[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1540":3,"related-1540":112},{"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":31,"secondary_topics":37,"classification":44,"search_phrases":80,"slug":83,"view_count":84,"doi":85,"paper":86,"created_at":111},1540,"Three-way debate – measurements, pedotransfer functions, and inverse modeling – input strategy for soil hydraulic parameters in wheat simulations","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffagro.2026.1912611","Accurate characterization of soil hydraulic parameters is crucial for simulating soil-plant-water dynamics in agroecosystem models. Hydraulic parameters, specifically the field capacity and permanent wilting point, govern the soil water balance and define the limits of plant-available water. This study evaluated the impact of soil hydraulic parameters in the Decision Support System for Agrotechnology Transfer (DSSAT) by comparing simulated soil water dynamics, wheat growth, and yield with observed data. To this end, a detailed 3-yr field dataset (2022, 2023, and 2025) from South Germany was employed, distinguished by its integration of wheat growth with an extensive daily record of soil water content and matric potential measurements at multiple depths. Within the DSSAT shell, permanent wilting point and field capacity were derived using both the Saxton and Rawls pedotransfer functions (PTFs); these estimates were then evaluated against lab-measured and sensor data using retention curves and soil-water simulations. In particular, the Saxton PTF introduced higher uncertainty in soil-water simulations and was selected as the starting point for an inverse modeling approach using Bayesian and Grid search algorithms to optimize field capacity and permanent wilting point. Using soil water content, wheat growth, and biomass data as target variables in the optimization procedure significantly reduced the normalized Root Mean Square Error (nRMSE) for both optimization algorithms. Overall model performance improved significantly, as shown by a reduction in nRMSE from 20% of the Saxton PTF to ≤ 10% for Bayesian targeting of grain weight and Grid search targeting of above-ground biomass, thereby enhancing the accuracy of wheat growth and yield predictions. This study provides a realistic evaluation of how measured, estimated, and calibrated parameters affect the soil water balance, demonstrating that plant response data can serve as an effective target variable for optimizing field capacity and permanent wilting point.","土壤水力参数的准确表征对于农业生态系统模型中土壤-植物-水分动态的模拟至关重要。水力参数，特别是田间持水量和永久萎蔫点，控制着土壤水平衡，并界定了植物可利用水的范围。本研究通过在农业技术转让决策支持系统（DSSAT）中比较模拟的土壤水分动态、小麦生长和产量与观测数据，评估了土壤水力参数的影响。为此，采用了来自德国南部的一项详细的3年田间数据集（2022年、2023年和2025年），该数据集的独特之处在于将小麦生长与多个深度土壤含水量和基质势的密集逐日记录相结合。在DSSAT框架内，使用Saxton和Rawls土壤传递函数（PTFs）推导了永久萎蔫点和田间持水量；随后，利用持水曲线和土壤水分模拟，将这些估计值与实验室测量和传感器数据进行了对比评估。特别是，Saxton PTF在土壤水分模拟中引入了较高的不确定性，因此被选为逆建模方法的起点，采用贝叶斯和网格搜索算法优化田间持水量和永久萎蔫点。在优化过程中，以土壤含水量、小麦生长和生物量数据作为目标变量，显著降低了两种优化算法的归一化均方根误差（nRMSE）。整体模型性能显著提升，表现为nRMSE从Saxton PTF的20%降至贝叶斯算法以籽粒重量为目标时的≤10%，以及网格搜索算法以地上生物量为目标时的≤10%，从而提高了小麦生长和产量预测的准确性。