guard cells under both control and after 7 days of treatment (representative control images in Figure 8A–D , complete dataset available on Zenodo, https://zenodo.org/records/10711864 ). In addition, while HLP oil appeared to form spherical droplets, it did not “line” the stomatal opening as in WT (Figure 8C,D ).
Figure 8
High lipid producing (HLP) had excessive oil droplets in stomatal guard cells.
Representative confocal microscopy images, shown as focused Z‐stack, of tobacco leaf tissue fixed in paraformaOpen asset ↗Zenodolines:115-123Code · publicmated marginal means (LSMEANS) to determine which sample types were significantly different from others. Means are reported in text with standard error. Plots were made using ggplot2 package (v.3.5.0) in R. Jupyter notebooks associated with PlantCV analyses and R scripts associated with this manuscript are available on Github ( https://github.com/danforthcenter/tobacco‐heat‐paper ).
AUTHOR CONTRIBUTIONS
DKA, MAG, PDB, BSJ and KMM designed experiments. KMM and BSJ performed experiments and data analysis. KJC designed and aided KMM in confocal and brightfield microscopy experiments and advised TEM experiments. JW performed TEM experiments, and KG‐O and SK performed data analysis of TEM images.Open asset ↗GitHublines:171-182Code · publictification was used to isolate only individual plants in each mask. Then, the mask was applied to the registered thermal image to calculate the average plant temperature, as well as a histogram of pixel temperatures for each plant. A PlantCV workflow was used to analyze the images in parallel. A tutorial is available on GitHub: https://github.com/danforthcenter/plantcv‐tutorial‐thermal?tab=readme‐ov‐file (Acosta‐Gamboa et al., 2024 ). Scripts for this project are available at https://github.com/danforthcenter/tobacco‐heat‐paper . Raw image data are available on Zenodo, https://zenodo.org/records/10711864 .
Stomatal aperture measurements
To measure stomatal number and aperture, leaf impressioOpen asset ↗GitHublines:142-146Code · publicpackage was then used to calculate the number of stomata and the area of the aperture. A limitation of this method is that it does not provide the width and length of stomata, or measurements of the guard cells themselves; instead, it provides the aperture area (a result of length and width). A tutorial is available on GitHub: https://github.com/danforthcenter/plantcv‐stomata‐tutorial‐pcv4 (Murphy, 2024 ). Scripts for this project are available at https://github.com/danforthcenter/tobacco‐heat‐paper . Raw image data are available on Zenodo, https://zenodo.org/records/10711864 .
Photosynthesis and gas exchangeOpen asset ↗GitHublines:142-146Code · publicPlantCV (Gehan et al., 2017 ) using the photosynthesis package; the chlorophyll fluorescence image was used to mask the image for only plant pixels, and average F
v / F
m , F q ′ / F m ′ , NPQ, chlorophyll index, and anthocyanin index were calculated as an average per plant at each timepoint. A tutorial is available on GitHub: https://github.com/danforthcenter/plantcv‐tutorial‐photosynthesis?tab=readme‐ov‐file (Schuhl et al., 2024 ). Scripts for this project are available at https://github.com/danforthcenter/tobacco‐heat‐paper . Raw image data are available on Zenodo, https://zenodo.org/records/10711864 .
Microscopy imaging of lipids
Leaf samples analyzed for lipid content were taken from thOpen asset ↗GitHublines:156-164Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Recent research has shown that optimizing photosynthetic and stomatal traits holds promise for improved crop performance. However, standard phenotyping tools such as gas exchange systems have limited throughput. In this work, a novel approach based on a bespoke gas exchange chamber allowing combined measurement of the quantum yield of PSII (Fq'/Fm'), with an estimation of stomatal conductance via thermal imaging was used to phenotype a range of bread wheat (Triticum aestivum L.) genotypes. Using the dual-imaging methods and traditional approaches, we found broad and significant variation in key traits, including photosynthetic CO2 uptake at saturating light and ambient CO2 concentration (Asat), photosynthetic CO2 uptake at saturating light and elevated CO2 concentration (Amax), the maximum velocity of Rubisco for carboxylation (Vcmax), time for stomatal opening (Ki), and leaf evaporative cooling. Anatomical analysis revealed significant variation in flag leaf adaxial stomatal density. Associations between traits highlighted significant relationships between leaf evaporative cooling, leaf stomatal conductance, and Fq'/Fm', highlighting the importance of stomatal conductance and stomatal rapidity in maintaining optimal leaf temperature for photosynthesis in wheat. Additionally, gsmin and gsmax were positively associated, indicating that potential combinations of preferable traits (i.e. inherently high gsmax, low Ki, and maintained leaf evaporative cooling) are present in wheat. This work highlights the effectiveness of thermal imaging in screening dynamic gs in a panel of wheat genotypes. The wide phenotypic variation observed suggested the presence of exploitable genetic variability in bread wheat for dynamic stomatal conductance traits and photosynthetic capacity for targeted optimization within future breeding programmes.
Why it matches plant phenotyping methods特注ガス交換チャンバーと熱画像を組み合わせた動的な気孔コンダクタンス・光合成形質の取得手法を開発し、複数のコムギ遺伝子型で実証しているため、植物フェノタイピング手法が中心です。
abstracta novel approach based on a bespoke gas exchange chamber allowing combined measurement of the quantum yield of PSII (Fq'/Fm'), with an estimation of stomatal conductance via thermal imaging was used to phenotype a range of bread wheat (Triticum aestivum L.) genotypes.
Reproduction assets foundThe paper's Data Availability statement points to a public Dryad repository containing the raw phenotyping data (photosynthesis and stomatal kinetics measurements) for this study, matching an allowed URL. Supplementary datasets S1–S2 are calculation spreadsheets but no standalone public URL is given for them beyond theDataset · publicRaw data can be accessed from the Dryad Digital Repository ( Faralli et al. , 2024 ) ( https://doi.org/10.5061/dryad.79cnp5j4d ).Open asset ↗Dryad Digital Repository · 10.5061/dryad.79cnp5j4dlines:117-171Code / dataset availability confirmedOpenAlex · bioRxiv · checked 15 Sept 2026
Abstract Globally, vegetation biodiversity is expected to decline as the rate of plant adaptation struggles to keep pace with rising temperatures. To support conservation efforts through remote sensing, we disentangled the nested effects of genetic and environmental influences on reflectance spectra, leveraging spectroscopy to assess plant adaptations to temperature. Specifically, we quantified the relative effect of plasticity and heritability on Populus fremontii (Fremont cottonwood) leaf reflectance using clonal replicates propagated from 16 populations and grown across three common gardens spanning a mean annual temperature gradient representing the thermal range of P. fremontii . We used variance partitioning to decompose phenotypic variation expressed in the leaf spectra into genotypic and environmental components to estimate broad-sense heritability. Heritability was strongly expressed in the spectral red edge (∼680-750nm) and shortwave infrared (∼1400-3000nm), though the heritability peak in the red edge was sensitive to extreme temperatures. By comparing distances of group centroids in principal component space, we determined that P. fremontii intraspecific spectral variation was shaped by the interaction between common garden site conditions and source population. Support vector machine models indicated pronounced environmental influence on spectral variation, as P. fremontii source population and garden location were classified at 71.8% and 92.6% accuracy, respectively. These findings emphasize the utility of reflectance data in separating genetic and environmental influences on plant phenotypes, offering a pathway to scale these insights across broader landscapes and aid in the conservation and management of vulnerable ecosystems in a warming climate.
Why it matches plant phenotyping methods葉の反射スペクトルを植物表現型として取得し、遺伝性・環境効果の分離、スペクトル変異の分類、温度適応評価に体系的に利用しており、単なる補助的な測定ではなく主要な解析基盤である。
abstractwe quantified the relative effect of plasticity and heritability on Populus fremontii (Fremont cottonwood) leaf reflectance
Reproduction assets foundThe paper's analysis code is explicitly stated to be publicly available on GitHub at the authors' repository (MegsSeeley/temperature_cottonwood). The phenotype/spectral data files are promised on Figshare only 'upon acceptance', so they are not yet publicly actionable and the Figshare DOI is not in the allowed URL listCode · publicAll authors reviewed
528 several drafts and agreed with the final version.
529 Availability of data: All data files will be made available on the Figshare database upon
530 acceptance of the manuscript at DOI: 10.6084/m9.figshare.25719585.
531 Code availability: Code is available on GitHub and is maintained by Seeley (2025)
532 https://github.com/MegsSeeley/temperature_cottonwood.
533 Conflict of interest: The authors have declared that no competing interests exist.
534
535 References
536 Ahmad, P., & Prasad, M. N. V. (2011). Environmental Adaptations and Stress Tolerance of
537 Plants in the Era of Climate Change. Springer Science & Business Media.
24Open asset ↗MegsSeeley/temperature_cottonwoodpdf-layout-page:24 lines:1-55Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Premise Automated disease, weed, and crop classification with computer vision will be invaluable in the future of agriculture. However, existing model architectures like ResNet, EfficientNet, and ConvNeXt often underperform on smaller, specialised datasets typical of such projects. Methods We address this gap with informed data collection and the development of a new convolutional neural network architecture, PhytNet. Utilising a novel dataset of infrared cocoa tree images, we demonstrate PhytNet's development and compare its performance with existing architectures. Data collection was informed by spectroscopy data, which provided useful insights into the spectral characteristics of cocoa trees. Cocoa was chosen as a focal species due to the diverse pathology of its diseases, which pose significant challenges for detection. Results ResNet18 showed some signs of overfitting, while EfficientNet variants showed distinct signs of overfitting. By contrast, PhytNet displayed excellent attention to relevant features, almost no overfitting, and an exceptionally low computation cost of 1.19 GFLOPS. Conclusions We show that PhytNet is a promising candidate for rapid disease or plant classification and for precise localisation of disease symptoms for autonomous systems. We also show that the most informative light spectra for detecting cocoa disease are outside the visible spectrum and that efforts to detect disease in cocoa should be focused on local symptoms, rather than the systemic effects of disease.
Why it matches plant phenotyping methods植物病害画像から症状を検出・局在化するCNNアーキテクチャPhytNetを開発し、既存モデルと比較検証しており、植物表現型取得・抽出法が中心である。
abstractthe development of a new convolutional neural network architecture, PhytNet
Reproduction assets foundThe paper's cocoa disease image/spectroscopy data are deposited on OSF (freely accessible via the provided link) and the PhytNet training/optimisation code is publicly available on GitHub. Both are paper-specific, public, and actionable.Code · publicThe code to optimise and train PhytNet for your data can be found at: https://Github.com/jrsykes/PhytNet .Open asset ↗Github · jrsykes/PhytNetlines:214-297Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
RiceThermalLeafStress / disease detectionStress response / tolerancePlant / canopy temperature
Diatraea saccharalis (Fabricius) is one of the main pests of rice crops and its early detection, that is, before the plants show damage, is essential to avoid yield losses and define effective and rational control. This work aimed to model the infrared-thermal responses of rice cultivars to D. saccharalis infestation levels. Between 2019 and 2020, two experiments were conducted in a protected environment with the cultivars IR 40 and BR IRGA 409, which presented, in a previous study, different resistance reactions. Rice plants grown in pots were manually infested with first-instar larvae of D. saccharalis, from 0 to 10 caterpillars/plant, with the plants kept in cages covered with voile fabric throughout the test. With the adjustment of regression models, it was noticed that the leaf surface temperature is related to the level of infestation and could be used to detect which IR 40 is susceptible.
