[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3278":3,"related-3278":130},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":37,"classification":49,"search_phrases":80,"slug":83,"view_count":17,"doi":84,"paper":85,"created_at":129},3278,"Research on the optimal modeling path for inversion of Pb content in rice leaves based on hyperspectral data of ground objects and machine learning and cross-scale remote sensing monitoring","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10661-026-15959-x","Research on the optimal modeling path for inversion of Pb content in rice leaves based on hyperspectral data of ground objects and machine learning and cross-scale remote sensing monitoring。Environmental Monitoring and Assessment","基于地物高光谱数据与机器学习的稻叶铅含量反演最优建模路径及跨尺度遥感监测研究。环境监测与评估",null,"Environmental Monitoring and Assessment","2026-09-22T00:00:00Z","论文",10,false,64,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,18,16,13,9,1,"基于地物高光谱与机器学习的水稻叶片铅含量反演建模研究，方法有创新但属细分领域学术进展，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业遥感","水稻","机器学习","高光谱遥感",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[38,44],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":50,"locked":14,"version":51,"method":52,"evidence":53},"classified","2026-10-22.2","rules",{"candidates":54,"agricultural_evidence":57},[55,64,70,75],{"code":45,"score":56,"supported":57,"title":58,"abstract":61,"tags":63},27,true,[59,60],"remote sensing","hyperspectral",[62,59,60],"遥感",[28,31],{"code":39,"score":65,"supported":57,"title":66,"abstract":68,"tags":69},15,[67],"machine learning",[30,67],[30],{"code":33,"score":71,"supported":57,"title":72,"abstract":73,"tags":74},12,[34],[34],[29],{"code":76,"score":22,"supported":14,"title":77,"abstract":78,"tags":79},"I1",[],[],[27],[81,82],"水稻叶片 铅含量 高光谱 反演","稻米 重金属 遥感 监测","水稻叶片铅含量高光谱反演-3278","10.1007\u002Fs10661-026-15959-x",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":121,"oa_url":9,"card":122,"direction":126,"ingested_from":128},"W7214027889",[88,91,94,97,100,103,105,107,110,113,115,117,119],{"name":89,"orcid":90},"Zhenlong Zhang","https:\u002F\u002Forcid.org\u002F0009-0008-2354-9123",{"name":92,"orcid":93},"Zhe Wang","https:\u002F\u002Forcid.org\u002F0000-0003-1266-7251",{"name":95,"orcid":96},"Chengxia Wang","https:\u002F\u002Forcid.org\u002F0009-0001-0820-2462",{"name":98,"orcid":99},"Wenxue Lin","https:\u002F\u002Forcid.org\u002F0000-0002-8245-9063",{"name":101,"orcid":102},"Jingyan Zhang","https:\u002F\u002Forcid.org\u002F0009-0004-4567-5316",{"name":104,"orcid":9},"Ying Luo",{"name":106,"orcid":9},"Jiaqian Zhang",{"name":108,"orcid":109},"Kai Ye","https:\u002F\u002Forcid.org\u002F0000-0002-2851-6741",{"name":111,"orcid":112},"Yiming Chen","https:\u002F\u002Forcid.org\u002F0000-0002-8121-3109",{"name":114,"orcid":9},"Chaoliang Peng",{"name":116,"orcid":9},"Duan Tian",{"name":118,"orcid":9},"Weihao Wang",{"name":120,"orcid":9},"Jiaxin Liu",0,{"tldr":123,"method":124,"finding":125,"direction":126,"opportunity":127},"研究基于地面高光谱与机器学习反演水稻叶片铅含量，并探索跨尺度遥感监测的最优建模路径。","地面高光谱数据结合机器学习建模，开展跨尺度遥感监测。","明确了水稻叶片铅含量反演的最优建模路径，实现跨尺度遥感监测。","农业遥感与作物表型","可探索多尺度遥感数据融合与迁移学习，提升重金属胁迫反演的普适性与精度。","openalex","2026-09-23T23:30:19.291361Z",{"total":131,"page":22,"page_size":131,"items":132},6,[133,241,319,405,472,536],{"id":134,"title":135,"url":136,"summary":137,"summary_zh":138,"content":9,"source_name":139,"source_url":136,"published_at":140,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":141,"score_detail":142,"sources":146,"tags":148,"primary_topic":150,"secondary_topics":151,"classification":154,"search_phrases":206,"slug":209,"view_count":210,"doi":211,"paper":212,"created_at":240},3494,"Rice Cropping Pattern Mapping Using GEE-Based Sentinel-1\u002F2 Time-Series Imagery