本研究对实测、估算和校准参数如何影响土壤水平衡进行了现实评估，证明植物响应数据可作为优化田间持水量和永久萎蔫点的有效目标变量。",null,"Frontiers in Agronomy","2026-09-01T00:00:00Z","论文",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,18,12,7,1,"研究评估不同土壤水力参数获取方式对小麦模拟的影响，方法严谨，数据详实，对精准农业有参考价值。",[25],{"name":10,"url":6},[27,28,29,30],"智慧农业","作物模型","土壤水动力学","参数优化",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[38],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":45,"locked":14,"version":46,"method":47,"evidence":48},"classified","2026-10-22.2","rules",{"candidates":49,"agricultural_evidence":52},[50,56,61,68,75],{"code":32,"score":51,"supported":52,"title":53,"abstract":54,"tags":55},14,true,[33],[34,33],[],{"code":39,"score":51,"supported":52,"title":57,"abstract":58,"tags":60},[40],[59,40],"土壤",[],{"code":62,"score":63,"supported":52,"title":64,"abstract":65,"tags":67},"I2",4,[],[66],"decision support",[28],{"code":69,"score":70,"supported":52,"title":71,"abstract":72,"tags":74},"H6",3,[],[73],"农业生态",[],{"code":76,"score":22,"supported":14,"title":77,"abstract":78,"tags":79},"I1",[],[],[27],[81,82],"土壤水动力学 作物模型 参数优化 智慧农业","土壤水动力学 作物模型","土壤水动力学作物模型参数优化智慧农业-1540",2,"10.3389\u002Ffagro.2026.1912611",{"doi":85,"openalex_id":87,"authors":88,"venue":10,"cited_by_count":101,"oa_url":102,"card":103,"direction":109,"ingested_from":110},"W7204969062",[89,92,95,98],{"name":90,"orcid":91},"Jonas Trenz","https:\u002F\u002Forcid.org\u002F0000-0002-4850-5767",{"name":93,"orcid":94},"Emir Memic","https:\u002F\u002Forcid.org\u002F0000-0002-0184-5481",{"name":96,"orcid":97},"Dennis Gekeler","https:\u002F\u002Forcid.org\u002F0009-0003-3725-205X",{"name":99,"orcid":100},"Simone Graeff‐Hönninger","https:\u002F\u002Forcid.org\u002F0000-0001-9996-961X",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fagronomy\u002Farticles\u002F10.3389\u002Ffagro.2026.1912611\u002Fpdf",{"tldr":104,"method":105,"finding":106,"direction":107,"opportunity":108},"比较测量、传递函数和反演建模获取土壤水力参数对小麦模拟的影响。","使用DSSAT模型，结合Saxton和Rawls PTF、贝叶斯和网格搜索反演优","反演优化显著降低nRMSE至≤10%，提高小麦生长和产量预测精度。","农业人工智能与决策模型","可探索利用作物生长数据反演土壤参数在其他作物和区域的应用，或开发更高效的优化算法。","农业绿色发展与碳","openalex","2026-09-03T23:31:04.621734Z",{"total":113,"page":22,"page_size":113,"items":114},6,[115,207,281,370,461,533],{"id":116,"title":117,"url":118,"summary":119,"summary_zh":120,"content":9,"source_name":121,"source_url":118,"published_at":122,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":123,"score_detail":124,"sources":130,"tags":132,"primary_topic":137,"secondary_topics":138,"classification":145,"search_phrases":182,"slug":185,"view_count":101,"doi":186,"paper":187,"created_at":206},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":125,"substance":126,"depth":127,"authority":128,"freshness":13,"relevant":22,"comment":129},16,21,17,13,"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。",[131],{"name":121,"url":118},[27,133,134,135,136],"机器学习","遥感监测","土壤墒情","冬小麦",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[139,140],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"code":62,"slug":141,"name":142,"path":143,"parent_code":144},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":45,"locked":14,"version":46,"method":47,"evidence":146},{"candidates":147,"agricultural_evidence":52},[148,154,158,163,171,178],{"code":32,"score":149,"supported":52,"title":150,"abstract":152,"tags":153},26,[151,33],"winter wheat",[34,151,33],[136],{"code":39,"score":17,"supported":52,"title":155,"abstract":156,"tags":157},[40],[59,40],[135],{"code":62,"score":17,"supported":52,"title":159,"abstract":161,"tags":162},[160],"machine learning",[133,160],[133],{"code":164,"score":13,"supported":52,"title":165,"abstract":166,"tags":170},"I3",[],[167,168,169],"遥感","remote