[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2622":3,"related-2622":103},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":66,"slug":69,"view_count":52,"doi":70,"paper":71,"created_at":102},2622,"Synergizing process-based modeling and data-driven learning for precision nitrogen optimization in winter wheat","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104983","Synergizing process-based modeling and data-driven learning for precision nitrogen optimization in winter wheat。Agricultural Systems",null,"Agricultural Systems","2026-09-16T00:00:00Z","论文",10,false,79,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},18,20,17,14,1,"将过程模型与数据驱动学习融合用于冬小麦精准氮肥优化，方法新颖、发表于核心期刊且时效性强，具备进入每日精选的价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","精准施肥","作物模型","冬小麦",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,50,56,61],{"code":31,"score":44,"supported":45,"title":46,"abstract":48,"tags":49},23,true,[47,32],"winter wheat",[47,32],[29],{"code":51,"score":52,"supported":13,"title":53,"abstract":54,"tags":55},"I2",2,[],[],[28,26],{"code":57,"score":20,"supported":13,"title":58,"abstract":59,"tags":60},"F3",[],[],[27],{"code":62,"score":20,"supported":13,"title":63,"abstract":64,"tags":65},"I1",[],[],[25],[67,68],"农业人工智能 作物模型 智慧农业 精准施肥","农业人工智能 作物模型","农业人工智能作物模型智慧农业精准施肥-2622","10.1016\u002Fj.agsy.2026.104983",{"doi":70,"openalex_id":72,"authors":73,"venue":9,"cited_by_count":100,"oa_url":6,"card":8,"direction":8,"ingested_from":101},"W7213352238",[74,76,79,82,84,86,88,90,92,94,96,98],{"name":75,"orcid":8},"Yuru Ye",{"name":77,"orcid":78},"Qian Wang","https:\u002F\u002Forcid.org\u002F0000-0003-0750-7843",{"name":80,"orcid":81},"Davide Cammarano","https:\u002F\u002Forcid.org\u002F0000-0003-0918-550X",{"name":83,"orcid":8},"Kang Yu",{"name":85,"orcid":8},"Siva K. Balasundram",{"name":87,"orcid":8},"Wei Li",{"name":89,"orcid":8},"Xiuli Li",{"name":91,"orcid":8},"Xiaojun Liu",{"name":93,"orcid":8},"Yongchao Tian",{"name":95,"orcid":8},"Yan Zhu",{"name":97,"orcid":8},"Weixing Cao",{"name":99,"orcid":8},"Qiang Cao",0,"openalex","2026-09-16T23:30:05.340754Z",{"total":104,"page":20,"page_size":104,"items":105},6,[106,171,231,299,371,463],{"id":107,"title":108,"url":109,"summary":110,"summary_zh":8,"content":8,"source_name":111,"source_url":8,"published_at":112,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":113,"score_detail":114,"sources":119,"tags":121,"primary_topic":125,"secondary_topics":126,"classification":127,"search_phrases":157,"slug":160,"view_count":117,"doi":8,"paper":161,"created_at":170},3325,"MBF-HybridNet：在极端气候下仍可提前一月预测冬小麦产量的多分支AI模型——Qingdao六县R² 0.756-0.765 MAPE 4.2%","https:\u002F\u002Fbioengineer.org\u002Fnew-multi-branch-ai-model-predicts-winter-wheat-yields-weeks-before-harvest-even-under-extreme-weather\u002F","MBF-HybridNet由青岛六县研究团队开发和测试：采用多分支并行架构，包括处理日常遥感和气象数据的动态变量模块、处理年度尺度极端气候指数数据的动态ECI模块以及处理土壤属性的静态变量模块。动态模块堆叠三个二维卷积层，插入自注意力机制；静态模块独立处理土壤有机碳、阳离子交换容量、pH、砂和粘土含量。研究团队计算了九个极端气候指数（热日、热应力强度、连续热日、霜日、冷应力强度、连续冷日、强降水日、连续湿日和连续干日）用于每个生长阶段。