Why it matches plant phenotyping methods赤外線サーモグラフィーでイネ葉面温度から害虫感染レベルと感受性を推定する方法が研究の中心であり、植物状態の取得・推定に該当する。
abstractThis work aimed to model the infrared-thermal responses of rice cultivars to D. saccharalis infestation levels.
Reproduction assets foundThe preprint's Data Availability Statement points to the authors' experimental dataset (leaf temperature, infestation, and resistance trait measurements) deposited in Harvard Dataverse under DOI 10.7910/DVN/Q1DRVV. This is a paper-specific, publicly accessible phenotype dataset. No author analysis code or trained modelDataset · publicn (AIC) and the root-mean-squared-error (RMSE) were used to choose and evaluate the
goodness-of-fit of models. The analyses were performed with the R software (www.r-project.org).
Data Availability Statement: The experimental data that support the results and findings of this study are
openly available in Harvard DataverseV1 at https://doi.org/10.7910/DVN/Q1DRVV.
References
1. Bortoli, S. A. D., Dória, H. O. S., Albergaria, N. M. M. S., & Botti, M. V. (2005). Biological aspects and damage
of Diatraea saccharalis (Lepidoptera: Pyralidae) in sorghum, under different doses of nitrogen and
potassium. Ciência e Agrotecnologia, 29(2), 267-273. https://doi.org/10.1590/S1413-70542005000200001Open asset ↗Harvard Dataverse · 10.7910/DVN/Q1DRVVpdf-layout-page:7 lines:1-60Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Early prediction of crop production by remote sensing (RS) may help to plan the harvest and ensure food security. This study aims to improve the quantification of yield, grain protein concentration (GPC), and nitrogen (N) output in winter wheat with RS imagery. Ground-truth wheat traits were measured at flowering and harvest in a field experiment combining four N and two water levels in central Spain over 2 years. Hyperspectral and thermal airborne images coincident with Sentinel-1 and Sentinel-2 were acquired at flowering. A parametric linear model using all hyperspectral normalized difference spectral indices (NDSI) and two non-parametric models (artificial neural network and random forest) were used to assess their estimation ability combining NDSIs and other RS indicators. The feasibility of using freely available multispectral satellite was tested by applying the same methodology but using Sentinel-1 and Sentinel-2 bands. Yield estimation obtained the highest R² value, showing that the visible and short-wave infrared region (VSWIR) had similar accuracy to the hyperspectral and Sentinel-2 imagery (R² ≈ 0.84). The SWIR bands were important in the GPC estimation with both sensors, whereas N output was better estimated using red-edge-based NDSIs, obtaining satisfactory results with the hyperspectral sensor (R² = 0.74) and with the Sentinel-2 (R² = 0.62). When including the Sentinel-2 SWIR index, the NDSI (B11, B3) improved the estimation of N output (R² = 0.71). Ensemble models based on Sentinel were found to be as reliable as those based on hyperspectral imagery, and including SWIR information improved the quantification of N-related traits.
Why it matches plant phenotyping methods航空ハイパースペクトル画像とSentinel画像、複数の推定モデルを用いて小麦の収量・タンパク質濃度・窒素出力を定量化し、センサー間の性能を比較しているため、表現型取得・推定法が研究の中心である。
abstractThis study aims to improve the quantification of yield, grain protein concentration (GPC), and nitrogen (N) output in winter wheat with RS imagery.
Reproduction assets foundThe paper's Data availability statement points to a public Figshare deposit (DOI 10.6084/m9.figshare.21865410.v1) containing the data supporting the study's winter wheat trait estimations from airborne hyperspectral and Sentinel imagery. This is a paper-specific, publicly accessible dataset with an authors' URL. No作者分析Dataset · publicatory work,
and QuantaLab-IAS-CSIC staff members A. Hornero, A. Vera, D. Notario, and R. Romero for airborne and
laboratory assistance.
Funding Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature.
Data availability The data that support the findings presented in this study are available online at https://doi.org/10.6084/m9.figshare.21865410.v1.Declarations
Conflict of interest The authors declare no conflict of interest.
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License,
which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long
as you give appropriate credit to the oOpen asset ↗figshare · 10.6084/m9.figshare.21865410.v1pdf-raw-page:20 lines:1-46Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
By means of a unique, low vibration circular conveyor system, plant sensors capturing light detection and ranging (LiDAR) unit and thermal camera were moved on the same route, around blocks of apple trees, with seven Malus x domestica Borkh. 'Gala' apple trees in each block. Measurements took place four times during the season. Additionally at harvest, diurnal courses were recorded with 18 readings during three days. The data are provided as [i] raw data (3D point clouds of 3 blocks of trees scanned from right and left sides and thermal images), [ii] processed 3D point clouds of canopies annotated with temperature data from the thermal camera, and [iii] manually segmented 3D point clouds of fruit, representing the spatially-resolved fruit surface temperature (FST). Manual FST readings are provided on each measuring date and during diurnal courses. The fruit data are capturing 1236 FST, providing temperature distribution as 3D point cloud and one manually recorded reference FST per fruit. Additionally, fruit size and colour were measured for each fruit, despite for the first date, when fruit were too small for colour readings. Weather data are provided from a station located in the orchard. Usage of data could be (a) in developing methodology for 3D point cloud processing based on raw data, accomplished with reference FST data. Furthermore, (b) the pre-processed point clouds of fruit surface temperature can be reused in ecophysiological studies related to global warming, optimizing fruit production systems, and other. Because the sensors and trees were measured from the same angle and distance, time series analysis of the canopies would be possible.
Why it matches plant phenotyping methodsLiDARと熱画像を統合し、果実表面温度を3D点群として取得・注釈化した再利用可能なデータセットであり、植物表現型取得手法とデータ提供が中心です。
abstractplant sensors capturing light detection and ranging (LiDAR) unit and thermal camera were moved on the same route, around blocks of apple trees
Reproduction assets foundThe paper is a Data in Brief article describing a public Zenodo deposit containing the paper's own phenotyping measurements: raw LiDAR point clouds, thermal images, temperature-annotated 3D point clouds of apple canopies, 1236 manually segmented fruit point clouds with FST reference readings, fruit size/colour data, anDataset · publicocation
The conveyor system is located 52.4673340479, 12.9606589643 in the experimental station of Leibniz Institute for Agricultural Engineering and Bioeconomy in Potsdam, Germany (ATB). Data repository is stored on Zenodo server [ 1 ]
Data accessibility
Repository name: Zenodo
Doi: https://doi.org/10.5281/zenodo.10792723
url: https://zenodo.org/records/10792723
Related research article
1
Value of the Data
•
The stationary conveyor system enabled repeated readings of apple tree canopies, with minimum vibration due to electric engine of the conveyor, and equal geometry between sensors and samples in all measurements. The value of 3D point clouds obtained with LiDAR sensor was enhanced bOpen asset ↗Zenodo · 10.5281/zenodo.10792723lines:46-71Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Canopy temperature (CT) is often interpreted as representing leaf activity traits such as photosynthetic rates, gas exchange rates, or stomatal conductance. This interpretation is based on the observation that leaf activity traits correlate with transpiration which affects leaf temperature. Accordingly, CT measurements may provide a basis for high throughput assessments of the productivity of wheat canopies during early grain filling, which would allow distinguishing functional from dysfunctional stay-green. However, whereas the usefulness of CT as a fast surrogate measure of sustained vigor under soil drying is well established, its potential to quantify leaf activity traits under high-yielding conditions is less clear. To better understand sensitivity limits of CT measurements under high yielding conditions, we generated within-genotype variability in stay-green functionality by means of differential short-term pre-anthesis canopy shading that modified the sink:source balance. We quantified the effects of these modifications on stay-green properties through a combination of gold standard physiological measurements of leaf activity and newly developed methods for organ-level senescence monitoring based on timeseries of high-resolution imagery and deep-learning-based semantic image segmentation. In parallel, we monitored CT by means of a pole-mounted thermal camera that delivered continuous, ultra-high temporal resolution CT data. Our results show that differences in stay-green functionality translate into measurable differences in CT in the absence of major confounding factors. Differences amounted to approximately 0.8°C and 1.5°C for a very high-yielding source-limited genotype, and a medium-yielding sink-limited genotype, respectively. The gradual nature of the effects of shading on CT during the stay-green phase underscore the importance of a high measurement frequency and a time-integrated analysis of CT, whilst modest effect sizes confirm the importance of restricting screenings to a limited range of morphological and phenological diversity.
Why it matches plant phenotyping methods高解像度画像・深層学習による器官レベル老化モニタリングと熱画像による連続的なキャノピー温度測定を開発・適用し、stay-green機能の表現型評価法として検証しているため、方法が中心的である。
abstractnewly developed methods for organ-level senescence monitoring based on timeseries of high-resolution imagery and deep-learning-based semantic image segmentation
Reproduction assets foundThe paper publicly deposits its manually annotated segmentation datasets (target-domain patches for the off-nadir stem/ear segmentation model) via the ETH Zurich research repository. All other raw phenotyping data (thermal images, physiological measurements) is only available on request from the authors. Generic tools/Dataset · publicd through logical operations to obtain the fractions of green, chlorotic, and necrotic tissues for each vegetation component. For details, refer to ( Anderegg et al., 2023 ). The annotated data sets representing the target domain will be made freely available via the Repository for Publications and Research data of ETH Zürich ( https://doi.org/10.3929/ethz-b-000668219 ).
Figure 2
Effects of canopy shading on agronomic traits and canopy characteristics. Effects of shading on (A) grain yield, (B) above ground vegetative dry biomass (total above ground biomass after threshing), (C) peduncle length, (D) plant height, (E) spike volume, (F) thousand kernel weight, (G) grain protein concentration.Open asset ↗Repository for Publications and Research data of ETH Zürich · 10.3929/ethz-b-000668219lines:58-67Code / dataset availability confirmedEurope PMC · checked 7 Sept 2026
Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.
Why it matches plant phenotyping methods植物のRGB・マルチ/ハイパースペクトル・熱・深度画像と植物形質ラベルを生成するシミュレーション基盤を開発しており、表現型取得・学習用データ生成が中心的な方法論的貢献である。
abstractwe proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation.
Reproduction assets foundThe paper's phenotyping analysis relies on three public, paper-specific assets: the Helios framework code (used to generate the synthetic annotated images), the MSU-PID bean image dataset, and the strawberry.00 annotated dataset, all with explicit open-availability statements and URLs.Dataset · publicThe Bean data that support the findings of this study are openly available in MSU-PID at https://www.cse.msu.edu/computervision/MVA15-MSU-PID.zipOpen asset ↗MSU-PIDlines:255-283Dataset · publicThe strawberry data that support the findings of this study are openly available in strawberry.00 at https://universe.roboflow.com/skripsie/strawberry.00Open asset ↗strawberry.00lines:255-283Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Three F2-derived biparental doubled haploid (DH) maize populations were generated for genetic mapping of resistance to common rust. Each of the three populations has the same susceptible parent, but a different resistance donor parent. Population 1 and 3 consist of 320 lines each, population 2 consists of 260 lines. The DH lines were evaluated for their susceptibility to common rust in two years and with two replications in each year. For phenotyping, a visual score (VS) for susceptibility was assigned. Additionally, unmanned aerial vehicle (UAV) derived multispectral and thermal infrared data was recorded and combined in different vegetation indices ("remote sensing", RS). The DH lines were genotyped with the DarTseq method, to obtain data on single nucleotide polymorphisms (SNPs). After quality control, 9051 markers remained. Missing values were "imputed" by the empirical mean of the marker scores of the respective locus. We used the data for comparison of genome-wide association studies and genomic prediction when based on different phenotyping methods, that is either VS or RS data. The data may be interesting for reuse for instance for benchmarking genomic prediction models, for phytopathological studies addressing common rust, or for specifications of vegetation indices.