sensing","multispectral",[134],{"code":172,"score":113,"supported":52,"title":173,"abstract":174,"tags":177},"H3",[],[175,176],"灌溉","irrigation",[],{"code":76,"score":63,"supported":52,"title":179,"abstract":180,"tags":181},[],[27],[27],[183,184],"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":186,"openalex_id":188,"authors":189,"venue":121,"cited_by_count":101,"oa_url":118,"card":199,"direction":205,"ingested_from":110},"W7223156204",[190,193,195,197],{"name":191,"orcid":192},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":194,"orcid":9},"Yi Zhang",{"name":196,"orcid":9},"WEI Lei",{"name":198,"orcid":9},"Chengcai Zhang",{"tldr":200,"method":201,"finding":202,"direction":203,"opportunity":204},"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。","农业遥感与作物表型","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",{"id":208,"title":209,"url":210,"summary":211,"summary_zh":212,"content":9,"source_name":213,"source_url":210,"published_at":214,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":215,"score_detail":216,"sources":220,"tags":222,"primary_topic":227,"secondary_topics":228,"classification":233,"search_phrases":263,"slug":266,"view_count":22,"doi":267,"paper":268,"created_at":280},2033,"Regenerative benefits of legume–wheat intercropping systems on soil quality and resource-use efficiency under deficit irrigation in Egypt","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1923296","Background Soil degradation and water scarcity are major constraints to sustainable cereal production in arid and semi-arid regions. Legume–wheat intercropping may simultaneously improve soil quality and resource-use efficiency, but its regenerative performance under deficit irrigation remains insufficiently quantified. Methods A two-year field experiment was conducted during 2021\u002F22 and 2022\u002F23 in El-Minia Governorate, Middle Egypt, using a split-plot design with three replications. Three irrigation regimes—100%, 85%, and 70% of crop evapotranspiration (ETc)—were evaluated in combination with sole wheat and wheat intercropped with faba bean, pea, or fahl clover. Soil organic matter, available N, P, and K, soil pH, Soil Quality Index (SQI), crop yield, land equivalent ratio (LER), water equivalent ratio (WER), and change in water use (DWU) were assessed. Results All legume–wheat intercropping systems significantly improved soil organic matter and available macronutrients relative to sole wheat. Faba bean–wheat generally produced the greatest improvements in soil properties and SQI. The beneficial effects of intercropping persisted under severe deficit irrigation (70% ETc). Pea–wheat achieved the highest total LER (1.39) and WER (1.26), together with the highest wheat grain yield and a DWU of -20.48%. Conclusion Legume–wheat intercropping enhanced soil quality, land-use efficiency, and water-use efficiency under deficit irrigation. The results demonstrate that integrating legumes with wheat can provide a practical regenerative strategy for improving productivity and resilience of wheat-based systems in water-limited environments.","背景 土壤退化与水资源短缺是干旱和半干旱地区可持续谷物生产的主要限制因素。豆科作物-小麦间作可能同时改善土壤质量和资源利用效率，但其在亏缺灌溉条件下的再生性能仍缺乏充分的定量评估。方法 于2021\u002F22和2022\u002F23年度在埃及中部明亚省开展了一项为期两年的田间试验，采用裂区设计，设三次重复。评估了三种灌溉制度——分别为作物蒸散量（ETc）的100%、85%和70%——与单作小麦及小麦分别与蚕豆、豌豆或埃及三叶草间作的组合。测定了土壤有机质、速效氮、磷、钾、土壤pH、土壤质量指数（SQI）、作物产量、土地当量比（LER）、水当量比（WER）以及水分利用变化量（DWU）。结果 与单作小麦相比，所有豆科作物-小麦间作系统均显著提高了土壤有机质和速效大量元素含量。蚕豆-小麦间作通常在改善土壤性质和SQI方面效果最佳。间作的有益效应在严重亏缺灌溉（70% ETc）条件下依然持续。豌豆-小麦间作实现了最高的总LER（1.39）和WER（1.26），同时小麦籽粒产量最高，DWU为-20.48%。结论 豆科作物-小麦间作在亏缺灌溉条件下提高了土壤质量、土地利用效率和水分利用效率。