Accurately estimating leaf area index (LAI) is vital for evaluating crop growth and predicting yields. Conventional approaches, however, often struggle due to the limited representativeness of available data and the complex structure of plant canopies, which reduce their reliability across diverse canopy architectures and observation conditions. To overcome these challenges, this work introduces an LAI retrieval framework that combines a three-dimensional radiative transfer model (3D RTM) with deep learning techniques. Representative 3D maize canopy scenarios were generated using the LESS model, producing synthetic LiDAR point clouds constrained by realistic structural parameters. A deep learning model based on PointNet++ was trained, and transfer learning (TL) was employed to facilitate knowledge transfer from simulated to actual measured data. The TL-enhanced model demonstrated significant improvement, with R2 rising from 0.537 to 0.842 and RMSE dropping from 0.541 to 0.288 m2·m−2. Moreover, retrieval performance was notably affected by scanning mode, angle, and stem diameter, achieving optimal results under TLS acquisition, moderate scanning angles, and intermediate stem widths. These findings suggest that integrating 3D RTM-generated synthetic point clouds with transfer learning is an effective strategy for enhancing the robustness and generalization of LiDAR-based LAI retrieval.
Why it matches plant phenotyping methodsLiDAR点群からトウモロコシのLAIを推定する手法を、3D放射伝達モデル、PointNet++、転移学習で開発・検証しており、植物形態形質の取得・推定が研究の中心です。
abstractthis work introduces an LAI retrieval framework that combines a three-dimensional radiative transfer model (3D RTM) with deep learning techniques.
Reproduction assets foundThe paper's field-measured LiDAR point cloud and LAI data (Yingke Oasis and Huazhaizi sites) come from a publicly accessible TPDC dataset with an explicit URL in the Data Availability Statement. No author analysis code, trained models, or synthetic dataset deposit is stated.Dataset · public2024WX06.
Data Availability Statement: The dataset used in this study was obtained from the National Tibetan
Plateau Data Center (TPDC, https://www.tpdc.ac.cn/ (accessed on 6 September 2025)), a publicly
accessible scientific data platform providing multi-source geoscientific datasets. The specific dataset
can be accessed via: https://www.tpdc.ac.cn/zh-hans/data/4d60d570-0aa9-417b-8a9d-c32b73b564
(accessed on 6 September 2025). The TPDC database integrates long-term observational and remote
sensing data with standardized quality control, ensuring the reliability and consistency of the datasets
for scientific research.
Acknowledgments: The authors would like to acknowledge the National TibetaOpen asset ↗4d60d570-0aa9-417b-8a9d-c32b73b564pdf-raw-page:19 lines:1-51Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Given the increasing frequency, severity, and socioecological impacts of wildfires, there is an urgent need for robust frameworks to better characterize fire behavior and flammability patterns across ecosystems to support early warning, mitigation, and management strategies. However, flammability remains difficult to quantify and scale, as it involves multiple interacting components that are typically measured at the bench scale. This study aimed to establish empirical links between spectral information, plant traits, and flammability metrics, and to scale these relationships to satellite imagery to translate these metrics into a spatial context. We combined laboratory spectroscopy, plant trait measurements including leaf mass per area, carbon, and cellulose, and combustion experiments using a simple and reproducible burning device. In total, 84 samples were collected and analysed, allowing us to characterise how spectral signatures relate to vegetation traits and fire behaviour. Spectral indices were developed to estimate plant traits, which were subsequently used as predictors in flammability models. These models were then transferred to Environmental Mapping and Analysis Program (EnMAP) hyperspectral imagery to derive spatial estimates across eucalypt forests and grasslands of the Australian Capital Territory (ACT). Spectral information distinguished fuel types and captured variability of the plant traits, while these traits showed associations with combustion behaviour. Based on these links, the best-performing model predicted the rate of temperature increase, a combustibility metric, in eucalypt forests (R2 = 0.70; Root Mean Square Error = 32.48 °C/s). In contrast, grassland models showed limited predictive performance, likely due to weaker relationships between plant traits and flammability metrics. Overall, this study demonstrates a practical and scalable approach for deriving flammability maps from hyperspectral and in situ data, highlighting the potential of plant-trait-based remote sensing. The resulting maps should not be interpreted as standalone fire risk products, but rather as a characterization of the structural and biochemical drivers of flammability. The main constraint of this work is the limited sample size. Future research should expand spatial and temporal coverage to better capture vegetation variability and enable the inclusion of independent validation datasets. Exploring alternative combustion protocols and testing more advanced spectral modelling approaches for trait estimation would provide additional insights.
Why it matches plant phenotyping methods植物形質を分光情報から推定し、ハイパースペクトル画像へ展開して可燃性関連の植物状態を評価する手法が研究の中心であり、モデル性能も検証しているため。
abstractSpectral indices were developed to estimate plant traits, which were subsequently used as predictors in flammability models.
Reproduction assets foundThe paper's supplementary materials (hosted publicly by MDPI) contain the paper-specific plant phenotype measurements: sampled species lists, fractional cover, and measured vegetation traits across dates and plots, plus combustion replicate variability and trait–flammability relationship data. The raw underlying data,谱Supplement · publicbroader environmental coverage, improved plant trait retrieval meth-
ods, and independent validation. Future work should also explore non-linear modelling
frameworks to better capture the complexity of vegetation flammability across ecosystems.
Supplementary Materials: The following supporting information can be downloaded at:
https://www.mdpi.com/article/10.3390/rs18101546/s1, Supplementary Table S1 provides the list of
sampled plant species and their percentage cover across sites, paddocks, plots, and fuel types; Table
S2 presents the fractional cover of each species and litter component; Figure S1 shows the study-site
vegetation map; Figures S2–S6 show the measured vegetation traits acrosOpen asset ↗pdf-raw-page:22 lines:1-49Code / dataset availability confirmedOpenAlex · Crossref · checked 14 Sept 2026
This work proposes a novel tree detection methodology, named DTCD (Distance Transform Circle Detection), based on a fast circle detection method via Distance Transform and Akaike Information Criterion (AIC) optimization. More specifically, a visible-band vegetation index (RGBVI) is calculated to enhance canopy regions, followed by morphological filtering to delineate individual tree crowns. The Euclidean Distance Transform is then applied, and the local maxima of the smoothed distance map are extracted as candidate tree locations. The final detections are iteratively refined using the AIC to optimize the number of trees with respect to canopy coverage efficiency. Additionally, this work introduces DTCD-PC, a modified algorithm tailored for point clouds, which significantly enhances detection accuracy in complex environments. This work makes a significant contribution to tree detection in the following ways: (1) by creating a tree detection framework entirely based on an unsupervised technique, which outperforms state-of-the-art unsupervised and supervised tree detection methods; (2) by introducing a new urban dataset, named AgiosNikolaos-3, that consists of orthomosaics and photogrammetrically reconstructed 3D point clouds, allowing the assessment of the proposed method in complex urban environments. The proposed DTCD approach was evaluated on the Acacia-6 dataset, consisting of UAV images of six-month-old Acacia trees in Southeast Asia, demonstrating superior detection performance compared to existing state-of-the-art techniques, both unsupervised and supervised. Additional experiments were conducted in the custom-developed Urban Dataset, confirming the robustness and generalizability of the DTCD-PC method in heterogeneous environments.
Why it matches plant phenotyping methodsUAV画像・3D点群から個体樹冠を抽出する新規手法を開発し、複数データセットで精度・頑健性を評価しているため、植物形態の取得・抽出が中心である。
abstractThis work proposes a novel tree detection methodology, named DTCD (Distance Transform Circle Detection), based on a fast circle detection method via Distance Transform and Akaike Information Criterion (AIC) optimization.
Reproduction assets foundThe authors state that the MATLAB code implementing the DTCD/DTCD-PC method, together with the datasets (Acacia-6, AgiosNikolaos-3) and results, is publicly available at their project page. Since the article is published (accepted), this is an actionable public asset containing the paper's tree-detection analysis code,Code · public.P.; All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The code implementing the proposed method together with our
results, and the links to the datasets are publicly available after paper acceptance at the following
linkhttps://sites.google.com/site/costaspanagiotakis/research/tree-detection-dtcd, accessed on 30
January 2026.
Conflicts of Interest: The authors declare no conflicts of interest.
Abbreviations
The following abbreviations are used in this manuscript:
AIC Akaike Information Criterion
AMS3D Adaptive Mean Shift 3D
CHM Canopy Height Model
CHT Circular Hough Transform
CSP ComOpen asset ↗pdf-layout-page:24 lines:1-62Code / dataset availability confirmedCrossref · checked 6 Sept 2026
Accurate and timely prediction of diseases in water-intensive crops is critical for sustainable agriculture and food security. AI-based crop disease management tools are essential for an optimized approach, as they offer significant potential for enhancing yield and sustainability. This study centers on maize, training deep learning models on UAV imagery and satellite remote-sensing data to detect and predict disease. The performance of multiple convolutional neural networks, such as ResNet-50, DenseNet-121, etc., is evaluated by their ability to classify maize diseases such as Northern Leaf Blight, Gray Leaf Spot, Common Rust, and Blight using UAV drone data. Remotely sensed MODIS satellite data was used to generate spatial severity maps over a uniform grid by implementing time-series modeling. Furthermore, reinforcement learning techniques were used to identify hotspots and prioritize the next locations for inspection by analyzing spatial and temporal patterns, identifying critical factors that affect disease progression, and enabling better decision-making. The integrated pipeline automates data ingestion and delivers farm-level condition views without manual uploads. The combination of multiple remotely sensed data sources leads to an efficient and scalable solution for early disease detection.
Why it matches plant phenotyping methodsトウモロコシの病徴・病害重症度をUAV画像および衛星データから推定する深層学習・時系列解析パイプラインが研究の中心であり、植物状態の取得・評価手法に該当する。
abstracttraining deep learning models on UAV imagery and satellite remote-sensing data to detect and predict disease
Reproduction assets foundThe paper's UAV maize disease imagery is a public Kaggle dataset (corn disease drone images from Cornell's Musgrave Research Farm) explicitly cited as the source of the 9967 images and 42,117 annotations used for training the deep learning classifiers. No author analysis code, trained models, or processed MODIS/weatherDataset · public25. UAV dataset Musgrave Research Farms. Available online: https://www.kaggle.com/datasets/alexanderyevchenko/corn-Open asset ↗Kaggle · alexanderyevchenko/corn-pdf-page:31 lines:57-58Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Rice is a staple crop for over half the world’s population, and accurate, timely information on its planted area and production is crucial for food security and agricultural policy, particularly in developing nations like Sri Lanka. However, reliable rice monitoring in regions like Sri Lanka faces significant challenges due to frequent cloud cover and the fragmented nature of smallholder farms. This research introduces a novel, cost-effective method for mapping rice-planted area and yield at field scales in Sri Lanka using optical satellite data. The rice-planted fields were identified and mapped using a phenologically tuned image classification algorithm that highlights rice presence by observing water occurrence during transplanting and vegetation activity during subsequent crop growth. To estimate yields, a random forest regression model was trained at the district level by incorporating a satellite-derived chlorophyll index and environmental variables and subsequently applied at the field level. The approach has enabled the creation of two decades (2000–2022) of reliable, field-scale rice area and yield estimates, achieving map accuracies between 70% and over 90% and yield estimates with less than 20% error. These highly granular results, which are not available through traditional surveys, show a strong correlation with government statistics. They also demonstrate the advantages of a rule-based, phenology-driven classification over purely statistical machine learning models for long-term consistency in dynamic agricultural environments. This work highlights the significant potential of remote sensing to provide accurate and detailed insights into rice cultivation, supporting policy decisions and enhancing food security in Sri Lanka and other cloud-prone regions.
Why it matches plant phenotyping methods衛星画像から圃場レベルのイネ作付面積・収量を推定する分類および回帰手法が研究の中心であり、精度評価も実施しているため、植物形質推定の方法論として適格。
abstractThis research introduces a novel, cost-effective method for mapping rice-planted area and yield at field scales in Sri Lanka using optical satellite data.
Reproduction assets foundThe paper's Data Availability Statement explicitly states that all data and code to reproduce the rice area and yield maps are publicly available in the authors' GitHub repository (ozdogan15/srilanka), which directly reproduces this paper's rice mapping and yield estimation analysis.Code · publicbrella Facility for Trade trust fund
(financed by the governments of the Netherlands, Norway, Sweden, Switzerland, and the United
Kingdom) and the World Bank’s Research Support Budget for financial support.
Data Availability Statement: All data and code to reproduce rice and yield maps are publicly
available at this repository: https://github.com/ozdogan15/srilanka#.
Acknowledgments: The authors acknowledge funding from the World Bank Whole of Economy
Program. We also thank the reviewers. The findings, interpretations, and conclusions expressed in
this paper are solely those of the authors and do not necessarily represent the views of the World
Bank, its affiliated organizations, or the ExOpen asset ↗ozdogan15/srilankapdf-layout-page:23 lines:1-59Code / dataset availability confirmedCrossref · checked 13 Sept 2026
Residual dry matter (RDM) is a term used in rangeland management to describe the non-photosynthetic plant material left on the soil surface at the end of the growing season. RDM measurements are used by agencies and conservation entities for managing grazing and fire fuels. Measuring the RDM using traditional methods is labor-intensive, costly, and subjective, making consistent sampling challenging. Previous studies have assessed the use of multispectral remote sensing to estimate the RDM, but with limited success across space and time. The existing approaches may be improved through the use of spectroscopic (hyperspectral) sensors, capable of capturing the cellulose and lignin present in dry grass, as well as Unmanned Aerial Vehicle (UAV)-mounted Light Detection and Ranging (LiDAR) sensors, capable of capturing centimeter-scale 3D vegetation structures. Here, we evaluate the relationships between the RDM and spectral and LiDAR data across the Jack and Laura Dangermond Preserve (Santa Barbara County, CA, USA), which uses grazing and prescribed fire for rangeland management. The spectral indices did not correlate with the RDM (R2
Why it matches plant phenotyping methodsUAV LiDARとフィールド分光法を用いて、植生残渣量（RDM）という植物状態を推定するセンサー手法の評価が研究の中心であり、単なる農業実験での routine measurement ではない。
titleEvaluating UAV LiDAR and Field Spectroscopy for Estimating Residual Dry Matter Across Conservation Grazing Lands
Reproduction assets foundThe paper's UAV LiDAR data (used to derive canopy height models for RDM estimation) is explicitly stated to be publicly available in the OpenTopography Community Dataspace. The KNB deposit containing RDM weights, field spectra, and analysis data is also mentioned, but its DOI URL is not among the allowed URLs, so only Dataset · publicAll the LiDAR data used in this study are publicly available in the
Open Topography Community Dataspace: https://doi.org/10.5069/G9S180QVOpen asset ↗10.5069/G9S180QVpdf-page:17 lines:1-33Code / dataset availability confirmedCrossref · checked 6 Sept 2026
Object detection is essential for precision agriculture applications like automated plant counting, but the minimum dataset requirements for effective model deployment remain poorly understood for arable crop seedling detection on orthomosaics. This study investigated how much annotated data is required to achieve standard counting accuracy (R2 = 0.85) for maize seedlings across different object detection approaches. We systematically evaluated traditional deep learning models requiring many training examples (YOLOv5, YOLOv8, YOLO11, RT-DETR), newer approaches requiring few examples (CD-ViTO), and methods requiring zero labeled examples (OWLv2) using drone-captured orthomosaic RGB imagery. We also implemented a handcrafted computer graphics algorithm as baseline. Models were tested with varying training sources (in-domain vs. out-of-distribution data), training dataset sizes (10–150 images), and annotation quality levels (10–100%). Our results demonstrate that no model trained on out-of-distribution data achieved acceptable performance, regardless of dataset size. In contrast, models trained on in-domain data reached the benchmark with as few as 60–130 annotated images, depending on architecture. Transformer-based models (RT-DETR) required significantly fewer samples (60) than CNN-based models (110–130), though they showed different tolerances to annotation quality reduction. Models maintained acceptable performance with only 65–90% of original annotation quality. Despite recent advances, neither few-shot nor zero-shot approaches met minimum performance requirements for precision agriculture deployment. These findings provide practical guidance for developing maize seedling detection systems, demonstrating that successful deployment requires in-domain training data, with minimum dataset requirements varying by model architecture.
Why it matches plant phenotyping methodsトウモロコシ幼苗の個体数という植物形質を画像から推定する物体検出手法について、複数モデル、データ量、アノテーション品質を系統的に比較・評価しており、手法の性能検証が中心である。
abstractThis study investigated how much annotated data is required to achieve standard counting accuracy (R2 = 0.85) for maize seedlings across different object detection approaches.