Why it matches plant phenotyping methodsトウモロコシのさび病抵抗性を対象に、UAVマルチスペクトル・熱赤外データから植物状態を評価し、目視評価との比較や再利用可能なデータセットとして提示しており、表現型取得法が中心的です。
abstractFor phenotyping, a visual score (VS) for susceptibility was assigned. Additionally, unmanned aerial vehicle (UAV) derived multispectral and thermal infrared data was recorded and combined in different vegetation indices ("remote sensing", RS).
Reproduction assets foundThe paper deposits its own phenotype data (visual scores, UAV multispectral/thermal remote-sensing vegetation indices) and imputed SNP genotypes for three maize DH populations in the CIMMYT Research Data & Software Repository Network, with a direct public URL (hdl:11529/10548898). This is a paper-specific, publicly resDataset · publicData accessibility
Repository name: CIMMYT Research Data & Software Repository Network [2]
Data identification number: 10548898
Direct URL to data:Open asset ↗CIMMYT Research Data & Software Repository Networklines:1-57Dataset · public016/j.fcr.2024.109281.
2. Loladze A., Rodrigues F., Petroli C., Muñoz C., Macia Naranjo S., San Vicente F., Gerard B., Montesinos-López O.A., Crossa J., Martini J. CIMMYT Research Data & Software Repository Network, V1. 2023. Replication data for: use of remote sensing for genome-wide association studies and genomic prediction. https://hdl.handle.net/11529/10548898
Associated Data
Supplementary Materials
Image, application 1
Data Availability Statement
Replication Data for: Use of Remote Sensing for Genome-Wide Association Studies and Genomic Prediction (Original data) (Dataverse) [2] .Open asset ↗CIMMYT Research Data & Software Repository Networklines:219-242Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
CottonGreenhouseThermalLeafClassificationPhotosynthesis / fluorescenceStress response / toleranceWater status / transpiration
Introduction Drought detection, spanning from early stress to severe conditions, plays a crucial role in maintaining productivity, facilitating recovery, and preventing plant mortality. While handheld thermal cameras have been widely employed to track changes in leaf water content and stomatal conductance, research on thermal image classification remains limited due mainly to low resolution and blurry images produced by handheld cameras. Methods In this study, we introduce a computer vision pipeline to enhance the significance of leaf-level thermal images across 27 distinct cotton genotypes cultivated in a greenhouse under progressive drought conditions. Our approach involved employing a customized software pipeline to process raw thermal images, generating leaf masks, and extracting a range of statistically relevant thermal features (e.g., min and max temperature, median value, quartiles, etc.). These features were then utilized to develop machine learning algorithms capable of assessing leaf hydration status and distinguishing between well-watered (WW) and dry-down (DD) conditions. Results Two different classifiers were trained to predict the plant treatment-random forest and multilayer perceptron neural networks-finding 75% and 78% accuracy in the treatment prediction, respectively. Furthermore, we evaluated the predicted versus true labels based on classic physiological indicators of drought in plants, including volumetric soil water content, leaf water potential, and chlorophyll a fluorescence, to provide more insights and possible explanations about the classification outputs. Discussion Interestingly, mislabeled leaves mostly exhibited notable responses in fluorescence, water uptake from the soil, and/or leaf hydration status. Our findings emphasize the potential of AI-assisted thermal image analysis in enhancing the informative value of common heterogeneous datasets for drought detection. This application suggests widening the experimental settings to be used with deep learning models, designing future investigations into the genotypic variation in plant drought response and potential optimization of water management in agricultural settings.
Why it matches plant phenotyping methods葉の熱画像からマスクと熱特徴量を抽出し、機械学習で水分状態・乾燥処理を判定する画像解析パイプラインが中心であり、植物表現型の取得・推定手法に該当する。
abstractOur approach involved employing a customized software pipeline to process raw thermal images, generating leaf masks, and extracting a range of statistically relevant thermal features
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Dataset · publicSupplementary Table S3
Single measurements of volumetric soil water content across all collected images.Open asset ↗lines:440-465Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
CucumberPepper / chilliTomatoThermalLeafPhysiological trait estimationPlant / canopy temperature
Image-based high-throughput phenotyping promises the rapid determination of functional traits in large plant populations. However, interpretation of some traits - such as those related to photosynthesis or transpiration rates - is only meaningful if the irradiance absorbed by the measured leaves is known, which can differ greatly between different parts of the same plant and within canopies. No feasible method currently exists to rapidly measure absorbed irradiance in three-dimensional plants and canopies. We developed a method and protocols to derive absorbed irradiance at any visible part of a canopy with a thermal camera, by fitting a leaf energy balance model to transient changes in leaf temperature. Leaves were exposed to short light pulses (30 s) that were not long enough to trigger stomatal opening but strong enough to induce transient changes in leaf temperature that was proportional to the absorbed irradiance. The method was successfully validated against point measurements of absorbed irradiance in plant species with relatively simple architecture (sweet pepper, cucumber, tomato, and lettuce). Once calibrated, the model was used to produce absorbed irradiance maps from thermograms. Our method opens new avenues for the interpretation of plant responses derived from imaging techniques and can be adapted to existing high-throughput phenotyping platforms.
Why it matches plant phenotyping methods熱画像と葉エネルギーバランスモデルにより、植物キャノピー内の吸収光量を迅速に推定・可視化するフェノタイピング手法を開発し、点測定で検証しているため。
abstractWe developed a method and protocols to derive absorbed irradiance at any visible part of a canopy with a thermal camera, by fitting a leaf energy balance model to transient changes in leaf temperature.
Reproduction assets foundThe paper's authors explicitly state that all analysis code (R/STAN energy-balance fitting and Julia absorbed-irradiance mapping) is publicly available on their GitHub repository, which directly reproduces the paper's phenotyping computations. No separate phenotype dataset or image deposit is stated in the supplied.Code · publicData analysis
Calculations to solve Eqns 2 and 3 were run in R (R project,
v.4.2.0). The absorbed irradiance map was calculated in JULIA
(v.1.40.1; https://julialang.org/). All codes are available on
GitHub (https://github.com/jiayu0903/leaf-absorbed-irradiance.git). Statistical analysis was performed using a Student’s t-test for
paired samples to determine significant differences (P < 0.05)
between means.
Results
The temperature of sweet pepper (Fig. 2a), cucumber (Fig. S6a),
and tomato leaves (Fig. S7) showed a near-linear increase when
exposed to a brief 30 s period of irradiance fromOpen asset ↗https://github.com/jiayu0903/leaf-absorbed-irradiance.gitpdf-raw-page:7 lines:1-87Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 7 Sept 2026
BACKGROUND: Thermography is a popular tool to assess plant water-use behavior, as plant temperature is influenced by transpiration rate, and is commonly used in field experiments to detect plant water deficit. Its application in indoor automated phenotyping platforms is still limited and mainly focuses on differences in plant temperature between genotypes or treatments, instead of estimating stomatal conductance or transpiration rate. In this study, the transferability of commonly used thermography analysis protocols from the field to greenhouse phenotyping platforms was evaluated. In addition, the added value of combining thermal infrared (TIR) with hyperspectral imaging to monitor drought effects on plant transpiration rate (E) was evaluated. RESULTS: The sensitivity of commonly used TIR indices to detect drought-induced and genotypic differences in water status was investigated in eight maize inbred lines in the automated phenotyping platform PHENOVISION. Indices that normalized plant temperature for vapor pressure deficit and/or air temperature at the time of imaging were most sensitive to drought and could detect genotypic differences in the plants' water-use behavior. However, these indices were not strongly correlated to stomatal conductance and E. The canopy temperature depression index, the crop water stress index and the simplified stomatal conductance index were more suitable to monitor these traits, and were consequently used to develop empirical E prediction models by combining them with hyperspectral indices and/or environmental variables. Different modeling strategies were evaluated, including single index-based, machine learning and mechanistic models. Model comparison showed that combining multiple TIR indices in a random forest model can improve E prediction accuracy, and that the contribution of the hyperspectral data is limited when multiple indices are used. However, the empirical models trained on one genotype were not transferable to all eight inbred lines. CONCLUSION: Overall, this study demonstrates that existing TIR indices can be used to monitor drought stress and develop E prediction models in an indoor setup, as long as the indices normalize plant temperature for ambient air temperature or relative humidity.
Why it matches plant phenotyping methods屋内自動植物フェノタイピング環境で、熱画像・ハイパースペクトル画像による干ばつストレス、水利用、蒸散速度の推定手法を評価・モデル比較しており、フェノタイピング手法が中心である。
abstractthe transferability of commonly used thermography analysis protocols from the field to greenhouse phenotyping platforms was evaluated
Reproduction assets foundThe article's Availability of data and materials statement deposits the datasets generated and analyzed in this study (thermal/hyperspectral phenotyping data and analyses) in three Zenodo repositories with public DOIs. These are paper-specific, publicly accessible assets. No author analysis code with an explicit publicDataset · publicThe datasets generated and analyzed during the current study are available in the zenodo repository ( https://doi.org/10.5281/zenodo.7807989 , https://doi.org/10.5281/zenodo.8164473 , https://doi.org/10.5281/zenodo.8033640 ).Open asset ↗zenodo · 10.5281/zenodo.7807989lines:198-347Dataset · publicThe datasets generated and analyzed during the current study are available in the zenodo repository ( https://doi.org/10.5281/zenodo.7807989 , https://doi.org/10.5281/zenodo.8164473 , https://doi.org/10.5281/zenodo.8033640 ).Open asset ↗zenodo · 10.5281/zenodo.8164473lines:198-347Dataset · publicThe datasets generated and analyzed during the current study are available in the zenodo repository ( https://doi.org/10.5281/zenodo.7807989 , https://doi.org/10.5281/zenodo.8164473 , https://doi.org/10.5281/zenodo.8033640 ).Open asset ↗zenodo · 10.5281/zenodo.8033640lines:198-347Code / dataset availability confirmedOpenAlex · bioRxiv · Europe PMC · Crossref · checked 15 Sept 2026
Abstract Background Thermography is a popular tool to assess plant water use behavior, as plant temperature is influenced by transpiration rate, and is commonly used in field experiments to detect drought stress. Its application in indoor automated phenotyping platforms is still limited and mainly focuses on differences in plant temperature between genotypes or treatments, instead of estimating stomatal conductance or transpiration rate. In this study, the transferability of commonly used thermography analysis protocols from the field to greenhouse phenotyping platforms was evaluated. In addition, the added value of combining thermal infrared (TIR) with hyperspectral imaging to monitor drought effects on plant transpiration rate (E) was evaluated. Results The sensitivity of commonly used TIR indices to detect drought-induced and genotypic differences in water status was investigated in eight maize inbred lines in the automated phenotyping platform PHENOVISION. Indices that normalized plant temperature for vapor pressure deficit and/or air temperature at the time of imaging were most sensitive to drought and could detect genotypic difference in the plants’ water use behavior. However, these indices were not strongly correlated to stomatal conductance and E. The canopy temperature depression index, the crop water stress index and the simplified stomatal conductance index were more suitable to monitor these traits, and were consequently used to develop empirical E prediction models by combining them with hyperspectral indices and/or environmental variables. Different modeling strategies were evaluated including single index-based, machine learning and mechanistic models. Model comparison showed that combining multiple thermal infrared indices in a random forest model can improve E prediction accuracy, and that the contribution of the hyperspectral data is limited when multiple indices are used. However, the empirical models trained on one genotype were not transferable to all eight inbred lines. Conclusion Overall, this study demonstrates that existing TIR indices can be used to monitor drought stress and develop E prediction models in an indoor setup, as long as the indices normalize plant temperature for ambient air temperature or relative humidity.
