[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1443":3,"related-1443":100},{"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":23,"tags":25,"primary_topic":9,"secondary_topics":30,"classification":31,"search_phrases":74,"slug":77,"view_count":78,"doi":79,"paper":80,"created_at":99},1443,"Detecting soil moisture drought impacts on ecosystem physiology from earth observation data","https:\u002F\u002Fdoi.org\u002F10.5194\u002Fegusphere-2026-5000","Abstract. Satellite remote sensing is widely used to monitor vegetation drought impacts, yet water stress triggers both structural changes and physiological adjustments, whose relative importance varies across space and time. Structural responses, captured by multispectral vegetation indices are well documented, while the extent to which readily available satellite data can detect physiological drought effects remains insufficiently quantified. Here, we assess how much information on drought-induced physiological responses is contained in multispectral reflectance, land surface temperature (LST), and climate reanalysis data. We combine MODIS reflectance and thermal data with an ERA5-Land potential cumulative water deficits metric (PCWD), and train a machine-learning model using eddy covariance data. The target variable represents drought-induced reductions in light use efficiency (fLUE), explicitly separating physiological regulation from structural canopy changes. Our resulting data-driven model captures variations in drought-related physiological response more accurately than previously documented indices commonly applied for drought monitoring (R² = 0.64, RMSE = 0.112, spatial cross-validation). Application across central Europe during two recent summers demonstrates that the model detects drought impacts on photosynthesis earlier and more sensitively than NDVI, particularly in evergreen ecosystems where structural signals are muted. Our results show that a systematically trained, data-driven integration of multispectral reflectance, thermal signals, and climate data can extract a substantial portion of the physiological drought response from Earth observation data. This approach enables a more confident and spatially consistent assessment of drought impacts on photosynthesis using the full combined information content of satellite and climate datasets, beyond what structural vegetation indices alone can provide.","摘要：卫星遥感被广泛用于监测植被干旱影响，然而水分胁迫同时引发结构变化与生理调节，二者的相对重要性在时空上存在差异。多光谱植被指数所捕捉的结构响应已有充分记录，而现成卫星数据能在多大程度上检测干旱的生理效应仍未得到充分量化。本研究评估了多光谱反射率、地表温度（LST）及气候再分析数据中包含多少干旱诱导的生理响应信息。我们将MODIS反射率与热红外数据同ERA5-Land潜在累积水分亏缺指标（PCWD）相结合，并利用涡度协方差数据训练机器学习模型。目标变量代表干旱引起的光能利用效率降低（fLUE），明确将生理调节与冠层结构变化区分开来。我们所得的数据驱动模型对干旱相关生理响应变化的捕捉精度优于以往常用于干旱监测的指数（R² = 0.64，RMSE = 0.112，空间交叉验证）。将该模型应用于中欧近两个夏季的案例表明，其检测干旱对光合作用影响的时间早于且灵敏度高于NDVI，尤其在结构信号微弱的常绿生态系统中表现突出。研究结果表明，经过系统训练的多光谱反射率、热信号与气候数据的数据驱动集成方法，能够从地球观测数据中提取出干旱生理响应的相当大一部分信息。