and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193302","Accurate mapping of rice cropping patterns is fundamental to sustainable agricultural management and regional food security assessment. In this study, we developed a high-precision mapping framework for major rice cropping patterns in the Yangtze River Delta region, China, using the Google Earth Engine (GEE) cloud platform. A multi-temporal and multi-source feature set was constructed by integrating Sentinel-1 radar backscatter (VV\u002FVH polarization), Sentinel-2 optical indices, including the normalized difference vegetation index (NDVI) and land surface water index (LSWI), and topographic factors (DEM and slope), to classify three predominant cropping systems, namely, wheat–rice rotation, double rice, and rapeseed–rice rotation. A total of 548 field-surveyed sample points collected during the 2024–2025 growing season were used for model training and validation. Three classical classifiers—Random Forest (RF), A Gradient Boosting Tree (GBTREE), and a Support Vector Machine (SVM)—were systematically compared. The ablation experiment demonstrated that the fusion of Sentinel-1 and Sentinel-2 outperformed both the Sentinel-1-only and Sentinel-2-only configurations across all three classifiers. Among them, the GBTREE achieved the highest overall accuracy (93.8%), Kappa coefficient (0.87), and macro-average F1 score (88.3%) in this specific experiment. Notably, it also performed best on the more challenging double-rice class. The SHapley Additive exPlanations (SHAP)-based feature importance analysis revealed that multi-temporal NDVI phenological features were the primary drivers of classification accuracy, while radar backscatter and water indices provided essential complementary information, and topographic factors served as spatial constraints at the regional scale. The spatial distribution derived from the GBTREE classification exhibited clear patterns: wheat–rice rotation dominated the northern plains (northern Jiangsu, northern Anhui, and the Hangjiahu Plain); double rice was concentrated in the southern Zhejiang hills and scattered valley plains; and rapeseed–rice rotation showed a scattered, mosaic distribution. Overall, this study demonstrates that integrating multi-source remote sensing data on the GEE platform with the GBTREE classifier enables effective and scalable high-precision mapping of rice cropping patterns in complex agricultural landscapes. This approach provides a reliable technical foundation for regional agricultural structure analysis, crop rotation assessment, and sustainable agricultural monitoring.","准确绘制水稻种植模式图是实现可持续农业管理和区域粮食安全评估的基础。本研究基于Google Earth Engine（GEE）云平台，构建了长江三角洲地区主要水稻种植模式的高精度制图框架。通过整合Sentinel-1雷达后向散射（VV\u002FVH极化）、Sentinel-2光学指数（包括归一化差异植被指数NDVI和地表水体指数LSWI）以及地形因子（DEM和坡度），构建了多时相、多源特征集，用于分类三种主要种植制度，即麦–稻轮作、双季稻和油–稻轮作。利用2024—2025年生长季采集的548个实地调查样点进行模型训练与验证。系统比较了三种经典分类器——随机森林（RF）、梯度提升树（GBTREE）和支持向量机（SVM）。消融实验表明，Sentinel-1与Sentinel-2的融合在三种分类器中均优于仅使用Sentinel-1或仅使用Sentinel-2的配置。其中，GBTREE在本实验中取得了最高的总体精度（93.8%）、Kappa系数（0.87）和宏平均F1分数（88.3%）。值得注意的是，其在更具挑战性的双季稻类别上同样表现最佳。基于SHapley加法解释（SHAP）的特征重要性分析表明，多时相NDVI物候特征是分类精度的主要驱动因素，雷达后向散射和水体指数提供了必要的补充信息，而地形因子则在区域尺度上起到空间约束作用。基于GBTREE分类得到的空间分布呈现出清晰的格局：麦–稻轮作主导北部平原（苏北、皖北和杭嘉湖平原）；双季稻集中于浙南丘陵和零散的河谷平原；油–稻轮作则呈零散镶嵌状分布。总体而言，本研究表明，在GEE平台上整合多源遥感数据与GBTREE分类器，能够对复杂农业景观中的水稻种植模式进行有效且可扩展的高精度制图。