Why it matches plant phenotyping methods屋内自動植物フェノタイピング基盤で、熱画像・ハイパースペクトル画像から乾燥ストレス、蒸散速度、気孔コンダクタンスを推定する手法の評価・モデル開発が中心である。
abstractthe transferability of commonly used thermography analysis protocols from the field to greenhouse phenotyping platforms was evaluated
Reproduction assets foundThe paper's declarations state that the datasets generated and analyzed during the study (thermal/hyperspectral imaging, environmental, and transpiration data from the maize drought phenotyping experiment) are publicly available in three Zenodo deposits with explicit DOIs. These are paper-specific, public, and directlyDataset · publicyield of photosystem II
ψ water potential
744
Declarations
745
Ethics approval and consent to participate
746
Not applicable.
747
748
Consent for publication
749
Not applicable.
750
751
Availability of data and materials
752
The datasets generated and analyzed during the current study are available in the zenodo repository
753
(https://doi.org/10.5281/zenodo.7807989, https://doi.org/10.5281/zenodo.8164473,
754
https://doi.org/10.5281/zenodo.8033640)
755
756
Competing interests
757
The authors declare that this study received funding from BASF. The funder had the following
758
involvement in the study: collaboratively conceived the original screening and research plans. J.V.,
759
and W.B. wOpen asset ↗zenodo · 10.5281/zenodo.7807989pdf-raw-page:30 lines:1-62Dataset · publicl
744
Declarations
745
Ethics approval and consent to participate
746
Not applicable.
747
748
Consent for publication
749
Not applicable.
750
751
Availability of data and materials
752
The datasets generated and analyzed during the current study are available in the zenodo repository
753
(https://doi.org/10.5281/zenodo.7807989, https://doi.org/10.5281/zenodo.8164473,
754
https://doi.org/10.5281/zenodo.8033640)
755
756
Competing interests
757
The authors declare that this study received funding from BASF. The funder had the following
758
involvement in the study: collaboratively conceived the original screening and research plans. J.V.,
759
and W.B. were employed by BASF Corporation, USA.
7Open asset ↗zenodo · 10.5281/zenodo.8164473pdf-raw-page:30 lines:1-62Dataset · publiconsent to participate
746
Not applicable.
747
748
Consent for publication
749
Not applicable.
750
751
Availability of data and materials
752
The datasets generated and analyzed during the current study are available in the zenodo repository
753
(https://doi.org/10.5281/zenodo.7807989, https://doi.org/10.5281/zenodo.8164473,
754
https://doi.org/10.5281/zenodo.8033640)
755
756
Competing interests
757
The authors declare that this study received funding from BASF. The funder had the following
758
involvement in the study: collaboratively conceived the original screening and research plans. J.V.,
759
and W.B. were employed by BASF Corporation, USA.
760
761
Funding
762
This work was supported bOpen asset ↗zenodo · 10.5281/zenodo.8033640pdf-raw-page:30 lines:1-62Code / dataset availability confirmedEurope PMC · Crossref · checked 14 Sept 2026
Background The current development of sensor technologies towards ever more cost-effective and powerful systems is steadily increasing the application of low-cost sensors in different horticultural sectors. In plant in vitro culture, as a fundamental technique for plant breeding and plant propagation, the majority of evaluation methods to describe the performance of these cultures are based on destructive approaches, limiting data to unique endpoint measurements. Therefore, a non-destructive phenotyping system capable of automated, continuous and objective quantification of in vitro plant traits is desirable. Results An automated low-cost multi-sensor system acquiring phenotypic data of plant in vitro cultures was developed and evaluated. Unique hardware and software components were selected to construct a xyz-scanning system with an adequate accuracy for consistent data acquisition. Relevant plant growth predictors, such as projected area of explants and average canopy height were determined employing multi-sensory imaging and various developmental processes could be monitored and documented. The validation of the RGB image segmentation pipeline using a random forest classifier revealed very strong correlation with manual pixel annotation. Depth imaging by a laser distance sensor of plant in vitro cultures enabled the description of the dynamic behavior of the average canopy height, the maximum plant height, but also the culture media height and volume. Projected plant area in depth data by RANSAC (random sample consensus) segmentation approach well matched the projected plant area by RGB image processing pipeline. In addition, a successful proof of concept for in situ spectral fluorescence monitoring was achieved and challenges of thermal imaging were documented. Potential use cases for the digital quantification of key performance parameters in research and commercial application are discussed. Conclusion The technical realization of "Phenomenon" allows phenotyping of plant in vitro cultures under highly challenging conditions and enables multi-sensory monitoring through closed vessels, ensuring the aseptic status of the cultures. Automated sensor application in plant tissue culture promises great potential for a non-destructive growth analysis enhancing commercial propagation as well as enabling research with novel digital parameters recorded over time.
Why it matches plant phenotyping methods植物組織培養の形質を自動・非破壊・連続測定するマルチセンサーフェノタイピングシステムを開発し、画像分割や深度計測を検証しており、方法が研究の中心である。
abstractAn automated low-cost multi-sensor system acquiring phenotypic data of plant in vitro cultures was developed and evaluated.
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 · publicThe dataset supporting the conclusions of this article (Hard- and Software of “Phenomenon” phenotyping system) are available in an open-access Github repository, https://github.com/halube/Phenomenon .Open asset ↗halube/Phenomenonlines:224-282Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Cultivation of wild rocket [ Diplotaxis tenuifolia (L.) D.C.] as a baby-leaf vegetable for the high-convenience food chain is constantly growing due to its nutritional and taste qualities. As is well known, these crops are particularly exposed to soil-borne fungal diseases and need to be effectively protected. At present, wild rocket disease management is performed by using permitted synthetic fungicides or through the application of agro-ecological and biological methods that must be optimized. In this regard, the implementation of innovative digital-based technologies, such as infrared thermography (IT), as supporting systems to decision-making processes is welcome. In this work, leaves belonging to wild rocket plants inoculated with the soil-borne pathogens Rhizoctonia solani Kühn and Sclerotinia sclerotiorum (Lib.) de Bary were analyzed and monitored by both active and passive thermographic methods and compared with visual detection. A comparison between the thermal analysis carried out in both medium (MWIR)- and long (LWIR)-wave infrared was made and discussed. The results achieved highlight how the monitoring based on the use of IT is promising for carrying out an early detection of the rot diseases induced by the investigated pathogens, allowing their detection in 3-6 days before the canopy is completely wilted. Active thermal imaging has the potential to detect early soil-borne rotting diseases.
Why it matches plant phenotyping methods野生ルッコラの感染植物を対象に、能動・受動熱画像法を比較し、熱画像による病害症状の早期検出性能を評価しており、植物状態の取得手法が中心である。
abstractleaves belonging to wild rocket plants inoculated with the soil-borne pathogens Rhizoctonia solani Kühn and Sclerotinia sclerotiorum (Lib.) de Bary were analyzed and monitored by both active and passive thermographic methods and compared with visual detection.
Reproduction assets foundThe paper's supplementary materials (hosted publicly by MDPI) contain the paper-specific thermographic images of inoculated vs. control wild rocket leaves (Figures S1–S5) and the Right Prevision (RP%) calculation underlying the AT analysis. No separate phenotype dataset deposit or author analysis code repository is披露; Supplement · public–6 days before they are detectable by visual analysis. Our results confirm the potential of these techniques in monitoring wild rocket for the preventive detection of soil diseases with the aim of avoiding their extension and preserving the crops.
Supplementary Materials
The following supporting information can be downloaded at https://www.mdpi.com/article/10.3390/plants12081615/s1 , Figure S1: Examples of active thermography analysis for uninoculated control leaves of rocket plants; Figures S2–S5: Examples of active thermography analysis for leaves of rocket plants inoculated with treatments T1, T2, T3, and T4. Right Prevision (RP%) calculation.
Click here for additional data file.
Author COpen asset ↗lines:153-168Code / dataset availability confirmedOpenAlex · Europe PMC · checked 14 Sept 2026
Advanced plant phenotyping techniques to measure biophysical traits of crops are helping to deliver improved crop varieties faster. Phenotyping of plants using different sensors for image acquisition and its analysis with novel computational algorithms are increasingly being adapted to measure plant traits. Thermal and multispectral imagery provides novel opportunities to reliably phenotype crop genotypes tested for biotic and abiotic stresses under glasshouse conditions. However, optimization for image acquisition, pre-processing, and analysis is required to correct for optical distortion, image co-registration, radiometric rescaling, and illumination correction. This study provides a computational pipeline that optimizes these issues and synchronizes image acquisition from thermal and multispectral sensors. The image processing pipeline provides a processed stacked image comprising RGB, green, red, NIR, red edge, and thermal, containing only the pixels present in the object of interest, e.g., plant canopy. These multimodal outputs in thermal and multispectral imageries of the plants can be compared and analysed mutually to provide complementary insights and develop vegetative indices effectively. This study offers digital platform and analytics to monitor early symptoms of biotic and abiotic stresses and to screen a large number of genotypes for improved growth and productivity. The pipeline is packaged as open source and is hosted online so that it can be utilized by researchers working with similar sensors for crop phenotyping.
Why it matches plant phenotyping methods植物の熱画像・マルチスペクトル画像を用いた表現型取得と解析のためのオープンソース計算パイプラインを開発しており、画像補正・共登録・解析が中心的な方法論的貢献である。
abstractThis study provides a computational pipeline that optimizes these issues and synchronizes image acquisition from thermal and multispectral sensors.
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。Code · publicAll codes were written in MATLAB to produce a library package which is available at https://github.com/SmartSense-iHub/Thermal-and-Multispectral-Image-Analysis-Processing-Pipeline.git (accessed on 12 November 2022).Open asset ↗SmartSense-iHub/Thermal-and-Multispectral-Image-Analysis-Processing-Pipelinelines:35-43Dataset · publicThe data is freely shared in google drive and can be accessed from the following link. https://drive.google.com/file/d/1VSqRu5CUZhyd3MF23kdRjqrtRke7sbJU/view?usp=share_link .Open asset ↗lines:91-241Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Agricultural industry is facing a serious threat from plant diseases that cause production and economic losses. Early information on disease development can improve disease control using suitable management strategies. This study sought to detect downy mildew ( Peronospora ) on grapevine ( Vitis vinifera ) leaves at early stages of development using thermal imaging technology and to determine the best time during the day for image acquisition. In controlled experiments, 1587 thermal images of grapevines grown in a greenhouse were acquired around midday, before inoculation, 1, 2, 4, 5, 6, and 7 days after an inoculation. In addition, images of healthy and infected leaves were acquired at seven different times during the day between 7:00 a.m. and 4:30 p.m. Leaves were segmented using the active contour algorithm. Twelve features were derived from the leaf mask and from meteorological measurements. Stepwise logistic regression revealed five significant features used in five classification models. Performance was evaluated using K-folds cross-validation. The support vector machine model produced the best classification accuracy of 81.6%, F1 score of 77.5% and area under the curve (AUC) of 0.874. Acquiring images in the morning between 10:40 a.m. and 11:30 a.m. resulted in 80.7% accuracy, 80.5% F1 score, and 0.895 AUC.