该方法利用卫星与气候数据集的综合信息含量，能够对干旱对光合作用的影响进行更为可靠且空间上一致的评估，超越了单纯结构植被指数所能提供的范围。",null,"OpenAlex","2026-09-01T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,7,1,"研究利用多源遥感与气候数据提升干旱对作物生理影响的监测能力，方法新颖，对农业信息化有实质贡献。",[24],{"name":10,"url":6},[26,27,28,29],"智慧农业","农业遥感","作物模型","干旱监测",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":35},"needs_review","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":14,"reason":73},[37,46,54,61,68],{"code":38,"score":39,"supported":40,"title":41,"abstract":43,"tags":45},"H7",15,true,[42],"drought",[44,42],"干旱",[29],{"code":47,"score":13,"supported":40,"title":48,"abstract":49,"tags":53},"I3",[],[50,51,52],"遥感","remote sensing","multispectral",[27],{"code":55,"score":56,"supported":40,"title":57,"abstract":59,"tags":60},"H2",8,[58],"soil",[],[],{"code":62,"score":63,"supported":40,"title":64,"abstract":65,"tags":67},"I2",4,[],[66],"机器学习",[28],{"code":69,"score":21,"supported":14,"title":70,"abstract":71,"tags":72},"I1",[],[],[26],"农业相关性需要复核",[75,76],"作物模型 农业遥感 干旱监测 智慧农业","作物模型 农业遥感","作物模型农业遥感干旱监测智慧农业-1443",3,"10.5194\u002Fegusphere-2026-5000",{"doi":79,"openalex_id":81,"authors":82,"venue":9,"cited_by_count":90,"oa_url":91,"card":92,"direction":96,"ingested_from":98},"W7204905170",[83,85,87],{"name":84,"orcid":9},"Yousra El-Mejjaouy",{"name":86,"orcid":9},"Koen Hufkens",{"name":88,"orcid":89},"Benjamin D. Stocker","https:\u002F\u002Forcid.org\u002F0000-0003-2697-9096",0,"https:\u002F\u002Fegusphere.copernicus.org\u002Fpreprints\u002F2026\u002Fegusphere-2026-5000\u002Fegusphere-2026-5000.pdf",{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"利用多光谱、热红外和气候数据，通过机器学习提取植被干旱的生理响应，比NDVI更早更敏感。","结合MODIS反射率、地表温度与ERA5-Land水分亏缺，训练机器学习模型预测","模型能检测干旱对光合作用的影响，比NDVI更早更敏感，尤其在常绿生态系统中。","农业遥感与作物表型","可探索将生理干旱响应模型应用于作物监测，或结合高光谱数据提高精度，并验证在不同生态系统中的适用性。","openalex","2026-09-02T23:30:53.675473Z",{"total":101,"page":21,"page_size":101,"items":102},6,[103,178,265,347,445,502],{"id":104,"title":105,"url":106,"summary":107,"summary_zh":9,"content":9,"source_name":108,"source_url":106,"published_at":109,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":115,"tags":117,"primary_topic":120,"secondary_topics":126,"classification":132,"search_phrases":153,"slug":156,"view_count":157,"doi":158,"paper":159,"created_at":177},4650,"A process-oriented framework for daily dynamic monitoring of summer maize drought: From meteorological stress to agricultural impact","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.105011","A process-oriented framework for daily dynamic monitoring of summer maize drought: From meteorological stress to agricultural impact。Agricultural Systems","Agricultural Systems","2026-10-11T00:00:00Z",81,{"impact":17,"substance":112,"depth":17,"authority":113,"freshness":13,"relevant":21,"comment":114},21,14,"核心期刊提出的面向过程的夏玉米干旱逐日动态监测框架，方法新颖、面向农业信息化应用，时效性强，值得进入每日精选。",[116],{"name":108,"url":106},[26,27,118,119,29],"夏玉米","农业气象",{"code":121,"slug":122,"name":123,"path":124,"parent_code":125},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[127],{"code":38,"slug":128,"name":129,"path":130,"parent_code":131},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":133,"locked":14,"version":33,"method":34,"evidence":134},"classified",{"candidates":135,"agricultural_evidence":40},[136,140,145,149],{"code":38,"score":19,"supported":40,"title":137,"abstract":138,"tags":139},[42],[42],[119,29],{"code":121,"score":141,"supported":40,"title":142,"abstract":143,"tags":144},12,[122],[122],[118],{"code":69,"score":21,"supported":14,"title":146,"abstract":147,"tags":148},[],[],[26],{"code":47,"score":21,"supported":14,"title":150,"abstract":151,"tags":152},[],[],[27],[154,155],"夏玉米 干旱 动态监测","气象胁迫 农业影响 监测框架","夏玉米干旱动态监测-4650",2,"10.1016\u002Fj.agsy.2026.105011",{"doi":158,"openalex_id":160,"authors":161,"venue":108,"cited_by_count":90,"oa_url":106,"card":9,"direction":96,"ingested_from":98},"W7221308782",[162,164,166,168,171,173,175],{"name":163,"orcid":9},"Yuanda