Reproduction assets foundThe paper's Data Availability Statement provides two paper-specific public assets: the authors' handcrafted-method analysis code on a GitHub gist and the ID (in-distribution) annotation datasets created for this study on Zenodo. Both have explicit availability language and public URLs.Code · publicThe code for the handcrafted methods used in this study is available at
https://gist.github.com/SamueleBumbaca/4a227bbe7b78d6be3424899c16c60bb4 (accessed on 20
June 2025).Open asset ↗gist.github.com/SamueleBumbacapdf-page:23 lines:1-52Dataset · publicThe datasets created during this study (ID datasets) are available at the Zenodo repository
https://doi.org/10.5281/zenodo.15235602 (accessed on 20 June 2025)Open asset ↗Zenodo · 10.5281/zenodo.15235602pdf-page:23 lines:1-52Code / 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 confirmedCrossref · checked 13 Sept 2026
Leaf rust and yellow rust are globally significant fungal diseases that severely impact wheat production, causing yield losses of up to 60% in highly susceptible cultivars. Early and accurate detection is crucial for integrating precision crop protection strategies to mitigate these losses. This study investigates the potential of 3D LiDAR technology for monitoring rust-induced physiological changes in wheat by analyzing variations in plant height, biomass, and light reflectance intensity. Results showed that grain yield decreased by 10–50% depending on cultivar susceptibility, with the durum wheat cultivar ‘Kiko Nick’ and bread wheat ‘Califa’ exhibiting the most severe reductions (~50–60%). While plant height and biomass remained relatively unaffected, LiDAR-derived intensity values strongly correlated with disease severity (R2 = 0.62–0.81, depending on the cultivar and infection stage). These findings demonstrate that LiDAR can serve as a non-destructive, high-throughput tool for early rust detection and biomass estimation, highlighting its potential for integration into precision agriculture workflows to enhance disease monitoring and improve wheat yield forecasting. To promote transparency and reproducibility, the dataset used in this study is openly available on Zenodo, and all processing code is accessible via GitHub, cited at the end of this manuscript.
Why it matches plant phenotyping methodsLiDARによる小麦の病害状態・バイオマス等の非破壊推定を中心に評価しており、植物フェノタイピング手法の実質的な適用・検証に該当する。
abstractThis study investigates the potential of 3D LiDAR technology for monitoring rust-induced physiological changes in wheat by analyzing variations in plant height, biomass, and light reflectance intensity.
Reproduction assets foundThe paper's LiDAR-derived wheat rust phenotyping dataset is openly available on Zenodo (DOI 10.5281/zenodo.14889285), and the authors' point-cloud processing and parameter-extraction code is publicly available on GitHub (eapolo/agrolidarwheatrust). Both are explicitly stated in the Data Availability Statement.Dataset · publicData Availability Statement: The dataset used in this study has been published on the Zenodo
platform under the DOI: https://doi.org/10.5281/zenodo.14889285Open asset ↗Zenodo · 10.5281/zenodo.14889285pdf-page:21 lines:1-60Code · publicalong with the code, which is
available in the GitHub repository at https://github.com/eapolo/agrolidarwheatrust, accessed on
10 March 2025.Open asset ↗github.com/eapolo/agrolidarwheatrustpdf-page:21 lines:1-60Code / dataset availability confirmedCrossref · checked 6 Sept 2026
Extracting the quantity and geolocation data of small objects at the organ level via large-scale aerial drone monitoring is both essential and challenging for precision agriculture. The quality of reconstructed digital orthophoto maps (DOMs) often suffers from seamline distortion and ghost effects, making it difficult to meet the requirements for organ-level detection. While raw images do not exhibit these issues, they pose challenges in accurately obtaining the geolocation data of detected small objects. The detection of small objects was improved in this study through the fusion of orthophoto maps with raw images using the EasyIDP tool, thereby establishing a mapping relationship from the raw images to geolocation data. Small object detection was conducted by using the Slicing-Aided Hyper Inference (SAHI) framework and YOLOv10n on raw images to accelerate the inferencing speed for large-scale farmland. As a result, comparing detection directly using a DOM, the speed of detection was accelerated and the accuracy was improved. The proposed SAHI-YOLOv10n achieved precision and mean average precision (mAP) scores of 0.825 and 0.864, respectively. It also achieved a processing latency of 1.84 milliseconds on 640×640 resolution frames for large-scale application. Subsequently, a novel crop canopy organ-level object detection dataset (CCOD-Dataset) was created via interactive annotation with SAHI-YOLOv10n, featuring 3986 images and 410,910 annotated boxes. The proposed fusion method demonstrated feasibility for detecting small objects at the organ level in three large-scale in-field farmlands, potentially benefiting future wide-range applications.
Why it matches plant phenotyping methodsUAV画像と生画像の融合、SAHI-YOLOv10nによる作物器官の検出・位置推定を中心に開発・評価し、器官レベルの大規模データセットも構築しているため、植物表現型取得法が研究の中心である。
abstractThe detection of small objects was improved in this study through the fusion of orthophoto maps with raw images using the EasyIDP tool, thereby establishing a mapping relationship from the raw images to geolocation data.
Reproduction assets foundThe paper's CCOD-Dataset (3986 UAV images, 410,910 annotated bounding boxes of crop canopy organs) is publicly released on Hugging Face, and the authors' SAHI-YOLOv10 detection framework code is hosted in a public GitHub repository. Other code (fusion/EasyIDP pipeline) is only available upon request.Dataset · publicThe CCOD-Dataset link
is publicly available at Hugging Face at https://huggingface.co/datasets/Nir-Open asset ↗CCOD-Datasetpdf-page:8 lines:1-51Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Three raster-based (RB) and one point cloud-based (PCB) algorithms were tested to segment individual Aleppo pine trees and extract their tree height (H) and crown diameter (CD) using two types of point clouds generated from two different techniques: (1) Low-Density (≈1.5 points/m2) Airborne Laser Scanning (LD-ALS) and (2) photogrammetry based on high-resolution unmanned aerial vehicle (UAV) images. Through intensive experiments, it was concluded that the tested RB algorithms performed best in the case of UAV point clouds (F1-score > 80.57%, H Pearson’s r > 0.97, and CD Pearson´s r > 0.73), while the PCB algorithm yielded the best results when working with LD-ALS point clouds (F1-score = 89.51%, H Pearson´s r = 0.94, and CD Pearson´s r = 0.57). The best set of algorithm parameters was applied to all plots, i.e., it was not optimized for each plot, in order to develop an automatic pipeline for mapping large areas of Mediterranean forests. In this case, tree detection and height estimation showed good results for both UAV and LD-ALS (F1-score > 85% and >76%, and H Pearson´s r > 0.96 and >0.93, respectively). However, very poor results were found when estimating crown diameter (CD Pearson´s r around 0.20 for both approaches).
Why it matches plant phenotyping methods個体樹のセグメンテーション手法を比較・検証し、樹高と樹冠径という植物形質を点群から推定する自動パイプラインを評価しており、フェノタイピング手法が中心です。
titleBenchmarking of Individual Tree Segmentation Methods in Mediterranean Forest Based on Point Clouds from Unmanned Aerial Vehicle Imagery and Low-Density Airborne Laser Scanning
Reproduction assets foundThe paper's Data Availability Statement states that the data presented in the study (the UAV/LD-ALS point clouds, reference tree measurements, and segmentation outputs underlying the phenotyping analysis) are openly available on Zenodo under DOI 10.5281/zenodo.10518411. This is a paper-specific, publicly actionablephenDataset · publicData Availability Statement: The data presented in this study are openly available in zenodo at
10.5281/zenodo.10518411.Open asset ↗zenodo · 10.5281/zenodo.10518411pdf-page:25 lines:1-56Code / dataset availability confirmedCrossref · checked 13 Sept 2026
Unmanaged forest ecosystems play a critical role in addressing the ongoing climate and biodiversity crises. As there is no commercial interest in monitoring the health and development of such inaccessible habitats, low-cost assessment approaches are needed. We used a method combining RGB imagery acquired using an Unmanned Aerial Vehicle (UAV), Sentinel-2 data, and field surveys to determine the carbon stock of an unmanaged forest in the UNESCO World Heritage Site wilderness area Dürrenstein-Lassingtal in Austria. The entry-level consumer drone (DJI Mavic Mini) and freely available Sentinel-2 multispectral datasets were used for the evaluation. We merged the Sentinel-2 derived vegetation index NDVI with aerial photogrammetry data and used an orthomosaic and a Digital Surface Model (DSM) to map the extent of woodland in the study area. The Random Forest (RF) machine learning (ML) algorithm was used to classify land cover. Based on the acquired field data, the average carbon stock per hectare of forest was determined to be 371.423 ± 51.106 t of CO2 and applied to the ML-generated class Forest. An overall accuracy of 80.8% with a Cohen’s kappa value of 0.74 was achieved for the land cover classification, while the carbon stock of the living above-ground biomass (AGB) was estimated with an accuracy within 5.9% of field measurements. The proposed approach demonstrated that the combination of low-cost remote sensing data and field work can predict above-ground biomass with high accuracy. The results and the estimation error distribution highlight the importance of accurate field data.
Why it matches plant phenotyping methodsUAV・衛星リモートセンシングと機械学習により森林の地上部バイオマス（炭素蓄積量）を推定し、現地測定と精度検証しているため、植物群落レベルの形質推定手法が中心です。
abstractWe used a method combining RGB imagery acquired using an Unmanned Aerial Vehicle (UAV), Sentinel-2 data, and field surveys to determine the carbon stock of an unmanaged forest
Reproduction assets foundThe paper's Data Availability Statement points to an openly available Zenodo deposit containing the original study data (field carbon stock measurements, UAV-derived datasets, and Sentinel-2 based analysis inputs). No separate author analysis code or trained model repository is mentioned.Dataset · publicData Availability Statement: The original data presented in the study are openly available here:
https://doi.org/10.5281/zenodo.11657557, accessed on 5 June 2024.Open asset ↗zenodo · 10.5281/zenodo.11657557pdf-page:17 lines:1-58Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Uncrewed aerial system (UAS) structure from motion (SfM) monitoring strategies for individual trees has rapidly expanded in the early 21st century. It has become common for studies to report accuracies for individual tree heights and DBH, along with stand density metrics. This study evaluates individual tree detection and stand basal area accuracy and precision in five ponderosa pine sites against the range of SfM parameters in the Agisoft Metashape, Pix4DMapper, and OpenDroneMap algorithms. The study is designed to frame UAS-SfM individual tree monitoring accuracy in the context of data processing and storage demands as a function of SfM algorithm parameter levels. Results show that when SfM algorithms are properly tuned, differences between software types are negligible, with Metashape providing a median F-score improvement over OpenDroneMap of 0.02 and PIX4DMapper of 0.06. However, tree extraction performance varied greatly across algorithm parameters, with the greatest extraction rates typically coming from parameters causing increased density in dense point clouds and minimal point cloud filtering. Transferring UAS-SfM forest monitoring into management will require tradeoffs between accuracy and efficiency. Our analysis shows that a one-step reduction in dense point cloud quality saves 77–86% in point cloud processing time without decreasing tree extraction (F-score) or basal area precision using Metashape and PIX4DMapper but the same parameter change for OpenDroneMap caused a ~5% loss in precision. Providing reproducible processing strategies is a vital step in successfully transferring these technologies into usage as management tools.
Why it matches plant phenotyping methodsUAS-SfMの処理パラメータと複数ソフトウェアを比較し、個体樹の抽出精度、樹高・DBH、林分断面積を評価する技術検証が中心である。
abstractThis study evaluates individual tree detection and stand basal area accuracy and precision in five ponderosa pine sites against the range of SfM parameters in the Agisoft Metashape, Pix4DMapper, and OpenDroneMap algorithms.
Reproduction assets foundThe paper's Data Availability Statement explicitly publishes the project's data and analysis source code to a public GitHub repository, which qualifies as a paper-specific public code asset. No separate phenotype dataset deposit is stated beyond this repository.Code · publicData Availability Statement: Data and analysis source code for this project has been published to the
public domain at: https://github.com/georgewoolsey/uas_sfm_tree_detection.Open asset ↗georgewoolsey/uas_sfm_tree_detectionpdf-page:19 lines:1-56Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Accurate coffee plant counting is a crucial metric for yield estimation and a key component of precision agriculture. While multispectral UAV technology provides more accurate crop growth data, the varying spectral characteristics of coffee plants across different phenological stages complicate automatic plant counting. This study compared the performance of mainstream YOLO models for coffee detection and segmentation, identifying YOLOv9 as the best-performing model, with it achieving high precision in both detection (P = 89.3%, mAP50 = 94.6%) and segmentation performance (P = 88.9%, mAP50 = 94.8%). Furthermore, we studied various spectral combinations from UAV data and found that RGB was most effective during the flowering stage, while RGN (Red, Green, Near-infrared) was more suitable for non-flowering periods. Based on these findings, we proposed an innovative dual-channel non-maximum suppression method (dual-channel NMS), which merges YOLOv9 detection results from both RGB and RGN data, leveraging the strengths of each spectral combination to enhance detection accuracy and achieving a final counting accuracy of 98.4%. This study highlights the importance of integrating UAV multispectral technology with deep learning for coffee detection and offers new insights for the implementation of precision agriculture.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像とYOLOv9、二重チャネルNMSを用いてコーヒー植物の検出・セグメンテーション・個体数推定手法を開発し、精度評価しているため、植物フェノタイピング手法が中心である。
titleA Coffee Plant Counting Method Based on Dual-Channel NMS and YOLOv9 Leveraging UAV Multispectral Imaging
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicWe will publish all the codes and datasets in this study after the article is accepted
https://github.com/legend2588/Coffee-plant-counting.gitOpen asset ↗https://github.com/legend2588/Coffee-plant-counting.gitpdf-page:19 lines:1-58Code / dataset availability confirmedCrossref · checked 7 Sept 2026
Precision agriculture integrates multiple sensors and data types to support farmers with informed decision-making tools throughout crop cycles. This study evaluated Aboveground Biomass (AGB) estimates of Rye using attributes derived from PlanetScope (PS) optical, Sentinel-1 Synthetic Aperture Radar (SAR), and hybrid (optical plus SAR) datasets. Optical attributes encompassed surface reflectance from PS’s blue, green, red, and near-infrared (NIR) bands, alongside the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI). Sentinel-1 SAR attributes included the C-band Synthetic Aperture Radar Ground Range Detected, VV and HH polarizations, and both Ratio and Polarization (Pol) indices. Ground reference AGB data for Rye (Secale cereal L.) were collected from 50 samples and four dates at a farm located in southern Brazil, aligning with image acquisition dates. Multiple linear regression models were trained and validated. AGB was estimated based on individual (optical PS or Sentinel-1 SAR) and combined datasets (optical plus SAR). This process was repeated 100 times, and variable importance was extracted. Results revealed improved Rye AGB estimates with integrated optical and SAR data. Optical vegetation indices displayed higher correlation coefficients (r) for AGB estimation (r = +0.67 for both EVI and NDVI) compared to SAR attributes like VV, Ratio, and polarization (r ranging from −0.52 to −0.58). However, the hybrid regression model enhanced AGB estimation (R2 = 0.62, p
Why it matches plant phenotyping methods光学・SARセンサーデータを統合してライムギの地上部バイオマスを推定し、回帰モデルを訓練・検証しているため、植物形質の取得・推定手法が研究の中心です。
abstractThis study evaluated Aboveground Biomass (AGB) estimates of Rye using attributes derived from PlanetScope (PS) optical, Sentinel-1 Synthetic Aperture Radar (SAR), and hybrid (optical plus SAR) datasets.
Reproduction assets foundThe paper's Sentinel-1 SAR processing workflow is publicly shared as a Google Earth Engine JavaScript script with an explicit availability statement and URL. The field AGB measurements and PlanetScope data are not public (available only on reasonable request from the corresponding author).Code · publicData Availability Statement: The Google Earth Engine script to process Sentinel-1 data is available at
[https://code.earthengine.google.com/219fc3c05b8ae8132ae2d758ccba3d1e?noload=true] (accessed
on 12 July 2024).Open asset ↗pdf-page:17 lines:1-59Code / dataset availability confirmedCrossref · checked 7 Sept 2026
Vegetation vertical complexity influences biodiversity and ecosystem productivity. Rapid warming in the boreal region is altering patterns of vertical complexity. LiDAR sensors offer novel structural metrics for quantifying these changes, but their spatiotemporal limitations and their need for ecological context complicate their application and interpretation. Satellite variables can estimate LiDAR metrics, but retrievals of vegetation structure using optical reflectance can lack interpretability and accuracy. We compare vertical complexity from the airborne LiDAR Land Vegetation and Ice Sensor (LVIS) in boreal Canada and Alaska to plant functional type, optical, and phenological variables. We show that spring onset and green season length from satellite phenology algorithms are more strongly correlated with vegetation vertical complexity (R = 0.43–0.63) than optical reflectance (R = 0.03–0.43). Median annual temperature explained patterns of vegetation vertical complexity (R = 0.45), but only when paired with plant functional type data. Random forest models effectively learned patterns of vegetation vertical complexity using plant functional type and phenological variables, but the validation performance depended on the validation methodology (R2 = 0.50–0.80). In correlating satellite phenology, plant functional type, and vegetation vertical complexity, we propose new methods of retrieving vertical complexity with satellite data.