Why it matches plant phenotyping methods熱画像と画像解析・分類モデルを用いてブドウ葉の病害状態を早期推定する手法を開発・評価しており、植物病害表現型の取得が中心です。
abstractThis study sought to detect downy mildew ( Peronospora ) on grapevine ( Vitis vinifera ) leaves at early stages of development using thermal imaging technology
Reproduction assets foundThe paper's Data Availability Statement explicitly deposits the authors' phenotyping datasets (thermal-image-derived leaf temperature features, meteorological measurements, and disease severity labels) as Excel files in two public GitHub repositories, both listed in allowed_urls. These directly reproduce the paper's 1,Dataset · publicThe datasets generated and analyzed during the current study are available in GitHub: Data sets (Excel): https://github.com/BarCohenBGU/database.git (29 September 2021). ‘All data new’—the classification dataset included 1403 records.Open asset ↗BarCohenBGU/databaselines:635-637Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Improved accuracy of evapotranspiration (ET) estimation, including its partitioning between transpiration (T) and surface evaporation (E), is key to monitor agricultural water use in vineyards, especially to enhance water use efficiency in semi-arid regions such as California, USA. Remote-sensing methods have shown great utility in retrieving ET from surface energy balance models based on thermal infrared data. Notably, the two-source energy balance (TSEB) has been widely and robustly applied in numerous landscapes, including vineyards. However, vineyards add an additional complexity where the landscape is essentially made up of two distinct zones: the grapevine and the interrow, which is often seasonally covered by an herbaceous cover crop. Therefore, it becomes more complex to disentangle the various contributions of the different vegetation elements to total ET, especially through TSEB, which assumes a single vegetation source over a soil layer. As such, a remote-sensing-based three-source energy balance (3SEB) model, which essentially adds a vegetation source to TSEB, was applied in an experimental vineyard located in California's Central Valley to investigate whether it improves the depiction of the grapevine-interrow system. The model was applied in four different blocks in 2019 and 2020, where each block had an eddy-covariance (EC) tower collecting continuous flux, radiometric, and meteorological measurements. 3SEB's latent and sensible heat flux retrievals were accurate with an overall RMSD ~ 50 W/m 2 compared to EC measurements. 3SEB improved upon TSEB simulations, with the largest differences being concentrated in the spring season, when there is greater mixing between grapevine foliage and the cover crop. Additionally, 3SEB's modeled ET partitioning (T/ET) compared well against an EC T/ET retrieval method, being only slightly underestimated. Overall, these promising results indicate 3SEB can be of great utility to vineyard irrigation management, especially to improve T/ET estimations and to quantify the contribution of the cover crop to ET. Improved knowledge of T/ET can enhance grapevine water stress detection to support irrigation and water resource management. Supplementary information The online version contains supplementary material available at 10.1007/s00271-022-00787-x.
Why it matches plant phenotyping methodsリモートセンシングによる3SEBモデルを用いてブドウ樹・被覆作物の蒸発散分離を推定し、渦相関測定および既存モデルと比較検証している。水利用管理への応用を含むが、植物の生理状態推定手法の技術評価が中心である。
abstracta remote-sensing-based three-source energy balance (3SEB) model, which essentially adds a vegetation source to TSEB, was applied in an experimental vineyard located in California's Central Valley to investigate whether it improves the depiction of the grapevine-interrow system.
Reproduction assets foundThe paper applies the authors' 3SEB model to vineyard ET partitioning and explicitly points to the authors' public GitHub repository as the model source code. No public phenotype/trait datasets or trained models are deposited; the GRAPEX flux/radiometric data are described but no public URL is given.Code · publicRefer to Burchard-Levine et al. ( 2022 ) or the source code ( https://github.com/VicenteBurchard/3SEB ) for model details and specifications.Open asset ↗VicenteBurchard/3SEBlines:112-122Code / dataset availability confirmedEurope PMC · checked 8 Sept 2026
Unmanned aerial vehicles (UAVs) equipped with multispectral sensors offer high spatial and temporal resolution imagery for monitoring crop stress at early stages of development. Analysis of UAV-derived data with advanced machine learning models could improve real-time management in agricultural systems, but guidance for this integration is currently limited. Here we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas. Both deep learning strategies showed improvements upon traditional statistical learning approaches including linear regression and gradient boosted decision trees. First, we explicitly accounted for variation across developmental stages using a 3D convolutional neural network (CNN) architecture that captures both spatial and temporal dimensions of UAV images from multiple time points throughout one growing season. 3D-CNNs achieved low prediction error on the test set, with a Root Mean Squared Error (RMSE) of 8.8% of the mean yield. For the second strategy, a 2D-CNN, we considered only spatial relationships among pixels for image features acquired during a single flyover. 2D-CNNs trained on images from a single day were most accurate when images were taken during booting stage or later, with RMSE ranging from 7.4 to 8.2% of the mean yield. A primary benefit of convolutional autoencoder-like models (based on analyses of prediction maps and feature importance) is the spatial denoising effect that corrects yield predictions for individual pixels based on the values of vegetation index and thermal features for nearby pixels. Our results highlight the promise of convolutional autoencoders for UAV-based yield prediction in rice.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像からイネの収量を推定する深層学習ワークフローを比較・評価しており、植物形質の取得・推定手法が研究の中心である。
abstractHere we compare two deep learning-based strategies for early warning detection of crop stress, using multitemporal imagery throughout the growing season to predict field-scale yield in irrigated rice in eastern Arkansas.
Reproduction assets foundThe paper's authors explicitly state that the Python and R code used to process the UAV imagery data, train and evaluate the CNN models, and recreate Figures 2–5 is publicly available on GitHub. No separate public phenotype dataset or trained model checkpoint deposit is stated in the supplied blocks; other URLs are forCode · publicPython and R code used to process data, train and evaluate models, and recreate Figures 2 – 5 , is available at https://github.com/em-bellis/XASU_rice .Open asset ↗em-bellis/XASU_ricelines:521-535Code / dataset availability confirmedOpenAlex · Europe PMC · checked 8 Sept 2026
Tree architecture shows large genotypic variability, but how this affects water-deficit responses is poorly understood. To assess the possibility of reaching ideotypes with adequate combinations of architectural and functional traits in the face of climate change, we combined high-throughput field phenotyping and genome-wide association studies (GWAS) on an apple tree (Malus domestica) core-collection. We used terrestrial light detection and ranging (T-LiDAR) scanning and airborne multispectral and thermal imagery to monitor tree architecture, canopy shape, light interception, vegetation indices and transpiration on 241 apple cultivars submitted to progressive field soil drying. GWAS was performed with single nucleotide polymorphism (SNP)-by-SNP and multi-SNP methods. Large phenotypic and genetic variability was observed for all traits examined within the collection, especially canopy surface temperature in both well-watered and water deficit conditions, suggesting control of water loss was largely genotype-dependent. Robust genomic associations revealed independent genetic control for the architectural and functional traits. Screening associated genomic regions revealed candidate genes involved in relevant pathways for each trait. We show that multiple allelic combinations exist for all studied traits within this collection. This opens promising avenues to jointly optimize tree architecture, light interception and water use in breeding strategies. Genotypes carrying favourable alleles depending on environmental scenarios and production objectives could thus be targeted.
Why it matches plant phenotyping methods高スループット圃場フェノタイピングを中核として、T-LiDAR、マルチスペクトル・熱画像から樹体構造、光 interception、蒸散などの植物形質を測定しているため。
abstractwe combined high-throughput field phenotyping and genome-wide association studies (GWAS) on an apple tree (Malus domestica) core-collection.
Reproduction assets foundThe paper's raw phenotypes and BLUPs (T-LiDAR architectural traits, thermal/multispectral indices, water potentials) are publicly deposited on Portail Data INRAE at https://doi.org/10.15454/C8IPII, explicitly stated in the Data availability section. The SNP genotyping deposit (10.15454/F5XIVJ) is a molecular omics-typeDataset · publicRaw data and BLUPs of phenotypes together with the list of the 241 cultivars with the recently attributed MUNQ codes (for Malus UNiQue genotype code, Denancé et al ., 2020 ) are publicly available in Coupel‐Ledru et al . ( 2022 ) at this site: https://doi.org/10.15454/C8IPIIOpen asset ↗10.15454/C8IPIIlines:663-812Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
Plant pathogens pose increasing threats to global food security, causing yield losses that exceed 30% in food-deficit regions. Xylella fastidiosa (Xf) represents the major transboundary plant pest and one of the world's most damaging pathogens in terms of socioeconomic impact. Spectral screening methods are critical to detect non-visual symptoms of early infection and prevent spread. However, the subtle pathogen-induced physiological alterations that are spectrally detectable are entangled with the dynamics of abiotic stresses. Here, using airborne spectroscopy and thermal scanning of areas covering more than one million trees of different species, infections and water stress levels, we reveal the existence of divergent pathogen- and host-specific spectral pathways that can disentangle biotic-induced symptoms. We demonstrate that uncoupling this biotic-abiotic spectral dynamics diminishes the uncertainty in the Xf detection to below 6% across different hosts. Assessing these deviating pathways against another harmful vascular pathogen that produces analogous symptoms, Verticillium dahliae, the divergent routes remained pathogen- and host-specific, revealing detection accuracies exceeding 92% across pathosystems. These urgently needed hyperspectral methods advance early detection of devastating pathogens to reduce the billions in crop losses worldwide.
Why it matches plant phenotyping methods航空分光法と熱スキャンを用いて植物病原体感染を非視覚的な生理・スペクトル形質として検出し、複数病原体・宿主で精度を検証しており、表現型取得手法が研究の中心である。
abstractSpectral screening methods are critical to detect non-visual symptoms of early infection and prevent spread.
Reproduction assets foundThe paper's data availability and code availability statements point to a public GitHub repository (HyperSens/HyperSens-Divergent-spectral-responses-Nature-Communications) with a Zenodo DOI (10.5281/zenodo.5535095) containing the study's spectral trait datasets and analysis code. The large airborne hyperspectral imagecDataset · publicThe data used in this study 74 are available at the repository https://github.com/HyperSens/HyperSens-Divergent-spectral-responses-Nature-Communications and can be cited as https://doi.org/10.5281/zenodo.5535095Open asset ↗HyperSens/HyperSens-Divergent-spectral-responses-Nature-Communications · 10.5281/zenodo.5535095lines:133-192Code · publicThe codes used for this study 74 are available at the repository https://github.com/HyperSens/HyperSens-Divergent-spectral-responses-Nature-Communications and can be cited as https://doi.org/10.5281/zenodo.5535095Open asset ↗HyperSens/HyperSens-Divergent-spectral-responses-Nature-Communications · 10.5281/zenodo.5535095lines:133-192Code / dataset availability confirmedEurope PMC · checked 9 Sept 2026
A primary selection target for wheat ( Triticum aestivum ) improvement is grain yield. However, the selection for yield is limited by the extent of field trials, fluctuating environments, and the time needed to obtain multiyear assessments. Secondary traits such as spectral reflectance and canopy temperature (CT), which can be rapidly measured many times throughout the growing season, are frequently correlated with grain yield and could be used for indirect selection in large populations particularly in earlier generations in the breeding cycle prior to replicated yield testing. While proximal sensing data collection is increasingly implemented with high-throughput platforms that provide powerful and affordable information, efficient and effective use of these data is challenging. The objective of this study was to monitor wheat growth and predict grain yield in wheat breeding trials using high-density proximal sensing measurements under extreme terminal heat stress that is common in Bangladesh. Over five growing seasons, we analyzed normalized difference vegetation index (NDVI) and CT measurements collected in elite breeding lines from the International Maize and Wheat Improvement Center at the Regional Agricultural Research Station, Jamalpur, Bangladesh. We explored several variable reduction and regularization techniques followed by using the combined secondary traits to predict grain yield. Across years, grain yield heritability ranged from 0.30 to 0.72, with variable secondary trait heritability (0.0-0.6), while the correlation between grain yield and secondary traits ranged from -0.5 to 0.5. The prediction accuracy was calculated by a cross-fold validation approach as the correlation between observed and predicted grain yield using univariate and multivariate models. We found that the multivariate models resulted in higher prediction accuracies for grain yield than the univariate models. Stepwise regression performed equal to, or better than, other models in predicting grain yield. When incorporating all secondary traits into the models, we obtained high prediction accuracies (0.58-0.68) across the five growing seasons. Our results show that the optimized phenotypic prediction models can leverage secondary traits to deliver accurate predictions of wheat grain yield, allowing breeding programs to make more robust and rapid selections.