2004至2019年留一年交叉验证，MBF-HybridNet在三个累积生长阶段的R²达到0.756-0.765，平均绝对百分比误差约为4.2%。","MBF-HybridNet 2026 (Qingdao)","2026-09-17T00:00:00Z",78,{"impact":16,"substance":115,"depth":16,"authority":116,"freshness":117,"relevant":20,"comment":118},22,12,8,"多分支AI融合遥感气象与极端气候指数，提前一月预测冬小麦产量且精度可靠，方法新颖、数据扎实，对农业信息化与智慧农业有较高参考价值。",[120],{"name":111,"url":109},[25,26,122,123,29,124],"产量预测","遥感监测","极端气候",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":128},{"candidates":129,"agricultural_evidence":45},[130,135,142,149,153],{"code":31,"score":131,"supported":45,"title":132,"abstract":133,"tags":134},9,[33],[],[29],{"code":136,"score":137,"supported":45,"title":138,"abstract":139,"tags":141},"I3",5,[],[140],"遥感",[122,123],{"code":143,"score":144,"supported":45,"title":145,"abstract":146,"tags":148},"H2",3,[],[147],"土壤",[],{"code":62,"score":20,"supported":13,"title":150,"abstract":151,"tags":152},[],[],[25],{"code":51,"score":20,"supported":13,"title":154,"abstract":155,"tags":156},[],[],[26],[158,159],"MBF-HybridNet 冬小麦 产量预测","青岛 冬小麦 遥感 极端气候","MBF-HybridNet冬小麦产量预测-3325",{"doi":8,"openalex_id":8,"authors":162,"venue":8,"cited_by_count":100,"oa_url":8,"card":163,"direction":167,"ingested_from":169},[],{"tldr":164,"method":165,"finding":166,"direction":167,"opportunity":168},"提出多分支AI模型MBF-HybridNet，融合遥感、气象与土壤数据，提前一月预测冬小麦产量。","多分支并行架构，含2D卷积、自注意力与极端气候指数，2004-2019年留一年交","在青岛六县三个累积生长阶段R²达0.756-0.765，MAPE约4.2%，极端气候下仍可提前一月预","农业人工智能与决策模型","可探索极端气候指数与深度学习结合在其他作物或区域的泛化能力，并提升可解释性。","agent","2026-09-24T00:04:02.748442Z",{"id":172,"title":173,"url":174,"summary":175,"summary_zh":8,"content":8,"source_name":176,"source_url":8,"published_at":177,"category":11,"cover_url":8,"hotness":178,"is_selected":13,"score":179,"score_detail":180,"sources":182,"tags":187,"primary_topic":190,"secondary_topics":191,"classification":192,"search_phrases":218,"slug":221,"view_count":52,"doi":8,"paper":222,"created_at":230},2998,"物候阶段渐进式多源数据融合的县域冬小麦产量预测","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-09-18\u002Fdoc-inisheny8322115.shtml","西安财经大学王毅等联合江苏大学张立元副教授、西安理工大学西北旱区生态水利国家重点实验室、中国科学院重庆绿色智能技术研究院团队，以河南省100个冬小麦主产县为研究区融合2013—2022年遥感变量、气象变量和日光诱导叶绿素荧光光合变量，构建覆盖冬小麦分蘖期至成熟期的多源时序特征集。提出物候阶段渐进式多源数据融合方法明确不同物候阶段信息累积对县域冬小麦估产性能的影响。","智慧农业(中英文)2026,8(4):70-84","2026-09-18T00:00:00Z",25,80,{"impact":16,"substance":115,"depth":16,"authority":19,"freshness":117,"relevant":20,"comment":181},"以河南100个主产县2013—2022年遥感、气象与SIF数据构建物候阶段渐进式融合估产方法，数据规模与方法新颖性突出，对县域粮食产量预测有参考价值。",[183,184],{"name":176,"url":174},{"name":185,"url":186},"《智慧农业（中英文）》2026年第4期","https:\u002F\u002Ffinance.sina.cn\u002F2026-09-18\u002Fdetail-inisheny8322115.d.html",[25,26,188,29,189],"遥感估产","多源数据融合",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":193},{"candidates":194,"agricultural_evidence":45},[195,199,205,209,213],{"code":31,"score":116,"supported":45,"title":196,"abstract":197,"tags":198},[33],[33],[29],{"code":136,"score":200,"supported":45,"title":201,"abstract":202,"tags":204},7,[],[140,203],"估产",[188],{"code":62,"score":20,"supported":13,"title":206,"abstract":207,"tags":208},[],[],[25],{"code":51,"score":20,"supported":13,"title":210,"abstract":211,"tags":212},[],[],[26],{"code":214,"score":20,"supported":13,"title":215,"abstract":216,"tags":217},"I5",[],[],[189],[219,220],"河南 