Why it matches plant phenotyping methods植生キャノピーの垂直複雑性という明示的な植物構造形質を、LiDAR・衛星フェノロジー・機械学習で推定し、検証する方法研究であり、測定手法が中心的です。
abstractLiDAR sensors offer novel structural metrics for quantifying these changes
Reproduction assets foundThe paper's phenotyping/structural analysis is built entirely on publicly archived datasets cited with DOIs/URLs in the text: NASA LVIS full-waveform LiDAR L1B/L2 (ABoVE and LVIS Facility versions) providing the vertical complexity measurements, NEON vegetation structure in situ plant trait data, the ABoVE Landsat landDataset · publicABoVE LVIS L1B Geolocated Return Energy Waveforms, Version 1 [Data Set]. Boulder, Colorado USA.
NASA National Snow and Ice Data Center Distributed Active Archive Center. 2018. Available online:
https://nsidc.org/data/ablvis1b/versions/1 (accessed on 18 April 2024). https://doi.org/10.5067/UMRAWS57QAFUOpen asset ↗NASA National Snow and Ice Data Center Distributed Active Archive Center · 10.5067/UMRAWS57QAFUpdf-page:29 lines:1-52Dataset · publicABoVE LVIS L2 Geolocated Surface Elevation Product, Version 1 [Data Set]. Boulder, Colorado USA.
NASA National Snow and Ice Data Center Distributed Active Archive Center. 2018. Available online:
https://nsidc.org/data/ablvis2/versions/1 (accessed on 18 April 2024). https://doi.org/10.5067/IA5WAX7K3YGYOpen asset ↗NASA National Snow and Ice Data Center Distributed Active Archive Center · 10.5067/IA5WAX7K3YGYpdf-page:29 lines:1-52Dataset · publicLVIS Facility L2 Geolocated Surface Elevation and Canopy Height Product, Version 1 [Data Set]. Boulder,
Colorado USA. NASA National Snow and Ice Data Center Distributed Active Archive Center. 2020. Available online:
https://nsidc.org/data/lvisf2/versions/1 (accessed on 18 April 2024). https://doi.org/10.5067/VP7J20HJQISDOpen asset ↗NASA National Snow and Ice Data Center Distributed Active Archive Center · 10.5067/VP7J20HJQISDpdf-page:29 lines:1-52Dataset · publicNEON (National Ecological Observatory Network). Vegetation Structure (DP1.10098.001), RELEASE-2024. Available online:
https://Data.Neonscience.Org/Data-Products/DP1.10098.001/RELEASE-2024 (accessed on 18 April 2024).
https://doi.org/10.48443/3bh3-Qz86.Open asset ↗NEON (National Ecological Observatory Network) · DP1.10098.001pdf-page:29 lines:1-52Dataset · publicHLS Operational Land
Imager Surface Reflectance and TOA Brightness Daily Global 30 m v2.0. 2021, Distributed by NASA EOSDIS Land Processes
DAAC. Available online: https://doi.org/10.5067/HLS/HLSL30.002 (accessed on 18 April 2024).Open asset ↗10.5067/HLS/HLSL30.002pdf-page:29 lines:1-52Code / dataset availability confirmedCrossref · checked 7 Sept 2026
Accurate retrieval of canopy nutrient content has been made possible using visible-to-shortwave infrared (VSWIR) imaging spectroscopy. While this strategy has often been tested on closed green plant canopies, little is known about how nutrient content estimates perform when applied to pixels not dominated by photosynthetic vegetation (PV). In such cases, contributions of bare soil (BS) and non-photosynthetic vegetation (NPV), may significantly and nonlinearly reduce the spectral features relied upon for nutrient content retrieval. We attempted to define the loss of prediction accuracy under reduced PV fractional cover levels. To do so, we utilized VSWIR imaging spectroscopy data from the Global Airborne Observatory (GAO) and a large collection of lab-calibrated field samples of nitrogen (N) content collected across numerous crop species grown in several farming regions of the United States. Fractional cover values of PV, NPV, and BS were estimated from the GAO data using the Automated Monte Carlo Unmixing algorithm (AutoMCU). Errors in prediction from a partial least squares N model applied to the spectral data were examined in relation to the fractional cover of the unmixed components. We found that the most important factor in the accuracy of the partial least squares regression (PLSR) model is the fraction of photosynthetic vegetation (PV) cover, with pixels greater than 60% cover performing at the optimal level, where the coefficient of determination (R2) peaks to 0.66 for PV fractions of more than 60% and bare soil (BS) fractions of less than 20%. Our findings guide future spaceborne imaging spectroscopy missions as applied to agricultural cropland N monitoring.
Why it matches plant phenotyping methodsVSWIR画像分光とスペクトル混合分解・PLSRを用いて作物キャノピー窒素含量の推定精度を検証しており、植物形質取得法が研究の中心である。
abstractAccurate retrieval of canopy nutrient content has been made possible using visible-to-shortwave infrared (VSWIR) imaging spectroscopy.
Reproduction assets foundThe authors' PLSR nitrogen-retrieval Python code is publicly available on GitHub (NitrogenRetrieval repository) and archived on Zenodo (10.5281/zenodo.7967292). The AutoMCU code, airborne imaging spectroscopy data, and spectral reflectance data are only available by request from the corresponding author, so those are 'Code · publicAdditional
details regarding the algorithm employed for N retrieval and the corresponding Python
code can be found in the NitrogenRetrieval repository on our GitHub page, accessible at
the following URL: https://github.com/CMLandOcean/NitrogenRetrievalOpen asset ↗CMLandOcean/NitrogenRetrievalpdf-page:8 lines:1-56Code / dataset availability confirmedCrossref · checked 7 Sept 2026
The monitoring of crop phenology informs decisions in environmental and agricultural management at both global and farm scales. Current methodologies for crop monitoring using remote sensing data track crop growth stages over time based on single, scalar vegetative indices (e.g., NDVI). Crop growth and senescence are indistinguishable when using scalar indices without additional information (e.g., planting date). By using a pair of normalized difference (ND) metrics derived from hyperspectral data—one primarily sensitive to chlorophyll concentration and the other primarily sensitive to water content—it is possible to track crop characteristics based on the spectral changes only. In a two-dimensional plot of the metrics (ND-space), bare soil, full canopy, and senesced vegetation data all plot in separate, distinct locations regardless of the year. The path traced in the ND-space over the growing season repeats from year to year, with variations that can be related to weather patterns. Senescence follows a return path that is distinct from the growth path.
Why it matches plant phenotyping methodsハイパースペクトル由来の2種類の正規化差分指標を組み合わせ、作物の成長・老化過程や生育段階を時系列で推定する手法が研究の中心であるため。
abstractBy using a pair of normalized difference (ND) metrics derived from hyperspectral data—one primarily sensitive to chlorophyll concentration and the other primarily sensitive to water content—it is possible to track crop characteristics based on the spectral changes only.
Reproduction assets foundThe paper's analysis is based on the publicly available GHISA EO-1 Hyperion hyperspectral dataset from USGS, explicitly named in the Data Availability Statement. No author analysis code or trained models are deposited.Dataset · publicData Availability Statement: The data are publicly available at https://www.usgs.gov/media/files/
ghisa-usa-eo-1-hyperion-dataset (accessed on 14 November 2023).Open asset ↗ghisa-usa-eo-1-hyperion-datasetpdf-page:13 lines:1-56Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Remote-sensing data has become essential for site-specific farming methods. It is also a powerful tool for monitoring the agroecosystem services offered by integrating cover crops (CC) into crop rotations. This study presents a method to determine the canopy height (CH), defined as the average height of the crop stand surface, including tops and gaps, of heterogeneous and multi-species CC using commercial unmanned aerial vehicles (UAVs). Images captured with red–green–blue cameras mounted on UAVs in two missions varying in ground sample distances were used as input for generating three-dimensional point clouds using the structure-from-motion approach. These point clouds were then compared to manual ground measurements. The results showed that the agreement between the methods was closest when CC presented dense and smooth canopies. However, stands with rough canopies or gaps showed substantial differences between the UAV method and ground measurements. We conclude that the UAV method is substantially more precise and accurate in determining CH than measurements taken with a ruler since the UAV introduces additional dimensions with greatly increased resolution. CH can be a reliable indicator of biomass yield, but no differences between the investigated methods were found, probably due to allometric variations of different CC species. We propose the presented UAV method as a promising tool to include site-specific information on CC in crop production strategies.
Why it matches plant phenotyping methodsUAV画像とSfM点群を用いて被覆作物の群落高を推定する手法を提示し、地上測定と比較検証しており、植物形質取得法が研究の中心である。
abstractThis study presents a method to determine the canopy height (CH), defined as the average height of the crop stand surface, including tops and gaps, of heterogeneous and multi-species CC using commercial unmanned aerial vehicles (UAVs).
Reproduction assets foundThe paper's canopy height and biomass measurements (UAV-derived CH, ruler measurements, DMY) are openly available as a Zenodo dataset, explicitly stated in the Data Availability Statement. The Metashape scripts GitHub link and CRAN raster package are generic third-party tools, not authors' analysis code.Dataset · publicData Availability Statement: The data presented in this study are openly available in the Zenodo
archive at the following DOI: https://doi.org/10.5281/zenodo.7713341 (Kümmerer, 2023).Open asset ↗Zenodo · 10.5281/zenodo.7713341pdf-page:15 lines:1-51Code / dataset availability confirmedOpenAlex · checked 15 Sept 2026
Field / plotLiDAR / point cloudWhole plant / canopy / plot / field2D/3D reconstructionArchitecture / morphology / geometry
LiDAR point clouds are characterized by high geometric and radiometric resolution and are therefore of great use for large-scale forest analysis. Although the analysis of 3D geometries and shapes has improved at different resolutions, processing large-scale 3D LiDAR point clouds is difficult due to their enormous volume. From the perspective of using LiDAR point clouds for forests, the challenge lies in learning local and global features, as the number of points in a typical 3D LiDAR point cloud is in the range of millions. In this research, we present a novel end-to-end deep learning framework called ADCoSNet, capable of adaptively reconstructing 3D LiDAR point clouds from a few sparse measurements. ADCoSNet uses empirical mode decomposition (EMD), a data-driven signal processing approach with Deep Learning, to decompose input signals into intrinsic mode functions (IMFs). These IMFs capture hierarchical implicit features in the form of decreasing spatial frequency. This research proposes using the last IMF (least varying component), also known as the Residual function, as a statistical prior for capturing local features, followed by fusing with the hierarchical convolutional features from the deep compressive sensing (CS) network. The central idea is that the Residue approximately represents the overall forest structure considering it is relatively homogenous due to the presence of vegetation. ADCoSNet utilizes this last IMF for generating sparse representation based on a set of CS measurement ratios. The research presents extensive experiments for reconstructing 3D LiDAR point clouds with high fidelity for various CS measurement ratios. Our approach achieves a maximum peak signal-to-noise ratio (PSNR) of 48.96 dB (approx. 8 dB better than reconstruction without data-dependent transforms) with reconstruction root mean square error (RMSE) of 7.21. It is envisaged that the proposed framework finds high potential as an end-to-end learning framework for generating adaptive and sparse representations to capture geometrical features for the 3D reconstruction of forests.
Why it matches plant phenotyping methods森林植生の3D構造を対象に、疎なLiDAR観測から高忠実度の3D点群を再構成する手法を開発・評価しており、植物群落の幾何学的状態の取得が中心である。
abstractwe present a novel end-to-end deep learning framework called ADCoSNet, capable of adaptively reconstructing 3D LiDAR point clouds from a few sparse measurements.
Reproduction assets foundThe paper's 3D LiDAR forest point cloud inputs are publicly available OpenTopography datasets (Andrews Experimental Forest/Willamette NF 2008 and USFS Tahoe NF 2014), explicitly cited with DOIs in the Data Availability Statement. No author analysis code, trained models, or checkpoints are stated as available.Dataset · publicview & editing, S.D.; visualization, R.S.; super-
vision, S.D.; project administration, S.D.; All authors have read and agreed to the published version
of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The data presented in this study are openly available in OpenTopog-
raphy at https://doi.org/10.5069/G92N506P and https://doi.org/10.5069/G9V122Q1.Acknowledgments: The authors, express their gratitude towards the OpenTopography Facility
with support from the National Science Foundation for publishing the open LiDAR data. The NSF
OpenTopography Facility provides the 2014 USFS Tahoe National Forest LiDAR and Andrews Ex-
perimental ForestOpen asset ↗OpenTopography · 10.5069/G92N506Ppdf-raw-page:24 lines:1-52Dataset · publicR.S.; super-
vision, S.D.; project administration, S.D.; All authors have read and agreed to the published version
of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The data presented in this study are openly available in OpenTopog-
raphy at https://doi.org/10.5069/G92N506P and https://doi.org/10.5069/G9V122Q1.Acknowledgments: The authors, express their gratitude towards the OpenTopography Facility
with support from the National Science Foundation for publishing the open LiDAR data. The NSF
OpenTopography Facility provides the 2014 USFS Tahoe National Forest LiDAR and Andrews Ex-
perimental Forest and Willamette National Forest LiDAR (Aug 20Open asset ↗OpenTopography · 10.5069/G9V122Q1pdf-raw-page:24 lines:1-52Code / dataset availability confirmedOpenAlex · Crossref · checked 8 Sept 2026
A phenotype is the composite of an observable expression of a genome for traits in a given environment. The trajectories of phenotypes computed from an image sequence and timing of important events in a plant’s life cycle can be viewed as temporal phenotypes and indicative of the plant’s growth pattern and vigor. In this paper, we introduce a novel method called FlowerPhenoNet, which uses deep neural networks for detecting flowers from multiview image sequences for high-throughput temporal plant phenotyping analysis. Following flower detection, a set of novel flower-based phenotypes are computed, e.g., the day of emergence of the first flower in a plant’s life cycle, the total number of flowers present in the plant at a given time, the highest number of flowers bloomed in the plant, growth trajectory of a flower, and the blooming trajectory of a plant. To develop a new algorithm and facilitate performance evaluation based on experimental analysis, a benchmark dataset is indispensable. Thus, we introduce a benchmark dataset called FlowerPheno, which comprises image sequences of three flowering plant species, e.g., sunflower, coleus, and canna, captured by a visible light camera in a high-throughput plant phenotyping platform from multiple view angles. The experimental analyses on the FlowerPheno dataset demonstrate the efficacy of the FlowerPhenoNet.
Why it matches plant phenotyping methods花の検出と時系列表現型の抽出を行う深層学習手法を開発し、ベンチマークデータセットと評価も提示しており、植物フェノタイピング手法が中心である。
abstractwe introduce a novel method called FlowerPhenoNet, which uses deep neural networks for detecting flowers from multiview image sequences for high-throughput temporal plant phenotyping analysis.
Reproduction assets foundThe paper publicly releases the FlowerPheno benchmark dataset (17,022 multiview RGB image sequences of sunflower, canna, and coleus with ground-truth flower bounding boxes) and the FlowerPhenoNet source code, both with explicit availability statements and URLs.Dataset · publicThe dataset can be freely downloaded
from https://plantvision.unl.edu/dataset, accessed on 15 February 2021.Open asset ↗plantvision.unl.edupdf-page:4 lines:1-41Code · publicThe source code is available at
https://github.com/localchocotaco/FlowerPhenoNet, accessed on 27 November 2022.Open asset ↗github.com/localchocotaco/FlowerPhenoNetpdf-page:18 lines:1-58Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Automated plant diagnosis is a technology that promises large increases in cost-efficiency for agriculture. However, multiple problems reduce the effectiveness of drones, including the inverse relationship between resolution and speed and the lack of adequate labeled training data. This paper presents a two-step machine learning approach that analyzes low-fidelity and high-fidelity images in sequence, preserving efficiency as well as accuracy. Two data-generators are also used to minimize class imbalance in the high-fidelity dataset and to produce low-fidelity data that are representative of UAV images. The analysis of applications and methods is conducted on a database of high-fidelity apple tree images which are corrupted with class imbalance. The application begins by generating high-fidelity data using generative networks and then uses these novel data alongside the original high-fidelity data to produce low-fidelity images. A machine learning identifier identifies plants and labels them as potentially diseased or not. A machine learning classifier is then given the potentially diseased plant images and returns actual diagnoses for these plants. The results show an accuracy of 96.3% for the high-fidelity system and a 75.5% confidence level for our low-fidelity system. Our drone technology shows promising results in accuracy when compared to labor-based methods of diagnosis.
Why it matches plant phenotyping methodsUAV画像と機械学習、GANを組み合わせ、植物画像から病害状態を推定する二段階手法が研究の中心であり、精度評価も実施しているため。
abstractThis paper presents a two-step machine learning approach that analyzes low-fidelity and high-fidelity images in sequence, preserving efficiency as well as accuracy.
Reproduction assets foundThe paper's experiments were conducted on the Plant Pathology 2020 dataset, and the authors explicitly point to its public Kaggle URL in the Data Availability Statement. No author analysis code, models, or generated synthetic data are stated to be publicly available.Dataset · public.D.B.;
validation, Mathew Horak and W.D.B.; visualization, A.P. and N.M.; writing—original draft, A.P.,
N.M., M.H. and W.D.B.; writing—review and editing, M.H. and W.D.B. All authors have read and
agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: https://www.kaggle.com/c/plant-pathology-2020-fgvc7 (accessed on
8 August 2022).
Conflicts of Interest: The authors declare no conflict of interest.
