[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2114":3,"related-2114":101},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":35,"classification":36,"search_phrases":58,"slug":61,"view_count":62,"doi":63,"paper":64,"created_at":100},2114,"Estimating wheat lodging fraction from Sentinel-1\u002F2 imagery using UAV-derived reference labels","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112410","Estimating wheat lodging fraction from Sentinel-1\u002F2 imagery using UAV-derived reference labels。Computers and Electronics in Agriculture","利用无人机获取的参考标签，从Sentinel-1\u002F2影像估算小麦倒伏比例。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-11T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":20,"comment":21},18,21,14,1,"核心期刊论文，提出用Sentinel-1\u002F2结合无人机参考标签估算小麦倒伏比例，方法新颖、数据可靠，对农业遥感监测有实质参考价值。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","无人机","小麦","遥感监测","作物倒伏",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},"A2","wheat","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":37,"locked":14,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44},[42,48,53],{"code":31,"score":43,"supported":44,"title":45,"abstract":46,"tags":47},15,true,[32],[27,32],[27],{"code":49,"score":20,"supported":14,"title":50,"abstract":51,"tags":52},"I1",[],[],[25],{"code":54,"score":20,"supported":14,"title":55,"abstract":56,"tags":57},"I3",[],[],[28],[59,60],"作物倒伏 智慧农业 遥感监测 无人机","作物倒伏 智慧农业","作物倒伏智慧农业遥感监测无人机-2114",3,"10.1016\u002Fj.compag.2026.112410",{"doi":63,"openalex_id":65,"authors":66,"venue":10,"cited_by_count":92,"oa_url":6,"card":93,"direction":97,"ingested_from":99},"W7212131491",[67,69,72,74,77,79,81,84,86,89],{"name":68,"orcid":9},"Baoyuan Zhang",{"name":70,"orcid":71},"Tianxiang Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-0996-2586",{"name":73,"orcid":9},"Xingyu Liu",{"name":75,"orcid":76},"Chao Song","https:\u002F\u002Forcid.org\u002F0000-0002-0328-9239",{"name":78,"orcid":9},"Xiaoyuan Bao",{"name":80,"orcid":9},"Qian Sun",{"name":82,"orcid":83},"Yuchun Pan","https:\u002F\u002Forcid.org\u002F0000-0002-1163-5963",{"name":85,"orcid":9},"Xia Yao",{"name":87,"orcid":88},"Meiyan Shu","https:\u002F\u002Forcid.org\u002F0000-0002-1519-5520",{"name":90,"orcid":91},"Xiaohe Gu","https:\u002F\u002Forcid.org\u002F0000-0002-7102-1939",0,{"tldr":94,"method":95,"finding":96,"direction":97,"opportunity":98},"利用无人机标签结合Sentinel-1\u002F2影像估算小麦倒伏比例。","Sentinel-1\u002F2卫星影像与无人机参考标签，机器学习回归。","无人机标签可有效训练卫星影像模型，实现区域小麦倒伏比例估算。","农业遥感与作物表型","可探索多时相卫星与无人机协同的倒伏早期预警及不同品种泛化能力。","openalex","2026-09-11T23:30:01.591874Z",{"total":102,"page":20,"page_size":102,"items":103},6,[104,186,283,339,406,504],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":109,"content":9,"source_name":110,"source_url":107,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":113,"sources":119,"tags":121,"primary_topic":124,"secondary_topics":125,"classification":131,"search_phrases":157,"slug":160,"view_count":92,"doi":161,"paper":162,"created_at":185},5367,"Integration of multi-source UAV remote sensing features and derived features for winter wheat aboveground biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102656","Accurate estimation of winter wheat ( Triticum aestivum L.) aboveground biomass (AGB) is important for crop growth monitoring and field management. However, unmanned aerial vehicle (UAV)-based AGB estimation remains challenging due to variations in canopy conditions across growth