该方法为区域农业结构分析和作物","Remote Sensing","2026-09-24T00:00:00Z",79,{"impact":19,"substance":143,"depth":18,"authority":144,"freshness":21,"relevant":22,"comment":145},22,14,"基于GEE与Sentinel-1\u002F2时序影像结合机器学习实现长三角水稻种植模式高精度制图，方法扎实、结论可靠，对农业遥感监测有参考价值。",[147],{"name":139,"url":136},[27,29,30,62,149],"作物分类",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},[152,153],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":155},{"candidates":156,"agricultural_evidence":57},[157,161,165,169,176,183,190,196,202],{"code":33,"score":65,"supported":57,"title":158,"abstract":159,"tags":160},[34],[29,34],[29],{"code":39,"score":21,"supported":57,"title":162,"abstract":163,"tags":164},[67],[],[30],{"code":45,"score":17,"supported":57,"title":166,"abstract":167,"tags":168},[],[62,59],[149,62],{"code":170,"score":131,"supported":57,"title":171,"abstract":172,"tags":175},"A7",[],[173,174],"轮作","crop rotation",[],{"code":177,"score":131,"supported":57,"title":178,"abstract":179,"tags":182},"A8",[],[180,181],"粮食安全","food security",[],{"code":184,"score":185,"supported":57,"title":186,"abstract":187,"tags":189},"A2",3,[],[188],"wheat",[],{"code":191,"score":185,"supported":57,"title":192,"abstract":193,"tags":195},"A4",[],[194],"rapeseed",[],{"code":197,"score":185,"supported":57,"title":198,"abstract":199,"tags":201},"H8",[],[200],"可持续农业",[],{"code":76,"score":22,"supported":14,"title":203,"abstract":204,"tags":205},[],[],[27],[207,208],"长三角 水稻 种植模式 遥感","Sentinel-1 Sentinel-2 水稻制图","长三角水稻种植模式遥感-3494",5,"10.3390\u002Frs18193302",{"doi":211,"openalex_id":213,"authors":214,"venue":139,"cited_by_count":121,"oa_url":136,"card":235,"direction":126,"ingested_from":128},"W7214147197",[215,218,221,224,226,229,232],{"name":216,"orcid":217},"Xuan Li","https:\u002F\u002Forcid.org\u002F0000-0001-5509-2385",{"name":219,"orcid":220},"Lintao Chen","https:\u002F\u002Forcid.org\u002F0009-0000-6558-1289",{"name":222,"orcid":223},"Lin Chen","https:\u002F\u002Forcid.org\u002F0000-0002-9270-1626",{"name":225,"orcid":9},"Chao Su",{"name":227,"orcid":228},"Hoi Leong Lee","https:\u002F\u002Forcid.org\u002F0000-0002-4984-2183",{"name":230,"orcid":231},"Ruci Wang","https:\u002F\u002Forcid.org\u002F0000-0001-7049-7006",{"name":233,"orcid":234},"Xuguang Tang","https:\u002F\u002Forcid.org\u002F0009-0008-3494-8867",{"tldr":236,"method":237,"finding":238,"direction":126,"opportunity":239},"基于GEE融合Sentinel-1\u002F2时序与地形特征，用机器学习高精度制图长三角水稻种植模式。","GEE平台、Sentinel-1\u002F2时序特征、DEM、548个实地样本、RF\u002FG","GBTREE精度最高（总体93.8%、Kappa 0.87），双季稻识别最好；NDVI物候特征贡献最","可探索样本稀缺区迁移学习与多作物轮作模式泛化制图，并耦合产量与碳核算。","2026-09-25T23:30:30.511522Z",{"id":242,"title":243,"url":244,"summary":245,"summary_zh":9,"content":9,"source_name":246,"source_url":244,"published_at":247,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":248,"score_detail":249,"sources":252,"tags":254,"primary_topic":257,"secondary_topics":258,"classification":261,"search_phrases":281,"slug":284,"view_count":22,"doi":285,"paper":286,"created_at":318},4500,"Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11163942\u002Fv1","Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice。Research Square","Research Square","2026-10-08T00:00:00Z",74,{"impact":18,"substance":250,"depth":18,"authority":13,"freshness":17,"relevant":22,"comment":251},20,"将无人机遥感与深度学习结合用于水稻白叶枯病早期检测，方法有创新、结论具应用价值，但属预印本且为细分技术进展，适合进入主题聚合而非头条精选。",[253],{"name":246,"url":244},[27,255,29,62,256],"农业人工智能","病害检测",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},[259,260],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":262},{"candidates":263,"agricultural_evidence":57},[264,268,273,277],{"code":33,"score":71,"supported":57,"title":265,"abstract":266,"tags":267},[34],[34],[29],{"code":39,"score":71,"supported":57,"title":269,"abstract":271,"tags":272},[270],"deep learning",[270],[255],{"code":45,"score":71,"supported":57,"title":274,"abstract":275,"tags":276},[59],[59],[62],{"code":76,"score":22,"supported":14,"title":278,"abstract":279,"tags":280},[],[],[27],[282,283],"无人机遥感 水稻 白叶枯病","深度学习 水稻病害 