[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5007":3,"related-5007":85},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":52,"slug":55,"view_count":56,"doi":57,"paper":58,"created_at":84},5007,"Kernel-Driven Model Correction of Thermal Directionality: Pixel-Level Analysis Using Airborne Multi-Angular Observations","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18203525","Directional anisotropy (DA) in thermal infrared (TIR) remote sensing introduces significant variability in land surface temperature (LST) retrievals, particularly in high-resolution observations. This study presents the empirical pixel-level modelling of DA, by using multi-angular airborne data from the NETSense campaign over an agricultural area near Grosseto, Italy. Six kernel-driven models (KDMs) are evaluated for their ability to fit directional effects, with the Vinnikov–Roujean–Lagouarde (Vinnikov–RL) model achieving the highest accuracy (RMSE = 1.07 K). At 40 m resolution, modelled directional effects reach median deviations of +1.80 K at the hotspot position, −2.03 K opposite to the Sun, and −1.37 K perpendicular to the solar principal plane, with extremes up to ±6 K, highlighting their operational significance for missions such as LSTM, TRISHNA, and SBG. To improve operational feasibility, two simplified models—adapted RL (RLa) and Vinnikov–RLa—are introduced, leveraging a consistent inverse relationship between hotspot magnitude and width to reduce parameter complexity via a power-law formulation. The analysis reveals that directional effects vary with spatial resolution and are influenced by canopy structure and solar geometry, while biophysical parameters alone are insufficient for coefficient estimation. Validation using an independent flight day confirms the robustness of the simplified models under different acquisition geometries, surface types, and geophysical conditions. A tiered model strategy is proposed for future satellite missions, recommending model selection based on day or night observations and data availability. These findings support the integration of directional correction into operational pipelines, enabling consistent and accurate LST products across platforms, resolutions, and observation conditions.","热红外（TIR）遥感中的方向各向异性（DA）会导致地表温度（LST）反演出现显著变化，在高分辨率观测中尤为明显。本研究利用意大利格罗塞托附近农业区NETSense campaign的多角度机载数据，开展了像元尺度的DA经验建模。评估了六种核驱动模型（KDM）拟合方向效应的能力，其中Vinnikov–Roujean–Lagouarde（Vinnikov–RL）模型精度最高（RMSE = 1.07 K）。在40 m分辨率下，模拟的方向效应在热点位置达到中位偏差+1.80 K，背阳方向为−2.03 K，垂直于太阳主平面方向为−1.37 K，极值可达±6 K，凸显了其对LSTM、TRISHNA和SBG等任务的实际意义。为提高业务可行性，引入了两种简化模型——改进RL（RLa）和Vinnikov–RLa，利用热点幅度与宽度之间一致的负相关关系，通过幂律公式降低参数复杂度。分析表明，方向效应随空间分辨率变化，并受冠层结构和太阳几何影响，而仅凭生物物理参数不足以估计系数。利用独立飞行日的验证证实了简化模型在不同观测几何、地表类型和地球物理条件下的稳健性。提出了面向未来卫星任务的分层模型策略，建议根据白天或夜间观测及数据可用性选择模型。这些发现支持将方向校正集成到业务化流程中，从而在不同平台、分辨率和观测条件下实现一致且准确的LST产品。",null,"Remote Sensing","2026-10-14T00:00:00Z","论文",10,false,83,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,23,19,14,9,1,"基于航空多角度观测的热红外方向性建模研究，方法新颖、数据扎实，对LSTM、TRISHNA等农业遥感卫星任务的地表温度产品校正具有直接参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"LSTM","遥感","地表温度","热红外","TRISHNA",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":51},8,true,[],[28,50],"remote sensing",[29,28],[53,54],"NETSense 航空 多角度 热红外","LSTM TRISHNA SBG 地表温度","NETSense航空多角度热红外-5007",3,"10.3390\u002Frs18203525",{"doi":57,"openalex_id":59,"authors":60,"venue":10,"cited_by_count":76,"oa_url":6,"card":77,"direction":81,"ingested_from":83},"W7221818626",[61,64,67,70,73],{"name":62,"orcid":63},"Louis Snyders","https:\u002F\u002Forcid.org\u002F0000-0003-1093-2517",{"name":65,"orcid":66},"J. A. D. L. Blommaert","https:\u002F\u002Forcid.org\u002F0000-0002-5797-2439",{"name":68,"orcid":69},"J. León-Tavares","https:\u002F\u002Forcid.org\u002F0000-0002-6186-9936",{"name":71,"orcid":72},"Mary