stages, and different remote sensing features can capture complementary characteristics related to AGB estimation. This study integrated multi-source UAV-derived features, including vegetation indices (VIs), texture features (TFs), light detection and ranging (LiDAR)-derived features, and derived features (DFs) generated from the original feature sets, with four machine learning algorithms for winter wheat AGB estimation. Results showed that TFs provided better prediction performance than other single-source feature sets. Compared with single-source feature sets, the integration of VIs, TFs, LiDAR-derived features, and DFs further improved AGB estimation, and the random forest (RF) model achieved the best performance among the evaluated models (R² = 0.923, RMSE = 1.731 Mg ha⁻¹). Incremental R² analysis based on a stage-only baseline model showed that the RF model explained additional variation in AGB beyond growth-stage information, with an incremental R² of 0.479. Stage-specific evaluation indicated that model performance varied among growth stages, with the highest accuracy observed at the booting stage (R² = 0.632, RMSE = 1.425 Mg ha⁻¹). Feature contribution analysis based on the full-feature fusion model using all growth-stage data identified canopy coverage and several DFs as important predictors, while stage-specific analyses showed differences in dominant predictors across growth stages. The integration of multi-source UAV-derived features and DFs with machine learning provides an effective approach for winter wheat AGB estimation, while model performance remains strongly dependent on growth stage.","准确估算冬小麦（Triticum aestivum L.）地上生物量（aboveground biomass, AGB）对作物生长监测和田间管理具有重要意义。然而，由于不同生育期冠层条件存在差异，且不同遥感特征能够捕捉与AGB估算相关的互补信息，基于无人机（unmanned aerial vehicle, UAV）的AGB估算仍面临挑战。本研究将多源无人机衍生特征，包括植被指数（vegetation indices, VIs）、纹理特征（texture features, TFs）、激光雷达（light detection and ranging, LiDAR）衍生特征以及由原始特征集生成的衍生特征（derived features, DFs），与四种机器学习算法相结合，用于冬小麦AGB估算。结果表明，TFs的预测性能优于其他单一来源特征集。与单一来源特征集相比，融合VIs、TFs、LiDAR衍生特征和DFs进一步提高了AGB估算精度，其中随机森林（random forest, RF）模型在所评估的模型中表现最佳（R² = 0.923，RMSE = 1.731 Mg ha⁻¹）。基于仅含生育期信息的基线模型进行的增量R²分析表明，RF模型在生育期信息之外解释了AGB的额外变异，增量R²为0.479。分生育期评估表明，模型性能在不同生育期之间存在差异，其中在孕穗期观察到最高精度（R² = 0.632，RMSE = 1.425 Mg ha⁻¹）。基于使用全部生育期数据的全特征融合模型进行的特征贡献分析识别出冠层覆盖度和若干DFs为重要预测因子，而分生育期分析则表明不同生育期的主导预测因子存在差异。将多源无人机衍生特征和DFs与机器学习相结合，为冬小麦AGB估算提供了一种有效方法，但模型性能仍强烈依赖于生育期。","Smart Agricultural Technology","2026-10-17T00:00:00Z",77,{"impact":114,"substance":115,"depth":17,"authority":116,"freshness":117,"relevant":20,"comment":118},16,22,13,8,"该研究融合无人机多源遥感特征与衍生特征，用随机森林估算冬小麦地上生物量，方法新颖、结论可靠，对作物长势监测有参考价值。",[120],{"name":110,"url":107},[25,26,28,122,123],"冬小麦","生物量估算",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[126],{"code":54,"slug":127,"name":128,"path":129,"parent_code":130},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":37,"locked":14,"version":38,"method":39,"evidence":132},{"candidates":133,"agricultural_evidence":44},[134,140,146,153],{"code":31,"score":135,"supported":44,"title":136,"abstract":138,"tags":139},26,[137,32],"winter wheat",[27,137,32],[122],{"code":54,"score":114,"supported":44,"title":141,"abstract":143,"tags":145},[142],"remote sensing",[144,142],"遥感",[123,28],{"code":147,"score":102,"supported":44,"title":148,"abstract":149,"tags":152},"I2",[],[150,151],"机器学习","machine learning",[],{"code":49,"score":20,"supported":14,"title":154,"abstract":155,"tags":156},[],[],[25],[158,159],"无人机 