早期检测","无人机遥感水稻白叶枯病-4500","10.21203\u002Frs.3.rs-11163942\u002Fv1",{"doi":285,"openalex_id":287,"authors":288,"venue":246,"cited_by_count":121,"oa_url":244,"card":9,"direction":126,"ingested_from":128},"W7221055917",[289,292,295,297,299,302,304,306,309,311,313,315],{"name":290,"orcid":291},"Carlito B. Balingbing","https:\u002F\u002Forcid.org\u002F0000-0002-3672-9253",{"name":293,"orcid":294},"Dmytro Chebotarov","https:\u002F\u002Forcid.org\u002F0000-0003-1351-9453",{"name":296,"orcid":9},"Ian  Carlo Perilla",{"name":298,"orcid":9},"Stephen Klassen",{"name":300,"orcid":301},"Nancy Castilla","https:\u002F\u002Forcid.org\u002F0000-0002-9143-4933",{"name":303,"orcid":9},"Raphael  Gabriel Carvajal",{"name":305,"orcid":9},"Kendrix Ortega",{"name":307,"orcid":308},"Joseph M. Sandro","https:\u002F\u002Forcid.org\u002F0000-0002-8311-2299",{"name":310,"orcid":9},"Nurmi Pangesti",{"name":312,"orcid":9},"Caesar Arloo R. Centeno",{"name":314,"orcid":9},"Arnel Rala",{"name":316,"orcid":317},"Li-Yu  Daisy Liu","https:\u002F\u002Forcid.org\u002F0000-0001-6997-8101","2026-10-09T23:30:18.390549Z",{"id":320,"title":321,"url":322,"summary":323,"summary_zh":324,"content":9,"source_name":325,"source_url":322,"published_at":326,"category":12,"cover_url":9,"hotness":327,"is_selected":14,"score":328,"score_detail":329,"sources":333,"tags":337,"primary_topic":339,"secondary_topics":340,"classification":343,"search_phrases":389,"slug":392,"view_count":121,"doi":393,"paper":394,"created_at":404},4310,"Comprehensive remote sensing and machine learning framework for multi-regional rice yield forecasting under hydroclimatic variability in Sahelian Niger","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149579","It is crucial to forecast rice yields effectively in order to improve agricultural planning and resilience to climate change in the Sahel, where production is greatly affected by hydroclimatic variability. This research has developed an integrated framework combining remote sensing analysis and machine learning to assess the variability in rice production in Niamey, Dosso, Tillaberi and Diffa, in Niger, over the period 2010–2025. They combined Landsat-derived NDVI and EVI with parameters such as evapotranspiration, precipitation, temperature, humidity, solar radiation, soil moisture, cultivated area, year and season. We processed and harmonised the datasets using Google Earth Engine and Python. We then evaluated four regression algorithms separately, Random Forest (RF), k-nearest neighbours (KNN), support vector regression (SVR) and XGBoost (XGB), for each region. The correlation analysis revealed modest positive links between rice yield and the NDVI (r = 0.27) and the EVI (r = 0.14), while a strong correlation was observed between the NDVI and the EVI (r = 0.80). The vegetation indices showed marked seasonal and interannual variability, generally exhibiting higher values during the wet season. Model performance varied considerably from one region to another","在萨赫勒地区，有效预测水稻产量对于改善农业规划和增强气候变化适应能力至关重要，因为该地区的生产在很大程度上受到水文气候变率的制约。本研究开发了一个集成框架，将遥感分析与机器学习相结合，以评估尼日尔尼亚美、多索、蒂拉贝里和迪法在2010—2025年期间水稻产量的变异性。研究将基于Landsat的归一化植被指数（NDVI）和增强型植被指数（EVI）与蒸散发、降水、温度、湿度、太阳辐射、土壤水分、耕地面积、年份和季节等参数相结合。利用Google Earth Engine和Python对数据集进行了处理和协调。随后，针对每个地区分别评估了四种回归算法：随机森林（RF）、k近邻（KNN）、支持向量回归（SVR）和XGBoost（XGB）。相关分析显示，水稻产量与NDVI（r = 0.27）和EVI（r = 0.14）之间存在弱正相关，而NDVI与EVI之间则观察到强相关（r = 0.80）。植被指数表现出明显的季节性和年际变异性，通常在湿季呈现较高值。模型性能在不同地区之间差异显著。