Why it matches plant phenotyping methods小麦育種試験で近接センシングによりNDVI・群落温度を取得し、統計モデルで収量を予測するワークフローを5年間検証しており、形質取得と予測手法が研究の中心である。
abstractThe objective of this study was to monitor wheat growth and predict grain yield in wheat breeding trials using high-density proximal sensing measurements under extreme terminal heat stress that is common in Bangladesh.
Reproduction assets foundThe paper's data availability statement explicitly deposits all phenotypic data (NDVI, CT, agronomic traits) and analysis code in the Dryad Digital Repository with a public DOI, making it a paper-specific, publicly actionable asset.Dataset · publicAll phenotypic data and code for analysis have been placed in the Dryad Digital Repository available at: https://doi.org/10.5061/dryad.vdncjsxrz .Open asset ↗Dryad Digital Repository · 10.5061/dryad.vdncjsxrzlines:724-739Code / dataset availability confirmedarXiv · checked 15 Sept 2026
Field / plotRGB / grayscaleMultispectral / hyperspectralThermalWhole plant / canopy / plot / field
A core objective of the TERRA-REF project was to generate an open-access reference dataset for the evaluation of sensing technologies to study plants under field conditions. The TERRA-REF program deployed a suite of high-resolution, cutting edge technology sensors on a gantry system with the aim of scanning 1 hectare (10$^4$) at around 1 mm$^2$ spatial resolution multiple times per week. The system contains co-located sensors including a stereo-pair RGB camera, a thermal imager, a laser scanner to capture 3D structure, and two hyperspectral cameras covering wavelengths of 300-2500nm. This sensor data is provided alongside over sixty types of traditional plant phenotype measurements that can be used to train new machine learning models. Associated weather and environmental measurements, information about agronomic management and experimental design, and the genomic sequences of hundreds of plant varieties have been collected and are available alongside the sensor and plant phenotype data. Over the course of four years and ten growing seasons, the TERRA-REF system generated over 1 PB of sensor data and almost 45 million files. The subset that has been released to the public domain accounts for two seasons and about half of the total data volume. This provides an unprecedented opportunity for investigations far beyond the core biological scope of the project. The focus of this paper is to provide the Computer Vision and Machine Learning communities an overview of the available data and some potential applications of this one of a kind data.
Why it matches plant phenotyping methods植物の高解像度マルチセンサーデータと植物表現型データを含む公開ベンチマーク／データセットを紹介し、コンピュータビジョンでの利用を主目的とするため、フェノタイピング手法・基盤として中心的です。
abstractgenerate an open-access reference dataset for the evaluation of sensing technologies to study plants under field conditions
Reproduction assets foundThe paper describes the TERRA-REF public domain release of plant phenotyping sensor data (RGB, thermal, laser scanner, hyperspectral, PSII) plus derived phenotypes, and explicitly points to public code repositories for the processing pipeline (terraref GitHub, PhytoOracle, AgPipeline) and a data access portal. All are,Dataset · publicprocessing, reviewing, curating, describing, and hosting the data.
Instead, we focused on an initial public release and plan to make new datasets available based on need.
Access to unpublished data can be requested from the authors, and as data are curated they will be added to subsequent versions of the public domain release ( https://terraref.org/data/access-data ).
In addition to hosting an archival copy of data on Dryad [ 16 ] , the
documentation includes instructions for browsing and accessing these
data through a variety of online portals. These portals provide access
to web user interfaces as well as databases, APIs, and R and Python
clients. In some cases it will be easier to acceOpen asset ↗lines:234-317Code · publicapproach described by Li et al . [ 18 ] .
Herritt et al . [ 14 , 13 ] demonstrate and provide software used in analysis of a sequence of images that capture plant fluorescence response to a pulse of light.
Most of the algorithms used to generate data products have not been published as papers but are made available on GitHub ( https://github.com/terraref ); code
used to release the data publication in 2020 is available on Zenodo [ 25 , 15 , 10 , 6 , 4 , 19 , 8 , 7 , 5 , 9 , 17 ] .
Pipeline development continues to support ongoing use of the field scanner as well as more general applications in plant sensing pipelines.
Recent advances have improved pipeline scalability and modulOpen asset ↗terrareflines:193-233Code · publiclant sensing pipelines.
Recent advances have improved pipeline scalability and modularity by adopting workflow tools and making use of heterogeneous computing environments.
The TERRA-REF computing pipeline has been adapted and extended for continuing use with the Field Scanner with the new name ”PhytoOracle” and is available at https://github.com/LyonsLab/PhytoOracle . Related work generalizing the pipeline for other phenomics applications has been released under the name ”AgPipeline” https://github.com/agpipeline with applications to aerial imaging described by Schnaufer et al . [ 22 ] .
All of these software are made available with permissive open source licenses on GitHub to enable accesOpen asset ↗PhytoOraclelines:193-233Code · publicnvironments.
The TERRA-REF computing pipeline has been adapted and extended for continuing use with the Field Scanner with the new name ”PhytoOracle” and is available at https://github.com/LyonsLab/PhytoOracle . Related work generalizing the pipeline for other phenomics applications has been released under the name ”AgPipeline” https://github.com/agpipeline with applications to aerial imaging described by Schnaufer et al . [ 22 ] .
All of these software are made available with permissive open source licenses on GitHub to enable access and community development.
Figure 4: Summary of public sensor datasets from Seasons 4 and 6. Each dot represents the dates for which a particular daOpen asset ↗agpipelinelines:193-233Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 8 Sept 2026
One of the objectives of many studies conducted by breeding programs is to characterize and select rootstocks well-adapted to drought conditions. In recent years, field high-throughput phenotyping methods have been developed to characterize plant traits and to identify the most water use efficient varieties and rootstocks. However, none of these studies have been able to quantify the behavior of crop evapotranspiration in almond rootstocks under different water regimes. In this study, remote sensing phenotyping methods were used to assess the evapotranspiration of almond cv. “Marinada” grafted onto a rootstock collection. In particular, the two-source energy balance and Shuttleworth and Wallace models were used to, respectively, estimate the actual and potential evapotranspiration of almonds grafted onto 10 rootstock under three different irrigation treatments. For this purpose, three flights were conducted during the 2018 and 2019 growing seasons with an aircraft equipped with a thermal and multispectral camera. Stem water potential (Ψstem) was also measured concomitant to image acquisition. Biophysical traits of the vegetation were firstly assessed through photogrammetry techniques, spectral vegetation indices and the radiative transfer model PROSAIL. The estimates of canopy height, leaf area index and daily fraction of intercepted radiation had root mean square errors of 0.57 m, 0.24 m m–1 and 0.07%, respectively. Findings of this study showed significant differences between rootstocks in all of the evaluated parameters. Cadaman® and Garnem® had the highest canopy vigor traits, evapotranspiration, Ψstem and kernel yield. In contrast, Rootpac® 20 and Rootpac® R had the lowest values of the same parameters, suggesting that this was due to an incompatibility between plum-almond species or to a lower water absorption capability of the rooting system. Among the rootstocks with medium canopy vigor, Adesoto and IRTA 1 had a lower evapotranspiration than Rootpac® 40 and Ishtara®. Water productivity (WP) (kg kernel/mm water evapotranspired) tended to decrease with Ψstem, mainly in 2018. Cadaman® and Garnem® had the highest WP, followed by INRA GF-677, IRTA 1, IRTA 2, and Rootpac® 40. Despite the low Ψstem of Rootpac® R, the WP of this rootstock was also high.
Why it matches plant phenotyping methodsリモートセンシングによる植物形質・蒸発散の推定が研究の中心で、熱・マルチスペクトル画像、フォトグラメトリ、モデルを用いた推定精度も評価している。
abstractIn recent years, field high-throughput phenotyping methods have been developed to characterize plant traits and to identify the most water use efficient varieties and rootstocks.
Reproduction assets foundThe paper's data availability statement points to the author's public GitHub profile (Héctor Nieto, pyTSEB developer) as the location of the datasets analyzed, which include the remote sensing phenotyping measurements (thermal/multispectral imagery-derived ETa, LAI, fiPAR, Ψstem relationships) and the TSEB-based model.Dataset · publicPublicly available datasets were analyzed in this study. This data can be found here: https://github.com/hectornieto .Open asset ↗hectornietolines:1046-1107Code / dataset availability confirmedOpenAlex · Crossref · checked 15 Sept 2026
The persistence and productivity of forage grasses, important sources for feed production, are threatened by climate change-induced drought. Breeding programs are in search of new drought tolerant forage grass varieties, but those programs still rely on time-consuming and less consistent visual scoring by breeders. In this study, we evaluate whether Unmanned Aerial Vehicle (UAV) based remote sensing can complement or replace this visual breeder score. A field experiment was set up to test the drought tolerance of genotypes from three common forage types of two different species: Festuca arundinacea, diploid Lolium perenne and tetraploid Lolium perenne. Drought stress was imposed by using mobile rainout shelters. UAV flights with RGB and thermal sensors were conducted at five time points during the experiment. Visual-based indices from different colour spaces were selected that were closely correlated to the breeder score. Furthermore, several indices, in particular H and NDLab, from the HSV (Hue Saturation Value) and CIELab (Commission Internationale de l’éclairage) colour space, respectively, displayed a broad-sense heritability that was as high or higher than the visual breeder score, making these indices highly suited for high-throughput field phenotyping applications that can complement or even replace the breeder score. The thermal-based Crop Water Stress Index CWSI provided complementary information to visual-based indices, enabling the analysis of differences in ecophysiological mechanisms for coping with reduced water availability between species and ploidy levels. All species/types displayed variation in drought stress tolerance, which confirms that there is sufficient variation for selection within these groups of grasses. Our results confirmed the better drought tolerance potential of Festuca arundinacea, but also showed which Lolium perenne genotypes are more tolerant.