多源遥感 冬小麦 生物量","冬小麦 地上生物量 随机森林","无人机多源遥感冬小麦生物量-5367","10.1016\u002Fj.atech.2026.102656",{"doi":161,"openalex_id":163,"authors":164,"venue":110,"cited_by_count":92,"oa_url":107,"card":180,"direction":97,"ingested_from":99},"W7222806066",[165,167,169,171,174,176,178],{"name":166,"orcid":9},"Guangtao Wang",{"name":168,"orcid":9},"Sumei Yao",{"name":170,"orcid":9},"Yanzheng Xie",{"name":172,"orcid":173},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":175,"orcid":9},"Xiangdong Chen",{"name":177,"orcid":9},"Yuhao Zhang",{"name":179,"orcid":9},"Lina Jiang",{"tldr":181,"method":182,"finding":183,"direction":97,"opportunity":184},"融合无人机多源遥感特征与衍生特征，用机器学习估算冬小麦地上生物量。","无人机植被指数、纹理、LiDAR特征及衍生特征结合四种机器学习算法建模。","多源特征融合优于单一特征，随机森林最优（R²=0.923），精度随生育期变化。","可探索生育期自适应建模与特征选择，提升跨期生物量估算的稳健性与可迁移性。","2026-10-20T23:30:03.106267Z",{"id":187,"title":188,"url":189,"summary":190,"summary_zh":191,"content":9,"source_name":192,"source_url":189,"published_at":193,"category":12,"cover_url":9,"hotness":13,"is_selected":44,"score":194,"score_detail":195,"sources":200,"tags":202,"primary_topic":205,"secondary_topics":206,"classification":207,"search_phrases":222,"slug":225,"view_count":226,"doi":227,"paper":228,"created_at":282},4078,"Assessing plant area index and 3D plant area distribution in wheat canopies from a terrestrial LiDAR system for high-throughput plant phenotyping","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115711","This study investigates a new methodology to estimate plant area index ( PAI ) and its spatial distribution from 3D point clouds acquired by a system of 3 LiDARs (2 nadir-viewing and one at 45°) mounted on the Phenomobile Unmanned Ground Vehicle designed for high-throughput phenotyping of herbaceous crops. It relies on the computation of the gap fraction at the voxel level using the trajectories of the laser beams to numerically invert the Beer-Lambert law (BL), enabling the simultaneous estimation of PAI and AIA (Average Inclination Angle, in°). The method is evaluated on wheat crops both in silico (i.e. simulations based on the AdelWheat functional structural crop model coupled with a point cloud simulator) and in actual phenotyping trials of a panel of 10 bread wheat genotypes grown in two study sites under different treatments of plant density, water stress and sowing dates. The in silico validation indicates that the numeric inversion of BL with the LiDAR system of the Phenomobile leads to a relative error of 9.8% (RMSE = 0.32, R 2 = 0.99) and 8.4% (RMSE =5.4°, R 2 = 0.95) in the estimation of PAI and AIA , respectively. The validation in actual phenotyping experiments against destructive measurements produced satisfactory results for canopy PAI (RMSE = 1.44, R 2 = 0.82), while requiring prior knowledge on AIA , e.g. either by (i) introducing a regularization term in the cost function used to invert BL, to avoid unexpected high AIA estimations, (ii) using a fixed, reference value of 60°. The analysis of the results indicates that the inclusion of a regularization term mitigates the impact of actual differences in leaf inclination among cultivars on PAI accuracy, while providing a relative description of the actual variability in the vertical profile of leaf inclination across the different cultivars.","本研究探讨了一种新方法，用于从三维点云中估算植物面积指数（PAI）及其空间分布。该点云由安装在Phenomobile无人地面车辆上的3台激光雷达（LiDAR）系统（2台天底视角和1台45°视角）获取，该车辆专为草本作物的高通量表型设计。