[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2998":3,"related-2998":45},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"search_phrases":30,"slug":33,"view_count":34,"doi":8,"paper":35,"created_at":44},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。",null,"智慧农业(中英文)2026,8(4):70-84","2026-09-18T00:00:00Z","论文",10,false,80,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,14,8,1,"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。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","遥感估产","冬小麦","多源数据融合",[31,32],"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",0,{"doi":8,"openalex_id":8,"authors":36,"venue":8,"cited_by_count":34,"oa_url":8,"card":37,"direction":41,"ingested_from":43},[],{"tldr":38,"method":39,"finding":40,"direction":41,"opportunity":42},"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。","agent","2026-09-20T00:03:07.932461Z",{"total":46,"page":20,"page_size":46,"items":47},6,[48,79,131,170,217,270],{"id":49,"title":50,"url":51,"summary":52,"summary_zh":8,"content":8,"source_name":53,"source_url":8,"published_at":54,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":55,"score_detail":56,"sources":62,"tags":64,"search_phrases":67,"slug":70,"view_count":34,"doi":8,"paper":71,"created_at":78},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":57,"substance":58,"depth":59,"authority":60,"freshness":19,"relevant":20,"comment":61},15,21,17,13,"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。",[63],{"name":53,"url":51},[25,26,65,28,66],"无人机遥感","多传感器融合",[68,69],"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":72,"venue":8,"cited_by_count":34,"oa_url":8,"card":73,"direction":41,"ingested_from":43},[],{"tldr":74,"method":75,"finding":76,"direction":41,"opportunity":77},"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":80,"title":81,"url":82,"summary":83,"summary_zh":8,"content":8,"source_name":84,"source_url":82,"published_at":85,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":86,"score_detail":87,"sources":90,"tags":92,"search_phrases":95,"slug":98,"view_count":34,"doi":99,"paper":100,"created_at":130},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","Agricultural Systems","2026-09-16T00:00:00Z",79,{"impact":16,"substance":88,"depth":59,"authority":18,"freshness":12,"relevant":20,"comment":89},20,"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。",[91],{"name":84,"url":82},[25,26,93,94,28],"精准施肥","作物模型",[96,97],"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":99,"openalex_id":101,"authors":102,"venue":84,"cited_by_count":34,"oa_url":82,"card":8,"direction":8,"ingested_from":129},"W7213352238",[103,105,108,111,113,115,117,119,121,123,125,127],{"name":104,"orcid":8},"Yuru Ye",{"name":106,"orcid":107},"Qian Wang","https:\u002F\u002Forcid.org\u002F0000-0003-0750-7843",{"name":109,"orcid":110},"Davide Cammarano","https:\u002F\u002Forcid.org\u002F0000-0003-0918-550X",{"name":112,"orcid":8},"Kang Yu",{"name":114,"orcid":8},"Siva K. Balasundram",{"name":116,"orcid":8},"Wei Li",{"name":118,"orcid":8},"Xiuli Li",{"name":120,"orcid":8},"Xiaojun Liu",{"name":122,"orcid":8},"Yongchao Tian",{"name":124,"orcid":8},"Yan Zhu",{"name":126,"orcid":8},"Weixing Cao",{"name":128,"orcid":8},"Qiang Cao","openalex","2026-09-16T23:30:05.340754Z",{"id":132,"title":133,"url":134,"summary":135,"summary_zh":136,"content":8,"source_name":137,"source_url":134,"published_at":138,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":139,"score_detail":140,"sources":143,"tags":145,"search_phrases":148,"slug":151,"view_count":34,"doi":152,"paper":153,"created_at":169},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":17,"depth":16,"authority":60,"freshness":141,"relevant":20,"comment":142},2,"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。",[144],{"name":137,"url":134},[25,26,146,147,28],"遥感","产量估算",[149,150],"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":152,"openalex_id":154,"authors":155,"venue":137,"cited_by_count":34,"oa_url":134,"card":163,"direction":41,"ingested_from":129},"W7211938917",[156,158,160],{"name":157,"orcid":8},"Anqi Xue",{"name":159,"orcid":8},"Shufang Tian",{"name":161,"orcid":162},"Tingyan Fu","https:\u002F\u002Forcid.org\u002F0000-0003-4207-4211",{"tldr":164,"method":165,"finding":166,"direction":167,"opportunity":168},"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。","农业人工智能与决策模型","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":171,"title":172,"url":173,"summary":174,"summary_zh":175,"content":8,"source_name":176,"source_url":173,"published_at":138,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":177,"score_detail":178,"sources":181,"tags":183,"search_phrases":185,"slug":188,"view_count":34,"doi":189,"paper":190,"created_at":216},1966,"Knowledge-guided deep learning improves estimation of rice aboveground biomass","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112398","Knowledge-guided deep learning improves estimation of rice aboveground biomass。