冬小麦 遥感估产","物候阶段 多源数据融合 产量预测","河南冬小麦遥感估产-2998",{"doi":8,"openalex_id":8,"authors":223,"venue":8,"cited_by_count":100,"oa_url":8,"card":224,"direction":228,"ingested_from":169},[],{"tldr":225,"method":226,"finding":227,"direction":228,"opportunity":229},"融合遥感、气象与SIF数据，提出物候阶段渐进式融合方法预测河南县域冬小麦产量。","2013—2022年河南100县遥感、气象、SIF多源时序特征，按物候阶段渐进融","明确不同物候阶段信息累积对县域冬小麦估产性能的影响，提升预测精度。","农业遥感与作物表型","可探索物候自适应加权与深度学习融合，并迁移至其他作物及极端气候情景下的县域估产。","2026-09-20T00:03:07.932461Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":8,"content":8,"source_name":236,"source_url":8,"published_at":237,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":238,"score_detail":239,"sources":244,"tags":246,"primary_topic":249,"secondary_topics":250,"classification":260,"search_phrases":287,"slug":290,"view_count":52,"doi":8,"paper":291,"created_at":298},2854,"面向冬小麦水分含量的无人机遥感自动机器学习预测——MDPI Remote Sensing","https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F18\u002F18\u002F3161","本研究探索了无人机遥感快速准确评估冬小麦水分含量的潜力。在开花期和灌浆期使用配备多光谱、RGB和热红外相机的无人机获取高分辨率冠层遥感图像。集成地面真值采样数据与无人机遥感数据,使用自动机器学习(AutoML)框架建立回归模型预测冬小麦水分含量(MC)。结果表明,MC预测在灌浆期表现最佳,TIR传感器精度最高(R²=0.812,MAE=0.0204,RMSE=0.0274)。多传感器融合相比单传感器方法进一步提升预测性能,MC预测的R²达0.876、MAE 0.0191、RMSE 0.0259。来自中国农业科学院农田灌溉研究所。","MDPI Remote Sensing","2026-09-15T00:00:00Z",74,{"impact":240,"substance":241,"depth":18,"authority":242,"freshness":117,"relevant":20,"comment":243},15,21,13,"中国农科院团队用AutoML融合多光谱、RGB与热红外无人机数据预测冬小麦水分含量，多传感器融合R²达0.876，方法新颖、结论可靠，对精准灌溉有实用价值，值得进入每日精选。",[245],{"name":236,"url":234},[25,26,247,29,248],"无人机遥感","多传感器融合",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[251,256],{"code":136,"slug":252,"name":253,"path":254,"parent_code":255},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"code":51,"slug":257,"name":258,"path":259,"parent_code":255},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":38,"locked":13,"version":39,"method":40,"evidence":261},{"candidates":262,"agricultural_evidence":45},[263,268,272,277,283],{"code":136,"score":17,"supported":45,"title":264,"abstract":266,"tags":267},[140,265],"remote sensing",[140],[247],{"code":31,"score":116,"supported":45,"title":269,"abstract":270,"tags":271},[33],[33],[29],{"code":51,"score":116,"supported":45,"title":273,"abstract":275,"tags":276},[274],"机器学习",[274],[26],{"code":278,"score":144,"supported":45,"title":279,"abstract":280,"tags":282},"H3",[],[281],"灌溉",[],{"code":62,"score":20,"supported":13,"title":284,"abstract":285,"tags":286},[],[],[25],[288,289],"农业人工智能 多传感器融合 无人机遥感 智慧农业","农业人工智能 