该方法依赖于利用激光束轨迹在体素水平上计算间隙率，以数值反演Beer-Lambert定律（BL），从而能够同时估算PAI和AIA（平均倾角，单位为°）。该方法在小麦作物上进行了评估，既包括计算机模拟（即基于AdelWheat功能结构作物模型结合点云模拟器的模拟），也包括在实际表型试验中对10个面包小麦基因型组成的 panel 在两个研究地点、不同植株密度、水分胁迫和播种日期处理下的种植。计算机模拟验证表明，利用Phenomobile的LiDAR系统对BL进行数值反演，在PAI和AIA估算中分别产生9.8%（RMSE = 0.32，R² = 0.99）和8.4%（RMSE = 5.4°，R² = 0.95）的相对误差。在实际表型试验中与破坏性测量进行验证，冠层PAI获得了令人满意的结果（RMSE = 1.44，R² = 0.82），但需要关于AIA的先验知识，例如通过以下方式之一：（i）在用于反演BL的代价函数中引入正则化项，以避免出现意外的高AIA估算值；（ii）使用固定的参考值60°。结果分析表明，引入正则化项减轻了品种间叶片倾角实际差异对PAI精度的影响，同时提供了不同品种间叶片倾角垂直剖面实际变异性的相对描述。","Remote Sensing of Environment","2026-10-02T00:00:00Z",84,{"impact":17,"substance":196,"depth":197,"authority":43,"freshness":198,"relevant":20,"comment":199},23,19,9,"基于车载三激光雷达点云反演小麦植物面积指数与倾角分布，仿真与田间验证扎实，属高通量表型领域方法学新进展。",[201],{"name":192,"url":189},[25,27,28,203,204],"高通量表型","激光雷达",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":208},{"candidates":209,"agricultural_evidence":44},[210,214,218],{"code":31,"score":43,"supported":44,"title":211,"abstract":212,"tags":213},[32],[27,32],[27],{"code":49,"score":20,"supported":14,"title":215,"abstract":216,"tags":217},[],[],[25],{"code":54,"score":20,"supported":14,"title":219,"abstract":220,"tags":221},[],[],[28],[223,224],"Phenomobile 激光雷达 小麦","植物面积指数 三维点云","Phenomobile激光雷达小麦-4078",7,"10.1016\u002Fj.rse.2026.115711",{"doi":227,"openalex_id":229,"authors":230,"venue":192,"cited_by_count":92,"oa_url":189,"card":277,"direction":97,"ingested_from":99},"W7215681984",[231,234,236,239,241,243,246,248,251,254,257,259,261,263,265,267,269,271,274],{"name":232,"orcid":233},"Raúl López‐Lozano","https:\u002F\u002Forcid.org\u002F0000-0001-6499-4743",{"name":235,"orcid":9},"Tian Ma",{"name":237,"orcid":238},"Maxime Soma","https:\u002F\u002Forcid.org\u002F0000-0002-9242-3283",{"name":240,"orcid":9},"Marie Weiss",{"name":242,"orcid":9},"Aurélien Ausset",{"name":244,"orcid":245},"Philippe Burger","https:\u002F\u002Forcid.org\u002F0000-0003-3662-7924",{"name":247,"orcid":9},"Bruno Berthon",{"name":249,"orcid":250},"Romain Chapuis","https:\u002F\u002Forcid.org\u002F0000-0001-7196-4622",{"name":252,"orcid":253},"Marie-Pia D'argaignon","https:\u002F\u002Forcid.org\u002F0009-0004-6568-9213",{"name":255,"orcid":256},"Antonin Grau","https:\u002F\u002Forcid.org\u002F0000-0002-5366-9360",{"name":258,"orcid":9},"Florian Larue",{"name":260,"orcid":9},"Romane Le-Roy",{"name":262,"orcid":9},"Rémy Marandel",{"name":264,"orcid":9},"Vincent Mercier",{"name":266,"orcid":9},"Mathieu Roy",{"name":268,"orcid":9},"Gilles Tison",{"name":270,"orcid":9},"Frédéric Venault",{"name":272,"orcid":273},"Pierre Martre","https:\u002F\u002Forcid.org\u002F0000-0002-7419-6558",{"name":275,"orcid":276},"Frédéric Baret","https:\u002F\u002Forcid.org\u002F0000-0002-7655-8997",{"tldr":278,"method":279,"finding":280,"direction":97,"opportunity":281},"利用车载三LiDAR点云反演小麦冠层植物面积指数与三维分布，实现高通量表型分析。","体素间隙率结合Beer-Lambert数值反演，用AdelWheat模型仿真与1","PAI估算R²=0.82，加入正则项可减少叶倾角差异影响并描述垂直分布变异。","可探索多角度LiDAR与正则化反演结合，提升不同基因型叶倾角垂直分布的鲁棒表型提取。","2026-10-03T23:30:24.403056Z",{"id":284,"title":285,"url":286,"summary":287,"summary_zh":288,"content":9,"source_name":289,"source_url":286,"published_at":290,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":291,"score_detail":292,"sources":294,"tags":296,"primary_topic":299,"secondary_topics":300,"classification":301,"search_phrases":317,"slug":320,"view_count":62,"doi":321,"paper":322,"created_at":338},4020,"Robust QR Code Detection in Oblique Aerial Images for Agricultural Field