Computers and Electronics in Agriculture","知识引导的深度学习提升了水稻地上生物量估算精度。《农业计算机与电子》","Computers and Electronics in Agriculture",64,{"impact":57,"substance":88,"depth":57,"authority":179,"freshness":141,"relevant":20,"comment":180},12,"知识引导深度学习提升水稻生物量估算，方法新颖，对精准农业有参考价值。",[182],{"name":176,"url":173},[25,26,184,27],"水稻",[186,187],"农业人工智能 智慧农业 遥感估产 水稻","农业人工智能 智慧农业","农业人工智能智慧农业遥感估产水稻-1966","10.1016\u002Fj.compag.2026.112398",{"doi":189,"openalex_id":191,"authors":192,"venue":176,"cited_by_count":34,"oa_url":8,"card":211,"direction":41,"ingested_from":129},"W7211953860",[193,195,198,201,204,206,208],{"name":194,"orcid":8},"Qiyu Tian",{"name":196,"orcid":197},"Renhai Zhong","https:\u002F\u002Forcid.org\u002F0000-0001-8922-0138",{"name":199,"orcid":200},"Xingguo Xiong","https:\u002F\u002Forcid.org\u002F0000-0001-8635-8764",{"name":202,"orcid":203},"Hao Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-5122-0412",{"name":205,"orcid":8},"Jingfeng Huang",{"name":207,"orcid":8},"Zhenhong Du",{"name":209,"orcid":210},"Tao Lin","https:\u002F\u002Forcid.org\u002F0000-0001-9721-5363",{"tldr":212,"method":213,"finding":214,"direction":41,"opportunity":215},"提出知识引导的深度学习模型，提高水稻地上生物量估算精度。","结合作物生长模型与深度学习，利用遥感数据估算生物量。","知识引导的深度学习显著优于传统方法，估算精度更高。","可探索将更多农学知识融入深度学习，提升其他作物性状估算的泛化能力。","2026-09-09T23:30:01.433974Z",{"id":218,"title":219,"url":220,"summary":221,"summary_zh":222,"content":8,"source_name":223,"source_url":220,"published_at":224,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":225,"score_detail":226,"sources":230,"tags":232,"search_phrases":233,"slug":235,"view_count":34,"doi":236,"paper":237,"created_at":269},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":17,"depth":227,"authority":179,"freshness":228,"relevant":20,"comment":229},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。",[231],{"name":223,"url":220},[25,26,94,27],[234,97],"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":236,"openalex_id":238,"authors":239,"venue":223,"cited_by_count":34,"oa_url":220,"card":264,"direction":167,"ingested_from":129},"W7125531933",[240,242,244,247,250,253,255,257,259,261],{"name":241,"orcid":8},"Yue Shi",{"name":243,"orcid":8},"Amit Kumar Srivastava",{"name":245,"orcid":246},"Dominik Behrend","https:\u002F\u002Forcid.org\u002F0009-0000-9081-7169",{"name":248,"orcid":249},"Thomas Gaiser","https:\u002F\u002Forcid.org\u002F0000-0002-5820-2364",{"name":251,"orcid":252},"Thuy Huu Nguyen","https:\u002F\u002Forcid.org\u002F0000-0003-3870-986X",{"name":254,"orcid":8},"Xin Zhang",{"name":256,"orcid":8},"Tam Sobeih",{"name":258,"orcid":8},"Frank Ewert",{"name":260,"orcid":8},"Krishnagopal Halder",{"name":262,"orcid":263},"Liangxiu Han","https:\u002F\u002Forcid.org\u002F0000-0003-2491-7473",{"tldr":265,"method":266,"finding":267,"direction":167,"opportunity":268},"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":271,"title":272,"url":273,"summary":274,"summary_zh":8,"content":8,"source_name":275,"source_url":8,"published_at":276,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":277,"score_detail":278,"sources":280,"tags":282,"search_phrases":286,"slug":289,"view_count":34,"doi":8,"paper":290,"created_at":297},3002,"改进生物神经网络的农业播种机全覆盖路径规划","https:\u002F\u002Fwww.mdpi.com\u002F2077-0472\u002F16\u002F18\u002F1968","江苏大学魏军等提出一种考虑播种与非播种运动模式切换机制的改进生物神经网络（BNN）方法，基于周围环境条件将下一节点状态分类为播种、封闭或转移节点。在BNN景观引导下机器沿平行直线路径继续播种操作；检测到封闭节点时切换至非播种模式并使用深度优先搜索算法搜索潜在封闭区域；检测到转移节点时同样切换非播种模式搜索合理的新目标节点。仿真表明该方法实现播种操作的完全覆盖同时避免重复遍历已播种区域。","MDPI Agriculture 16(18):1968","2026-09-14T00:00:00Z",69,{"impact":179,"substance":58,"depth":59,"authority":60,"freshness":46,"relevant":20,"comment":279},"提出改进生物神经网络的全覆盖路径规划方法，方法新颖、结论可靠，但属细分领域学术进展，公共影响有限。",[281],{"name":275,"url":273},[25,26,283,284,285],"智能农机","路径规划","播种机",[287,288],"江苏大学 播种机 全覆盖路径规划","生物神经网络 播种机 路径规划","江苏大学播种机全覆盖路径规划-3002",{"doi":8,"openalex_id":8,"authors":291,"venue":8,"cited_by_count":34,"oa_url":8,"card":292,"direction":167,"ingested_from":43},[],{"tldr":293,"method":294,"finding":295,"direction":167,"opportunity":296},"提出改进生物神经网络，实现农业播种机全覆盖路径规划并避免重复播种。","改进BNN结合节点分类与深度优先搜索，仿真验证。","方法实现播种完全覆盖，同时避免重复遍历已播种区域。","可结合真实农田地形与多机协同，验证动态环境下的路径规划鲁棒性。","2026-09-20T00:03:08.288198Z"]