Zhang",{"name":165,"orcid":9},"Peijuan Wang",{"name":167,"orcid":9},"Jun Zhu",{"name":169,"orcid":170},"Yang Li","https:\u002F\u002Forcid.org\u002F0000-0001-9021-0201",{"name":172,"orcid":9},"Dianchen Han",{"name":174,"orcid":9},"Dingrong Wu",{"name":176,"orcid":9},"Jianping Guo","2026-10-11T23:30:03.734429Z",{"id":179,"title":180,"url":181,"summary":182,"summary_zh":183,"content":9,"source_name":184,"source_url":181,"published_at":185,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":186,"score_detail":187,"sources":189,"tags":191,"primary_topic":194,"secondary_topics":198,"classification":200,"search_phrases":231,"slug":234,"view_count":101,"doi":235,"paper":236,"created_at":264},1898,"Connecting earth observation anomalies to farmer surveys for monitoring impacts of agricultural drought on rainfed rice yields in Nigeria","https:\u002F\u002Fdoi.org\u002F10.5194\u002Feo-1-77-2026","Abstract. Agricultural drought threatens rainfed rice production in Nigeria, where smallholder farmers depend on rainfall and have limited capacity to buffer climate shocks. While meteorological drought indices such as the SPI and the SPEI are widely used in national early warning systems, their ability to capture the impacts of droughts on rainfed rice yields at the smallholder field-level remains uncertain. This study evaluates the added value of earth observation (EO)-derived vegetation and soil moisture anomalies for monitoring and predicting drought impacts on rainfed rice yields in Nigeria. Satellite-based Normalized Difference Vegetation Index anomalies (NDVIA) and Soil Water Index anomalies (SWIA) were derived using a zonal clustering and thresholding approach and combined with farmer survey and yield data collected from 146 rainfed rice farmers across four major rice-growing states between 2019 and 2024. Multivariate regression models were used to assess the relationships between EO indicator anomalies and annual yield changes, and the effects of different zonal clustering and anomaly thresholds on anomaly calculation were evaluated. Results show that SPI and SPEI explain a substantial share of yield variability in some years, particularly when droughts coincide with sensitive phenological stages. However, EO-based anomaly indicators, especially SWIA (maximum improved R2 = 0.25), provide complementary information and significantly improve yield predictions in years when meteorological indices alone perform poorly. The timing of anomalies relative to rice phenology was critical, with droughts during panicle initiation having the largest yield impacts. Integrating EO-based vegetation and soil moisture anomaly indicators with existing meteorological indices can contribute to the monitoring of agricultural droughts and improve the operational relevance of early warning systems for rainfed rice farmers in Nigeria.","摘要：农业干旱威胁着尼日利亚依赖雨养的水稻生产，当地小农户依靠降雨为生，缓冲气候冲击的能力有限。尽管诸如标准化降水指数（SPI）和标准化降水蒸散指数（SPEI）等气象干旱指数被广泛应用于国家早期预警系统，但它们在捕捉小农田间尺度上干旱对雨养水稻产量影响的能力仍不确定。本研究评估了基于地球观测（EO）的植被和土壤湿度异常在监测和预测尼日利亚干旱对雨养水稻产量影响方面的附加价值。采用分区聚类和阈值方法，推导出基于卫星的归一化差异植被指数异常（NDVIA）和土壤水分指数异常（SWIA），并结合2019年至2024年间从四个主要水稻种植州的146位雨养水稻农户收集的农户调查和产量数据。使用多元回归模型评估EO指标异常与年度产量变化之间的关系，并评估不同分区聚类和异常阈值对异常计算的影响。结果表明，在某些年份，SPI和SPEI解释了产量变异的很大一部分，特别是当干旱与敏感物候阶段重合时。