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-05T00:00:00Z",25,72,{"impact":71,"substance":330,"depth":331,"authority":20,"freshness":21,"relevant":22,"comment":332},21,17,"基于Landsat植被指数与四种机器学习模型的多区域水稻产量预测研究，方法扎实、数据跨度长，但属区域性学术成果，对国内农业信息化有方法借鉴价值。",[334,335],{"name":325,"url":322},{"name":325,"url":336},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[27,255,29,338,62],"产量预测",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},[341,342],{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":344},{"candidates":345,"agricultural_evidence":57},[346,350,354,358,365,372,379,385],{"code":45,"score":19,"supported":57,"title":347,"abstract":348,"tags":349},[59],[62,59],[338,62],{"code":33,"score":65,"supported":57,"title":351,"abstract":352,"tags":353},[34],[29,34],[29],{"code":39,"score":65,"supported":57,"title":355,"abstract":356,"tags":357},[67],[30,67],[255],{"code":359,"score":131,"supported":57,"title":360,"abstract":361,"tags":364},"H2",[],[362,363],"土壤","soil",[],{"code":366,"score":131,"supported":57,"title":367,"abstract":368,"tags":371},"H3",[],[369,370],"蒸散发","evapotranspiration",[],{"code":373,"score":131,"supported":57,"title":374,"abstract":375,"tags":378},"H7",[],[376,377],"气候变化","climate change",[],{"code":380,"score":185,"supported":57,"title":381,"abstract":382,"tags":384},"J1",[],[383],"农业规划",[],{"code":76,"score":22,"supported":14,"title":386,"abstract":387,"tags":388},[],[],[27],[390,391],"尼日尔 水稻 遥感 产量预测","Landsat NDVI 水稻 机器学习","尼日尔水稻遥感产量预测-4310","10.5281\u002Fzenodo.23149579",{"doi":393,"openalex_id":395,"authors":396,"venue":325,"cited_by_count":121,"oa_url":322,"card":399,"direction":126,"ingested_from":128},"W7220391503",[397],{"name":398,"orcid":9},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":400,"method":401,"finding":402,"direction":126,"opportunity":403},"结合遥感植被指数与机器学习，预测尼日尔萨赫勒四地区2010–2025年水稻产量。","Landsat NDVI\u002FEVI 加气象土壤变量，GEE与Python处理，比较","NDVI\u002FEVI与产量仅弱相关，模型精度区域差异大，植被指数呈明显季节与年际波动。","可引入时序深度学习与迁移学习，解决跨区域泛化差及植被指数解释力弱的问题。","2026-10-06T23:30:20.077977Z",{"id":406,"title":407,"url":408,"summary":409,"summary_zh":410,"content":9,"source_name":411,"source_url":408,"published_at":412,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":413,"score_detail":414,"sources":416,"tags":418,"primary_topic":420,"secondary_topics":421,"classification":424,"search_phrases":449,"slug":452,"view_count":453,"doi":454,"paper":455,"created_at":471},3164,"Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16182034","Accurate plant height estimation is important for monitoring crop growth and supporting precision agricultural management. Manual measurements are labor-intensive, while LiDAR-based methods are expensive and require complex processing. UAV photogrammetry provides a lower-cost alternative but remains challenging in flooded rice paddies because of canopy deformation and difficulties in terrain extraction. This study proposes Rice-STNet, a spatiotemporal deep learning framework for end-to-end rice plant height estimation using multi-temporal UAV RGB imagery. Rice-STNet integrates a convolutional neural network for spatial feature extraction, Time2Vec for temporal encoding, and a gated recurrent unit network for modeling temporal dependencies across observation dates. The framework was evaluated using field data collected from rice paddies over two growing seasons. Rice-STNet achieved an R2 of 0.97, a root mean squared error of 1.97 cm, and a mean absolute error of 1.14 cm. It outperformed random forest, support vector regression, a CNN-only baseline, and a UAV photogrammetry-based point-cloud approach. In addition, the framework generated high-resolution plant height maps for field-scale analysis of spatial growth variability. These results underscore the importance of jointly modeling spatial and temporal characteristics for continuously evolving crop traits. The proposed framework offers an accurate, scalable, and non-destructive solution for large-scale crop phenotyping and precision agriculture.","准确的株高估算对于监测作物生长和支持精准农业管理具有重要意义。人工测量劳动强度大，而基于激光雷达（LiDAR）的方法成本高昂且需要复杂的处理。无人机摄影测量提供了一种成本较低的替代方案，但在淹水稻田中仍面临挑战，原因在于冠层变形和地形提取困难。本研究提出了Rice-STNet，一种时空深度学习框架，用于利用多时相无人机RGB影像进行端到端水稻株高估算。