结果表明，将豆科作物与小麦整合可为水资源受限环境中提高小麦种植系统的生产力和韧性提供一种实用的再生策略。","Frontiers in Sustainable Food Systems","2026-09-09T00:00:00Z",76,{"impact":125,"substance":217,"depth":127,"authority":128,"freshness":218,"relevant":22,"comment":219},22,8,"两年田间试验量化了亏缺灌溉下豆科-小麦间作的土壤改良与资源利用效率提升，数据扎实、结论可靠，对干旱半干旱区小麦可持续生产有参考价值。",[221],{"name":213,"url":210},[34,223,224,225,226],"土壤健康","节水灌溉","间作套种","豆科绿肥",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[229,232],{"code":172,"slug":176,"name":230,"path":231,"parent_code":43},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":234},{"candidates":235,"agricultural_evidence":52},[236,242,246,250,257],{"code":172,"score":19,"supported":52,"title":237,"abstract":238,"tags":241},[176],[175,239,176,240],"水资源","evapotranspiration",[224],{"code":32,"score":17,"supported":52,"title":243,"abstract":244,"tags":245},[33],[34,33],[34],{"code":39,"score":17,"supported":52,"title":247,"abstract":248,"tags":249},[40],[59,40],[223],{"code":251,"score":51,"supported":52,"title":252,"abstract":254,"tags":256},"A7",[253],"intercropping",[255,253],"间作",[],{"code":258,"score":70,"supported":52,"title":259,"abstract":260,"tags":262},"H7",[],[261],"干旱",[],[264,265],"土壤健康 节水灌溉 豆科绿肥 间作套种","土壤健康 节水灌溉","土壤健康节水灌溉豆科绿肥间作套种-2033","10.3389\u002Ffsufs.2026.1923296",{"doi":267,"openalex_id":269,"authors":270,"venue":213,"cited_by_count":101,"oa_url":210,"card":275,"direction":109,"ingested_from":110},"W7212074132",[271,273],{"name":272,"orcid":9},"S.A.H. Ouda",{"name":274,"orcid":9},"Abd El-Hafeez Zohry",{"tldr":276,"method":277,"finding":278,"direction":109,"opportunity":279},"埃及两年试验表明，豆科-小麦间作在亏缺灌溉下仍能提升土壤质量与资源利用效率。","裂区试验，3种灌溉水平与4种种植模式，测SQI、LER、WER等指标。","蚕豆-小麦改善土壤最佳，豌豆-小麦LER和WER最高，间作效益在70%ETc下仍存在。","可探究间作系统在不同气候与土壤类型下的长期固碳减排潜力及微生物机制。","2026-09-10T23:30:07.672063Z",{"id":282,"title":283,"url":284,"summary":285,"summary_zh":286,"content":9,"source_name":287,"source_url":284,"published_at":288,"category":12,"cover_url":9,"hotness":13,"is_selected":52,"score":289,"score_detail":290,"sources":294,"tags":296,"primary_topic":299,"secondary_topics":300,"classification":305,"search_phrases":334,"slug":337,"view_count":218,"doi":338,"paper":339,"created_at":369},4087,"Improving regional winter wheat yield estimation by assimilating cross-scale heterogeneity information from UAV and satellite remote sensing","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115701","Accurate high-resolution winter wheat yield estimation remains challenging in heterogeneous agricultural systems. Conventional yield estimation approaches remain limited by high uncertainty (process-based crop models) or weak transferability due to insufficient physical knowledge and scarce sample sizes (statistical models based on remote sensing data). Data assimilation offers a promising approach to overcome these limitations, but its performance is constrained by the neglect of heterogeneous information within assimilation grids, particularly in low-intensity agricultural systems. Therefore, we developed a novel cross-scale data assimilation framework to enhance winter wheat yield estimation by integrating unmanned aerial vehicle (UAV) and satellite remote sensing with the WOFOST crop model. First, UAV-derived crop-soil parameters, including leaf area index (LAI), aboveground biomass (AGB), and soil moisture at 10 and 20 cm depths (SMC-10 and SMC-20), served as a bridge linking in situ sampling data with Sentinel satellite images. Next, a mixture density network (MDN) was employed to construct an upscaling model for predicting probability distributions, thereby