然而，基于EO的异常指标，尤其是SWIA（最大改进R²=0.25），提供了补充信息，并在气象指数单独表现不佳的年份显著改善了产量预测。异常相对于水稻物候的时机至关重要，穗分化期发生的干旱对产量影响最大。将基于EO的植被和土壤湿度异常指标与现有气象指数相结合，有助于监测农业干旱，并提高尼日利亚雨养水稻农户早期预警系统的业务相关性。","Earth Observation","2026-09-07T00:00:00Z",74,{"impact":39,"substance":18,"depth":17,"authority":141,"freshness":20,"relevant":21,"comment":188},"研究结合遥感与农户调查，提升雨养水稻干旱监测精度，对非洲小农预警有参考价值。",[190],{"name":184,"url":181},[26,27,192,29,193],"水稻","尼日利亚",{"code":195,"slug":196,"name":192,"path":197,"parent_code":125},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice",[199],{"code":38,"slug":128,"name":129,"path":130,"parent_code":131},{"status":133,"locked":14,"version":33,"method":34,"evidence":201},{"candidates":202,"agricultural_evidence":40},[203,207,211,218,223,227],{"code":195,"score":39,"supported":40,"title":204,"abstract":205,"tags":206},[196],[192,196],[192],{"code":38,"score":39,"supported":40,"title":208,"abstract":209,"tags":210},[42],[44,42],[29],{"code":212,"score":101,"supported":40,"title":213,"abstract":214,"tags":217},"G2",[],[215,216],"小农户","smallholder",[],{"code":55,"score":101,"supported":40,"title":219,"abstract":220,"tags":222},[],[221,58],"土壤",[],{"code":69,"score":21,"supported":14,"title":224,"abstract":225,"tags":226},[],[],[26],{"code":47,"score":21,"supported":14,"title":228,"abstract":229,"tags":230},[],[],[27],[232,233],"农业遥感 尼日利亚 干旱监测 智慧农业","农业遥感 尼日利亚","农业遥感尼日利亚干旱监测智慧农业-1898","10.5194\u002Feo-1-77-2026",{"doi":235,"openalex_id":237,"authors":238,"venue":184,"cited_by_count":90,"oa_url":181,"card":259,"direction":96,"ingested_from":98},"W7162756810",[239,242,244,247,249,252,255,257],{"name":240,"orcid":241},"Nick Gutkin","https:\u002F\u002Forcid.org\u002F0000-0003-4708-3483",{"name":243,"orcid":9},"Chiamaka I. Ehiemere",{"name":245,"orcid":246},"Koen De Vos","https:\u002F\u002Forcid.org\u002F0000-0002-4607-7877",{"name":248,"orcid":9},"Nnamdi Ehiemere",{"name":250,"orcid":251},"Jeroen Degerickx","https:\u002F\u002Forcid.org\u002F0000-0001-9022-9623",{"name":253,"orcid":254},"Sarah Gebruers","https:\u002F\u002Forcid.org\u002F0000-0001-8426-4158",{"name":256,"orcid":9},"Uchechukwu Nwafor",{"name":258,"orcid":9},"Anne Gobin",{"tldr":260,"method":261,"finding":262,"direction":96,"opportunity":263},"评估EO异常指标监测尼日利亚雨养水稻干旱影响，补充气象指数，提高产量预测。","结合NDVI和土壤水分指数异常、聚类阈值法、农户调查与回归模型。","EO指标（尤其SWIA）补充气象指数，显著提高干旱年份产量预测，关键物候期干旱影响最大。","可探索将EO异常与物候模型结合，开发针对小农的干旱预警系统，并验证其他作物和区域。","2026-09-08T23:30:18.761711Z",{"id":266,"title":267,"url":268,"summary":269,"summary_zh":270,"content":9,"source_name":271,"source_url":268,"published_at":272,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":273,"score_detail":274,"sources":277,"tags":279,"primary_topic":281,"secondary_topics":285,"classification":286,"search_phrases":321,"slug":324,"view_count":78,"doi":325,"paper":326,"created_at":346},1751,"Downscaling SMAP Soil Moisture to 1 km with Machine Learning and MODIS Data for Agricultural Drought Assessment in Békés County, Hungary","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriengineering8090373","Accurate mapping of Soil moisture (SM) is essential for effectively monitoring agricultural drought. However, the coarse spatial resolution of passive microwave products, including the 9 km Soil Moisture Active Passive (SMAP) retrievals, limits their effectiveness at regional and local scales. To address this limitation, three machine learning-based