Rice-STNet集成了用于空间特征提取的卷积神经网络、用于时间编码的Time2Vec，以及用于建模观测日期之间时间依赖关系的门控循环单元网络。该框架利用两个生长季从稻田采集的田间数据进行了评估。Rice-STNet取得了R²为0.97、均方根误差为1.97 cm、平均绝对误差为1.14 cm的结果。其性能优于随机森林、支持向量回归、仅使用CNN的基线方法以及基于无人机摄影测量的点云方法。此外，该框架生成了高分辨率株高图，用于田块尺度空间生长变异性分析。这些结果凸显了联合建模空间与时间特征对于持续变化的作物性状的重要性。所提出的框架为大规模作物表型分析和精准农业提供了一种准确、可扩展且非破坏性的解决方案。","Agriculture","2026-09-21T00:00:00Z",80,{"impact":18,"substance":143,"depth":18,"authority":20,"freshness":21,"relevant":22,"comment":415},"提出时空深度学习框架Rice-STNet，用多时相无人机RGB影像实现水稻株高高精度估算，方法新颖、数据跨两个生长季，对作物表型与精准农业有实用价值。",[417],{"name":411,"url":408},[27,255,29,62,419],"作物表型",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},[422,423],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":425},{"candidates":426,"agricultural_evidence":57},[427,432,437,442],{"code":33,"score":18,"supported":57,"title":428,"abstract":429,"tags":431},[34],[29,430,34],"稻田",[29],{"code":39,"score":65,"supported":57,"title":433,"abstract":434,"tags":436},[270],[435,270],"深度学习",[255],{"code":45,"score":17,"supported":57,"title":438,"abstract":439,"tags":441},[],[419,440],"crop phenotyping",[419,62],{"code":76,"score":443,"supported":57,"title":444,"abstract":445,"tags":448},7,[],[446,447],"精准农业","precision agriculture",[27],[450,451],"无人机 RGB 水稻株高","Rice-STNet 水稻表型","无人机RGB水稻株高-3164",2,"10.3390\u002Fagriculture16182034",{"doi":454,"openalex_id":456,"authors":457,"venue":411,"cited_by_count":121,"oa_url":408,"card":466,"direction":126,"ingested_from":128},"W7213887432",[458,461,463],{"name":459,"orcid":460},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":462,"orcid":9},"Noboru Noguchi",{"name":464,"orcid":465},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":467,"method":468,"finding":469,"direction":126,"opportunity":470},"提出Rice-STNet时空深度学习框架，用多时相无人机RGB影像估算水稻株高。","CNN提取空间特征，Time2Vec编码时间，GRU建模时序依赖，两季稻田数据验","R²达0.97、RMSE 1.97cm，优于随机森林、SVR、纯CNN及点云方法。","可迁移至其他作物与多源遥感融合，探索轻量化模型及实时田间部署。","2026-09-22T23:30:18.545958Z",{"id":473,"title":474,"url":475,"summary":476,"summary_zh":477,"content":9,"source_name":478,"source_url":475,"published_at":479,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":480,"score_detail":481,"sources":483,"tags":485,"primary_topic":487,"secondary_topics":488,"classification":490,"search_phrases":507,"slug":510,"view_count":453,"doi":511,"paper":512,"created_at":535},2663,"Research on an automated mapping method for rice aboveground biomass based on low-altitude remote sensing","https:\u002F\u002Fdoi.org\u002F10.4081\u002Fjae.2026.2061","Accurate monitoring of rice aboveground biomass (AGB) is crucial for guiding agricultural production management. This study focuses on high-precision estimation and automated mapping of rice AGB. Field experiments were conducted in Nanxun District, Huzhou City, Zhejiang Province. We collected UAV RGB and multispectral images, rice AGB, and plant height data. By integrating vegetation indices, texture features, and plant height information, the AGB estimation model was established using algorithms such as Stacking. A framework combining \"SAM + MobileNetV3-Small classification\" was proposed to achieve automated paddy field extraction and phenology recognition. The results demonstrate that the rice AGB prediction model based on the Stacking ensemble algorithm performed excellently. The introduction of plant height significantly improved model accuracy. For example, during the heading stage, R2 increased from 0.421 to 0.739, and RPIQ rose from 1.995 to 3.015. The automated paddy field extraction and phenology recognition framework developed in this study achieved a segmentation accuracy of 0.968 and a classification accuracy of 0.993 on the dataset used in this study, without requiring manual annotation. This research provides a technical reference for automated and high-precision mapping of rice AGB.","准确监测水稻地上生物量(AGB)对指导农业生产管理至关重要。