References
1. FAO. Food and Agriculture Organization of the United Nations: International Plant Protection Convention. Available online:
https://www.fao.org/plant-health-2020/about/en (accessed on 17 September 2022).
2. BOpen asset ↗Kaggle · plant-pathology-2020-fgvc7pdf-raw-page:12 lines:1-52Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Monitoring within-field crop variability at fine spatial and temporal resolution can assist farmers in making reliable decisions during their agricultural management; however, it traditionally involves a labor-intensive and time-consuming pointwise manual process. To the best of our knowledge, few studies conducted a comparison of Sentinel-2 with UAV data for crop monitoring in the context of precision agriculture. Therefore, prospects of crop monitoring for characterizing biophysical plant parameters and leaf nitrogen of wheat and barley crops were evaluated from a more practical viewpoint closer to agricultural routines. Multispectral UAV and Sentinel-2 imagery was collected over three dates in the season and compared with reference data collected at 20 sample points for plant leaf nitrogen (N), maximum plant height, mean plant height, leaf area index (LAI), and fresh biomass. Higher correlations of UAV data to the agronomic parameters were found on average than with Sentinel-2 data with a percentage increase of 6.3% for wheat and 22.2% for barley. In this regard, VIs calculated from spectral bands in the visible part performed worse for Sentinel-2 than for the UAV data. In addition, large-scale patterns, formed by the influence of an old riverbed on plant growth, were recognizable even in the Sentinel-2 imagery despite its much lower spatial resolution. Interestingly, also smaller features, such as the tramlines from controlled traffic farming (CTF), had an influence on the Sentinel-2 data and showed a systematic pattern that affected even semivariogram calculation. In conclusion, Sentinel-2 imagery is able to capture the same large-scale pattern as can be derived from the higher detailed UAV imagery; however, it is at the same time influenced by management-driven features such as tramlines, which cannot be accurately georeferenced. In consequence, agronomic parameters were better correlated with UAV than with Sentinel-2 data. Crop growers as well as data providers from remote sensing services may take advantage of this knowledge and we recommend the use of UAV data as it gives additional information about management-driven features. For future perspective, we would advise fusing UAV with Sentinel-2 imagery taken early in the season as it can integrate the effect of agricultural management in the subsequent absence of high spatial resolution data to help improve crop monitoring for the farmer and to reduce costs.
Why it matches plant phenotyping methodsUAVおよびSentinel-2マルチスペクトル画像から草丈、LAI、バイオマス、葉窒素などの植物形質を推定し、参照データとの相関比較・技術評価を行っているため、植物フェノタイピング手法の検証・応用が中心です。
abstractprospects of crop monitoring for characterizing biophysical plant parameters and leaf nitrogen of wheat and barley crops were 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。Supplement · publicSupplementary Materials: The following supporting information can be downloaded at:
https://www.mdpi.com/article/10.3390/rs14174426/s1, Table S1: Summary statistics of the plant trait
variables measured at 20 sample points in field A; Table S2: Summary statistics of the plant trait
variables measured at 20 sample points in field G; Table S3: Absolute correlation results of plant
maximum height and mean height in field AOpen asset ↗pdf-page:20 lines:1-58Code / dataset availability confirmedOpenAlex · checked 15 Sept 2026
Satellite-based gross primary production (GPP) estimation has uncertainties due to shadow fraction caused by the geometric relationship between the complex forest structure and the Sun. The virtual forests allow shadow fraction estimation without 3D measurements, but require optimal structural parameters. In this study, we developed the reflectance simulator (Canopy-level Shadow and Reflectance Simulator, CSRS) that considers tree shadows and the method to determine the optimal canopy shape for shadow fraction estimation. The target forest is any tropical evergreen forest which accounts for 58% of tropical forests. Firstly, we analyzed the effects of canopy shape on the reflectance simulation based on virtual forests created with different canopy shapes. This result was checked by Tukey’s honestly significant difference (HSD) test. Secondly, the optimal canopy shape was determined by comparing the reflectance from Sentinel-2 Band 4 (red) bottom of atmosphere reflectance with those simulated from virtual forests. Finally, the shadow fraction estimated from the virtual forest was evaluated. Since the focus of this study was to derive the optimal canopy shape, unmanned aerial vehicle (UAV) structure from motion (SfM) was used to obtain the parameters other than canopy shape and to validate the estimated shadow fraction. The results showed that when the Sun zenith angle (SZA) was more than 20°, significant differences were observed among canopy shapes. The least root mean square error (RMSE) for reflectance simulation was 0.385 from the canopy shape of a half ellipsoid. Moreover, the half ellipsoid also showed the smallest RMSE in estimating shadow fraction (0.032), which indicated the reliability and applicability of CSRS. This study is the first attempt to determine the optimal canopy shape for estimating shadow fraction and is expected to improve the accuracy of GPP estimation in the future.
Why it matches plant phenotyping methods森林キャノピーの影分率という植物群落の状態を推定する反射シミュレータを開発し、UAV測定およびSentinel-2反射率との比較で検証しており、植物状態の取得・推定手法が中心である。
abstractwe developed the reflectance simulator (Canopy-level Shadow and Reflectance Simulator, CSRS) that considers tree shadows and the method to determine the optimal canopy shape for shadow fraction estimation.
Reproduction assets foundThe paper's CSRS reflectance/shadow simulation code is explicitly stated to be publicly available on the authors' GitHub repository. The ECOSTRESS Spectral Library is a generic external spectral database, not a paper-specific asset.Code · publicng—review and editing, W.T.; visualization, T.F.;
supervision, W.T.; project administration, W.T.; funding acquisition, W.T. All authors have read and
agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: The simulation code of CSRS is available from https://github.com/Takumi-Fuji6936/CSRS.git (accessed on 29 June 2022).
Conflicts of Interest: The authors declare no conflict of interest.
References
1. FAO. Assessment, Global Forest Resources 2020. Available online: https://www.fao.org/3/CA8753EN/CA8753EN.pdf (accessed
on 10 November 2021).
2. Beer, C.; Reichstein, M.; Tomelleri, E.; Ciais, P.; Jung, M.; CarvalhaisOpen asset ↗Takumi-Fuji6936/CSRSpdf-raw-page:13 lines:1-50Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Plant functional traits at the community level (plant community traits hereafter) are commonly used in trait-based ecology for the study of vegetation–environment relationships. Previous studies have shown that a variety of plant functional traits at the species or community level can be successfully retrieved by airborne or spaceborne imaging spectrometer in homogeneous, species-poor ecosystems. However, findings from these studies may not apply to heterogeneous, species-rich ecosystems. Here, we aim to determine whether unmanned aerial vehicle (UAV)-based hyperspectral imaging could adequately estimate plant community traits in a species-rich alpine meadow ecosystem on the Qinghai–Tibet Plateau. To achieve this, we compared the performance of four non-parametric regression models, i.e., partial least square regression (PLSR), the generic algorithm integrated with the PLSR (GA-PLSR), random forest (RF) and extreme gradient boosting (XGBoost) for the retrieval of 10 plant community traits using visible and near-infrared (450–950 nm) UAV hyperspectral imaging. Our results show that chlorophyll a, chlorophyll b, carotenoid content, starch content, specific leaf area and leaf thickness were estimated with good accuracies, with the highest R2 values between 0.64 (nRMSE = 0.16) and 0.83 (nRMSE = 0.11). Meanwhile, the estimation accuracies for nitrogen content, phosphorus content, plant height and leaf dry matter content were relatively low, with the highest R2 varying from 0.3 (nRMSE = 0.24) to 0.54 (nRMSE = 0.20). Among the four tested algorithms, the GA-PLSR produced the highest accuracy, followed by PLSR and XGBoost, and RF showed the poorest performance. Overall, our study demonstrates that UAV-based visible and near-infrared hyperspectral imaging has the potential to accurately estimate multiple plant community traits for the natural grassland ecosystem at a fine scale.
Why it matches plant phenotyping methodsUAVハイパースペクトル画像と複数の回帰モデルを用いて植物群落形質を推定し、手法性能を比較評価しているため、形質取得・推定法が研究の中心である。
abstractwe compared the performance of four non-parametric regression models, i.e., partial least square regression (PLSR), the generic algorithm integrated with the PLSR (GA-PLSR), random forest (RF) and extreme gradient boosting (XGBoost) for the retrieval of 10 plant community traits using visible and near-infrared (450–950 nm) UAV hyperspectral imaging.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Supplement · publicFigure S2: The UAV hyperspectral image used
for mapping plant community traits. The upper one is the raw image and the lower one is the
corrected image shown in true colour composites.Open asset ↗pdf-page:12 lines:1-58Code / dataset availability confirmedCrossref · checked 8 Sept 2026
Crop yield estimation from satellite data requires field observations to fit and evaluate predictive models. However, it is not clear how much field data collection methods matter for predictive performance. To evaluate this, we used maize yield estimates obtained with seven field methods (two farmer estimates, two point transects, and three crop cut methods) and the “true yield” measured from a full-field harvest for 196 fields in three districts in Ethiopia in 2019. We used a combination of nine vegetation indices and five temporal aggregation methods for the growing season from Sentinel-2 SR data as yield predictors in the linear regression and Random Forest models. Crop-cut-based models had the highest model fit and accuracy, similar to that of full-field-harvest-based models. When the farmer estimates were used as the training data, the prediction gain was negligible, indicating very little advantage to using remote sensing to predict yield when the training data quality is low. Our results suggest that remote sensing models to estimate crop yield should be fit with data from crop cuts or comparable high-quality measurements, which give better prediction results than low-quality training data sets, even when much larger numbers of such observations are available.
Why it matches plant phenotyping methods衛星データによる作物収量推定について、7種類の圃場測定法を比較し、収量推定モデルの適合度・精度への影響を検証している。収量という植物形質の取得・推定法が研究の中心である。
abstractTo evaluate this, we used maize yield estimates obtained with seven field methods (two farmer estimates, two point transects, and three crop cut methods) and the “true yield” measured from a full-field harvest for 196 fields in three districts in Ethiopia in 2019.
Reproduction assets foundThe paper's field-measured maize yield dataset (seven sampling methods plus full-field harvest for 196 Ethiopian fields) is openly available via a Zenodo DOI in the Data Availability Statement. No code availability is stated.Dataset · publicData Availability Statement: The data presented in this study are openly available here:
https://doi.org/10.5281/zenodo.6471977.Open asset ↗zenodo · 10.5281/zenodo.6471977pdf-page:11 lines:1-58Code / dataset availability confirmedCrossref · checked 8 Sept 2026
Biophysical parameter retrieval using remote sensing has long been utilized for crop yield forecasting and economic practices. Remote sensing can provide information across a large spatial extent and in a timely manner within a season. Plant Area Index (PAI), Vegetation Water Content (VWC), and Wet-Biomass (WB) play a vital role in estimating crop growth and helping farmers make market decisions. Many parametric and non-parametric machine learning techniques have been utilized to estimate these parameters. A general non-parametric approach that follows a Bayesian framework is the Gaussian Process (GP). The parameters of this process-based technique are assumed to be random variables with a joint Gaussian distribution. The purpose of this work is to investigate Gaussian Process Regression (GPR) models to retrieve biophysical parameters of three annual crops utilizing combinations of multiple polarizations from C-band SAR data. RADARSAT-2 full-polarimetric images and in situ measurements of wheat, canola, and soybeans obtained from the SMAPVEX16 campaign over Manitoba, Canada, are used to evaluate the performance of these GPR models. The results from this research demonstrate that both the full-pol (HH+HV+VV) combination and the dual-pol (HV+VV) configuration can be used to estimate PAI, VWC, and WB for these three crops.
Why it matches plant phenotyping methodsSARデータとGPRモデルにより作物のPAI・VWC・湿重量バイオマスを推定する手法を開発・評価しており、植物形質取得が研究の中心である。
abstractThe purpose of this work is to investigate Gaussian Process Regression (GPR) models to retrieve biophysical parameters of three annual crops utilizing combinations of multiple polarizations from C-band SAR data.
Reproduction assets foundThe paper's Data Availability Statement explicitly provides a public GitHub repository containing the authors' GPR analysis code for crop biophysical parameter retrieval from RADARSAT-2 data. The in situ SMAPVEX16-MB measurements and RADARSAT-2 imagery themselves are not stated as publicly released by the authors.Code · publicData Availability Statement: The code for the present work is available at: https://github.com/
Swarnendu-sekhar-ghosh/GPR_biophysical_parameter_retrieval_RS2, accessed 15 February 2022.Open asset ↗Swarnendu-sekhar-ghosh/GPR_biophysical_parameter_retrieval_RS2pdf-page:24 lines:1-60Code / dataset availability confirmedCrossref · checked 8 Sept 2026
Near-surface cameras, such as those in the PhenoCam network, are a common source of ground truth data in modelling and remote sensing studies. Despite having locations across numerous agricultural sites, few studies have used near-surface cameras to track the unique phenology of croplands. Due to management activities, crops do not have a natural vegetation cycle which many phenological extraction methods are based on. For example, a field may experience abrupt changes due to harvesting and tillage throughout the year. A single camera can also record several different plants due to crop rotations, fallow fields, and cover crops. Current methods to estimate phenology metrics from image time series compress all image information into a relative greenness metric, which discards a large amount of contextual information. This can include the type of crop present, whether snow or water is present on the field, the crop phenology, or whether a field lacking green plants consists of bare soil, fully senesced plants, or plant residue. Here, we developed a modelling workflow to create a daily time series of crop type and phenology, while also accounting for other factors such as obstructed images and snow covered fields. We used a mainstream deep learning image classification model, VGG16. Deep learning classification models do not have a temporal component, so to account for temporal correlation among images, our workflow incorporates a hidden Markov model in the post-processing. The initial image classification model had out of sample F1 scores of 0.83–0.85, which improved to 0.86–0.91 after all post-processing steps. The resulting time series show the progression of crops from emergence to harvest, and can serve as a daily, local-scale dataset of field states and phenological stages for agricultural research.
Why it matches plant phenotyping methodsPhenoCam画像から作物種と日次フェノロジーを抽出する深層学習・隠れマルコフモデルのワークフローを開発し、性能評価も行っているため、植物フェノタイピング手法が中心である。
abstractHere, we developed a modelling workflow to create a daily time series of crop type and phenology, while also accounting for other factors such as obstructed images and snow covered fields.
Reproduction assets foundThe authors deposited all analysis code, data, and final model predictions in a public Zenodo repository (DOI 10.5281/zenodo.5618316), and the paper's phenotyping inputs are PhenoCam images from the public PhenoCam data portal (phenocam.sr.unh.edu). Both are paper-specific, public, and actionable.Code · publicData Availability Statement: All code and data to reproduce this analysis, as well as the final model
predictions, are available in a Zenodo repository [44].Open asset ↗Zenodopdf-page:15 lines:1-59Code / dataset availability confirmedCrossref · checked 8 Sept 2026
Optimised farm crop productivity requires careful management in response to the spatial and temporal variability of yield. Accordingly, combination of crop simulation models and remote sensing data provides a pathway for providing the spatially variable information needed on current crop status and the expected yield. An ensemble Kalman filter (EnKF) data assimilation framework was developed to assimilate plant and soil observations into a prediction model to improve crop development and yield forecasting. Specifically, this study explored the performance of assimilating state observations into the APSIM-Wheat model using a dataset collected during the 2018/19 wheat season at a farm near Cora Lynn in Victoria, Australia. The assimilated state variables include (1) ground-based measurements of Leaf Area Index (LAI), soil moisture throughout the profile, biomass, and soil nitrate-nitrogen; and (2) remotely sensed observations of LAI and surface soil moisture. In a baseline scenario, an unconstrained (open-loop) simulation greatly underestimated the wheat grain with a relative difference (RD) of −38.3%, while the assimilation constrained simulations using ground-based LAI, ground-based biomass, and remotely sensed LAI were all found to improve the RD, reducing it to −32.7%, −9.4%, and −7.6%, respectively. Further improvements in yield estimation were found when: (1) wheat states were assimilated in phenological stages 4 and 5 (end of juvenile to flowering), (2) plot-specific remotely sensed LAI was used instead of the field average, and (3) wheat phenology was constrained by ground observations. Even when using parameters that were not accurately calibrated or measured, the assimilation of LAI and biomass still provided improved yield estimation over that from an open-loop simulation.
Why it matches plant phenotyping methods植物のLAI・バイオマス等の状態観測をリモートセンシングとデータ同化で作物モデルへ統合し、収量推定性能を評価する計算・計測ワークフローが研究の中心であるため、植物表現型計測手法として収載する。
abstractthe assimilation of LAI and biomass still provided improved yield estimation over that from an open-loop simulation.