Experiments","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193361","Field experiments in precision agriculture require reliable linkage of plant variants to experimental plots, which is difficult in oblique aerial imagery because the drone position does not identify the imaged ground location. We present and evaluate a reproducible workflow for detecting QR reference markers in high-resolution UAV images acquired over a wheat field before crop growth at a 45° viewing angle. The workflow combines manually defined regions of interest, documented preprocessing, a rotation sweep, and independent evaluation of OpenCV and pyzbar decoding backends. QR codes were selected for practical field deployment because their payload can directly encode a plot identifier and can be checked with an ordinary smartphone; the study does not benchmark QR codes against other fiducial-marker families. In 500 field-collected QR-code crops from 20 images, 491 codes (98.2%) were decoded; all nine failures had incomplete code visibility. The observed result is therefore a system-level outcome of both image acquisition and decoding under the tested configuration, rather than a growing-season operational accuracy. The mean processing time was approximately 0.41 s per region of interest on a standard PC. The work demonstrates QR-marker detection under the stated pre-growth conditions and provides a basis for future plot-label reference, calibration, and downstream Fusarium Head Blight phenotyping.","精准农业中的田间试验需要将植物变异可靠地关联到试验小区，而这在倾斜航空影像中较为困难，因为无人机位置并不能标识所成像的地面位置。我们提出并评估了一套可重复的工作流程，用于在作物生长前以45°视角获取的小麦田高分辨率无人机影像中检测QR参考标记。该工作流程结合了人工定义的感兴趣区域、有记录的前处理步骤、旋转扫描，以及对OpenCV和pyzbar解码后端的独立评估。选择QR码用于实际田间部署，是因为其有效载荷可直接编码小区标识符，并可用普通智能手机进行核验；本研究并未将QR码与其他基准标记类型进行基准比较。在来自20幅影像的500个田间采集QR码裁剪区域中，491个码（98.2%）被成功解码；全部9个失败案例均存在码可见性不完整的问题。因此，所观察到的结果是测试配置下图像采集与解码共同作用的系统级结果，而非整个生长季的运行精度。在标准PC上，每个感兴趣区域的平均处理时间约为0.41 s。该工作证明了在上述生长前条件下QR标记检测的可行性，并为未来的小区标签参考、校准以及下游赤霉病（Fusarium Head Blight）表型分析提供了基础。","Remote Sensing","2026-10-01T00:00:00Z",65,{"impact":117,"substance":17,"depth":114,"authority":19,"freshness":198,"relevant":20,"comment":293},"该论文提出斜视无人机影像中QR码检测的可复现流程，在500个样本中解码成功率达98.2%，为精准农业田间试验的地块标识提供了实用方案，方法新颖且数据可靠，但属细分技术进展，影响范围有限。",[295],{"name":289,"url":286},[25,26,297,27,298],"农业遥感","精准农业",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":302},{"candidates":303,"agricultural_evidence":44},[304,309,313],{"code":49,"score":117,"supported":44,"title":305,"abstract":306,"tags":308},[],[298,307],"precision agriculture",[25,298],{"code":31,"score":226,"supported":44,"title":310,"abstract":311,"tags":312},[],[27,32],[27],{"code":54,"score":20,"supported":14,"title":314,"abstract":315,"tags":316},[],[],[297],[318,319],"无人机 斜视影像 QR码 检测","小麦 田间试验 地块标识","无人机斜视影像QR码检测-4020","10.3390\u002Frs18193361",{"doi":321,"openalex_id":323,"authors":324,"venue":289,"cited_by_count":92,"oa_url":286,"card":333,"direction":97,"ingested_from":99},"W7215065180",[325,327,330],{"name":326,"orcid":9},"Gudrun Kinz",{"name":328,"orcid":329},"Hermann Buerstmayr","https:\u002F\u002Forcid.org\u002F0000-0002-0748-2351",{"name":331,"orcid":332},"Peter