本研究聚焦水稻AGB的高精度估算与自动化制图。田间试验在浙江省湖州市南浔区开展，采集了无人机RGB和多光谱影像、水稻AGB及株高数据。通过融合植被指数、纹理特征和株高信息，利用Stacking等算法构建AGB估算模型。提出了一种“SAM+MobileNetV3-Small分类”框架，以实现稻田自动化提取和物候识别。结果表明，基于Stacking集成算法的水稻AGB预测模型表现优异，株高的引入显著提高了模型精度。例如，在抽穗期，R2从0.421提升至0.739，RPIQ从1.995提升至3.015。本研究开发的稻田自动化提取与物候识别框架在本研究数据集上实现了0.968的分割精度和0.993的分类精度，且无需人工标注。本研究为水稻AGB的自动化高精度制图提供了技术参考。","Journal of Agricultural Engineering","2026-09-15T00:00:00Z",78,{"impact":19,"substance":143,"depth":18,"authority":144,"freshness":17,"relevant":22,"comment":482},"基于无人机遥感与Stacking集成模型实现水稻地上生物量自动化制图，方法新颖、数据扎实，对精准农业管理有参考价值。",[484],{"name":478,"url":475},[27,486,28,29,419],"无人机",{"code":33,"slug":34,"name":29,"path":35,"parent_code":36},[489],{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":491},{"candidates":492,"agricultural_evidence":57},[493,498,503],{"code":33,"score":18,"supported":57,"title":494,"abstract":495,"tags":497},[34],[29,430,34,496],"paddy",[29],{"code":45,"score":20,"supported":57,"title":499,"abstract":500,"tags":502},[59],[501],"multispectral",[419,28],{"code":76,"score":22,"supported":14,"title":504,"abstract":505,"tags":506},[],[],[27],[508,509],"作物表型 农业遥感 智慧农业 无人机","作物表型 农业遥感","作物表型农业遥感智慧农业无人机-2663","10.4081\u002Fjae.2026.2061",{"doi":511,"openalex_id":513,"authors":514,"venue":478,"cited_by_count":121,"oa_url":475,"card":530,"direction":126,"ingested_from":128},"W7213229220",[515,517,519,521,523,526,528],{"name":516,"orcid":9},"Honggang Xu",{"name":518,"orcid":9},"Xuehan Li",{"name":520,"orcid":9},"Jia Shen",{"name":522,"orcid":9},"Ziyi Li",{"name":524,"orcid":525},"Zhe Li","https:\u002F\u002Forcid.org\u002F0009-0008-6496-3697",{"name":527,"orcid":9},"Yiming Li",{"name":529,"orcid":9},"Pengcheng Nie",{"tldr":531,"method":532,"finding":533,"direction":126,"opportunity":534},"基于无人机RGB与多光谱影像，结合株高与Stacking集成算法，实现水稻地上生物量高精度自动制图。","无人机RGB\u002F多光谱影像、植被指数、纹理与株高，Stacking集成及SAM+M","引入株高显著提升精度，抽穗期R²从0.421升至0.739；自动稻田提取与物候识别精度达0.968和","可探索多生育期、多品种下株高与纹理特征的迁移性，并耦合深度学习实现全自动生物量时空制图。","2026-09-16T23:30:28.929376Z",{"id":537,"title":538,"url":539,"summary":540,"summary_zh":541,"content":9,"source_name":542,"source_url":539,"published_at":543,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":544,"score_detail":545,"sources":547,"tags":549,"primary_topic":552,"secondary_topics":553,"classification":555,"search_phrases":580,"slug":583,"view_count":22,"doi":584,"paper":585,"created_at":609},1532,"Analysis of crop residue cover in the North China Plain based on multispectral remote sensing and machine learning","https:\u002F\u002Fdoi.org\u002F10.1080\u002F01431161.2026.2727176","Crop residue cover (CRC) is a critical parameter for evaluating conservation tillage practices, mitigating soil erosion, and developing models for global carbon cycle monitoring. Traditional optical remote sensing index-based methods are significantly affected by variations in soil and crop residue moisture content as well as interference from emerging subsequent crops, resulting in low estimation accuracy and poor stability of CRC. Due to the presence of subsequent crops, the non-photosynthetic vegetation fraction (fNPV) derived from linear spectral mixture analysis is typically lower than the actual field CRC. This study proposes a novel CRC estimation method based on linear spectral mixture analysis. The workflow consists of three main components: (1) development of a Crop Residue Random Forest (CRRF) index using a random forest regression model to simulate the narrowband SINDRI index – which is less sensitive to moisture – from broadband multispectral reflectance; (2) construction of a two-dimensional triangular feature space combining the CRRF and NDVI indices, followed by