Reproduction assets foundThe paper's field validation dataset (wheat/soil state observations from the 2018/19 Cora Lynn experiment) is openly available on the authors' PRISM (Monash) site, and the authors' APSIM-EnKF data assimilation source code is explicitly stated to be publicly available on GitHub. Weather data sources (BoM, Weather UndergDataset · publicThe field validation data
presented in this study are openly available in the P-band Radiometer Inferred Soil Moisture (PRISIM)
website at https://www.prism.monash.edu/index.htmlOpen asset ↗pdf-page:19 lines:1-59Code · publicThe APSIM-EnKF data assimilation framework used in this study was the version
developed and described by Zhang [28] (source code available on https://github.com/Open asset ↗pdf-page:3 lines:1-53Code / dataset availability confirmedEurope PMC · checked 14 Sept 2026
Monitoring cropland phenology from optical satellite data remains a challenging task due to the influence of clouds and atmospheric artifacts. Therefore, measures need to be taken to overcome these challenges and gain better knowledge of crop dynamics. The arrival of cloud computing platforms such as Google Earth Engine (GEE) has enabled us to propose a Sentinel-2 (S2) phenology end-to-end processing chain. To achieve this, the following pipeline was implemented: (1) the building of hybrid Gaussian Process Regression (GPR) retrieval models of crop traits optimized with active learning, (2) implementation of these models on GEE (3) generation of spatiotemporally continuous maps and time series of these crop traits with the use of gap-filling through GPR fitting, and finally, (4) calculation of land surface phenology (LSP) metrics such as the start of season (SOS) or end of season (EOS). Overall, from good to high performance was achieved, in particular for the estimation of canopy-level traits such as leaf area index (LAI) and canopy chlorophyll content, with normalized root mean square errors (NRMSE) of 9% and 10%, respectively. By means of the GPR gap-filling time series of S2, entire tiles were reconstructed, and resulting maps were demonstrated over an agricultural area in Castile and Leon, Spain, where crop calendar data were available to assess the validity of LSP metrics derived from crop traits. In addition, phenology derived from the normalized difference vegetation index (NDVI) was used as reference. NDVI not only proved to be a robust indicator for the calculation of LSP metrics, but also served to demonstrate the good phenology quality of the quantitative trait products. Thanks to the GEE framework, the proposed workflow can be realized anywhere in the world and for any time window, thus representing a shift in the satellite data processing paradigm. We anticipate that the produced LSP metrics can provide meaningful insights into crop seasonal patterns in a changing environment that demands adaptive agricultural production.
Why it matches plant phenotyping methods衛星データから作物形質を推定し、GPRによる補間・時系列化とGEE上の再利用可能な処理ワークフローを構築・検証しており、フェノタイピング手法が中心である。
abstractthe building of hybrid Gaussian Process Regression (GPR) retrieval models of crop traits optimized with active learning
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 following link contains a repository with demo codes of the different procedures used in this paper https://github.com/msalinero/GEEGPRPhenoDemos.git .Open asset ↗GEEGPRPhenoDemoslines:353-362Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Unmanned aerial vehicle (UAV) remote sensing technology can be used for fast and efficient monitoring of plant diseases and pests, but these techniques are qualitative expressions of plant diseases. However, the yellow leaf disease of arecanut in Hainan Province is similar to a plague, with an incidence rate of up to 90% in severely affected areas, and a qualitative expression is not conducive to the assessment of its severity and yield. Additionally, there exists a clear correlation between the damage caused by plant diseases and pests and the change in the living vegetation volume (LVV). However, the correlation between the severity of the yellow leaf disease of arecanut and LVV must be demonstrated through research. Therefore, this study aims to apply the multispectral data obtained by the UAV along with the high-resolution UAV remote sensing images to obtain five vegetation indexes such as the normalized difference vegetation index (NDVI), optimized soil adjusted vegetation index (OSAVI), leaf chlorophyll index (LCI), green normalized difference vegetation index (GNDVI), and normalized difference red edge (NDRE) index, and establish five algorithm models such as the back-propagation neural network (BPNN), decision tree, naïve Bayes, support vector machine (SVM), and k-nearest-neighbor classification to determine the severity of the yellow leaf disease of arecanut, which is expressed by the proportion of the yellowing area of a single areca crown (in percentage). The traditional qualitative expression of this disease is transformed into the quantitative expression of the yellow leaf disease of arecanut per plant. The results demonstrate that the classification accuracy of the test set of the BPNN algorithm and SVM algorithm is the highest, at 86.57% and 86.30%, respectively. Additionally, the UAV structure from motion technology is used to measure the LVV of a single areca tree and establish a model of the correlation between the LVV and the severity of the yellow leaf disease of arecanut. The results show that the relative root mean square error is between 34.763% and 39.324%. This study presents the novel quantitative expression of the severity of the yellow leaf disease of arecanut, along with the correlation between the LVV of areca and the severity of the yellow leaf disease of arecanut. Significant development is expected in the degree of integration of multispectral software and hardware, observation accuracy, and ease of use of UAVs owing to the rapid progress of spectral sensing technology and the image processing and analysis algorithms.
Why it matches plant phenotyping methodsUAVマルチスペクトル画像とSfMにより、植物体ごとの病害重症度と生体植生量を定量推定する手法を開発・評価しており、表現型取得が研究の中心である。
abstractestablish five algorithm models such as the back-propagation neural network (BPNN), decision tree, naïve Bayes, support vector machine (SVM), and k-nearest-neighbor classification to determine the severity of the yellow leaf disease of arecanut
Reproduction assets foundThe paper's Data Availability Statement explicitly points to a publicly accessible dataset at the author's website (zixuanqiu.com), matching an allowed URL. The study's UAV multispectral imagery, vegetation index data, and 11,400 sample-point annotations for arecanut yellow leaf disease are the paper-specific phenotypcDataset · publicData Availability Statement: Data available in a publicly accessible repository that does not issue
DOIs Publicly available datasets were analyzed in this study. This data can be found here:
http://www.zixuanqiu.com/nd.jsp?id=39#_np=110_649 (accessed on 20 October 2021).Open asset ↗zixuanqiu.compdf-page:19 lines:1-58Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
This work presents an advanced photogrammetric pipeline for inspecting apple trees in the field, automatically detecting fruits from videos and quantifying their size and number. The proposed approach is intended to facilitate and accelerate farmers’ and agronomists’ fieldwork, making apple measurements more objective and giving a more extended collection of apples measured in the field while also estimating harvesting/apple-picking dates. In order to do this rapidly and automatically, we propose a pipeline that uses smartphone-based videos and combines photogrammetry, deep learning and geometric algorithms. Synthetic, laboratory and on-field experiments demonstrate the accuracy of the results and the potential of the proposed method. Acquired data, labelled images, code and network weights, are available at 3DOM-FBK GitHub account.
Why it matches plant phenotyping methodsリンゴ果実の数とサイズを動画から自動抽出するフォトグラメトリ手法を開発し、実験で精度を検証しており、植物フェノタイピング手法が中心である。
abstractThis work presents an advanced photogrammetric pipeline for inspecting apple trees in the field, automatically detecting fruits from videos and quantifying their size and number.
Reproduction assets foundThe authors explicitly state that acquired data, labelled images, code, and network weights for the apple phenotyping pipeline are publicly available on the 3DOM-FBK GitHub account, with a concrete URL given in reference [56]. This is a paper-specific, public, actionable asset covering the Mask R-CNN retraining code/权重Code · publicData Availability Statement: Data acquired and used in the presented experiments, labelled im-
ages, code, and network weights, are available to the scientific community at 3DOM-FBK-GitHub
[56].Open asset ↗pdf-page:16 lines:1-58Dataset · publicAcquired
data, labelled images, code and network weights, are available at 3DOM-FBK GitHub account.Open asset ↗pdf-page:1 lines:1-67Code / dataset availability confirmedOpenAlex · Crossref · checked 8 Sept 2026
Modern plant phenotyping requires tools that are robust to noise and missing data, while being able to efficiently process large numbers of plants. Here, we studied the skeletonization of plant architectures from 3D point clouds, which is critical for many downstream tasks, including analyses of plant shape, morphology, and branching angles. Specifically, we developed an algorithm to improve skeletonization at branch points (forks) by leveraging the geometric properties of cylinders around branch points. We tested this algorithm on a diverse set of high-resolution 3D point clouds of tomato and tobacco plants, grown in five environments and across multiple developmental timepoints. Compared to existing methods for 3D skeletonization, our method efficiently and more accurately estimated branching angles even in areas with noisy, missing, or non-uniformly sampled data. Our method is also applicable to inorganic datasets, such as scans of industrial pipes or urban scenes containing networks of complex cylindrical shapes.
Why it matches plant phenotyping methods植物の3D点群から分枝構造を骨格化し、分枝角度を推定するアルゴリズムを開発・比較評価しており、植物表現型の抽出手法が研究の中心です。
abstractHere, we studied the skeletonization of plant architectures from 3D point clouds
Reproduction assets foundThe paper's Data Availability Statement explicitly states that data and code executable are publicly available at the authors' GitHub repository iziamtso/P3D, which is an allowed URL. This covers the paper-specific plant point cloud data and skeletonization analysis code.Code · publicData Availability Statement: Data and code executable are available at: https://github.com/iziamtso/P3D.Open asset ↗iziamtso/P3Dpdf-page:14 lines:1-59Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Leaf mass per area (LMA) is a key plant functional trait closely related to leaf biomass. Estimating LMA in fresh leaves remains challenging due to its masked absorption by leaf water in the short-wave infrared region of reflectance. Vegetation indices (VIs) are popular variables used to estimate LMA. However, their physical foundations are not clear and the generalization ability is limited by the training data. In this study, we proposed a hybrid approach by establishing a three-dimensional (3D) VI matrix for LMA estimation. The relationship between LMA and VIs was constructed using PROSPECT-D model simulations. The three-VI space constituting a 3D matrix was divided into cubical cells and LMA values were assigned to each cell. Then, the 3D matrix retrieves LMA through the three VIs calculated from observations. Two 3D matrices with different VIs were established and validated using a second synthetic dataset, and two comprehensive experimental datasets containing more than 1400 samples of 49 plant species. We found that both 3D matrices allowed good assessments of LMA (R2 = 0.76 and 0.78, RMSE = 0.0016 g/cm2 and 0.0017 g/cm2, respectively for the pooled datasets), and their results were superior to the corresponding single Vis, 2D matrices, and two machine learning methods established with the same VI combinations.
Why it matches plant phenotyping methods植物機能形質LMAを可視・近赤外観測から推定する3D植生指数行列を開発し、合成データおよび大規模実験データで検証しており、表現型取得手法が中心である。
abstractIn this study, we proposed a hybrid approach by establishing a three-dimensional (3D) VI matrix for LMA estimation.
Reproduction assets foundThe paper's two experimental phenotyping datasets (LOPEX leaf spectra/LMA and the Madison, WI leaf spectra dataset) are explicitly stated to be publicly available on EcoSIS with direct URLs in the Data Availability Statement. No author analysis code or trained model is shared.Dataset · publicResearch Funds for the Central Universities, China Uni-
versity of Geosciences, Wuhan (grant number 111-G1323520290). T.T. was funded by SNSA (Dnr
96/16) and the EU-Aid-funded CASSECS project.
Data Availability Statement: All data used in this manuscript are publicly available through EcoSIS
spectral database, including LOPEX (https://ecosis.org/package/leaf-optical-properties-experiment-database--lopex93-) and MA (https://ecosis.org/package/7433af7d-fbbd-4617-8df4-4d892f0d4357).Acknowledgments: We thank the open access to the LOPEX and MA datasets, as well as the PRO-
SPECT-D model.
Conflicts of Interest: The authors declare no conflict of interest. Authors are aware of and comply
with bestOpen asset ↗EcoSIS · leaf-optical-properties-experiment-database--lopex93-pdf-raw-page:13 lines:1-51Dataset · publicant number 111-G1323520290). T.T. was funded by SNSA (Dnr
96/16) and the EU-Aid-funded CASSECS project.
Data Availability Statement: All data used in this manuscript are publicly available through EcoSIS
spectral database, including LOPEX (https://ecosis.org/package/leaf-optical-properties-experiment-database--lopex93-) and MA (https://ecosis.org/package/7433af7d-fbbd-4617-8df4-4d892f0d4357).Acknowledgments: We thank the open access to the LOPEX and MA datasets, as well as the PRO-
SPECT-D model.
Conflicts of Interest: The authors declare no conflict of interest. Authors are aware of and comply
with best practices in publication ethics specifically about authorship (avoidance of guest authorOpen asset ↗EcoSIS · 7433af7d-fbbd-4617-8df4-4d892f0d4357pdf-raw-page:13 lines:1-51Code / dataset availability confirmedCrossref · checked 9 Sept 2026
This research reports the findings of a Landsat Next expert review panel that evaluated the use of narrow shortwave infrared (SWIR) reflectance bands to measure ligno-cellulose absorption features centered near 2100 and 2300 nm, with the objective of measuring and mapping non-photosynthetic vegetation (NPV), crop residue cover, and the adoption of conservation tillage practices within agricultural landscapes. Results could also apply to detection of NPV in pasture, grazing lands, and non-agricultural settings. Currently, there are no satellite data sources that provide narrowband or hyperspectral SWIR imagery at sufficient volume to map NPV at a regional scale. The Landsat Next mission, currently under design and expected to launch in the late 2020’s, provides the opportunity for achieving increased SWIR sampling and spectral resolution with the adoption of new sensor technology. This study employed hyperspectral data collected from 916 agricultural field locations with varying fractional NPV, fractional green vegetation, and surface moisture contents. These spectra were processed to generate narrow bands with centers at 2040, 2100, 2210, 2260, and 2230 nm, at various bandwidths, that were subsequently used to derive 13 NPV spectral indices from each spectrum. For crop residues with minimal green vegetation cover, two-band indices derived from 2210 and 2260 nm bands were top performers for measuring NPV (R2 = 0.81, RMSE = 0.13) using bandwidths of 30 to 50 nm, and the addition of a third band at 2100 nm increased resistance to atmospheric correction residuals and improved mission continuity with Landsat 8 Operational Land Imager Band 7. For prediction of NPV over a full range of green vegetation cover, the Cellulose Absorption Index, derived from 2040, 2100, and 2210 nm bands, was top performer (R2 = 0.77, RMSE = 0.17), but required a narrow (≤20 nm) bandwidth at 2040 nm to avoid interference from atmospheric carbon dioxide absorption. In comparison, broadband NPV indices utilizing Landsat 8 bands centered at 1610 and 2200 nm performed poorly in measuring fractional NPV (R2 = 0.44), with significantly increased interference from green vegetation.
Why it matches plant phenotyping methodsSWIRバンドとスペクトル指数を用いて非光合植生・作物残渣被覆を測定する手法を開発・比較評価しており、植物状態の取得方法が研究の中心である。
abstractThis study employed hyperspectral data collected from 916 agricultural field locations with varying fractional NPV, fractional green vegetation, and surface moisture contents.
Reproduction assets foundThe paper's core phenotyping input — the 916 agricultural field surface reflectance spectra used to derive NPV indices — is published as a USGS data release (reference 44) with a public DOI. No author analysis code or trained models are stated as available. Other URLs (Earth Explorer WV3 imagery, CTIC, NGAC, Auscope) pDataset · publicHively, W.D.; Lamb, B.T.; Daughtry, C.S.T.; Serbin, G.; Dennison, P. Reflectance Spectra of Agricultural Field Conditions
Supporting Remote Sensing Evaluation of Non-Photosynthetic Vegetative Cover. 2021. (U.S. Geological Survey Data Release.
Available online: https://doi.org/10.5066/P9XK3867 (accessed on 14 September 2021).Open asset ↗U.S. Geological Survey Data Release · 10.5066/P9XK3867pdf-page:31 lines:1-53Code / dataset availability confirmedCrossref · checked 14 Sept 2026
The estimation of plant growth is a challenging but key issue that may help us to understand crop vs. environment interactions. To perform precise and high-throughput analysis of plant growth in field conditions, remote sensing using LiDAR and unmanned aerial vehicles (UAV) has been developed, in addition to other approaches. Although there are software tools for the processing of LiDAR data in general, there are no specialized tools for the automatic extraction of experimental field blocks with crops that represent specific “points of interest”. Our tool aims to detect precisely individual field plots, small experimental plots (in our case 10 m2) which in agricultural research represent the treatment of a single plant or one genotype in a breeding trial. Cutting out points belonging to the specific field plots allows the user to measure automatically their growth characteristics, such as plant height or plot biomass. For this purpose, new method of edge detection was combined with Fourier transformation to find individual field plots. In our case study with winter wheat, two UAV flight levels (20 and 40 m above ground) and two canopy surface modelling methods (raw points and B-spline) were tested. At a flight level of 20 m, our algorithm reached a 0.78 to 0.79 correlation with LiDAR measurement with manual validation (RMSE = 0.19) for both methods. The algorithm, in the Python 3 programming language, is designed as open-source and is freely available publicly, including the latest updates.
Why it matches plant phenotyping methodsUAV-LiDAR点群から実験区画を自動抽出し、植物高や区画バイオマスなどの生育形質を測定するPythonアルゴリズムとツールの開発・検証が中心である。
abstractOur tool aims to detect precisely individual field plots, small experimental plots (in our case 10 m2) which in agricultural research represent the treatment of a single plant or one genotype in a breeding trial.