obtaining the distribution of crop-soil parameters within each satellite pixel as field heterogeneity information. Finally, these heterogeneity distributions were incorporated into WOFOST through an improved particle filter to generate high-resolution yield (10 m × 10 m) estimates at the regional scale. The results showed that robust crop-soil parameter inversion models were constructed using random forest with multispectral and thermal UAV images (R 2 : 0.73–0.88; NRMSE: 12.30%–22.83%). The MDN quantified within-pixel heterogeneity of crop-soil parameters through a UAV-satellite upscaling approach. The joint assimilation of LAI, AGB, and SMC-10 achieved optimal winter wheat yield estimation performance for MDN-based cross-scale data assimilation (R 2 = 0.83, NRMSE = 15.70% in 2024–2025), outperforming satellite-based and mean-based cross-scale assimilation. The proposed framework showed stable interannual performance in Xianyang (RMSE ≤758 kg ha −1 , NRMSE ≤17.20% in 2017–2023) and reasonable transferability in two external winter wheat regions (RMSE ≤943 kg ha −1 ; NRMSE ≤18.29% in Baoding and Changji). Overall, the cross-scale data assimilation framework exhibited strong performance in wheat yield estimation and would provide scientific support for intensive agricultural development.","在异质性农业系统中，实现准确的高分辨率冬小麦产量估算仍具挑战性。传统产量估算方法受限于较高不确定性（基于过程的作物模型）或可迁移性较弱（基于遥感数据的统计模型），后者源于物理知识不足和样本量稀缺。数据同化为克服这些局限提供了一种有前景的途径，但其性能受到同化网格内异质性信息被忽略的制约，尤其是在低强度农业系统中。因此，我们开发了一种新的跨尺度数据同化框架，通过将无人机（UAV）和卫星遥感与WOFOST作物模型相结合，提升冬小麦产量估算。首先，无人机获取的作物-土壤参数，包括叶面积指数（LAI）、地上生物量（AGB）以及10和20 cm深度土壤水分（SMC-10和SMC-20），作为连接原位采样数据与Sentinel卫星影像的桥梁。接下来，采用混合密度网络（MDN）构建升尺度模型以预测概率分布，从而获得每个卫星像元内作物-土壤参数的分布，作为田块异质性信息。最后，通过改进的粒子滤波器将这些异质性分布纳入WOFOST，以生成区域尺度的高分辨率产量（10 m × 10 m）估算。结果表明，利用随机森林结合多光谱和热红外无人机影像构建了稳健的作物-土壤参数反演模型（R²：0.73–0.88；NRMSE：12.30%–22.83%）。MDN通过无人机-卫星升尺度方法量化了作物-土壤参数的像元内异质性。LAI、AGB和SMC-10的联合同化使基于MDN的跨尺度数据同化取得了最优的冬小麦产量估算性能（2024–2025年R² = 0.83，NRMSE = 15.70%），优于基于卫星和基于均值的跨尺度同化。所提出的框架在咸阳表现出稳定的年际性能（2017–2023年RMSE ≤758 kg ha⁻¹，NRMSE ≤17.20%），并在两个外部冬小麦区域具有合理的可迁移性（保定和昌吉RMSE ≤943 kg ha⁻¹；NRMSE ≤18.29%）。总体而言，该跨尺度数据同化框架在小麦产量估算中表现出较强性能，可为集约化农业发展提供科学支持。","Remote Sensing of Environment","2026-10-01T00:00:00Z",83,{"impact":19,"substance":291,"depth":19,"authority":17,"freshness":292,"relevant":22,"comment":293},23,9,"该研究提出跨尺度数据同化框架，融合无人机与卫星遥感提升区域冬小麦估产精度，方法新颖、验证充分，对精准农业与农业遥感应用具有较高参考价值。",[295],{"name":287,"url":284},[27,28,134,297,298],"数据同化","小麦产量",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[301],{"code":164,"slug":302,"name":303,"path":304,"parent_code":144},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":45,"locked":14,"version":46,"method":47,"evidence":306},{"candidates":307,"agricultural_evidence":52},[308,313,317,321,325,329],{"code":32,"score":309,"supported":52,"title":310,"abstract":311,"tags":312},25,[151,33],[34,151,33],[],{"code":164,"score":19,"supported":52,"title":314,"abstract":315,"tags":316},[168],[167,168,169],[134],{"code":39,"score":113,"supported":52,"title":318,"abstract":319,"tags":320},[],[59,40],[],{"code":76,"score":22,"supported":14,"title":322,"abstract":323,"tags":324},[],[],[27],{"code":62,"score":22,"supported":14,"title":326,"abstract":327,"tags":328},[],[],[28],{"code":330,"score":22,"supported":14,"title":331,"abstract":332,"tags":333},"I5",[],[],[297],[335,336],"无人机 卫星 遥感 冬小麦 估产","WOFOST 数据同化 