多传感器融合","农业人工智能多传感器融合无人机遥感智慧农业-2854",{"doi":8,"openalex_id":8,"authors":292,"venue":8,"cited_by_count":100,"oa_url":8,"card":293,"direction":228,"ingested_from":169},[],{"tldr":294,"method":295,"finding":296,"direction":228,"opportunity":297},"用无人机多传感器遥感结合AutoML预测冬小麦水分含量。","无人机多光谱、RGB、热红外图像+地面真值，AutoML回归建模。","灌浆期热红外精度最高，多传感器融合将R²提升至0.876。","可探索不同生育期与品种的泛化性，及将水分预测接入灌溉决策系统。","2026-09-18T00:03:30.758419Z",{"id":300,"title":301,"url":302,"summary":303,"summary_zh":304,"content":8,"source_name":305,"source_url":302,"published_at":306,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":307,"score_detail":308,"sources":310,"tags":312,"primary_topic":314,"secondary_topics":315,"classification":318,"search_phrases":350,"slug":353,"view_count":144,"doi":354,"paper":355,"created_at":370},1996,"An Interpretable BO-TCBDA Deep Learning Framework for Winter Wheat Yield Estimation Using Multi-Source Remote Sensing Data","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183061","Reliable crop yield estimation is fundamental to food security and efficient agricultural management. However, current deep learning models still face limitations in selecting and integrating multi-source features, and their high predictive accuracy is often accompanied by limited interpretability. This study introduces a Bayesian Optimization–Temporal Convolutional Network–Bidirectional Long Short-Term Memory–Dual Attention (BO-TCBDA) deep learning framework for winter wheat yield estimation. Using Henan Province, China, as the study area, county-level winter wheat yield from 2013 to 2022 was estimated using the Enhanced Vegetation Index (EVI), Leaf Area Index (LAI), Solar-Induced Chlorophyll Fluorescence (SIF), and climate data. The proposed model was compared with five commonly used machine learning and deep learning models. BO-TCBDA achieved the best performance, with an R2 of 0.823 and an RMSE of 561.26 kg\u002Fha. SIF improved the predictive performance of all models, with statistically significant gains observed in the deep learning models. The dual-attention mechanism provided interpretable insights by revealing relatively balanced contributions among the input features and highlighting the grain-filling stage through temporal attention. Furthermore, SHAP-based cross-validation analysis identified T12, corresponding to the latter part of the jointing stage, as the period with the highest contribution to yield prediction. The model also achieved an R2 of approximately 0.80 about 25 days before harvest. Overall, BO-TCBDA provides an accurate and interpretable approach for county-level winter wheat yield estimation and supports regional food security assessments and precision agriculture.","可靠的作物产量估算对于粮食安全和高效农业管理至关重要。然而，当前的深度学习模型在多源特征的选择与整合方面仍存在局限，且高预测精度往往伴随着有限的可解释性。本研究提出了一种基于贝叶斯优化–时间卷积网络–双向长短期记忆–双重注意力（BO-TCBDA）的深度学习框架，用于冬小麦产量估算。以中国河南省为研究区域，利用增强型植被指数（EVI）、叶面积指数（LAI）、太阳诱导叶绿素荧光（SIF）及气候数据，对2013至2022年县级冬小麦产量进行了估算。将所提模型与五种常用的机器学习和深度学习模型进行了比较。BO-TCBDA取得了最佳性能，其决定系数（R²）为0.823，均方根误差（RMSE）为561.26千克\u002F公顷。SIF提升了所有模型的预测性能，其中在深度学习模型中观察到了统计学上显著的增益。双重注意力机制通过揭示输入特征间相对均衡的贡献，并借助时间注意力突出灌浆期，提供了可解释性的见解。此外，基于SHAP的交叉验证分析识别出T12时段（对应拔节期后期）对产量预测的贡献最大。该模型在收获前约25天时，R²亦达到约0.80。