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 · publicThis software tool is open-source and is freely available
here: https://github.com/UPOL-Plant-phenotyping-research-group/UAV-crop-analyzer,
accessed on 1 June 2021.Open asset ↗UPOL-Plant-phenotyping-research-group/UAV-crop-analyzerpdf-page:2 lines:1-59Code / dataset availability confirmedCrossref · checked 15 Sept 2026
Field / plotPhotogrammetry / SfM / MVSCalibration / preprocessing
Unmanned aerial vehicle (UAV) and structure from motion (SfM) photogrammetry techniques are widely used for field-based, high-throughput plant phenotyping nowadays, but some of the intermediate processes throughout the workflow remain manual. For example, geographic information system (GIS) software is used to manually assess the 2D/3D field reconstruction quality and cropping region of interests (ROIs) from the whole field. In addition, extracting phenotypic traits from raw UAV images is more competitive than directly from the digital orthomosaic (DOM). Currently, no easy-to-use tools are available to implement previous tasks for commonly used commercial SfM software, such as Pix4D and Agisoft Metashape. Hence, an open source software package called easy intermediate data processor (EasyIDP; MIT license) was developed to decrease the workload in intermediate data processing mentioned above. The functions of the proposed package include (1) an ROI cropping module, assisting in reconstruction quality assessment and cropping ROIs from the whole field, and (2) an ROI reversing module, projecting ROIs to relative raw images. The result showed that both cropping and reversing modules work as expected. Moreover, the effects of ROI height selection and reversed ROI position on raw images to reverse calculation were discussed. This tool shows great potential for decreasing workload in data annotation for machine learning applications.
Why it matches plant phenotyping methodsUAV植物フェノタイピングの中間データ処理を担うオープンソースPythonパッケージを開発しており、ROI抽出・逆投影などの画像解析ワークフローが中心である。
abstractThe functions of the proposed package include (1) an ROI cropping module, assisting in reconstruction quality assessment and cropping ROIs from the whole field, and (2) an ROI reversing module, projecting ROIs to relative raw images.
Reproduction assets foundThe paper's own analysis software, the EasyIDP Python package implementing the ROI cropping and reversing modules used for the UAV phenotyping measurements, is explicitly stated to be publicly downloadable under an MIT license from the authors' GitHub repository.Code · publicest
IoU Euclidean distance raw image was selected to mark the manual reference, and the
overall trend of the indicators was simply analyzed.
2.6. Implementation
The cropping and reversing modules mentioned above were implemented into a Py-
thon package called EasyIDP using the MIT license. The source code can be downloaded
from https://github.com/HowcanoeWang/EasyIDP. For specific package documentation,
please refer to https://github.com/HowcanoeWang/EasyIDP/wiki. Although the source
codes were cross-platform owing to the characteristics of the Python language, they were
programmed and tested on a Windows 10 64-bit platform and an Intel CPU with a math
kernel library (MKL). More than 8 GB ROpen asset ↗HowcanoeWang/EasyIDPpdf-raw-page:8 lines:1-38Code / dataset availability confirmedCrossref · checked 9 Sept 2026
Solving many phenotyping problems involves not only automatic detection of objects in an image, but also counting the number of parts per object. We propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster. The suggested network incorporates object detection, object resizing, and part counting as modules in a single deep network, with several variants tested. The detection module is based on a Retina-Net architecture, whereas for the counting modules, two different architectures are examined: the first based on direct regression of the predicted count, and the other on explicit parts detection and counting. The results are promising, with the mean relative deviation between estimated and visible part count in the range of 9.2% to 11.5%. Further inference of count-based yield related statistics is considered. For banana bunches, the actual banana count (including occluded bananas) is inferred from the count of visible bananas. For spikelets-per-wheat-spike, robust estimation methods are employed to get the average spikelet count across the field, which is an effective yield estimator.
Why it matches plant phenotyping methods植物器官の可視パーツ数を画像から検出・計数する深層学習手法を開発し、複数作物データセットで評価しているため、表現型取得・推定法が中心です。
abstractWe propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster.
Reproduction assets foundThe paper's grape experiments use the public Embrapa WGISD dataset, extended by the authors with berry dot annotations that they state were made publicly available as part of that dataset extension. The banana and wheat datasets (Israel Phenomics Consortium) and the authors' code/models have no stated public release,; Dataset · publicThe dot annotations were made
publicly available as part of Embrapa WGISD dataset extension.Open asset ↗Embrapa WGISDpdf-page:5 lines:1-59Code / dataset availability confirmedCrossref · Europe PMC · checked 9 Sept 2026
Nitrogen (N) is one of the key nutrients supplied in agricultural production worldwide. Over-fertilization can have negative influences on the field and the regional level (e.g., agro-ecosystems). Remote sensing of the plant N of field crops presents a valuable tool for the monitoring of N flows in agro-ecosystems. Available data for validation of satellite-based remote sensing of N is scarce. Therefore, in this study, field spectrometer measurements were used to simulate data of the Sentinel-2 (S2) satellites developed for vegetation monitoring by the ESA. The prediction performance of normalized ratio indices (NRIs), random forest regression (RFR) and Gaussian processes regression (GPR) for plant-N-related traits was assessed on a diverse real-world dataset including multiple crops, field sites and years. The plant N traits included the mass-based N measure, N concentration in the biomass (Nconc), and an area-based N measure approximating the plant N uptake (NUP). Spectral indices such as normalized ratio indices (NRIs) performed well, but the RFR and GPR methods outperformed the NRIs. Key spectral bands for each trait were identified using the RFR variable importance measure and the Gaussian processes regression band analysis tool (GPR-BAT), highlighting the importance of the short-wave infrared (SWIR) region for estimation of plant Nconc—and to a lesser extent the NUP. The red edge (RE) region was also important. The GPR-BAT showed that five bands were sufficient for plant N trait and leaf area index (LAI) estimation and that a surplus of bands effectively reduced prediction performance. A global sensitivity analysis (GSA) was performed on all traits simultaneously, showing the dominance of the LAI in the mixed remote sensing signal. To delineate the plant-N-related traits from this signal, regional and/or national data collection campaigns producing large crop spectral libraries (CSL) are needed. An improved database will likely enable the mapping of N at the agro-ecosystem level or for use in precision farming by farmers in the future.
Why it matches plant phenotyping methods圃場分光データとSentinel-2模擬データを用いて、植物体N関連形質を推定する手法を比較・評価しており、形質取得・推定手法が研究の中心である。
abstractTherefore, in this study, field spectrometer measurements were used to simulate data of the Sentinel-2 (S2) satellites developed for vegetation monitoring by the ESA.
Reproduction assets foundThe authors state the field-spectrometer spectral library and plant trait measurements (N conc, Chl AB, LAI, LAI-scaled traits) used in this study are openly available via an ETH research collection DOI, which is an allowed URL. This is a paper-specific, public, actionable phenotype/spectral dataset.Dataset · publicThe data presented in this study are openly available in: https://doi.org/10.3929/ethz-b-000488405 . Please also see the ‘ supplementary materials – dataset ’ for more information on the dataset.Open asset ↗ethz-b-000488405 · 10.3929/ethz-b-000488405lines:301-314Code / dataset availability confirmedOpenAlex · Crossref · checked 14 Sept 2026
Unoccupied aerial system (UAS; i.e., drone equipped with sensors) field-based high-throughput phenotyping (HTP) platforms are used to collect high quality images of plant nurseries to screen genetic materials (e.g., hybrids and inbreds) throughout plant growth at relatively low cost. In this study, a set of 100 advanced breeding maize (Zea mays L.) hybrids were planted at optimal (OHOT trial) and delayed planting dates (DHOT trial). Twelve UAS surveys were conducted over the trials throughout the growing season. Fifteen vegetative indices (VIs) and the 99th percentile canopy height measurement (CHMs) were extracted from processed UAS imagery (orthomosaics and point clouds) which were used to predict plot-level grain yield, days to anthesis (DTA), and silking (DTS). A novel statistical approach utilizing a nested design was fit to predict temporal best linear unbiased predictors (TBLUP) for the combined temporal UAS data. Our results demonstrated machine learning-based regressions (ridge, lasso, and elastic net) had from 4- to 9-fold increases in the prediction accuracies and from 13- to 73-fold reductions in root mean squared error (RMSE) compared to classical linear regression in prediction of grain yield or flowering time. Ridge regression performed best in predicting grain yield (prediction accuracy = ~0.6), while lasso and elastic net regressions performed best in predicting DTA and DTS (prediction accuracy = ~0.8) consistently in both trials. We demonstrated that predictor variable importance descended towards the terminal stages of growth, signifying the importance of phenotype collection beyond classical terminal growth stages. This study is among the first to demonstrate an ability to predict yield in elite hybrid maize breeding trials using temporal UAS image-based phenotypes and supports the potential benefit of phenomic selection approaches in estimating breeding values before harvest.
Why it matches plant phenotyping methodsUAS画像から植生指数と草冠高を抽出し、機械学習で収量・開花期を推定する高スループット表現型解析が研究の中心です。
abstractUnoccupied aerial system (UAS; i.e., drone equipped with sensors) field-based high-throughput phenotyping (HTP) platforms are used to collect high quality images of plant nurseries to screen genetic materials
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 · publicand PLSR regression. All R codes are available in Github repository (https://github.com/Open asset ↗pdf-page:8 lines:1-175Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Estimation of urban tree canopy parameters plays a crucial role in urban forest management. Unmanned aerial vehicles (UAV) have been widely used for many applications particularly forestry mapping. UAV-derived images, captured by an onboard camera, provide a means to produce 3D point clouds using photogrammetric mapping. Similarly, small UAV mounted light detection and ranging (LiDAR) sensors can also provide very dense 3D point clouds. While point clouds derived from both photogrammetric and LiDAR sensors can allow the accurate estimation of critical tree canopy parameters, so far a comparison of both techniques is missing. Point clouds derived from these sources vary according to differences in data collection and processing, a detailed comparison of point clouds in terms of accuracy and completeness, in relation to tree canopy parameters using point clouds is necessary. In this research, point clouds produced by UAV-photogrammetry and -LiDAR over an urban park along with the estimated tree canopy parameters are compared, and results are presented. The results show that UAV-photogrammetry and -LiDAR point clouds are highly correlated with R2 of 99.54% and the estimated tree canopy parameters are correlated with R2 of higher than 95%.
Why it matches plant phenotyping methodsUAVフォトグラメトリとLiDARによる樹冠パラメータ推定を比較・精度評価しており、植物形態形質の取得手法が研究の中心である。
abstracta detailed comparison of point clouds in terms of accuracy and completeness, in relation to tree canopy parameters using point clouds is necessary
Reproduction assets foundThe authors state that the UAV-LiDAR and photogrammetric point clouds used for tree canopy parameter estimation are freely available as Supplementary Materials via an MDPI link, making the paper's core phenotyping sensor data (3D point clouds) publicly accessible.Dataset · publicThe LiDAR and photogrammetric point clouds used in this research
are freely available (https://susy.mdpi.com/user/manuscripts/displayFile/d71a32682356d1cece4c0Open asset ↗pdf-page:14 lines:1-60Code / dataset availability confirmedOpenAlex · checked 8 Sept 2026
Unmanned aerial vehicles (UAV) carrying multispectral cameras are increasingly being used for high-throughput phenotyping (HTP) of above-ground traits of crops to study genetic diversity, resource use efficiency and responses to abiotic or biotic stresses. There is significant unexplored potential for repeated data collection through a field season to reveal information on the rates of growth and provide predictions of the final yield. Generating such information early in the season would create opportunities for more efficient in-depth phenotyping and germplasm selection. This study tested the use of high-resolution time-series imagery (5 or 10 sampling dates) to understand the relationships between growth dynamics, temporal resolution and end-of-season above-ground biomass (AGB) in 869 diverse accessions of highly productive (mean AGB = 23.4 Mg/Ha), photoperiod sensitive sorghum. Canopy surface height (CSM), ground cover (GC), and five common spectral indices were considered as features of the crop phenotype. Spline curve fitting was used to integrate data from single flights into continuous time courses. Random Forest was used to predict end-of-season AGB from aerial imagery, and to identify the most informative variables driving predictions. Improved prediction of end-of-season AGB (RMSE reduction of 0.24 Mg/Ha) was achieved earlier in the growing season (10 to 20 days) by leveraging early- and mid-season measurement of the rate of change of geometric and spectral features. Early in the season, dynamic traits describing the rates of change of CSM and GC predicted end-of-season AGB best. Late in the season, CSM on a given date was the most influential predictor of end-of-season AGB. The power to predict end-of-season AGB was greatest at 50 days after planting, accounting for 63% of variance across this very diverse germplasm collection with modest error (RMSE 1.8 Mg/ha). End-of-season AGB could be predicted equally well when spline fitting was performed on data collected from five flights versus 10 flights over the growing season. This demonstrates a more valuable and efficient approach to using UAVs for HTP, while also proposing strategies to add further value.
Why it matches plant phenotyping methodsUAV時系列画像から作物形質を抽出し、成長動態と収穫期バイオマスを予測するHTP手法を、サンプリング頻度や予測性能とともに技術的に評価しており、フェノタイピング手法が中心である。
abstractUnmanned aerial vehicles (UAV) carrying multispectral cameras are increasingly being used for high-throughput phenotyping (HTP) of above-ground traits of crops
Reproduction assets foundThe paper's UAV-derived sorghum phenotyping datasets (imagery features, AGB measurements) are deposited in the Illinois Databank with a public DOI listed in the Data Availability Statement. No author analysis code or trained models are explicitly shared.Dataset · publicData Availability Statement: The datasets used and analyzed during the current study are available
from the corresponding author via Illinois Databank at https://doi.org/10.13012/B2IDB-5649852_V2.Open asset ↗Illinois Databank · B2IDB-5649852_V2pdf-page:14 lines:1-59Code / dataset availability confirmedCrossref · checked 14 Sept 2026
Crop yield estimation is a major issue of crop monitoring which remains particularly challenging in developing countries due to the problem of timely and adequate data availability. Whereas traditional agricultural systems mainly rely on scarce ground-survey data, freely available multi-temporal and multi-spectral remote sensing images are excellent tools to support these vulnerable systems by accurately monitoring and estimating crop yields before harvest. In this context, we introduce the use of Sentinel-2 (S2) imagery, with a medium spatial, spectral and temporal resolutions, to estimate rice crop yields in Nepal as a case study. Firstly, we build a new large-scale rice crop database (RicePAL) composed by multi-temporal S2 and climate/soil data from the Terai districts of Nepal. Secondly, we propose a novel 3D Convolutional Neural Network (CNN) adapted to these intrinsic data constraints for the accurate rice crop yield estimation. Thirdly, we study the effect of considering different temporal, climate and soil data configurations in terms of the performance achieved by the proposed approach and several state-of-the-art regression and CNN-based yield estimation methods. The extensive experiments conducted in this work demonstrate the suitability of the proposed CNN-based framework for rice crop yield estimation in the developing country of Nepal using S2 data.
Why it matches plant phenotyping methods米収量という植物・作物群の形質を対象に、Sentinel-2データ用の3D CNNを開発し、データベース構築と既存手法との性能比較・検証を行っており、収量推定手法が中心である。
abstractwe build a new large-scale rice crop database (RicePAL) composed by multi-temporal S2 and climate/soil data
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 · publicData Availability Statement: The codes related to this work will be released for reproducible research
at https://github.com/rufernan/RicePAL (accessed on 3 April 2021).Open asset ↗rufernan/RicePALpdf-page:23 lines:1-60Code / dataset availability confirmedOpenAlex · Crossref · checked 15 Sept 2026
Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high-performance end-to-end machine learning pipelines with minimal effort from the user. However, despite AutoML showing great promise for computer vision tasks, to the best of our knowledge, no study has used AutoML for image-based plant phenotyping. To address this gap in knowledge, we examined the application of AutoML for image-based plant phenotyping using wheat lodging assessment with unmanned aerial vehicle (UAV) imagery as an example. The performance of an open-source AutoML framework, AutoKeras, in image classification and regression tasks was compared to transfer learning using modern convolutional neural network (CNN) architectures. For image classification, which classified plot images as lodged or non-lodged, transfer learning with Xception and DenseNet-201 achieved the best classification accuracy of 93.2%, whereas AutoKeras had a 92.4% accuracy. For image regression, which predicted lodging scores from plot images, transfer learning with DenseNet-201 had the best performance (R2 = 0.8303, root mean-squared error (RMSE) = 9.55, mean absolute error (MAE) = 7.03, mean absolute percentage error (MAPE) = 12.54%), followed closely by AutoKeras (R2 = 0.8273, RMSE = 10.65, MAE = 8.24, MAPE = 13.87%). In both tasks, AutoKeras models had up to 40-fold faster inference times compared to the pretrained CNNs. AutoML has significant potential to enhance plant phenotyping capabilities applicable in crop breeding and precision agriculture.