M. Roth","https:\u002F\u002Forcid.org\u002F0000-0001-9566-1298",{"tldr":334,"method":335,"finding":336,"direction":97,"opportunity":337},"提出并评估了在45°斜视无人机图像中检测田间二维码标记的可复现流程，解码成功率达98.2%。","结合手动ROI、预处理、旋转扫描及OpenCV与pyzbar双后端解码，使用50","491\u002F500个二维码成功解码，9个失败均因码可见性不完整，平均处理时间约0.41秒\u002FROI。","可探索斜视图像下多类基准标记的鲁棒检测与自动ROI定位，并接入生长季表型分析流程。","2026-10-02T23:30:19.815764Z",{"id":340,"title":341,"url":342,"summary":343,"summary_zh":9,"content":9,"source_name":344,"source_url":342,"published_at":290,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":345,"score_detail":346,"sources":349,"tags":351,"primary_topic":353,"secondary_topics":354,"classification":355,"search_phrases":371,"slug":374,"view_count":375,"doi":376,"paper":377,"created_at":405},3865,"Multisensor data fusion from uav platforms: a robust approach for estimating photosynthetic capacity across vertical leaf layers in winter wheat","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10452-4","Multisensor data fusion from uav platforms: a robust approach for estimating photosynthetic capacity across vertical leaf layers in winter wheat。Precision Agriculture","Precision Agriculture",80,{"impact":17,"substance":18,"depth":347,"authority":19,"freshness":13,"relevant":20,"comment":348},17,"该论文提出无人机多传感器数据融合方法估算冬小麦垂直叶层光合能力，方法新颖、数据可靠，对智慧农业遥感监测有参考价值，值得进入每日精选。",[350],{"name":344,"url":342},[25,26,27,144,352],"光合能力",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":356},{"candidates":357,"agricultural_evidence":44},[358,362,367],{"code":31,"score":196,"supported":44,"title":359,"abstract":360,"tags":361},[137,32],[137,32],[27],{"code":49,"score":363,"supported":44,"title":364,"abstract":365,"tags":366},4,[],[307],[25],{"code":54,"score":20,"supported":14,"title":368,"abstract":369,"tags":370},[],[],[144],[372,373],"无人机 多传感器 数据融合 冬小麦","光合能力 智慧农业 无人机 小麦","无人机多传感器数据融合冬小麦-3865",2,"10.1007\u002Fs11119-026-10452-4",{"doi":376,"openalex_id":378,"authors":379,"venue":344,"cited_by_count":92,"oa_url":9,"card":9,"direction":97,"ingested_from":99},"W7214905644",[380,382,385,388,391,393,395,398,401,403],{"name":381,"orcid":9},"Dongwei Han",{"name":383,"orcid":384},"Shaolong Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-2525-0095",{"name":386,"orcid":387},"Muhammad Zain","https:\u002F\u002Forcid.org\u002F0000-0002-8073-6282",{"name":389,"orcid":390},"Weijun Zhang","https:\u002F\u002Forcid.org\u002F0009-0006-1540-7382",{"name":392,"orcid":9},"Zhaokai Ma",{"name":394,"orcid":9},"Xintong Lu",{"name":396,"orcid":397},"Jianliang Wang","https:\u002F\u002Forcid.org\u002F0000-0001-5733-4202",{"name":399,"orcid":400},"Yuanyuan Zhao","https:\u002F\u002Forcid.org\u002F0000-0003-4202-6383",{"name":402,"orcid":9},"Tao Liu",{"name":404,"orcid":9},"Chengming Sun","2026-10-01T23:30:02.493554Z",{"id":407,"title":408,"url":409,"summary":410,"summary_zh":411,"content":9,"source_name":412,"source_url":409,"published_at":413,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":414,"score_detail":415,"sources":417,"tags":419,"primary_topic":421,"secondary_topics":422,"classification":424,"search_phrases":451,"slug":454,"view_count":62,"doi":455,"paper":456,"created_at":503},3354,"Optimizing canopy nitrogen retrieval in wheat from high-resolution UAV hyperspectral data using RTM-based Gaussian process regression","https:\u002F\u002Fdoi.org\u002F10.1080\u002F01904167.2026.2736627","The canopy nitrogen content (CNC) is one of the vital crop health indicators directly influencing the crop growth, yield, and nutritional status. Unmanned aerial vehicles (UAVs) that acquired hyperspectral imagery opened a new path for nondestructive, accurate, and timely estimation of CNC, facilitating the adoption of smart agro practices in precision agriculture for site-specific nutrient