Langsdale","https:\u002F\u002Forcid.org\u002F0000-0002-6078-0702",{"name":74,"orcid":75},"Lorenzo Genesio","https:\u002F\u002Forcid.org\u002F0000-0001-9265-886X",0,{"tldr":78,"method":79,"finding":80,"direction":81,"opportunity":82},"基于机载多角度热红外数据，在像素尺度评估核驱动模型并简化，以校正地表温度方向性效应。","使用NETSense机载多角度热红外数据，评估六种核驱动模型并构建简化模型。","Vinnikov–RL模型精度最高，方向性偏差中值达+1.80K至-2.03K，极端达±6K。","农业遥感与作物表型","可探索方向性校正与作物冠层结构参数耦合，提升卫星LST产品在农业监测中的一致性。","openalex","2026-10-15T23:30:29.753962Z",{"total":86,"page":22,"page_size":86,"items":87},6,[88,145,224,289,344,442],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":9,"source_name":94,"source_url":91,"published_at":95,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":97,"sources":101,"tags":103,"primary_topic":107,"secondary_topics":108,"classification":109,"search_phrases":128,"slug":131,"view_count":22,"doi":132,"paper":133,"created_at":144},4677,"Geospatial Analysis of Climate-Driven Landscape Change and Urban Expansion: Assessing Human–Environment Interactions, Resource Pressure, and Sustainable Spatial Planning","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23280111","The increasing demands and changing features of rapidly expanding cities and the impacts on land cover and the surface energy balance are evident. Yet, urban planners need to differentiate between the changes that have occurred and those which have been predicted. This study offers another geospatial analysis of the Delhi National Capital Region. This study complements previously published studies by the use of remote sensing techniques to retrieve land surface temperatures and studies of urban resource pressures. This study also incorporates land use and land cover studies of the years 2003, 2013 and 2023, which are based on the analysis of the Landsat imagery. The primary land use and land cover study analyzed an area of 13,754 km2 that includes the entirety of the Delhi National Capital Region and portions of the districts of Gurugram, Faridabad, Sonipat, Jhajjar, Ghaziabad, Gautam Buddha Nagar and Ghaziabad. This study also carried out a reanalysis of published land use and land cover maps to compute the absolute and relative changes and the annual growth rates. The area of land cover of built-up land increased from 1,893.64 km2 (13.77%) in 2003 to 3,386.76 km2 (24.62%) in the year 2023, which is an increase of 1,493.12 km (78.85%. CAGR 2.95%). Decreases were observed in the land cover of agricultural land, forests, water bodies and open land. The rate of land cover of built-up land slowed from an annual rate of 4.37% during 2003 to 2013, to an annual rate of 1.55% during the 2013 to 2023 period. The peripheral Shannon Entropy increased from a value of 0.24 to 0.36 during the same periods. The average land surface temperature of built-up land in Delhi, as reported independently of this study, increased by 5.23°C from 36.58°C in the year 2001 to 41.81°C in the year 2021. The integrated findings indicate that land that was previously agricultural and ecological cover has been extensively converted into built-up areas, intensifying surface warming and resource pressure across the urban periphery and underscoring the urgent need for sustainable spatial planning.","快速扩张的城市日益增长的需求和不断变化的特征，以及对土地覆盖和地表能量平衡的影响显而易见。然而，城市规划者需要区分已经发生的变化和预测的变化。本研究提供了对德里国家首都辖区的另一项地理空间分析。本研究通过利用遥感技术反演地表温度以及研究城市资源压力，对先前发表的研究进行了补充。本研究还纳入了基于Landsat影像分析的2003年、2013年和2023年的土地利用与土地覆盖研究。主要的土地利用与土地覆盖研究分析了13,754 km²的区域，涵盖德里国家首都辖区全境以及古尔冈、法里达巴德、索尼帕特、贾贾尔、加济阿巴德、乔达摩菩提那加尔和加济阿巴德等地区的部分区域。本研究还对已发表的土地利用与土地覆盖图进行了再分析，以计算绝对变化量、相对变化量及年增长率。建设用地土地覆盖面积从2003年的1,893.64 km²（13.77%）增加至2023年的3,386.76 km²（24.62%），增加了1,493.12 km²（78.85%，复合年增长率2.95%）。农业用地、森林、水体和裸地的土地覆盖均有所减少。建设用地土地覆盖的增长速率从2003年至2013年的年均4.37%放缓至2013年至2023年的年均1.55%。