Why it matches plant phenotyping methodsAutoMLと画像解析を用いた植物表現型測定手法を、コムギ倒伏評価で比較・検証しており、表現型取得・推定手法が研究の中心である。
titleAutomated Machine Learning for High-Throughput Image-Based Plant Phenotyping
Reproduction assets foundThe paper's Data Availability Statement points to a public GitHub repository containing the authors' source code to replicate the AutoML/transfer-learning phenotyping analyses and the best AutoKeras models. A Zenodo deposit with the wheat plot images and lodging ground-truth CSV is also referenced, but no Zenodo URL isCode · publicSource codes required to replicate the analyses in this article
and the best performing models reported for AutoKeras are provided in a GitHub repository [58].Open asset ↗pdf-raw-page:16 lines:1-53Code / dataset availability confirmedOpenAlex · Crossref · checked 13 Sept 2026
As a key canopy structure parameter, the estimation method of the Leaf Area Index (LAI) has always attracted attention. To explore a potential method to estimate forest LAI from 3D point cloud at low cost, we took photos from different angles of the drone and set five schemes (O (0°), T15 (15°), T30 (30°), OT15 (0° and 15°) and OT30 (0° and 30°)), which were used to reconstruct 3D point cloud of forest canopy based on photogrammetry. Subsequently, the LAI values and the leaf area distribution in the vertical direction derived from five schemes were calculated based on the voxelized model. Our results show that the serious lack of leaf area in the middle and lower layers determines that the LAI estimate of O is inaccurate. For oblique photogrammetry, schemes with 30° photos always provided better LAI estimates than schemes with 15° photos (T30 better than T15, OT30 better than OT15), mainly reflected in the lower part of the canopy, which is particularly obvious in low-LAI areas. The overall structure of the single-tilt angle scheme (T15, T30) was relatively complete, but the rough point cloud details could not reflect the actual situation of LAI well. Multi-angle schemes (OT15, OT30) provided excellent leaf area estimation (OT15: R2 = 0.8225, RMSE = 0.3334 m2/m2; OT30: R2 = 0.9119, RMSE = 0.1790 m2/m2). OT30 provided the best LAI estimation accuracy at a sub-voxel size of 0.09 m and the best checkpoint accuracy (OT30: RMSE [H] = 0.2917 m, RMSE [V] = 0.1797 m). The results highlight that coupling oblique photography and nadiral photography can be an effective solution to estimate forest LAI.
Why it matches plant phenotyping methodsUAV斜め写真測量と3D点群・ボクセル解析を用いて森林キャノピーのLAIを推定する手法を開発・比較検証しており、植物形態形質の取得方法が研究の中心である。
abstractTo explore a potential method to estimate forest LAI from 3D point cloud at low cost, we took photos from different angles of the drone and set five schemes
Reproduction assets foundThe paper's authors publicly released the voxelization/LAI extraction code on GitHub; phenotype data (UAV images, point clouds, LAI-2200 measurements) are only available upon request.Code · publicData Availability Statement: The source codes developed in this study were donated to GitHub
(https://github.com/TOTOROLLC/Forest‐Stand‐LAI‐Remote‐Sensing‐Retrieval‐Based‐on‐Photo‐
grammetry (accessed on 7 January 2021)). And the data used to support the findings of this study
are available from the corresponding author upon request.Open asset ↗https://github.com/TOTOROLLC/Forest‐Stand‐LAI‐Remote‐Sensing‐Retrieval‐Based‐on‐Photo‐pdf-page:15 lines:1-59Code / 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 confirmedCrossref · checked 13 Sept 2026
Accurate and continuous monitoring of leaf area index (LAI), a widely-used vegetation structural parameter, is crucial to characterize crop growth conditions and forecast crop yield. Meanwhile, advancements in collecting field LAI measurements have provided strong support for validating remote-sensing-derived LAI. This paper evaluates the performance of LAI retrieval from multi-source, remotely sensed data through comparisons with continuous field LAI measurements. Firstly, field LAI was measured continuously over periods of time in 2018 and 2019 using LAINet, a continuous LAI measurement system deployed using wireless sensor network (WSN) technology, over an agricultural region located at the Heihe watershed at northwestern China. Then, cloud-free images from optical satellite sensors, including Landsat 7 the Enhanced Thematic Mapper Plus (ETM+), Landsat 8 the Operational Land Imager (OLI), and Sentinel-2A/B Multispectral Instrument (MSI), were collected to derive LAI through inversion of the PROSAIL radiation transfer model using a look-up-table (LUT) approach. Finally, field LAI data were used to validate the multi-temporal LAI retrieved from remote-sensing data acquired by different satellite sensors. The results indicate that good accuracy was obtained using different inversion strategies for each sensor, while Green Chlorophyll Index (CIgreen) and a combination of three red-edge bands perform better for Landsat 7/8 and Sentinel-2 LAI inversion, respectively. Furthermore, the estimated LAI has good consistency with in situ measurements at vegetative stage (coefficient of determination R2 = 0.74, and root mean square error RMSE = 0.53 m2 m−2). At the reproductive stage, a significant underestimation was found (R2 = 0.41, and 0.89 m2 m−2 in terms of RMSE). This study suggests that time-series LAI can be retrieved from multi-source satellite data through model inversion, and the LAINet instrument could be used as a low-cost tool to provide continuous field LAI measurements to support LAI retrieval.
Why it matches plant phenotyping methodsLAIの連続測定システムと衛星画像によるLAI推定を構築し、実測値との比較で性能検証しており、植物形質取得法が中心である。
abstractfield LAI was measured continuously over periods of time in 2018 and 2019 using LAINet, a continuous LAI measurement system deployed using wireless sensor network (WSN) technology
Reproduction assets foundThe paper's continuous field LAI measurements (LAINet WSN datasets for 2018 and 2019 corn plots at the Heihe watershed) were explicitly released publicly via the National Science & Technology Infrastructure at the National Tibetan Plateau Data Center. Satellite imagery (Landsat/Sentinel-2) came from generic public USGSDataset · publicThe LAINet datasets of both years
have been released publicly via the National Science & Technology Infrastructure
(http://www.tpdc.ac.cn/zh-hans/, in Chinese).Open asset ↗National Science & Technology Infrastructurepdf-page:4 lines:1-54Code / dataset availability confirmedCrossref · checked 9 Sept 2026
In the headwater catchments of the Rocky Mountains, plant productivity and its dynamics are largely dependent upon water availability, which is influenced by changing snowmelt dynamics associated with climate change. Understanding and quantifying the interactions between snow, plants and soil moisture is challenging, since these interactions are highly heterogeneous in mountainous terrain, particularly as they are influenced by microtopography within a hillslope. Recent advances in satellite remote sensing have created an opportunity for monitoring snow and plant dynamics at high spatiotemporal resolutions that can capture microtopographic effects. In this study, we investigate the relationships among topography, snowmelt, soil moisture and plant dynamics in the East River watershed, Crested Butte, Colorado, based on a time series of 3-meter resolution PlanetScope normalized difference vegetation index (NDVI) images. To make use of a large volume of high-resolution time-lapse images (17 images total), we use unsupervised machine learning methods to reduce the dimensionality of the time lapse images by identifying spatial zones that have characteristic NDVI time series. We hypothesize that each zone represents a set of similar snowmelt and plant dynamics that differ from other identified zones and that these zones are associated with key topographic features, plant species and soil moisture. We compare different distance measures (Ward and complete linkage) to understand the effects of their influence on the zonation map. Results show that the identified zones are associated with particular microtopographic features; highly productive zones are associated with low slopes and high topographic wetness index, in contrast with zones of low productivity, which are associated with high slopes and low topographic wetness index. The zones also correspond to particular plant species distributions; higher forb coverage is associated with zones characterized by higher peak productivity combined with rapid senescence in low moisture conditions, while higher sagebrush coverage is associated with low productivity and similar senescence patterns between high and low moisture conditions. In addition, soil moisture probe and sensor data confirm that each zone has a unique soil moisture distribution. This cluster-based analysis can tractably analyze high-resolution time-lapse images to examine plant-soil-snow interactions, guide sampling and sensor placements and identify areas likely vulnerable to ecological change in the future.
Why it matches plant phenotyping methods高解像度NDVI時系列から植物の生産性・季節動態を抽出し、教師なしクラスタリングと距離尺度比較で空間ゾーニングする解析手法が研究の中心であるため、植物状態の計測・推定を伴う実質的な方法適用と判断する。
abstractwe use unsupervised machine learning methods to reduce the dimensionality of the time lapse images by identifying spatial zones that have characteristic NDVI time series.
Reproduction assets foundThe paper's supplementary materials, explicitly hosted at the MDPI supplementary URL, contain the paper-specific phenotyping assets: true-color and NDVI/snow-classified PlanetScope satellite imagery for all dates used, soil moisture sensor time series by zone, and the PlanetScope image IDs. No author analysis code is公开Dataset · publicSupplementary Materials: The following are available online at http://www.mdpi.com/2072-4292/12/17/2733/s1,
Figure S1: True color satellite imagery of scenes from all dates used in this study, Figure S2: NDVI and snow
classification of satellite imagery from all dates used in this study, Figure S3a,b: Time series of soil volumetric
water content from hourly sensor measurements by zone for 1 June–10 August 2017 and 2018, Table S1: Image IDs
for PlanetScope satellite imagery used in this studyOpen asset ↗mdpi.compdf-page:17 lines:1-56Code / dataset availability confirmedCrossref · checked 9 Sept 2026
Aerial imagery has the potential to advance high-throughput phenotyping for agricultural field experiments. This potential is currently limited by the difficulties of identifying pixels of interest (POI) and performing plot segmentation due to the required intensive manual operations. We developed a Python package, GRID (GReenfield Image Decoder), to overcome this limitation. With pixel-wise K-means cluster analysis, users can specify the number of clusters and choose the clusters representing POI. The plot grid patterns are automatically recognized by the POI distribution. The local optima of POI are initialized as the plot centers, which can also be manually modified for deletion, addition, or relocation. The segmentation of POI around the plot centers is initialized by automated, intelligent agents to define plot boundaries. A plot intelligent agent negotiates with neighboring agents based on plot size and POI distributions. The negotiation can be refined by weighting more on either plot size or POI density. All adjustments are operated in a graphical user interface with real-time previews of outcomes so that users can refine segmentation results based on their knowledge of the fields. The final results are saved in text and image files. The text files include plot rows and columns, plot size, and total plot POI. The image files include displays of clusters, POI, and segmented plots. With GRID, users are completely liberated from the labor-intensive task of manually drawing plot lines or polygons. The supervised automation with GRID is expected to enhance the efficiency of agricultural field experiments.
Why it matches plant phenotyping methods圃場航空画像から試験区を自動分割し、POIや区画サイズを抽出するPythonパッケージを開発した研究で、表現型取得ワークフローが中心である。
abstractWe developed a Python package, GRID (GReenfield Image Decoder), to overcome this limitation.
Reproduction assets foundThe authors explicitly state that the GRID executable, user manual, tutorials, and example datasets are freely available at http://zzlab.net/GRID, and that GRID is released as open-source software on GitHub at https://github.com/Poissonfish/photo_grid. These are paper-specific assets: the GRID package is the authors'分析Code · publicGRID is released as an open-source software on GitHub:
https://github.com/Poissonfish/photo_grid.Open asset ↗Poissonfish/photo_grid · Poissonfish/photo_gridpdf-page:14 lines:1-45Dataset · publicThe GRID executable file, user manual, tutorials, and example datasets are
freely available at GRID website (http://zzlab.net/GRID).Open asset ↗pdf-page:14 lines:1-45Code / dataset availability confirmedOpenAlex · checked 15 Sept 2026
Crop leaf purpling is a common phenotypic change when plants are subject to some biotic and abiotic stresses during their growth. The extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation. Due to the complexity of the field environment as well as differences in size, shape, texture, and color gradation among the leaves, purple leaf segmentation is difficult. In this study, we used a U-Net model for segmenting purple rapeseed leaves during the seedling stage based on unmanned aerial vehicle (UAV) RGB imagery at the pixel level. With the limited spatial resolution of rapeseed images acquired by UAV and small object size, the input patch size was carefully selected. Experiments showed that the U-Net model with the patch size of 256 × 256 pixels obtained better and more stable results with a F-measure of 90.29% and an Intersection of Union (IoU) of 82.41%. To further explore the influence of image spatial resolution, we evaluated the performance of the U-Net model with different image resolutions and patch sizes. The U-Net model performed better compared with four other commonly used image segmentation approaches comprising support vector machine, random forest, HSeg, and SegNet. Moreover, regression analysis was performed between the purple rapeseed leaf ratios and the measured N content. The negative exponential model had a coefficient of determination (R²) of 0.858, thereby explaining much of the rapeseed leaf purpling in this study. This purple leaf phenotype could be an auxiliary means for monitoring crop growth status so that crops could be managed in a timely and effective manner when nitrogen stress occurs. Results demonstrate that the U-Net model is a robust method for purple rapeseed leaf segmentation and that the accurate segmentation of purple leaves provides a new method for crop nitrogen stress monitoring.
Why it matches plant phenotyping methodsUAV画像から紫色葉という植物ストレス表現型を抽出するセグメンテーション手法の開発・比較が中心であり、植物フェノタイピング方法論に該当する。
abstractThe extraction of purple leaves can monitor crop stresses as an apparent trait and meanwhile contributes to crop phenotype analysis, monitoring, and yield estimation.
Reproduction assets foundThe paper's Data Availability statement links a public figshare deposit containing the rapeseed UAV image/segmentation datasets used in this study. No author code or trained model deposit is stated.Dataset · publicadded,
and purple leaf area will be assessed as a visual trait to find the optimal nitrogen threshold for
balancing crop yield and environmental impact. Moreover, other crops and stress types (e.g., water
stress) will be studied based on purple leaves.
Data Availability: The rapeseed datasets of this experience are available at
https://figshare.com/s/e7471d81a1e35d5ab0d1
Author Contributions: All authors have read and agreed to the published version of the manuscript. J.Z. and
T.X. designed the method, conducted the experiment, analyzed the data, discussed the results, and wrote the
majority of the manuscript. C.Y. guided the study design, advised on data analysis, and revised the manuscriptOpen asset ↗figsharepdf-raw-page:13 lines:1-34Code / dataset availability confirmedOpenAlex · checked 9 Sept 2026
For decades, significant effort has been put into the development of plant detection and classification algorithms. However, it has been difficult to compare the performance of the different algorithms, due to the lack of a common testbed, such as a public available annotated reference dataset. In this paper, we present the Open Plant Phenotype Database (OPPD), a public dataset for plant detection and plant classification. The dataset contains 7590 RGB images of 47 plant species. Each species is cultivated under three different growth conditions, to provide a high degree of diversity in terms of visual appearance. The images are collected at the semifield area at Aarhus University, Research Centre Flakkebjerg, Denmark, using a customized data acquisition platform that provides well-illuminated images with a ground resolution of ∼6.6 px mm − 1 . All images are annotated with plant species using the EPPO encoding system, bounding box annotations for detection and extraction of individual plants, applied growth conditions and time passed since seeding. Additionally, the individual plants have been tracked temporally and given unique IDs. The dataset is accompanied by two experiments for: (1) plant instance detection and (2) plant species classification. The experiments introduce evaluation metrics and methods for the two tasks and provide baselines for future work on the data.
Why it matches plant phenotyping methods植物の検出・分類アルゴリズム評価用の公開画像データセットを構築し、データ取得プラットフォーム、アノテーション、評価実験とベースラインを提示しており、植物フェノタイピング手法の基盤が中心である。
abstractIn this paper, we present the Open Plant Phenotype Database (OPPD), a public dataset for plant detection and plant classification.
Reproduction assets foundThe paper's own Open Plant Phenotype Database (OPPD) — 7590 annotated RGB plant images with bounding boxes, EPPO species labels, growth conditions, and temporal plant IDs — is explicitly stated to be publicly available at the authors' Aarhus University site.Dataset · publicThe full dataset are available at: https://vision.eng.au.dk/open-plant-phenotyping-database/.Open asset ↗pdf-page:2 lines:1-54Code / dataset availability confirmedCrossref · OpenAlex · checked 15 Sept 2026
Plant disease poses a serious threat to global food security. Accurate, high-throughput methods of quantifying disease are needed by breeders to better develop resistant plant varieties and by researchers to better understand the mechanisms of plant resistance and pathogen virulence. Northern leaf blight (NLB) is a serious disease affecting maize and is responsible for significant yield losses. A Mask R-CNN model was trained to segment NLB disease lesions in unmanned aerial vehicle (UAV) images. The trained model was able to accurately detect and segment individual lesions in a hold-out test set. The mean intersect over union (IOU) between the ground truth and predicted lesions was 0.73, with an average precision of 0.96 at an IOU threshold of 0.50. Over a range of IOU thresholds (0.50 to 0.95), the average precision was 0.61. This work demonstrates the potential for combining UAV technology with a deep learning-based approach for instance segmentation to provide accurate, high-throughput quantitative measures of plant disease.
Why it matches plant phenotyping methodsUAV画像とMask R-CNNを用いてトウモロコシ葉枯病病斑を高スループットに定量する手法の開発・性能評価が中心であり、植物病害状態の表現型取得に該当する。
abstractA Mask R-CNN model was trained to segment NLB disease lesions in unmanned aerial vehicle (UAV) images.