小麦","无人机卫星遥感冬小麦估产-4087","10.1016\u002Fj.rse.2026.115701",{"doi":338,"openalex_id":340,"authors":341,"venue":287,"cited_by_count":101,"oa_url":284,"card":364,"direction":203,"ingested_from":110},"W7215051418",[342,344,346,348,351,353,356,358,360,362],{"name":343,"orcid":9},"Zhikai Cheng",{"name":345,"orcid":9},"Xiaobo Gu",{"name":347,"orcid":9},"Yang Xu",{"name":349,"orcid":350},"Xiaohai Fang","https:\u002F\u002Forcid.org\u002F0000-0003-1322-1366",{"name":352,"orcid":9},"Zhengtao Zhang",{"name":354,"orcid":355},"Penglin Li","https:\u002F\u002Forcid.org\u002F0009-0005-2706-1326",{"name":357,"orcid":9},"Yupeng Li",{"name":359,"orcid":9},"Shikun Sun",{"name":361,"orcid":9},"Yadan Du",{"name":363,"orcid":9},"Huanjie Cai",{"tldr":365,"method":366,"finding":367,"direction":203,"opportunity":368},"构建跨尺度数据同化框架，融合无人机与卫星遥感提升区域冬小麦产量估算精度。","UAV-Sentinel数据、混合密度网络升尺度、改进粒子滤波同化WOFOST模","联合同化LAI、AGB与SMC-10最优，R²=0.83，跨年与跨区表现稳定。","可探索异质农田下多源遥感与作物模型同化的普适性及低成本无人机采样优化。","2026-10-03T23:30:33.709814Z",{"id":371,"title":372,"url":373,"summary":374,"summary_zh":375,"content":9,"source_name":376,"source_url":373,"published_at":377,"category":12,"cover_url":9,"hotness":13,"is_selected":52,"score":378,"score_detail":379,"sources":382,"tags":384,"primary_topic":386,"secondary_topics":390,"classification":392,"search_phrases":424,"slug":427,"view_count":113,"doi":428,"paper":429,"created_at":460},3525,"Multi-source data assimilation of Sentinel-2 reflectance and SMAP soil moisture into APSIM for maize biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10442-6","Crop growth models (CGMs) are valuable tools for agricultural monitoring. However, the need for many input parameters, the uncertainties related to model parametrization and structure, and the lack of spatial information motivate the application of techniques such as data assimilation (DA). This paper proposes a DA framework to improve maize biomass estimation. A particle filter (PF) was used to assimilate remotely sensed reflectance and soil moisture (SM) data, both independently and simultaneously, into the Agricultural Production Systems sIMulator (APSIM) model. Reflectance observations from Sentinel-2 were assimilated through coupling APSIM with the radiative transfer model (RTM) PROSAIL, while SMAP L-band SM products were directly assimilated into APSIM. The synthetic experiment, designed to evaluate the reliability of the proposed procedure, highlighted the strength of assimilating reflectance to constrain crop traits and of SM to provide complementary information on crop water status and to contribute to more robust ensemble trajectories. Real-case results confirmed these findings. DA assimilation of SM proved valuable particularly under data gaps and drought conditions. Although it did not consistently surpass single-source assimilation strategies, the joint assimilation yielded consistent results, especially in 2023, where RMSE, nRMSE and bias were 1258.83 kg\u002Fha, 16.62%, and - 220.52 kg\u002Fha, respectively. The proposed framework demonstrates the potential of multi-source DA to enhance biomass estimation and support robust, spatially explicit crop monitoring.","作物生长模型（CGM）是农业监测的重要工具。然而，其对大量输入参数的需求、模型参数化与结构相关的不确定性以及空间信息的缺乏，推动了数据同化（DA）等技术的应用。本文提出了一种数据同化框架，以改进玉米生物量估算。采用粒子滤波（PF）将遥感反射率和土壤水分（SM）数据分别独立及同时同化进入农业生产系统模拟器（APSIM）模型。Sentinel-2反射率观测数据通过将APSIM与辐射传输模型（RTM）PROSAIL耦合进行同化，而SMAP L波段土壤水分产品则直接同化进入APSIM。为评估所提方法可靠性而设计的合成实验，凸显了同化反射率在约束作物性状方面的优势，以及同化土壤水分在提供作物水分状况补充信息和促进更稳健集合轨迹方面的作用。实际案例结果证实了这些发现。土壤水分数据同化在数据缺失和干旱条件下尤为有价值。尽管联合同化未能持续超越单源同化策略，但其结果具有一致性，尤其在2023年，RMSE、nRMSE和偏差分别为1258.83 kg\u002Fha、16.62%和-220.52 kg\u002Fha。