management. With the purpose of processing such hyperspectral data into CNC maps, two hybrid retrieval approaches, protein-based (CNCprot) and chlorophyll-based (CNCchl) models, were built by combining a radiative transfer model with a machine learning Gaussian process regression (GPR) algorithm. The GPR retrieval models were trained using synthetic spectral data from the PROSAIL-PRO model, and the sampling was optimized using the Euclidean distance-based diversity (EBD) active learning (AL) technique. The CNC models were applied to a UAV-borne hyperspectral image in the spectral range of 400-1000 nm with an ultrahigh spatial resolution of 4 cm, acquired over the experimental wheat field of Indian Council of Agricultural Research (ICAR) -Indian Agricultural Research Institute (IARI), New Delhi, India. The GPR models yielded good prediction accuracies with R2 values of 0.74 and 0.56 and NRMSE of 13.62 and 23.82% for CNCchl and CNCprot, respectively. The consistent prediction accuracies and low associated uncertainties revealed that CNC was more accurately mapped using chlorophyll-based CNC retrieval applied to a Vis-NIR-based hyperspectral data. These promising results demonstrated the possibility of applying hybrid GPR models at ultrahigh resolution and the operational viability of UAV datasets for regular CNC monitoring.","冠层氮含量（CNC）是直接影响作物生长、产量和营养状况的重要作物健康指标之一。无人机（UAV）获取的高光谱影像为无损、精准、及时地估算CNC开辟了新途径，有助于在精准农业中采用智能农业实践进行定点养分管理。为了将此类高光谱数据处理为CNC分布图，本研究通过将辐射传输模型与机器学习高斯过程回归（GPR）算法相结合，构建了两种混合反演方法：基于蛋白质的模型（CNCprot）和基于叶绿素的模型（CNCchl）。GPR反演模型使用PROSAIL-PRO模型生成的合成光谱数据进行训练，并采用基于欧氏距离的多样性（EBD）主动学习（AL）技术优化采样。CNC模型被应用于一幅无人机载高光谱影像，光谱范围为400-1000 nm，空间分辨率高达4 cm，该影像获取自印度农业研究理事会（ICAR）-印度农业研究所（IARI）位于印度新德里的实验麦田。GPR模型取得了良好的预测精度，CNCchl和CNCprot的R²值分别为0.74和0.56，NRMSE分别为13.62%和23.82%。一致的预测精度和较低的相关不确定性表明，将基于叶绿素的CNC反演应用于基于可见光-近红外（Vis-NIR）的高光谱数据能够更准确地制图CNC。这些有前景的结果证明了在超高分辨率下应用混合GPR模型的可能性，以及无人机数据集用于常规CNC监测的可行性。","Journal of Plant Nutrition","2026-09-23T00:00:00Z",79,{"impact":17,"substance":115,"depth":17,"authority":116,"freshness":117,"relevant":20,"comment":416},"将辐射传输模型与高斯过程回归结合，用4厘米超高分辨率无人机高光谱实现小麦冠层氮素精准反演，方法新颖、结论可靠，对精准农业养分管理有实操参考价值。",[418],{"name":412,"url":409},[25,26,27,144,420],"氮素监测",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[423],{"code":54,"slug":127,"name":128,"path":129,"parent_code":130},{"status":37,"locked":14,"version":38,"method":39,"evidence":425},{"candidates":426,"agricultural_evidence":44},[427,432,437,441,445],{"code":31,"score":428,"supported":44,"title":429,"abstract":430,"tags":431},12,[32],[32],[27],{"code":54,"score":428,"supported":44,"title":433,"abstract":435,"tags":436},[434],"hyperspectral",[434],[144],{"code":49,"score":226,"supported":44,"title":438,"abstract":439,"tags":440},[],[298,307],[25],{"code":147,"score":102,"supported":44,"title":442,"abstract":443,"tags":444},[],[150,151],[],{"code":446,"score":62,"supported":44,"title":447,"abstract":448,"tags":450},"F3",[],[449],"养分管理",[],[452,453],"无人机 高光谱 小麦 氮素","PROSAIL 高斯过程回归 小麦","无人机高光谱小麦氮素-3354","10.1080\u002F01904167.2026.2736627",{"doi":455,"openalex_id":457,"authors":458,"venue":412,"cited_by_count":92,"oa_url":9,"card":497,"direction":502,"ingested_from":99},"W7214104831",[459,461,463,466,469,471,473,476,479,482,484,487,489,491,494],{"name":460,"orcid":9},"R. G. Rejith",{"name":462,"orcid":9},"Rabi N. Sahoo",{"name":464,"orcid":465},"Shalini Gakhar","https:\u002F\u002Forcid.org\u002F0000-0001-5717-1714",{"name":467,"orcid":468},"Jochem