Reproduction assets foundThe paper publicly releases its paper-specific assets: the annotated UAV image dataset (File S2) on CyVerse Data Commons, the ImageJ polygon annotation macro (File S1) and the Mask R-CNN training/validation code (File S3) in the authors' GoreLab GitHub repository. The matterport/Mask_RCNN dependency is a generic third‑Dataset · publicry Materials: The following are available online at www.mdpi.com/xxx/s1. File S1: ImageJ macro
used to create lesion polygon annotations. https://github.com/GoreLab/NLB_Mask-RCNN/tree/master/annotation_macro/NLB_polygon_annotation_macro.txt. File S2: Annotated image dataset used for training and
validating the Mask R-CNN model. http://datacommons.cyverse.org/browse/iplant/home/shared/GoreLab/dataFromPubs/Stewart_NLBimages_2019. File S3: Code used to train and validate the Mask R-CNN model.
https://github.com/GoreLab/NLB_Mask-RCNN.Author Contributions: Conceptualization, E.L.S. and M.A.G.; methodology, E.L.S.; formal analysis, E.L.S.;
investigation, E.L.S., T.W.-H., N.K.; resources, M.A.G., ROpen asset ↗GoreLab/dataFromPubs/Stewart_NLBimages_2019 · Stewart_NLBimages_2019pdf-raw-page:7 lines:1-19Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Retrieval of Sun-Induced Chlorophyll Fluorescence (F) spectrum is one of the challenging perspectives for further advancing F studies towards a better characterization of vegetation structure and functioning. In this study, a simplified Spectral Fitting retrieval algorithm suitable for retrieving the F spectrum with a limited number of parameters is proposed (two parameters for F). The novel algorithm is developed and tested on a set of radiative transfer simulations obtained by coupling SCOPE and MODTRAN5 codes, considering different chlorophyll content, leaf area index and noise levels to produce a large variability in fluorescence and reflectance spectra. The retrieval accuracy is quantified based on several metrics derived from the F spectrum (i.e., red and far-red peaks, O2 bands and spectrally-integrated values). Further, the algorithm is employed to process experimental field spectroscopy measurements collected over different crops during a long-lasting field campaign. The reliability of the retrieval algorithm on experimental measurements is evaluated by cross-comparison with F values computed by an independent retrieval method (i.e., SFM at O2 bands). For the first time, the evolution of the F spectrum along the entire growing season for a forage crop is analyzed and three diverse F spectra are identified at different growing stages. The results show that red F is larger for young canopy; while red and far-red F have similar intensity in an intermediate stage; finally, far-red F is significantly larger for the rest of the season.
Why it matches plant phenotyping methods作物群落の蛍光スペクトルから植物の生理状態を推定する検索アルゴリズムを開発し、シミュレーションと圃場分光測定で精度・信頼性を検証しているため、植物フェノタイピング手法が中心です。
abstracta simplified Spectral Fitting retrieval algorithm suitable for retrieving the F spectrum with a limited number of parameters is proposed
Reproduction assets foundThe paper's spectral fitting (SpecFit) retrieval algorithm is the core computational analysis of this study, and the authors explicitly state its Matlab source code is publicly available via a GitLab repository. No phenotype datasets or field measurement data are stated as publicly deposited.Code · publicThe Matlab source code of the present algorithm is available for
download through the git repository https://gitlab.com/ltda/flox-specfit.Open asset ↗gitlab.com/ltda/flox-specfitpdf-page:6 lines:1-108Code / dataset availability confirmedOpenAlex · checked 13 Sept 2026
Forest structure is a crucial component in the assessment of whether a forest is likely to act as a carbon sink under changing climate. Detailed 3D structural information about the tundra–taiga ecotone of Siberia is mostly missing and still underrepresented in current research due to the remoteness and restricted accessibility. Field based, high-resolution remote sensing can provide important knowledge for the understanding of vegetation properties and dynamics. In this study, we test the applicability of consumer-grade Unmanned Aerial Vehicles (UAVs) for rapid calculation of stand metrics in treeline forests. We reconstructed high-resolution photogrammetric point clouds and derived canopy height models for 10 study sites from NE Chukotka and SW Yakutia. Subsequently, we detected individual tree tops using a variable-window size local maximum filter and applied a marker-controlled watershed segmentation for the delineation of tree crowns. With this, we successfully detected 67.1% of the validation individuals. Simple linear regressions of observed and detected metrics show a better correlation (R2) and lower relative root mean square percentage error (RMSE%) for tree heights (mean R2 = 0.77, mean RMSE% = 18.46%) than for crown diameters (mean R2 = 0.46, mean RMSE% = 24.9%). The comparison between detected and observed tree height distributions revealed that our tree detection method was unable to representatively identify trees 15–20 m to capture homogeneous and representative forest stands. Additionally, we identify sources of omission and commission errors and give recommendations for their mitigation. In summary, the efficiency of the used method depends on the complexity of the forest’s stand structure.
Why it matches plant phenotyping methodsUAV画像から点群・樹冠高モデルを生成し、個体樹頂検出と樹冠分割によって樹高・樹冠径を推定する手法を開発・検証しており、植物形質取得が研究の中心である。
abstractWe reconstructed high-resolution photogrammetric point clouds and derived canopy height models for 10 study sites from NE Chukotka and SW Yakutia.
Reproduction assets foundThe paper's pre-processed photogrammetric point clouds used to derive forest metrics are publicly deposited in PANGAEA (doi:10.1594/PANGAEA.902259). Other URLs (Pix4D, R packages) are generic third-party tools, not paper-specific assets.Dataset · publicWe successfully detected a total of 4719 trees and derived individual tree, stand structure, and site
morphological metrics from 10 photogrammetric point clouds (Table 3; pre-processed point clouds are
available for download at https://doi.org/10.1594/PANGAEA.902259).Open asset ↗PANGAEA · 10.1594/PANGAEA.902259pdf-page:8 lines:1-56Code / 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 confirmedCrossref · Europe PMC · checked 15 Sept 2026
Plant height is a morphological characteristic of plant growth that is a useful indicator of plant stress resulting from water and nutrient deficit. While height is a relatively simple trait, it can be difficult to measure accurately, especially in crops with complex canopy architectures like cotton. This paper describes the deployment of four nadir view ultrasonic transducers (UTs), two light detection and ranging (LiDAR) systems, and an unmanned aerial system (UAS) with a digital color camera to characterize plant height in an upland cotton breeding trial. The comparison of the UTs with manual measurements demonstrated that the Honeywell and Pepperl+Fuchs sensors provided more precise estimates of plant height than the MaxSonar and db3 Pulsar sensors. Performance of the multi-angle view LiDAR and UAS technologies demonstrated that the UAS derived 3-D point clouds had stronger correlations (0.980) with the UTs than the proximal LiDAR sensors. As manual measurements require increased time and labor in large breeding trials and are prone to human error reducing repeatability, UT and UAS technologies are an efficient and effective means of characterizing cotton plant height.
Why it matches plant phenotyping methods綿花の草丈という植物形質を対象に、複数のセンサーとUASを比較・検証しており、取得手法の技術性能評価が研究の中心である。
abstractThis paper describes the deployment of four nadir view ultrasonic transducers (UTs), two light detection and ranging (LiDAR) systems, and an unmanned aerial system (UAS) with a digital color camera to characterize plant height in an upland cotton breeding trial.
Reproduction assets foundThe paper's supplementary materials, hosted publicly on MDPI, contain paper-specific plant-phenotyping results: growth curves for 2016 and 2017, plant height means and standard deviations, and repeatability estimates with standard errors. No author analysis code, raw sensor data, or UAS imagery is stated to be publiclySupplement · publicAS-based images were also found to be an effective way
to measure plant height. The LiDAR sensors explored in this study were found to be less effective
and efficient overall but may have more intrinsic value for more complex traits such as leaf and
branching angle.
Supplementary Materials: The following are available online at http://www.mdpi.com/2072-4292/11/6/700/s1,
Figure S1: Growth curves 2016, Figure S2: Growth curves 2017, Table S1: Plant height means and standard
deviations, Table S2: Repeatability and standard error.
Author Contributions: A.T., K.T., D.P., and P.A.-S. conceived of the project and its components. A.T., M.C., and
D.M.E. performed data collections along with acknowledOpen asset ↗pdf-raw-page:17 lines:1-49Code / dataset availability confirmedOpenAlex · checked 14 Sept 2026
In the value chain, yields are key information for both growers and other stakeholders in market supply and exports. However, orchard yields are often still based on an extrapolation of tree production which is visually assessed on a limited number of trees; a tedious and inaccurate task that gives no yield information at a finer scale than the orchard plot. In this work, we propose a method to accurately map individual tree production at the orchard scale by developing a trade-off methodology between mechanistic yield modelling and extensive fruit counting using machine vision systems. A methodological toolbox was developed and tested to estimate and map tree species, structure, and yields in mango orchards of various cropping systems (from monocultivar to plurispecific orchards) in the Niayes region, West Senegal. Tree structure parameters (height, crown area and volume), species, and mango cultivars were measured using unmanned aerial vehicle (UAV) photogrammetry and geographic, object-based image analysis. This procedure reached an average overall accuracy of 0.89 for classifying tree species and mango cultivars. Tree structure parameters combined with a fruit load index, which takes into account year and management effects, were implemented in predictive production models of three mango cultivars. Models reached satisfying accuracies with R2 greater than 0.77 and RMSE% ranging from 20% to 29% when evaluated with the measured production of 60 validation trees. In 2017, this methodology was applied to 15 orchards overflown by UAV, and estimated yields were compared to those measured by the growers for six of them, showing the proper efficiency of our technology. The proposed method achieved the breakthrough of rapidly and precisely mapping mango yields without detecting fruits from ground imagery, but rather, by linking yields with tree structural parameters. Such a tool will provide growers with accurate yield estimations at the orchard scale, and will permit them to study the parameters that drive yield heterogeneity within and between orchards.
Why it matches plant phenotyping methodsUAVフォトグラメトリと画像解析により樹体構造・品種・個体収量を推定・地図化する手法を開発し、検証・実 orchard 適用しており、植物フェノタイピングが中心である。
abstractIn this work, we propose a method to accurately map individual tree production at the orchard scale by developing a trade-off methodology between mechanistic yield modelling and extensive fruit counting using machine vision systems.
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 · publicSupplementary Materials: The following are available online at http://www.mdpi.com/2072-4292/10/12/1900/
s1, Figure S1: Image abacus used by expert in the field to estimate load index for (a) ‘Kent’, (b) ‘Keitt’, (c) and
‘BDH’ cultivar. Load index categories (low, medium and high) are displayed in column and different tree heights
(small, medium and tall) are represented in line. Table S1: Mean fruit weight and standard deviation (SD) for the
three variety in Niayes region. Table S2: Description of the 150 calibration trees: cultivar; number of fruit detected
by the KNN-based machine vision and yield measured; load index; and tree structure parameters (tree height,
crown area and volume).Open asset ↗pdf-page:18 lines:1-56Code / dataset availability confirmedCrossref · checked 10 Sept 2026
Real-time monitoring of crop phenology is critical for assisting farmers managing crop growth and yield estimation. In this study, we presented an approach to monitor in real time crop phenology using timely available daily Visible Infrared Imaging Radiometer Suite (VIIRS) observations and historical Moderate Resolution Imaging Spectroradiometer (MODIS) datasets in the Midwestern United States. MODIS data at a spatial resolution of 500 m from 2003 to 2012 were used to generate the climatology of vegetation phenology. By integrating climatological phenology and timely available VIIRS observations in 2014 and 2015, a set of temporal trajectories of crop growth development at a given time for each pixel were then simulated using a logistic model. The simulated temporal trajectories were used to identify spring green leaf development and predict the occurrences of greenup onset, mid-greenup phase, and maximum greenness onset using curvature change rate. Finally, the accuracy of real-time monitoring from VIIRS observations was evaluated by comparing with summary crop progress (CP) reports of ground observations from the National Agricultural Statistics Service (NASS) of the United States Department of Agriculture (USDA). The results suggest that real-time monitoring of crop phenology from VIIRS observations is a robust tool in tracing the crop progress across regional areas. In particular, the date of mid-greenup phase from VIIRS was significantly correlated to the planting dates reported in NASS CP for both corn and soybean with a consistent lag of 37 days and 27 days on average (p
Why it matches plant phenotyping methodsVIIRS・MODISによる作物フェノロジー（緑化開始、成長段階、最大緑度）の推定手法を提示し、地上観測報告との精度比較で検証しているため、植物フェノタイピング手法が中心である。
abstractwe presented an approach to monitor in real time crop phenology using timely available daily Visible Infrared Imaging Radiometer Suite (VIIRS) observations and historical Moderate Resolution Imaging Spectroradiometer (MODIS) datasets
Reproduction assets foundThe paper uses two public datasets directly in its phenotyping analysis: USDA NASS Crop Progress field observations (via QuickStats) for evaluation, and the Cropland Data Layer (via CropScape/Cropland release) to identify 'pure' corn and soybean VIIRS pixels. No author code, models, or derived data deposits are stated.Dataset · publicwe used CDL in 2014 and
2015 that were publicly available at https://www.nass.usda.gov/Research_and_Science/Cropland/
Release/index.php or at USDA CropScape (https://nassgeodata.gmu.edu/CropScape/)Open asset ↗pdf-page:6 lines:1-62Code / dataset availability confirmedCrossref · checked 11 Sept 2026
Field / plotLiDAR / point cloudMultispectral / hyperspectralWhole plant / canopy / plot / fieldClassificationGrowth / development / phenology
Multi-scale modeling of Arctic tundra vegetation requires characterization of the heterogeneous tundra landscape, which includes representation of distinct plant functional types (PFTs). We combined high-resolution multi-spectral remote sensing imagery from the WorldView-2 satellite with light detecting and ranging (LiDAR)-derived digital elevation models (DEM) to characterize the tundra landscape in and around the Barrow Environmental Observatory (BEO), a 3021-hectare research reserve located at the northern edge of the Alaskan Arctic Coastal Plain. Vegetation surveys were conducted during the growing season (June–August) of 2012 from 48 1 m × 1 m plots in the study region for estimating the percent cover of PFTs (i.e., sedges, grasses, forbs, shrubs, lichens and mosses). Statistical relationships were developed between spectral and topographic remote sensing characteristics and PFT fractions at the vegetation plots from field surveys. These derived relationships were employed to statistically upscale PFT fractions for our study region of 586 hectares at 0.25-m resolution around the sampling areas within the BEO, which was bounded by the LiDAR footprint. We employed an unsupervised clustering for stratification of this polygonal tundra landscape and used the clusters for segregating the field data for our upscaling algorithm over our study region, which was an inverse distance weighted (IDW) interpolation. We describe two versions of PFT distribution maps upscaled by IDW from WorldView-2 imagery and LiDAR: (1) a version computed from a single image in the middle of the growing season; and (2) a version computed from multiple images through the growing season. This approach allowed us to quantify the value of phenology for improving PFT distribution estimates. We also evaluated the representativeness of the field surveys by measuring the Euclidean distance between every pixel. This guided the ground-truthing campaign in late July of 2014 for addressing uncertainty based on representativeness analysis by selecting 24 1 m × 1 m plots that were well and poorly represented. Ground-truthing indicated that including phenology had a better accuracy ( R 2 = 0.75 , R M S E = 9.94 ) than the single image upscaling ( R 2 = 0.63 , R M S E = 12.05 ) predicted from IDW. We also updated our upscaling approach to include the 24 ground-truthing plots, and a second ground-truthing campaign in late August of 2014 indicated a better accuracy for the phenology model ( R 2 = 0.61 , R M S E = 13.78 ) than only using the original 48 plots for the phenology model ( R 2 = 0.23 , R M S E = 17.49 ). We believe that the cluster-based IDW upscaling approach and the representativeness analysis offer new insights for upscaling high-resolution data in fragmented landscapes. This analysis and approach provides PFT maps needed to inform land surface models in Arctic ecosystems.
Why it matches plant phenotyping methodsWorldView-2とLiDARを用いて植物機能型の被覆率を推定・地図化し、IDWアップスケーリング手法を精度評価しており、植物表現型取得・抽出が研究の中心です。
abstractStatistical relationships were developed between spectral and topographic remote sensing characteristics and PFT fractions at the vegetation plots from field surveys.
Reproduction assets foundThe paper's upscaling outputs (PFT distribution maps) are publicly archived at ORNL NGEE Arctic data collection (doi:10.5440/1123668), and the LiDAR DEM input used for the analysis is publicly available (doi:10.5065/D6KS6PQ3). No author analysis code repository is stated. The cited Sloan et al. vegetation survey DOI (0Dataset · publicSupplementary Materials: The PFT datasets [51] are available at http://dx.doi.org/10.5440/1123668.Open asset ↗10.5440/1123668pdf-page:20 lines:1-56Dataset · publicMore information on the LiDAR dataset can be found at http://dx.doi.org/10.5065/D6KS6PQ3.Open asset ↗10.5065/D6KS6PQ3pdf-page:6 lines:1-49