同期，边缘香农熵从0.24增加至0.36。据独立于本研究的报道，德里建设用地平均地表温度从2001年的36.58°C上升至2021年的41.81°C，升高了5.23°C。综合研究结果表明，原有的农业和生态用地已被大量转化为建设用地，加剧了城市边缘的地表增温和资源压力，凸显了可持续空间规划的迫切需求。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-10T00:00:00Z",79,{"impact":17,"substance":98,"depth":17,"authority":99,"freshness":46,"relevant":22,"comment":100},22,13,"基于Landsat遥感数据量化德里首都圈2003-2023年建设用地扩张与地表升温，方法扎实、数据具体，对农业信息化中的遥感监测与城乡空间规划有参考价值。",[102],{"name":94,"url":91},[28,104,29,105,106],"土地利用","城市扩张","空间规划",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":110},{"candidates":111,"agricultural_evidence":47},[112,116,123],{"code":33,"score":46,"supported":47,"title":113,"abstract":114,"tags":115},[],[28,50],[29,28],{"code":117,"score":118,"supported":47,"title":119,"abstract":120,"tags":122},"I4",4,[],[121],"空间分析",[106],{"code":124,"score":22,"supported":14,"title":125,"abstract":126,"tags":127},"H6",[],[],[104],[129,130],"城市扩张 地表温度 遥感","土地利用 地表温度 城市扩张 空间规划","城市扩张地表温度遥感-4677","10.5281\u002Fzenodo.23280111",{"doi":132,"openalex_id":134,"authors":135,"venue":94,"cited_by_count":76,"oa_url":91,"card":139,"direction":81,"ingested_from":83},"W7221308370",[136],{"name":137,"orcid":138},"Amit Kumar Singh","https:\u002F\u002Forcid.org\u002F0009-0008-5573-0525",{"tldr":140,"method":141,"finding":142,"direction":81,"opportunity":143},"基于Landsat遥感分析德里首都区2003-2023年土地利用变化、地表温度与城市扩张，评估资源压","Landsat影像解译、土地利用\u002F覆盖分类、地表温度反演、Shannon熵与增长","建设用地增78.85%，农林业与水体减少，地表升温5.23°C，城市外围资源压力加剧。","可结合多源遥感与作物模型，量化城市扩张对周边农地生产力与粮食安全的时空影响。","2026-10-11T23:30:30.090512Z",{"id":146,"title":147,"url":148,"summary":149,"summary_zh":150,"content":9,"source_name":151,"source_url":148,"published_at":152,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":153,"score_detail":154,"sources":156,"tags":158,"primary_topic":163,"secondary_topics":164,"classification":165,"search_phrases":175,"slug":178,"view_count":179,"doi":180,"paper":181,"created_at":223},2797,"Generation of representative datasets of future Copernicus Sentinel Expansion Mission Data (hyperspectral, thermal and L-band) as basis for innovative agricultural products","https:\u002F\u002Fdoi.org\u002F10.62880\u002Frars26005","The Copernicus Sentinel Expansion Missions will provide new and unique remote sensing data. To enable rapid use of real data as soon as it becomes available, it is essential to generate comparable synthetic data in advance. This study proposes a novel data set for three of the upcoming sensors. CHIME hyperspectral data are generated by inverting multispectral reflectance data from Sentinel-2 time series by radiative transfer modelling to retrieve land surface parameters and subsequently forward-simulating bottom-of-atmosphere reflectance using expected CHIME sensor characteristics. Future LSTM land surface temperature data are derived from Sentinel-3 and Sentinel-2 data using the Sen-ET workflow with spatial data mining sharpening. L-band backscatter and coherence data for ROSE-L are simulated using SAOCOM-1 data, which are transformed to match the expected spatial and radiometric characteristics. The novel data set is available for three areas of interest (AOIs) defined by Sentinel-2 tiles located in Germany, Belgium, and Estonia. A validation of simulated CHIME data using existing comparable sensor data from EnMAP showed a high spectral correlation with an average RMSE of 6.154 [%] and a correlation of 0.924 for the German AOI in 2024. This publicly available, unique and well validated dataset already enables the preparation and development of future products and services across a wide range of application areas based on data from the Sentinel Expansion Mission. Due to the high data availability resulting from extensive two-year time series, as well as the various AOIs, future products can already be tested for their temporal and spatial transferability.","哥白尼哨兵扩展任务将提供新的独特遥感数据。