linear spectral mixture analysis to simultaneously estimate field fNPV, photosynthetic vegetation fraction (fPV), and bare soil fraction (fBS); and (3) retrieval of the true CRC fraction at the sowing stage using the formula CRC = fNPV \u002F (1 − fPV). The proposed method was validated and applied regionally using multi-temporal Sentinel-2 MSI and MODIS imagery. Results demonstrate that: (1) the method effectively mitigates moisture interference and achieves high-accuracy fNPV estimation (R2 = 0.84, RMSE = 0.10); (2) the integration of Sentinel-2 and MODIS sensors enables stable estimation and spatio-temporal dynamic analysis of CRC across the North China Plain, with high temporal consistency between images acquired approximately 16 days apart (the majority of agricultural pixels showing absolute differences within ±0.15). This approach provides an efficient and robust technical solution for remote sensing monitoring of CRC fraction in complex agricultural environments and offers a valuable methodological reference for the assessment of conservation tillage practices.","作物残茬覆盖度（CRC）是评估保护性耕作措施、减缓土壤侵蚀以及构建全球碳循环监测模型的关键参数。传统光学遥感指数方法受土壤和作物残茬含水量变化及新生后茬作物干扰的影响显著，导致CRC估算精度低、稳定性差。由于后茬作物的存在，基于线性光谱混合分析提取的非光合植被覆盖度（fNPV）通常低于田间实际CRC值。本研究提出了一种基于线性光谱混合分析的CRC估算新方法。该方法流程主要包括三个部分：（1）利用随机森林回归模型模拟对水分敏感性较低的窄带SINDRI指数，进而构建作物残茬随机森林（CRRF）指数，该指数可由宽带多光谱反射率计算得到；（2）结合CRRF与NDVI指数构建二维三角特征空间，通过线性光谱混合分析同时估算田间fNPV、光合植被覆盖度（fPV）和裸土覆盖度（fBS）；（3）利用公式CRC = fNPV \u002F (1 − fPV)反演播种期真实CRC值。该方法利用多时相Sentinel-2 MSI和MODIS影像进行了验证及区域应用。结果表明：（1）该方法能有效削弱水分干扰，实现高精度fNPV估算（R² = 0.84，RMSE = 0.10）；（2）Sentinel-2与MODIS传感器的联合应用可实现华北平原CRC的稳定估算及时空动态分析，且间隔约16天获取的影像间具有较高时间一致性（绝大多数农业像元的绝对差异在±0.15以内）。该方法为复杂农业环境下CRC覆盖度的遥感监测提供了高效、稳健的技术方案，也为保护性耕作措施评估提供了有价值的方法参考。","International Journal of Remote Sensing","2026-09-02T00:00:00Z",76,{"impact":18,"substance":250,"depth":18,"authority":20,"freshness":443,"relevant":22,"comment":546},"提出基于随机森林与线性光谱混合分析的秸秆覆盖度估算新方法，在华北平原多源遥感数据上验证有效，对保护性耕作监测有方法论参考价值。",[548],{"name":542,"url":539},[27,28,30,550,551],"保护性耕作","秸秆覆盖",{"code":45,"slug":46,"name":47,"path":48,"parent_code":43},[554],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":50,"locked":14,"version":51,"method":52,"evidence":556},{"candidates":557,"agricultural_evidence":57},[558,563,567,571,576],{"code":45,"score":559,"supported":57,"title":560,"abstract":561,"tags":562},26,[59,501],[62,59,501],[28],{"code":39,"score":21,"supported":57,"title":564,"abstract":565,"tags":566},[67],[],[30],{"code":359,"score":131,"supported":57,"title":568,"abstract":569,"tags":570},[],[362,363],[],{"code":197,"score":572,"supported":57,"title":573,"abstract":574,"tags":575},4,[],[550],[550],{"code":76,"score":22,"supported":14,"title":577,"abstract":578,"tags":579},[],[],[27],[581,582],"保护性耕作 农业遥感 智慧农业 机器学习","保护性耕作 农业遥感","保护性耕作农业遥感智慧农业机器学习-1532","10.1080\u002F01431161.2026.2727176",{"doi":584,"openalex_id":586,"authors":587,"venue":542,"cited_by_count":121,"oa_url":9,"card":604,"direction":126,"ingested_from":128},"W7205007595",[588,591,594,596,599,602],{"name":589,"orcid":590},"Jibo Yue","https:\u002F\u002Forcid.org\u002F0000-0001-9766-5313",{"name":592,"orcid":593},"Ranran Yang","https:\u002F\u002Forcid.org\u002F0000-0003-1937-2042",{"name":595,"orcid":9},"Yinghao Lin",{"name":597,"orcid":598},"Nianxu Xu","https:\u002F\u002Forcid.org\u002F0000-0002-0152-8750",{"name":600,"orcid":601},"Qingjiu Tian","https:\u002F\u002Forcid.org\u002F0000-0003-0986-6479",{"name":603,"orcid":9},"Jia Tian",{"tldr":605,"method":606,"finding":607,"direction":126,"opportunity":608},"提出基于线性光谱混合分析和随机森林的作物残茬覆盖度遥感估算方法，应用于华北平原。","随机森林模拟窄带SINDRI，结合NDVI构建三角特征空间，线性光谱混合分析估算","方法有效缓解水分干扰，fNPV估算R²=0.84，RMSE=0.10，多源影像时间一致性高。","可探索将方法扩展至其他作物类型或区域，或结合高光谱影像提高精度，并研究残茬覆盖度与土壤碳动态的关系。","2026-09-03T23:30:30.109393Z"]