downscaling frameworks were compared to improve SMAP SM resolution from 9 km to 1 km over Békés County, Hungary. The study period covered the growing seasons (April to October) from 2020 to 2023. A set of multi-temporal MODIS-derived variables, including vegetation indices (NDVI, EVI), daytime and night-time land surface temperature, and evapotranspiration, along with land cover classification and topographic elevation, were combined as auxiliary predictor variables. Three machine learning algorithms, Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting Machine (GBM), were trained and evaluated. The results showed that (1) the RF model had the highest accuracy during the testing (R2 = 0.71, RMSE = 0.0295 m3\u002Fm3) phase and validation against four in situ monitoring stations with confirmed reliable SM estimation at the local scale; (2) daytime LST was the most important predictor in all models, underscoring the strong thermal–moisture coupling that governs surface SM dynamics; and (3) the validated RF model produced 1 km Standardized Soil Moisture Index (SSI) maps that effectively captured inter-annual drought variability, identifying the severe drought of July 2022. Overall, this study presents a downscaling approach for generating high-resolution SM data suitable for Central European agricultural environments. The resulting 1 km SM and SSI products provide valuable tools for decision-makers to enhance planning during drought periods and reduce agricultural losses through improved irrigation scheduling.","土壤水分（SM）的精确制图对于有效监测农业干旱至关重要。然而，被动微波产品（包括9公里分辨率的土壤水分主动被动（SMAP）反演数据）空间分辨率较粗，限制了其在区域和地方尺度上的有效性。为解决这一局限，本研究比较了三种基于机器学习的降尺度框架，旨在将匈牙利贝凯什县的SMAP土壤水分分辨率从9公里提升至1公里。研究时段覆盖2020年至2023年的生长季（4月至10月）。研究中将一组多时相MODIS衍生变量——包括植被指数（NDVI、EVI）、白天和夜间地表温度、蒸散量——以及土地覆盖分类和地形高程作为辅助预测变量。三种机器学习算法，即随机森林（RF）、极限梯度提升（XGBoost）和梯度提升机（GBM），被训练和评估。结果表明：（1）RF模型在测试阶段（R² = 0.71，RMSE = 0.0295 m³\u002Fm³）精度最高，且经四个原位监测站验证，确认其在小尺度上具有可靠的土壤水分估算能力；（2）白天地表温度是所有模型中最重要的预测变量，凸显了控制地表土壤水分动态的强烈热-湿耦合关系；（3）经过验证的RF模型生成的1公里标准化土壤水分指数（SSI）图有效捕捉了年际干旱变率，识别出2022年7月的严重干旱事件。总体而言，本研究提出了一种适用于中欧农业环境的降尺度方法，用于生成高分辨率土壤水分数据。所得到的1公里土壤水分和SSI产品为决策者在干旱期加强规划、通过改进灌溉调度减少农业损失提供了有价值的工具。","AgriEngineering","2026-09-04T00:00:00Z",66,{"impact":141,"substance":275,"depth":17,"authority":141,"freshness":63,"relevant":21,"comment":276},20,"研究利用机器学习将SMAP土壤水分降尺度至1km，提升农业干旱监测精度，方法新颖，数据详实，对区域农业管理有参考价值。",[278],{"name":271,"url":268},[26,27,66,29,280],"土壤水分",{"code":131,"slug":282,"name":283,"path":284,"parent_code":9},"environment","资源环境与气候变化","\u002Ftopic\u002Fenvironment",[],{"status":287,"locked":14,"version":33,"method":34,"evidence":288},"partial",{"candidates":289,"agricultural_evidence":40,"reason":320},[290,294,298,303,312,316],{"code":55,"score":39,"supported":40,"title":291,"abstract":292,"tags":293},[58],[221,58],[280],{"code":38,"score":39,"supported":40,"title":295,"abstract":296,"tags":297},[42],[44,42],[29],{"code":62,"score":39,"supported":40,"title":299,"abstract":301,"tags":302},[300],"machine learning",[66,300],[66],{"code":304,"score":305,"supported":40,"title":306,"abstract":307,"tags":311},"H3",9,[],[308,309,310],"灌溉","irrigation","evapotranspiration",[],{"code":69,"score":21,"supported":14,"title":313,"abstract":314,"tags":315},[],[],[26],{"code":47,"score":21,"supported":14,"title":317,"abstract":318,"tags":319},[],[],[27],"一级领域明确，二级方向需要细分",[322,323],"农业遥感 土壤水分 