所提出的框架展示了多源数据同化在增强生物量估算和支持稳健、空间显式作物监测方面的潜力。","Precision Agriculture","2026-09-25T00:00:00Z",82,{"impact":19,"substance":217,"depth":380,"authority":51,"freshness":292,"relevant":22,"comment":381},19,"将Sentinel-2反射率与SMAP土壤水分同化进APSIM模型估算玉米生物量，方法新颖、结论可靠，对作物遥感监测有参考价值。",[383],{"name":376,"url":373},[27,385,28,134,297],"玉米",{"code":387,"slug":388,"name":385,"path":389,"parent_code":36},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize",[391],{"code":39,"slug":40,"name":41,"path":42,"parent_code":43},{"status":45,"locked":14,"version":46,"method":47,"evidence":393},{"candidates":394,"agricultural_evidence":52},[395,399,403,408,412,416,420],{"code":387,"score":17,"supported":52,"title":396,"abstract":397,"tags":398},[388],[385,388],[385],{"code":39,"score":51,"supported":52,"title":400,"abstract":401,"tags":402},[40],[59,40],[],{"code":258,"score":113,"supported":52,"title":404,"abstract":405,"tags":407},[],[261,406],"drought",[],{"code":164,"score":63,"supported":52,"title":409,"abstract":410,"tags":411},[],[167],[134],{"code":76,"score":22,"supported":14,"title":413,"abstract":414,"tags":415},[],[],[27],{"code":62,"score":22,"supported":14,"title":417,"abstract":418,"tags":419},[],[],[28],{"code":330,"score":22,"supported":14,"title":421,"abstract":422,"tags":423},[],[],[297],[425,426],"Sentinel-2 SMAP APSIM 玉米生物量","多源数据同化 玉米 遥感","Sentinel-2SMAPAPSIM玉米生物量-3525","10.1007\u002Fs11119-026-10442-6",{"doi":428,"openalex_id":430,"authors":431,"venue":376,"cited_by_count":101,"oa_url":373,"card":455,"direction":203,"ingested_from":110},"W7214405444",[432,434,437,440,443,445,447,450,452],{"name":433,"orcid":9},"Manuela Montella",{"name":435,"orcid":436},"Christian Bossung","https:\u002F\u002Forcid.org\u002F0000-0003-4651-2645",{"name":438,"orcid":439},"Thanh Huy Nguyen","https:\u002F\u002Forcid.org\u002F0000-0003-2471-350X",{"name":441,"orcid":442},"Marco Chini","https:\u002F\u002Forcid.org\u002F0000-0002-9094-0367",{"name":444,"orcid":9},"Jean François Iffly",{"name":446,"orcid":9},"Thomas Udelhoven",{"name":448,"orcid":449},"Julia Kubanek","https:\u002F\u002Forcid.org\u002F0000-0001-9597-2029",{"name":451,"orcid":9},"Zoltan Szantoi",{"name":453,"orcid":454},"Miriam Machwitz","https:\u002F\u002Forcid.org\u002F0000-0002-4999-673X",{"tldr":456,"method":457,"finding":458,"direction":203,"opportunity":459},"将Sentinel-2反射率与SMAP土壤水分同化进APSIM模型，提升玉米生物量估算精度。","粒子滤波同化Sentinel-2反射率（经PROSAIL耦合）与SMAP土壤水分","联合同化结果稳健，2023年RMSE为1258.83 kg\u002Fha，nRMSE 16.62%，偏差-2","可探索多源数据同化在数据缺失与干旱条件下的自适应权重策略，并推广至其他作物与区域。","2026-09-26T23:30:03.247019Z",{"id":462,"title":463,"url":464,"summary":465,"summary_zh":9,"content":9,"source_name":466,"source_url":464,"published_at":467,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":468,"score_detail":469,"sources":471,"tags":473,"primary_topic":476,"secondary_topics":477,"classification":478,"search_phrases":498,"slug":501,"view_count":84,"doi":502,"paper":503,"created_at":532},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":19,"substance":18,"depth":127,"authority":51,"freshness":13,"relevant":22,"comment":470},"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。",[472],{"name":466,"url":464},[27,474,475,28,136],"农业人工智能","精准施肥",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":479},{"candidates":480,"agricultural_evidence":52},[481,485,489,494],{"code":32,"score":291,"supported":52,"title":482,"abstract":483,"tags":484},[151,33],[151,33],[136],{"code":62,"score":84,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[28,474],{"code":490,"score":22,"supported":14,"title":491,"abstract":492,"tags":493},"F3",[],[],[475],{"code":76,"score":22,"supported":14,"title":495,"abstract":496,"tags":497},[],[],[27],[499,500],"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":502,"openalex_id":504,"authors":505,"venue":466,"cited_by_count":101,"oa_url":464,"card":9,"direction":9,"ingested_from":110},"W7213352238",[506,508,511,514,516,518,520,522,524,526,528,530],{"name":507,"orcid":9},"Yuru