Why it matches plant phenotyping methodsUAVのRGB・熱画像から植生指数と水ストレス指標を抽出し、目視スコアとの相関や遺伝率を評価する高スループット表現型解析が研究の中心です。
abstractwe evaluate whether Unmanned Aerial Vehicle (UAV) based remote sensing can complement or replace this visual breeder score
Reproduction assets foundThe authors state their phenotyping data (UAV RGB/thermal-derived vegetation indices, breeder scores, and related measurements) are publicly available on Zenodo under DOI 10.5281/zenodo.4415643. This is a paper-specific, public, directly actionable dataset. No author analysis code repository is disclosed; the Matlab/CHDataset · publicData Availability Statement: Data is publicly available at 10.5281/zenodo.4415643.Open asset ↗Zenodo · 10.5281/zenodo.4415643pdf-raw-page:19 lines:1-46Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 9 Sept 2026
The development of high-throughput genotyping and phenotyping has provided access to many tools to accelerate plant breeding programs. Unmanned Aerial Systems (UAS)-based remote sensing is being broadly implemented for field-based high-throughput phenotyping due to its low cost and the capacity to rapidly cover large breeding populations. The Structure-from-Motion photogrammetry processes aerial images taken from multiple perspectives over a field to an orthomosaic photo of a complete field experiment, allowing spectral or morphological trait extraction from the canopy surface for each individual field plot. However, some phenotypic information observable in each raw aerial image seems to be lost to the orthomosaic photo, probably due to photogrammetry processes such as pixel merging and blending. To formally assess this, we introduced a set of image processing methods to extract phenotypes from orthorectified raw aerial images and compared them to the negative control of extracting the same traits from processed orthomosaic images. We predict that standard measures of accuracy in terms of the broad-sense heritability of the remote sensing spectral traits will be higher using the orthorectified photos than with the orthomosaic image. Using three case studies, we therefore compared the broad-sense heritability of phenotypes in wheat breeding nurseries including, (1) canopy temperature from thermal imaging, (2) canopy normalized difference vegetation index (NDVI), and (3) early-stage ground cover from multispectral imaging. We evaluated heritability estimates of these phenotypes extracted from multiple orthorectified aerial images via four statistical models and compared the results with heritability estimates of these phenotypes extracted from a single orthomosaic image. Our results indicate that extracting traits directly from multiple orthorectified aerial images yielded increased estimates of heritability for all three phenotypes through proper modeling, compared to estimation using traits extracted from the orthomosaic image. In summary, the image processing methods demonstrated in this study have the potential to improve the quality of the plant trait extracted from high-throughput imaging. This, in turn, can enable breeders to utilize phenomics technologies more effectively for improved selection.
Why it matches plant phenotyping methodsUAS画像から植物形質を抽出する画像処理手法を導入し、オルソモザイク画像との比較で精度・遺伝率を検証しており、フェノタイピング手法が中心である。
abstractwe introduced a set of image processing methods to extract phenotypes from orthorectified raw aerial images and compared them to the negative control of extracting the same traits from processed orthomosaic images.
Reproduction assets foundThe paper publicly deposits its plot-level orthomosaic and orthorectified images (the phenotyping inputs/outputs of this study) at a KSU repository. The authors' Python analysis code (bip, traitExtraction) is mentioned via GitHub footnotes, but those URLs are not in the allowed list, so they cannot be included as verifDataset · publicData associated with these experiments, including the cropped, plot-level orthomosaic images and corresponding orthorectified images, can be accessed at the public repository 7 .Open asset ↗lines:528-572Supplement · publicSupplementary Table 2 ), were used to extract two independent datasets for the CT trait.Open asset ↗lines:333-343Code / dataset availability confirmedbioRxiv · Europe PMC · checked 15 Sept 2026
Plant thermal tolerance is a crucial research area as the climate warms and extreme weather events become more frequent. Leaves exposed to temperature extremes have inhibited photosynthesis and will accumulate damage to photosystem II (PSII) if tolerance thresholds are exceeded. Temperature-dependent changes in basal chlorophyll fluorescence (T-F0) can be used to identify the critical temperature at which PSII is inhibited. We developed and tested a high-throughput method for measuring the critical temperatures for PSII at low (CTMIN) and high (CTMAX) temperatures using a Maxi-Imaging fluorimeter and a thermoelectric Peltier plate heating/cooling system. We examined how experimental conditions: wet vs dry surfaces for leaves and heating/cooling rate, affect CTMIN and CTMAX across four species. CTMAX estimates were not different whether measured on wet or dry surfaces, but leaves were apparently less cold tolerant when on wet surfaces. Heating/cooling rate had a strong effect on both CTMAX and CTMIN that was species-specific. We discuss potential mechanisms for these results and recommend settings for researchers to use when measuring T-F0. The approach that we demonstrated here allows the high-throughput measurement of a valuable ecophysiological parameter that estimates the critical temperature thresholds of leaf photosynthetic performance in response to thermal extremes.
Why it matches plant phenotyping methods葉の熱耐性・PSII機能の臨界温度を高スループットに測定する蛍光イメージング手法を開発・検証しており、表現型取得法が研究の中心である。
abstractWe developed and tested a high-throughput method for measuring the critical temperatures for PSII at low (CTMIN) and high (CTMAX) temperatures using a Maxi-Imaging fluorimeter and a thermoelectric Peltier plate heating/cooling system.
Reproduction assets foundThe paper provides authors' public R code and example files for extracting Tcrit values from T-F0 chlorophyll fluorescence curves, hosted on the authors' GitHub repository. The paper also states phenotype data are openly available in figshare (10.6084/m9.figshare.12545093), but no figshare URL is present in the allowedCode · publican leaf temperature estimated from
227 two thermocouples attached to leaves on the plate and relative F0 values using the segmented R
228 package (Muggeo 2017) using the R Environment for Statistical Computing (R Core Team
229 2020). We provide example files and example R code for extracting Tcrit values from T-F0
230 curves at https://github.com/pieterarnold/Tcrit-extraction.
231
232 Surface wetness experiment: effect of wet vs dry surfaces for leaves on CTMIN and CTMAX
233 Most experiments that measure T-F0 have measured leaf samples with all excess surface
234 moisture removed, on a dry surface. However, maintaining water content of detached leaves by
235 providing a wet surface where leaOpen asset ↗pieterarnold/Tcrit-extractionpdf-layout-page:8 lines:1-46Code / dataset availability confirmedOpenAlex · Crossref · Europe PMC · checked 15 Sept 2026
High-throughput plant phenotyping in controlled environments (growth chambers and glasshouses) is often delivered via large, expensive installations, leading to limited access and the increased relevance of "affordable phenotyping" solutions. We present two robot vectors for automated plant phenotyping under controlled conditions. Using 3D-printed components and readily-available hardware and electronic components, these designs are inexpensive, flexible and easily modified to multiple tasks. We present a design for a thermal imaging robot for high-precision time-lapse imaging of canopies and a Plate Imager for high-throughput phenotyping of roots and shoots of plants grown on media plates. Phenotyping in controlled conditions requires multi-position spatial and temporal monitoring of environmental conditions. We also present a low-cost sensor platform for environmental monitoring based on inexpensive sensors, microcontrollers and internet-of-things (IoT) protocols.
Why it matches plant phenotyping methods植物の熱画像ロボット、根・シュート用プレートイメージャ、環境センサープラットフォームを開発しており、表現型取得基盤が研究の中心である。
abstractWe present two robot vectors for automated plant phenotyping under controlled conditions.
Reproduction assets foundThe paper is a hardware/software design paper for low-cost phenotyping vectors and an IoT environmental sensor platform. It contains no public phenotype/trait datasets or plant images, but the authors explicitly deposit all 3D-printed hardware files, microcontroller sketches, LabVIEW control software, PCB schematics/fcCode · publiccontrolled by a program written in the LabVIEW development environment [ 18 ] running on the host computer. This provides a user-friendly graphical interface for control of the vector (distances moved, time-lapse parameters, etc.) and imaging sensor ( Figure 3 ). The microcontroller sketch and LabVIEW software are available at https://github.com/UoNMakerSpace/themal-imager-software . Once acquired, image sets are processed for leaf temperature values at multiple points on each rosette using macros written for the ImageJ/FIJI image analysis platforms [ 19 , 20 ].
2.1.4. Performance and Results
Operating characteristics of the Thermal Imager are given in Table 2 . For comparison, characteristiOpen asset ↗UoNMakerSpace/themal-imager-softwarelines:39-47Code · publicvidual directories for each plate position with unique filenames including acquisition time and date. Experimental settings can be saved as a configuration file and re-loaded on subsequent experimental runs, ensuring that image sets are appended to the same directory. The microcontroller sketch and LabVIEW code are available at https://github.com/UoNMakerSpace/plate-imager-software .
2.2.4. Performance
Characteristics of the Plate Imager are given in Table 3 . For comparison, characteristics of a previously published research system [ 26 ] and a typical commercially-available actuator are also given.
The Plate Imager outperforms the CPIB Imaging Robot (see Table 2 ) in all measured parameterOpen asset ↗UoNMakerSpace/plate-imager-softwarelines:48-56Code / dataset availability confirmedOpenAlex · Europe PMC · Crossref · checked 9 Sept 2026
BACKGROUND: Assessing the impact of the environment on plant performance requires growing plants under controlled environmental conditions. Plant phenotypes are a product of genotype × environment (G × E), and the Enviratron at Iowa State University is a facility for testing under controlled conditions the effects of the environment on plant growth and development. Crop plants (including maize) can be grown to maturity in the Enviratron, and the performance of plants under different environmental conditions can be monitored 24 h per day, 7 days per week throughout the growth cycle. RESULTS: The Enviratron is an array of custom-designed plant growth chambers that simulate different environmental conditions coupled with precise sensor-based phenotypic measurements carried out by a robotic rover. The rover has workflow instructions to periodically visit plants growing in the different chambers where it measures various growth and physiological parameters. The rover consists of an unmanned ground vehicle, an industrial robotic arm and an array of sensors including RGB, visible and near infrared (VNIR) hyperspectral, thermal, and time-of-flight (ToF) cameras, laser profilometer and pulse-amplitude modulated (PAM) fluorometer. The sensors are autonomously positioned for detecting leaves in the plant canopy, collecting various physiological measurements based on computer vision algorithms and planning motion via "eye-in-hand" movement control of the robotic arm. In particular, the automated leaf probing function that allows the precise placement of sensor probes on leaf surfaces presents a unique advantage of the Enviratron system over other types of plant phenotyping systems. CONCLUSIONS: The Enviratron offers a new level of control over plant growth parameters and optimizes positioning and timing of sensor-based phenotypic measurements. Plant phenotypes in the Enviratron are measured in situ-in that the rover takes sensors to the plants rather than moving plants to the sensors.
Why it matches plant phenotyping methodsロボット rover、複数センサー、コンピュータビジョン、葉面プロービングを統合した植物フェノタイピング基盤の開発・実証が中心である。
abstractThe Enviratron is an array of custom-designed plant growth chambers that simulate different environmental conditions coupled with precise sensor-based phenotypic measurements carried out by a robotic rover.