总体而言，BO-TCBDA为县级冬小麦产量估算提供了一种准确且可解释的方法，并支持区域粮食安全评估和精准农业实践。","Remote Sensing","2026-09-08T00:00:00Z",73,{"impact":16,"substance":115,"depth":16,"authority":242,"freshness":52,"relevant":20,"comment":309},"提出可解释的深度学习框架，结合多源遥感数据提升冬小麦估产精度与可解释性，对精准农业有实质贡献。",[311],{"name":305,"url":302},[25,26,140,313,29],"产量估算",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[316,317],{"code":51,"slug":257,"name":258,"path":259,"parent_code":255},{"code":136,"slug":252,"name":253,"path":254,"parent_code":255},{"status":38,"locked":13,"version":39,"method":40,"evidence":319},{"candidates":320,"agricultural_evidence":45},[321,326,333,337,343],{"code":31,"score":322,"supported":45,"title":323,"abstract":324,"tags":325},26,[47,32],[33,47,32],[29],{"code":51,"score":16,"supported":45,"title":327,"abstract":329,"tags":332},[328],"deep learning",[330,274,331,328],"深度学习","machine learning",[26],{"code":136,"score":12,"supported":45,"title":334,"abstract":335,"tags":336},[265],[],[313,140],{"code":62,"score":200,"supported":45,"title":338,"abstract":339,"tags":342},[],[340,341],"精准农业","precision agriculture",[25],{"code":344,"score":104,"supported":45,"title":345,"abstract":346,"tags":349},"A8",[],[347,348],"粮食安全","food security",[],[351,352],"农业人工智能 产量估算 智慧农业 冬小麦","农业人工智能 产量估算","农业人工智能产量估算智慧农业冬小麦-1996","10.3390\u002Frs18183061",{"doi":354,"openalex_id":356,"authors":357,"venue":305,"cited_by_count":100,"oa_url":302,"card":365,"direction":228,"ingested_from":101},"W7211938917",[358,360,362],{"name":359,"orcid":8},"Anqi Xue",{"name":361,"orcid":8},"Shufang Tian",{"name":363,"orcid":364},"Tingyan Fu","https:\u002F\u002Forcid.org\u002F0000-0003-4207-4211",{"tldr":366,"method":367,"finding":368,"direction":167,"opportunity":369},"提出BO-TCBDA深度学习框架，融合多源遥感数据估算冬小麦产量，兼具高精度与可解释性。","贝叶斯优化、TCN、BiLSTM、双注意力机制，结合EVI、LAI、SIF及气候","BO-TCBDA性能最优（R²=0.823），SIF提升预测，拔节后期贡献最大，收获前25天可预测。","可探索将双注意力与SHAP结合用于其他作物或区域，或开发实时预警系统，提升模型泛化与实用性。","2026-09-09T23:30:22.411579Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":376,"content":8,"source_name":377,"source_url":374,"published_at":378,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":379,"score_detail":380,"sources":384,"tags":386,"primary_topic":387,"secondary_topics":388,"classification":389,"search_phrases":426,"slug":428,"view_count":144,"doi":429,"paper":430,"created_at":462},1596,"AgriPINN: A Process-Informed Neural Network for Interpretable and Scalable Crop Biomass Prediction under Water Stress","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102539","Accurate estimation of crop above-ground dry biomass (AGB) under water stress is important for assessing agricultural production, managing irrigation, and supporting water-security-oriented decision-making. Data-driven models enable efficient large-scale prediction but often provide limited physiological interpretation and can be sensitive to domain shifts, whereas process-based crop models require extensive calibration and detailed management inputs. We propose AgriPINN, a process-informed neural network that embeds a differentiable biomass-growth equation derived from LINTUL5 into neural-network training. AGB is the sole supervised target. The network simultaneously estimates leaf area index (LAI), photosynthetically active radiation (PAR), radiation-use