Verrelst","https:\u002F\u002Forcid.org\u002F0000-0002-6313-2081",{"name":470,"orcid":9},"Amrita Bhandari",{"name":472,"orcid":9},"Tarun Kondraju",{"name":474,"orcid":475},"Rajeev Ranjan","https:\u002F\u002Forcid.org\u002F0000-0003-2233-9147",{"name":477,"orcid":478},"Mahesh C. Meena","https:\u002F\u002Forcid.org\u002F0000-0001-5386-883X",{"name":480,"orcid":481},"Abir Dey","https:\u002F\u002Forcid.org\u002F0000-0002-5009-9518",{"name":483,"orcid":9},"Joydeep Mukherjee",{"name":485,"orcid":486},"Sudhir Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-1089-7435",{"name":488,"orcid":9},"Mahesh Kumar",{"name":490,"orcid":9},"Raju Dhandapani",{"name":492,"orcid":493},"Anchal Dass","https:\u002F\u002Forcid.org\u002F0000-0003-3909-1803",{"name":495,"orcid":496},"Viswanathan Chinnusamy","https:\u002F\u002Forcid.org\u002F0000-0003-2174-9064",{"tldr":498,"method":499,"finding":500,"direction":97,"opportunity":501},"用PROSAIL-PRO与高斯过程回归从无人机高光谱数据反演小麦冠层氮含量。","PROSAIL-PRO合成光谱训练GPR，EBD主动学习采样，4cm无人机高光谱","叶绿素基模型精度更高，R²达0.74，NRMSE为13.62%，优于蛋白基模型。","可探索多生育期、多品种迁移能力及主动学习采样策略对反演精度的提升空间。","智慧农业 \u002F 农业物联网","2026-09-24T23:30:10.311254Z",{"id":505,"title":506,"url":507,"summary":508,"summary_zh":509,"content":9,"source_name":510,"source_url":507,"published_at":511,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":512,"sources":514,"tags":516,"primary_topic":518,"secondary_topics":519,"classification":530,"search_phrases":562,"slug":565,"view_count":92,"doi":566,"paper":567,"created_at":584},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy","2026-10-21T00:00:00Z",{"impact":114,"substance":18,"depth":347,"authority":116,"freshness":13,"relevant":20,"comment":513},"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[515],{"name":510,"url":507},[25,150,28,517,122],"土壤墒情",{"code":31,"slug":32,"name":27,"path":33,"parent_code":34},[520,526],{"code":521,"slug":522,"name":523,"path":524,"parent_code":525},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":147,"slug":527,"name":528,"path":529,"parent_code":130},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":37,"locked":14,"version":38,"method":39,"evidence":531},{"candidates":532,"agricultural_evidence":44},[533,537,542,546,551,558],{"code":31,"score":135,"supported":44,"title":534,"abstract":535,"tags":536},[137,32],[27,137,32],[122],{"code":521,"score":43,"supported":44,"title":538,"abstract":539,"tags":541},[522],[540,522],"土壤",[517],{"code":147,"score":43,"supported":44,"title":543,"abstract":544,"tags":545},[151],[150,151],[150],{"code":54,"score":13,"supported":44,"title":547,"abstract":548,"tags":550},[],[144,142,549],"multispectral",[28],{"code":552,"score":102,"supported":44,"title":553,"abstract":554,"tags":557},"H3",[],[555,556],"灌溉","irrigation",[],{"code":49,"score":363,"supported":44,"title":559,"abstract":560,"tags":561},[],[25],[25],[563,564],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":566,"openalex_id":568,"authors":569,"venue":510,"cited_by_count":92,"oa_url":507,"card":579,"direction":502,"ingested_from":99},"W7223156204",[570,573,575,577],{"name":571,"orcid":572},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":574,"orcid":9},"Yi Zhang",{"name":576,"orcid":9},"WEI Lei",{"name":578,"orcid":9},"Chengcai Zhang",{"tldr":580,"method":581,"finding":582,"direction":97,"opportunity":583},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","2026-10-22T11:20:18.887301Z"]