Reproduction assets foundThe paper describes the Enviratron phenotyping facility and explicitly states that a Git repository containing the code developed to operate and support the Enviratron is publicly available on GitLab. This is an authors' public code asset directly tied to this paper's phenotyping system. No phenotype datasets or image/Code · publicA git repository containing code developed to operate and support the Enviratron is available online at https://gitlab.com/dill_picl/enviratron .Open asset ↗dill_picl/enviratronlines:165-207Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
Published21 Sept 2019Plant science : an international journal of experimental plant biologyCited by 30 · OpenAlex ↗
This study compares distinct phenotypic approaches to assess wheat performance under different growing temperatures and vernalization needs. A set of 38 (winter and facultative) wheat cultivars were planted in Valladolid (Spain) under irrigation and two contrasting planting dates: normal (late autumn), and late (late winter). The late plating trial exhibited a 1.5 °C increase in average crop temperature. Measurements with different remote sensing techniques were performed at heading and grain filling, as well as carbon isotope composition (δ 13 C) and nitrogen content analysis. Multispectral and RGB vegetation indices and canopy temperature related better to grain yield (GY) across the whole set of genotypes in the normal compared with the late planting, with indices (such as the RGB indices Hue, a* and the spectral indices NDVI, EVI and CCI) measured at grain filling performing the best. Aerially assessed remote sensing indices only performed better than ground-acquired ones at heading. Nitrogen content and δ 13 C correlated with GY at both planting dates. Correlations within winter and facultative genotypes were much weaker, particularly in the facultative subset. For both planting dates, the best GY prediction models were achieved when combining remote sensing indices with δ 13 C and nitrogen of mature grains. Implications for phenotyping in the context of increasing temperatures are further discussed.
Why it matches plant phenotyping methods小麦収量を対象に、マルチスペクトル・RGB・熱赤外リモートセンシングと同位体指標を比較し、収量予測性能を評価することが中心であり、表現型取得・推定手法の検証に該当する。
titleRemote sensing techniques and stable isotopes as phenotyping tools to assess wheat yield performance
Reproduction assets foundThe paper used the authors' MosaicTool software (a FIJI plugin) to crop and process UAV RGB/thermal/multispectral plot images and compute vegetation indices for this wheat phenotyping study. MosaicTool is publicly available via the authors' GitLab repository and project page, both listed in the article text and in the,Code · publiclater overlaps up to 30 images (with at least 80%
ro
overlap) and removes UAV flight effects to produce accurate ortho-mosaics. Afterwards, regions
of interest (plots) were cropped and processed using the MosaicTool software (Prof. Shawn C.
Kefauver, https://integrativecropecophysiology.com/software-development/mosaictool/,
-p
https://gitlab.com/sckefauver/MosaicTool/, University of Barcelona, Barcelona, Spain)
integrated as a plugin for the open source image analysis platform FIJI (Fiji is Just ImageJ;
http://fiji.sc/Fiji) [40].
re
Extracted RGB vegetation indices collected from both ground and aerial platforms were obtained
using an updated version of the original Breedpix 2.0 software [41Open asset ↗sckefauver/MosaicToolpdf-layout-page:7 lines:1-78Code / dataset availability confirmedCrossref · OpenAlex · checked 14 Sept 2026
Climate change is one of the primary culprits behind the restraint in the increase of cereal crop yields. In order to address its effects, effort has been focused on understanding the interaction between genotypic performance and the environment. Recent advances in unmanned aerial vehicles (UAV) have enabled the assembly of imaging sensors into precision aerial phenotyping platforms, so that a large number of plots can be screened effectively and rapidly. However, ground evaluations may still be an alternative in terms of cost and resolution. We compared the performance of red–green–blue (RGB), multispectral, and thermal data of individual plots captured from the ground and taken from a UAV, to assess genotypic differences in yield. Our results showed that crop vigor, together with the quantity and duration of green biomass that contributed to grain filling, were critical phenotypic traits for the selection of germplasm that is better adapted to present and future Mediterranean conditions. In this sense, the use of RGB images is presented as a powerful and low-cost approach for assessing crop performance. For example, broad sense heritability for some RGB indices was clearly higher than that of grain yield in the support irrigation (four times), rainfed (by 50%), and late planting (10%). Moreover, there wasn’t any significant effect from platform proximity (distance between the sensor and crop canopy) on the vegetation indexes, and both ground and aerial measurements performed similarly in assessing yield.
Why it matches plant phenotyping methodsUAV・地上のRGB／マルチスペクトル／熱画像を用いた圃場表現型取得と、プラットフォーム間の性能比較が研究の中心であるため。
abstractRecent advances in unmanned aerial vehicles (UAV) have enabled the assembly of imaging sensors into precision aerial phenotyping platforms, so that a large number of plots can be screened effectively and rapidly.
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 · publicregions of interest corresponding to each plot were segmented
and exported using the MosaicTool (Shawn C. Kefauver, https://integrativecropecophysiology.com/
software-development/mosaictool/, https://gitlab.com/sckefauver/MosaicTool, University of Barcelona,
Barcelona, Spain)Open asset ↗sckefauver/MosaicToolpdf-page:4 lines:1-56Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
The feasibility of thermography as a technique for plant screening aiming at drought-tolerance has been proven by its relationship with gas exchange, biomass, and yield. In this study, unlike most of the previous, thermography was applied for phenotyping contrasting maize genotypes whose classification for drought tolerance had already been established in the field. Our objective was to determine whether thermography-based classification would discriminate the maize genotypes in a similar way as the field selection in which just grain yield was taken into account as a criterion. We evaluated gas exchange, daily water consumption, leaf relative water content, aboveground biomass, and grain yield. Indeed, the screening of maize genotypes based on canopy temperature showed similar results to traditional methods. Nevertheless, canopy temperature only partially reflected gas exchange rates and daily water consumption in plants under drought. Part of the explanation may lie in the changes that drought had caused in plant leaves and canopy structure, altering absorption and dissipation of energy, photosynthesis, transpiration, and partitioning rates. Accordingly, although there was a negative relationship between grain yield and plant canopy temperature, it does not necessarily mean that plants whose canopies were maintained cooler under drought achieved the highest yield.
Why it matches plant phenotyping methods熱画像サーモグラフィーを用いた作物表現型スクリーニングを、既知の乾燥耐性分類と比較して検証しており、方法の適用・妥当性評価が研究の中心です。
abstractthermography was applied for phenotyping contrasting maize genotypes
Reproduction assets foundThe paper's supplementary materials (hosted at the MDPI supplement URL) explicitly contain paper-specific phenotyping assets: weather data recorded during the experiment (Supplementary File 1), UAV/thermal-imager setup (File 2), the mean-shift segmentation procedure (File 3), segmented canopy masks (File 4), and the unSupplement · publicum quantum yield of photosystem II
gs
Stomatal conductance to water vapor
GY
Grain Yield
i WUE
Intrinsic Water Use Efficiency
LRWC
Leaf Relative Water Content
PSII
Photosystem II
RGB
Red, Green and Blue color model
SWC
Soil Water Content
UAV
Unmanned Aerial Vehicle
Supplementary Materials
Supplementary materials can be found at https://www.mdpi.com/1422-0067/20/9/2273/s1 .
Click here for additional data file.
Author Contributions
C.A.F.S., R.L.G. and P.C.M. conceived and designed the experiments; R.A.C.N.C., D.S.P., T.M.M.F. and V.N.B.S. performed the experiments; C.A.F.S., R.A.C.N.C., N.G.O., M.T.S.J., T.T.S. analyzed the data; C.A.F.S., H.B.C.M., A.K.K., T.T.S. and M.T.S.J. wrote the paperOpen asset ↗lines:105-166Code / dataset availability confirmedEurope PMC · OpenAlex · checked 10 Sept 2026
Background Maize (Zea mays ssp. mays) is 1 of 3 crops, along with rice and wheat, responsible for more than one-half of all calories consumed around the world. Increasing the yield and stress tolerance of these crops is essential to meet the growing need for food. The cost and speed of plant phenotyping are currently the largest constraints on plant breeding efforts. Datasets linking new types of high-throughput phenotyping data collected from plants to the performance of the same genotypes under agronomic conditions across a wide range of environments are essential for developing new statistical approaches and computer vision-based tools. Findings A set of maize inbreds-primarily recently off patent lines-were phenotyped using a high-throughput platform at University of Nebraska-Lincoln. These lines have been previously subjected to high-density genotyping and scored for a core set of 13 phenotypes in field trials across 13 North American states in 2 years by the Genomes 2 Fields Consortium. A total of 485 GB of image data including RGB, hyperspectral, fluorescence, and thermal infrared photos has been released. Conclusions Correlations between image-based measurements and manual measurements demonstrated the feasibility of quantifying variation in plant architecture using image data. However, naive approaches to measuring traits such as biomass can introduce nonrandom measurement errors confounded with genotype variation. Analysis of hyperspectral image data demonstrated unique signatures from stem tissue. Integrating heritable phenotypes from high-throughput phenotyping data with field data from different environments can reveal previously unknown factors that influence yield plasticity.
Why it matches plant phenotyping methods高スループット画像データセットの公開と、画像測定を手動測定と比較検証することが中心であり、植物形態形質の抽出・評価に直接関係するため。
abstractA total of 485 GB of image data including RGB, hyperspectral, fluorescence, and thermal infrared photos has been released.
Reproduction assets foundThe paper's phenotyping image dataset (RGB, hyperspectral, fluorescence, thermal) is publicly deposited at GigaScience Database (doi 10.5524/100371); a subset of RGB images is also available at plantvision.unl.edu/dataset; the authors' validation/analysis source code is publicly posted on GitHub (Maize_Phenotype_Map).Dataset · publicA subset of the RGB images within this dataset were previously analyzed in Choudhury et al. [ 18 ], and were made available for download from http://plantvision.unl.edu/dataset under the terms of the Toronto Agreement.Open asset ↗lines:399-408Code / dataset availability confirmedbioRxiv · Europe PMC · OpenAlex · checked 10 Sept 2026
Maize (Zea mays ssp. mays) is one of three crops, along with rice and wheat, responsible for more than 1/2 of all calories consumed around the world. Increasing the yield and stress tolerance of these crops is essential to meet the growing need for food. The cost and speed of plant phenotyping is currently the largest constraint on plant breeding efforts. Datasets linking new types of high throughput phenotyping data collected from plants to the performance of the same genotypes under agronomic conditions across a wide range of environments are essential for developing new statistical approaches and computer vision based tools. A set of maize inbreds - primarily recently off patent lines - were phenotyped using a high throughput platform at University of Nebraska-Lincoln. These lines have been previously subjected to high density genotyping, and scored for a core set of 13 phenotypes in field trials across 13 North American states in two years by the Genomes to Fields consortium. A total of 485 GB of image data including RGB, hyperspectral, fluorescence and thermal infrared photos has been released. Correlations between image-based measurements and manual measurements demonstrated the feasibility of quantifying variation in plant architecture using image data. However, naive approaches to measuring traits such as biomass can introduce nonrandom measurement errors confounded with genotype variation. Analysis of hyperspectral image data demonstrated unique signatures from stem tissue. Integrating heritable phenotypes from high-throughput phenotyping data with field data from different environments can reveal previously unknown factors influencing yield plasticity.
Why it matches plant phenotyping methods高速画像・ハイパースペクトル等を用いた植物表現型データセットの構築と、画像測定値を手動測定と比較する技術的検証が中心であるため、収載する。
abstractA total of 485 GB of image data including RGB, hyperspectral, fluorescence and thermal infrared photos has been released.
Reproduction assets foundThe paper releases ~485 GB of maize phenotyping image data (RGB, hyperspectral, fluorescence, thermal) publicly at plantvision.unl.edu/dataset, and the authors' validation/analysis source code is posted on GitHub (https://github.com/shanwai1234/Maize Phenotype Map). Both are paper-specific, public, and actionable.Dataset · publicA subset of the RGB images within
this dataset were previously analyzed in18 , and were made available for download from http://plantvision.unl.edu/dataset under
the terms of the Toronto Agreement.Open asset ↗pdf-page:6 lines:1-51Code · publicSource codes for all validation analysis are posted online (https://github.com/shanwai1234/Maize Phenotype Map).Open asset ↗shanwai1234/Maizepdf-page:6 lines:1-51