干旱监测 智慧农业","农业遥感 土壤水分","农业遥感土壤水分干旱监测智慧农业-1751","10.3390\u002Fagriengineering8090373",{"doi":325,"openalex_id":327,"authors":328,"venue":271,"cited_by_count":90,"oa_url":268,"card":340,"direction":345,"ingested_from":98},"W7208719644",[329,331,334,337],{"name":330,"orcid":9},"Mahrokh Shafiei",{"name":332,"orcid":333},"István Waltner","https:\u002F\u002Forcid.org\u002F0000-0002-6704-8936",{"name":335,"orcid":336},"Z. Vekerdy","https:\u002F\u002Forcid.org\u002F0000-0002-5677-8298",{"name":338,"orcid":339},"Gábor Halupka","https:\u002F\u002Forcid.org\u002F0000-0003-4640-0061",{"tldr":341,"method":342,"finding":343,"direction":96,"opportunity":344},"用机器学习将SMAP土壤水分降尺度至1km，评估匈牙利农业干旱。","比较RF、XGBoost、GBM，结合MODIS植被指数、地表温度等预测变量。","RF精度最高，白天LST最重要，成功捕捉2022年7月严重干旱。","可探索将降尺度方法应用于其他区域或作物，结合更高分辨率遥感或气象数据提升精度。","农业人工智能与决策模型","2026-09-05T23:30:50.054057Z",{"id":348,"title":349,"url":350,"summary":351,"summary_zh":352,"content":9,"source_name":353,"source_url":350,"published_at":354,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":355,"score_detail":356,"sources":359,"tags":361,"primary_topic":365,"secondary_topics":370,"classification":382,"search_phrases":413,"slug":416,"view_count":90,"doi":417,"paper":418,"created_at":444},5573,"Improving alfalfa nitrogen estimation with canopy structural priors from DSSAT–PROSAIL and UAV hyperspectral data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128375","Accurate estimation of nitrogen (N) concentration in alfalfa ( Medicago sativa L .) supports forage quality assessment and harvest scheduling. Empirical remote sensing models often overfit because of confounding effects of three-dimensional canopy structure. Incorporating structural parameters can stabilize biochemical inversions, but concurrent in situ morphological measurements are difficult to acquire at scale. We developed the Morphology-Aware Latent Embedding Network (MALENet), a hybrid framework integrating physiological and morphological mechanisms with hyperspectral data. The Decision Support System for Agrotechnology Transfer (DSSAT), coupled with the PROSAIL radiative transfer model, generated a structurally rich synthetic hyperspectral prior. A convolutional neural network (CNN) with a Squeeze-and-Excitation (SE) attention mechanism, was pre-trained on these data to distill ecophysiological knowledge into a dense latent representation. This mechanistically derived embedding was then fused with empirical hyperspectral measurements collected under diverse field conditions. Evaluation using multi-year field quadrats in the Hexi Corridor showed improved predictive performance ( R² = 0.71, RMSE = 0.30%) relative to conventional machine learning and deep learning models (LASSO-ANN: R² = 0.61; CNN: R² = 0.66). Feature attribution indicated that MALENet used near-infrared multiple scattering (58.3% attribution) as a structural proxy to calibrate nitrogen concentration retrieval against the confounding effects of canopy architecture. Despite constraints imposed by sample size and PROSAIL's 1D canopy assumption, these findings demonstrate the potential of physically guided deep learning to use structural information for agricultural trait retrieval in precision forage management.","准确估算紫花苜蓿（Medicago sativa L.）的氮浓度有助于饲草品质评估和收获期安排。经验性遥感模型常因三维冠层结构的混杂效应而出现过拟合。引入结构参数可以稳定生化反演，但同步开展原位形态学测量难以大规模获取。