Ye",{"name":509,"orcid":510},"Qian Wang","https:\u002F\u002Forcid.org\u002F0000-0003-0750-7843",{"name":512,"orcid":513},"Davide Cammarano","https:\u002F\u002Forcid.org\u002F0000-0003-0918-550X",{"name":515,"orcid":9},"Kang Yu",{"name":517,"orcid":9},"Siva K. Balasundram",{"name":519,"orcid":9},"Wei Li",{"name":521,"orcid":9},"Xiuli Li",{"name":523,"orcid":9},"Xiaojun Liu",{"name":525,"orcid":9},"Yongchao Tian",{"name":527,"orcid":9},"Yan Zhu",{"name":529,"orcid":9},"Weixing Cao",{"name":531,"orcid":9},"Qiang Cao","2026-09-16T23:30:05.340754Z",{"id":534,"title":535,"url":536,"summary":537,"summary_zh":538,"content":9,"source_name":539,"source_url":536,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":540,"score_detail":541,"sources":543,"tags":545,"primary_topic":547,"secondary_topics":548,"classification":549,"search_phrases":580,"slug":582,"view_count":70,"doi":583,"paper":584,"created_at":616},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",75,{"impact":19,"substance":217,"depth":380,"authority":20,"freshness":63,"relevant":22,"comment":542},"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。",[544],{"name":539,"url":536},[27,474,28,546],"遥感估产",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":45,"locked":14,"version":46,"method":47,"evidence":550},{"candidates":551,"agricultural_evidence":52},[552,556,560,564,568,572,576],{"code":32,"score":292,"supported":52,"title":553,"abstract":554,"tags":555},[],[34,151,33],[],{"code":387,"score":113,"supported":52,"title":557,"abstract":558,"tags":559},[],[385,388],[],{"code":172,"score":113,"supported":52,"title":561,"abstract":562,"tags":563},[],[175,176],[],{"code":69,"score":70,"supported":52,"title":565,"abstract":566,"tags":567},[],[73],[],{"code":62,"score":84,"supported":14,"title":569,"abstract":570,"tags":571},[],[],[28,474],{"code":76,"score":22,"supported":14,"title":573,"abstract":574,"tags":575},[],[],[27],{"code":164,"score":22,"supported":14,"title":577,"abstract":578,"tags":579},[],[],[546],[581,500],"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":583,"openalex_id":585,"authors":586,"venue":539,"cited_by_count":101,"oa_url":536,"card":611,"direction":107,"ingested_from":110},"W7125531933",[587,589,591,594,597,600,602,604,606,608],{"name":588,"orcid":9},"Yue Shi",{"name":590,"orcid":9},"Amit Kumar Srivastava",{"name":592,"orcid":593},"Dominik Behrend","https:\u002F\u002Forcid.org\u002F0009-0000-9081-7169",{"name":595,"orcid":596},"Thomas Gaiser","https:\u002F\u002Forcid.org\u002F0000-0002-5820-2364",{"name":598,"orcid":599},"Thuy Huu Nguyen","https:\u002F\u002Forcid.org\u002F0000-0003-3870-986X",{"name":601,"orcid":9},"Xin Zhang",{"name":603,"orcid":9},"Tam Sobeih",{"name":605,"orcid":9},"Frank Ewert",{"name":607,"orcid":9},"Krishnagopal Halder",{"name":609,"orcid":610},"Liangxiu Han","https:\u002F\u002Forcid.org\u002F0000-0003-2491-7473",{"tldr":612,"method":613,"finding":614,"direction":107,"opportunity":615},"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"]