efficiency (RUE), and the water-stress factor ( F W ); their predicted values enter the process residual, whereas the corresponding field measurements are held out from optimisation and used only for post hoc evaluation. AgriPINN is pretrained on 65 years of SIMPLACE simulations covering 397 German NUTS-3 regions and fine-tuned on three years of wheat and maize field experiments under sheltered, rainfed, and irrigated treatments. On the main benchmark, AgriPINN reduces RMSE by 29.7% for winter wheat and 22.8% for maize relative to CNN–Transformer. Relative to the strongest non-AgriPINN baseline for each crop, the corresponding reductions are 9.0% and 2.2%. Additional evaluations include four representative neural backbones, sensitivity analysis of the process-loss weight, an ablation without pretraining, and perturbation tests on simulated labels. The transferability demonstrated in this study is limited to the independent datasets and the German temperate agro-ecological setting evaluated here.","水分胁迫下作物地上部干生物量（AGB）的准确估算对于评估农业生产、管理灌溉以及支持以水安全为导向的决策至关重要。数据驱动模型能够实现高效的大尺度预测，但往往提供的生理学解释有限，且可能对领域偏移敏感；而基于过程的作物模型则需要大量校准和详细的管理输入。我们提出AgriPINN，一种过程信息神经网络，将源自LINTUL5的可微生物量增长方程嵌入神经网络训练中。AGB是唯一的监督目标。该网络同时估算叶面积指数（LAI）、光合有效辐射（PAR）、辐射利用效率（RUE）以及水分胁迫因子（F W ）；其预测值进入过程残差，而相应的田间实测值则从优化中排除，仅用于事后评估。AgriPINN在覆盖德国397个NUTS-3区域的65年SIMPLACE模拟数据上进行了预训练，并在三年遮雨、雨养和灌溉处理下的小麦和玉米田间试验数据上进行了微调。在主要基准测试中，相对于CNN–Transformer，AgriPINN使冬小麦的RMSE降低了29.7%，玉米降低了22.8%。相对于每种作物最强的非AgriPINN基线，相应的降幅分别为9.0%和2.2%。额外评估包括四种代表性神经骨干网络、过程损失权重的敏感性分析、无预训练的消融实验以及模拟标签的扰动测试。本研究所展示的可迁移性仅限于所评估的独立数据集和德国温带农业生态情境。","Smart Agricultural Technology","2026-09-01T00:00:00Z",75,{"impact":16,"substance":115,"depth":381,"authority":116,"freshness":382,"relevant":20,"comment":383},19,4,"提出过程信息神经网络AgriPINN，结合机理模型与深度学习，显著提升水分胁迫下作物生物量预测精度，方法新颖且数据扎实。",[385],{"name":377,"url":374},[25,26,28,188],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":390},{"candidates":391,"agricultural_evidence":45},[392,396,403,408,414,418,422],{"code":31,"score":131,"supported":45,"title":393,"abstract":394,"tags":395},[],[33,47,32],[],{"code":397,"score":104,"supported":45,"title":398,"abstract":399,"tags":402},"A3",[],[400,401],"玉米","maize",[],{"code":278,"score":104,"supported":45,"title":404,"abstract":405,"tags":407},[],[281,406],"irrigation",[],{"code":409,"score":144,"supported":45,"title":410,"abstract":411,"tags":413},"H6",[],[412],"农业生态",[],{"code":51,"score":52,"supported":13,"title":415,"abstract":416,"tags":417},[],[],[28,26],{"code":62,"score":20,"supported":13,"title":419,"abstract":420,"tags":421},[],[],[25],{"code":136,"score":20,"supported":13,"title":423,"abstract":424,"tags":425},[],[],[188],[427,68],"农业人工智能 作物模型 智慧农业 遥感估产","农业人工智能作物模型智慧农业遥感估产-1596","10.1016\u002Fj.atech.2026.102539",{"doi":429,"openalex_id":431,"authors":432,"venue":377,"cited_by_count":100,"oa_url":374,"card":457,"direction":167,"ingested_from":101},"W7125531933",[433,435,437,440,443,446,448,450,452,454],{"name":434,"orcid":8},"Yue Shi",{"name":436,"orcid":8},"Amit Kumar Srivastava",{"name":438,"orcid":439},"Dominik