我们开发了形态感知潜在嵌入网络（Morphology-Aware Latent Embedding Network，MALENet），这是一个将生理与形态机制同高光谱数据相结合的混合框架。农业技术转移决策支持系统（Decision Support System for Agrotechnology Transfer，DSSAT）与PROSAIL辐射传输模型耦合，生成了结构信息丰富的合成高光谱先验数据。在此基础上，预训练了一个带有挤压—激励（Squeeze-and-Excitation，SE）注意力机制的卷积神经网络（convolutional neural network，CNN），将生态生理学知识提炼为稠密潜在表征。随后，将这一机制性导出的嵌入与在不同田间条件下采集的经验性高光谱测量数据相融合。利用河西走廊多年田间样方进行的评估显示，相较于传统机器学习和深度学习模型（LASSO-ANN：R² = 0.61；CNN：R² = 0.66），预测性能有所提升（R² = 0.71，RMSE = 0.30%）。特征归因表明，MALENet利用近红外多次散射（归因占比58.3%）作为结构代理，以校准氮浓度反演，抵御冠层结构的混杂效应。尽管受样本量和PROSAIL一维冠层假设的限制，这些发现表明，物理引导的深度学习有潜力利用结构信息，在精准饲草管理中进行农业性状反演。","European Journal of Agronomy","2026-10-21T00:00:00Z",80,{"impact":357,"substance":18,"depth":17,"authority":113,"freshness":13,"relevant":21,"comment":358},16,"该研究将作物模型与辐射传输模型耦合生成结构先验，并结合无人机高光谱数据反演苜蓿氮素，方法新颖、田间验证扎实，对精准饲草管理有参考价值，值得进入每日精选。",[360],{"name":353,"url":350},[26,362,27,363,364],"农业人工智能","氮素监测","紫花苜蓿",{"code":366,"slug":367,"name":368,"path":369,"parent_code":125},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping",[371,376],{"code":47,"slug":372,"name":373,"path":374,"parent_code":375},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"code":377,"slug":378,"name":379,"path":380,"parent_code":381},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":133,"locked":14,"version":33,"method":34,"evidence":383},{"candidates":384,"agricultural_evidence":40},[385,390,396,402,409],{"code":47,"score":17,"supported":40,"title":386,"abstract":388,"tags":389},[387],"hyperspectral",[50,51,387],[27],{"code":366,"score":39,"supported":40,"title":391,"abstract":393,"tags":395},[392],"alfalfa",[394,392],"苜蓿",[364],{"code":377,"score":13,"supported":40,"title":397,"abstract":398,"tags":401},[],[399,394,400],"饲草","forage",[364],{"code":62,"score":13,"supported":40,"title":403,"abstract":404,"tags":408},[],[405,66,300,406,407],"深度学习","deep learning","decision support",[362],{"code":69,"score":21,"supported":14,"title":410,"abstract":411,"tags":412},[],[],[26],[414,415],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573","10.1016\u002Fj.eja.2026.128375",{"doi":417,"openalex_id":419,"authors":420,"venue":353,"cited_by_count":90,"oa_url":350,"card":439,"direction":96,"ingested_from":98},"W7223154576",[421,423,425,427,429,432,434,437],{"name":422,"orcid":9},"Shuai Fu",{"name":424,"orcid":9},"Yunhao Li",{"name":426,"orcid":9},"Chunli Miao",{"name":428,"orcid":9},"Jie Liu",{"name":430,"orcid":431},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":433,"orcid":9},"Yongjia Hu",{"name":435,"orcid":436},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":438,"orcid":9},"吴彩霞",{"tldr":440,"method":441,"finding":442,"direction":96,"opportunity":443},"构建MALENet融合DSSAT-PROSAIL结构先验与无人机高光谱，提升苜蓿氮浓度估算精度。","DSSAT耦合PROSAIL生成合成高光谱先验，预训练CNN-SE网络，再融合田","MALENet精度优于传统机器学习和深度学习模型，R²达0.71，近红外多次散射作为结构代理贡献58","可探索将作物模型结构先验迁移至其他牧草或作物生化参数反演，并缓解PROSAIL一维冠层假设局限。","2026-10-22T11:20:39.622844Z",{"id":446,"title":447,"url":448,"summary":449,"summary_zh":9,"content":9,"source_name":450,"source_url":9,"published_at":354,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":451,"score_detail":452,"sources":454,"tags":456,"primary_topic":460,"secondary_topics":465,"classification":468,"search_phrases":489,"slug":492,"view_count":21,"doi":9,"paper":493,"created_at":501},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21",82,{"impact":17,"substance":18,"depth":17,"authority":113