Behrend","https:\u002F\u002Forcid.org\u002F0009-0000-9081-7169",{"name":441,"orcid":442},"Thomas Gaiser","https:\u002F\u002Forcid.org\u002F0000-0002-5820-2364",{"name":444,"orcid":445},"Thuy Huu Nguyen","https:\u002F\u002Forcid.org\u002F0000-0003-3870-986X",{"name":447,"orcid":8},"Xin Zhang",{"name":449,"orcid":8},"Tam Sobeih",{"name":451,"orcid":8},"Frank Ewert",{"name":453,"orcid":8},"Krishnagopal Halder",{"name":455,"orcid":456},"Liangxiu Han","https:\u002F\u002Forcid.org\u002F0000-0003-2491-7473",{"tldr":458,"method":459,"finding":460,"direction":167,"opportunity":461},"提出过程信息神经网络AgriPINN，嵌入作物生长方程，提升水分胁迫下生物量预测精度与可解释性。","将LINTUL5生长方程嵌入神经网络训练，预训练于SIMPLACE模拟数据，微调","相比CNN-Transformer，冬小麦RMSE降低29.7%，玉米降低22.8%，且具有生理可解","可探索将过程信息神经网络扩展到其他作物、气候区或胁迫类型，并验证其跨域泛化能力。","2026-09-04T23:30:04.364676Z",{"id":464,"title":465,"url":466,"summary":467,"summary_zh":468,"content":8,"source_name":469,"source_url":466,"published_at":470,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":471,"score_detail":472,"sources":475,"tags":477,"primary_topic":479,"secondary_topics":480,"classification":487,"search_phrases":515,"slug":518,"view_count":100,"doi":519,"paper":520,"created_at":538},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",77,{"impact":473,"substance":241,"depth":18,"authority":242,"freshness":12,"relevant":20,"comment":474},16,"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。",[476],{"name":469,"url":466},[25,274,123,478,29],"土壤墒情",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[481,486],{"code":143,"slug":482,"name":483,"path":484,"parent_code":485},"soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":51,"slug":257,"name":258,"path":259,"parent_code":255},{"status":38,"locked":13,"version":39,"method":40,"evidence":488},{"candidates":489,"agricultural_evidence":45},[490,494,498,502,507,511],{"code":31,"score":322,"supported":45,"title":491,"abstract":492,"tags":493},[47,32],[33,47,32],[29],{"code":143,"score":240,"supported":45,"title":495,"abstract":496,"tags":497},[482],[147,482],[478],{"code":51,"score":240,"supported":45,"title":499,"abstract":500,"tags":501},[331],[274,331],[274],{"code":136,"score":12,"supported":45,"title":503,"abstract":504,"tags":506},[],[140,265,505],"multispectral",[123],{"code":278,"score":104,"supported":45,"title":508,"abstract":509,"tags":510},[],[281,406],[],{"code":62,"score":382,"supported":45,"title":512,"abstract":513,"tags":514},[],[25],[25],[516,517],"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":519,"openalex_id":521,"authors":522,"venue":469,"cited_by_count":100,"oa_url":466,"card":532,"direction":537,"ingested_from":101},"W7223156204",[523,526,528,530],{"name":524,"orcid":525},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":527,"orcid":8},"Yi Zhang",{"name":529,"orcid":8},"WEI Lei",{"name":531,"orcid":8},"Chengcai Zhang",{"tldr":533,"method":534,"finding":535,"direction":228,"opportunity":536},"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。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z"]