,"freshness":13,"relevant":21,"comment":453},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[455],{"name":450,"url":448},[26,27,457,458,459],"作物表型","无人机多光谱","小麦渍害",{"code":461,"slug":462,"name":463,"path":464,"parent_code":125},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[466,467],{"code":47,"slug":372,"name":373,"path":374,"parent_code":375},{"code":38,"slug":128,"name":129,"path":130,"parent_code":131},{"status":133,"locked":14,"version":33,"method":34,"evidence":469},{"candidates":470,"agricultural_evidence":40},[471,476,480,485],{"code":461,"score":472,"supported":40,"title":473,"abstract":474,"tags":475},11,[463],[463],[],{"code":47,"score":472,"supported":40,"title":477,"abstract":478,"tags":479},[458],[],[457,27,458],{"code":38,"score":56,"supported":40,"title":481,"abstract":483,"tags":484},[482],"渍害",[],[],{"code":69,"score":21,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[26],[490,491],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":9,"openalex_id":9,"authors":494,"venue":9,"cited_by_count":90,"oa_url":9,"card":495,"direction":96,"ingested_from":500},[],{"tldr":496,"method":497,"finding":498,"direction":96,"opportunity":499},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z",{"id":503,"title":504,"url":505,"summary":506,"summary_zh":9,"content":9,"source_name":507,"source_url":9,"published_at":508,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":509,"score_detail":510,"sources":513,"tags":515,"primary_topic":516,"secondary_topics":517,"classification":520,"search_phrases":539,"slug":542,"view_count":90,"doi":9,"paper":543,"created_at":550},5296,"雷添杰研究员团队《基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别》","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-16\u002Fdoc-inivmprm8363597.shtml","《智慧农业(中英文)》2026年第8卷第4期刊载梁万杰、刘晓君、雷添杰等论文,在小麦拔节—抽穗和抽穗—灌浆两个生长阶段进行对照、渍水胁迫、硅肥调控、氨基酸调控控制试验;利用大疆精灵4多光谱无人机采集小麦冠层多光谱图像建立数据集,基于VGG21模型构建识别模型,发现硅肥调控样本识别性能最好,识别精度最高,具良好鲁棒性和可扩展性,可为小麦渍害综合防控提供理论与技术支持。","智慧农业(中英文)(2026,8(4))","2026-10-16T00:00:00Z",76,{"impact":357,"substance":112,"depth":511,"authority":113,"freshness":56,"relevant":21,"comment":512},17,"核心期刊论文，方法新颖、结论可靠，对小麦渍害防控有实用价值，值得进入每日精选。",[514],{"name":507,"url":505},[26,27,457,458,459],{"code":461,"slug":462,"name":463,"path":464,"parent_code":125},[518,519],{"code":38,"slug":128,"name":129,"path":130,"parent_code":131},{"code":47,"slug":372,"name":373,"path":374,"parent_code":375},{"status":133,"locked":14,"version":33,"method":34,"evidence":521},{"candidates":522,"agricultural_evidence":40},[523,527,531,535],{"code":461,"score":472,"supported":40,"title":524,"abstract":525,"tags":526},[463],[463],[],{"code":38,"score":472,"supported":40,"title":528,"abstract":529,"tags":530},[482],[482],[],{"code":47,"score":472,"supported":40,"title":532,"abstract":533,"tags":534},[458],[],[457,27,458],{"code":69,"score":63,"supported":40,"title":536,"abstract":537,"tags":538},[],[26],[26],[540,541],"雷添杰 小麦渍害 无人机多光谱","VGG21 小麦渍害 识别模型","雷添杰小麦渍害无人机多光谱-5296",{"doi":9,"openalex_id":9,"authors":544,"venue":9,"cited_by_count":90,"oa_url":9,"card":545,"direction":96,"ingested_from":500},[],{"tldr":546,"method":547,"finding":548,"direction":96,"opportunity":549},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4采集冠层多光谱图像，构建VGG21识别模型。","硅肥调控样本识别性能最好、精度最高，模型鲁棒可扩展。","可探索多生育期多光谱特征与不同调控措施的耦合机制，并扩展到其他作物渍害监测。","2026-10-19T00:07:48.071055Z"]