为了在真实数据可用时尽快加以利用，必须提前生成可比的合成数据。本研究为其中三个即将发射的传感器提出了一个新的数据集。CHIME高光谱数据通过辐射传输建模对来自Sentinel-2时间序列的多光谱反射率数据进行反演，以获取地表参数，随后利用预期的CHIME传感器特征正向模拟大气底层反射率来生成。未来的LSTM地表温度数据利用Sen-ET工作流结合空间数据挖掘锐化方法，从Sentinel-3和Sentinel-2数据中导出。ROSE-L的L波段后向散射和相干性数据使用SAOCOM-1数据进行模拟，并将其转换为符合预期空间和辐射特征的形式。该新数据集可用于三个感兴趣区域（AOIs），分别位于德国、比利时和爱沙尼亚的Sentinel-2瓦片范围内。利用EnMAP现有可比传感器数据对模拟CHIME数据进行的验证表明，2024年德国AOI的光谱相关性较高，平均RMSE为6.154 [%]，相关系数为0.924。这一公开可用、独特且经过充分验证的数据集，已经能够支持基于哨兵扩展任务数据在广泛的应用领域中准备和开发未来产品与服务。由于两年广泛时间序列所带来的高数据可用性以及多个AOIs，未来产品已经可以测试其时间和空间可迁移性。","Recent advances in remote sensing.","2026-09-16T00:00:00Z",81,{"impact":17,"substance":98,"depth":19,"authority":99,"freshness":21,"relevant":22,"comment":155},"面向未来Sentinel扩展任务的高光谱、热红外与L波段合成数据集研究，方法新颖、验证充分且公开可用，对农业遥感产品预研具有实质价值，值得进入每日精选。",[157],{"name":151,"url":148},[159,160,28,29,161,162],"农业遥感","高光谱","哥白尼计划","合成数据",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":166},{"candidates":167,"agricultural_evidence":47},[168],{"code":33,"score":169,"supported":47,"title":170,"abstract":172,"tags":174},20,[171],"hyperspectral",[28,50,173,171],"multispectral",[159,29,28,160],[176,177],"哥白尼计划 农业遥感 合成数据 地表温度","哥白尼计划 农业遥感","哥白尼计划农业遥感合成数据地表温度-2797",2,"10.62880\u002Frars26005",{"doi":180,"openalex_id":182,"authors":183,"venue":151,"cited_by_count":76,"oa_url":148,"card":218,"direction":81,"ingested_from":83},"W7213413531",[184,186,188,191,194,197,198,201,202,205,207,209,211,213,216],{"name":185,"orcid":9},"Christian Miesgang",{"name":187,"orcid":9},"Sandra Dotzler",{"name":189,"orcid":190},"Anusha Sanmathi Sathyaniranjan","https:\u002F\u002Forcid.org\u002F0009-0009-8710-4622",{"name":192,"orcid":193},"Silke Migdall","https:\u002F\u002Forcid.org\u002F0000-0001-9089-6274",{"name":195,"orcid":196},"Heike Bach","https:\u002F\u002Forcid.org\u002F0000-0001-8060-2498",{"name":65,"orcid":66},{"name":199,"orcid":200},"Astrid Vannoppen","https:\u002F\u002Forcid.org\u002F0000-0001-5140-832X",{"name":62,"orcid":9},{"name":203,"orcid":204},"Mihkel Veske","https:\u002F\u002Forcid.org\u002F0000-0003-2367-9215",{"name":206,"orcid":9},"Sven Kautlenbach",{"name":208,"orcid":9},"Catherine Odera",{"name":210,"orcid":9},"Tetiana Shtym",{"name":212,"orcid":9},"Tanel Tamm",{"name":214,"orcid":215},"Anke Schickling","https:\u002F\u002Forcid.org\u002F0000-0001-7446-7752",{"name":217,"orcid":9},"Melisa Soledad Heredia",{"tldr":219,"method":220,"finding":221,"direction":81,"opportunity":222},"生成CHIME高光谱、LSTM热红外和ROSE-L L波段模拟数据集，为未来Sentinel扩展任务","辐射传输模型反演、Sen-ET时空锐化、SAOCOM-1模拟，覆盖德比爱三区两年","模拟CHIME与EnMAP光谱相关性0.924，RMSE 6.154%，数据集公开且验证良好。","可基于该模拟数据集提前开发高光谱、热红外与L波段融合的作物监测和表型反演新算法。","2026-09-17T23:30:37.404847Z",{"id":225,"title":226,"url":227,"summary":228,"summary_zh":229,"content":9,"source_name":230,"source_url":227,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":232,"score_detail":233,"sources":237,"tags":239,"primary_topic":243,"secondary_topics":244,"classification":245,"search_phrases":264,"slug":267,"view_count":76,"doi":268,"paper":269,"created_at":288},5571,"Temporal Multi-Scale Spatio-Temporal Network (TMST): Polarization–Temporal Feature Selection and Multi-Scale Spatiotemporal Fusion for Crop Mapping","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202068","Accurate and timely crop mapping supports agricultural resource management, yield prediction, and food security decision-making. In this study, we propose the Temporal Multi-scale Spatio-Temporal Network (TMST), a crop mapping method that integrates multi-source remote sensing time series through polarization–temporal feature selection and multi-scale spatiotemporal fusion. TMST combines Sentinel-1 dual-polarization synthetic aperture radar (SAR), Sentinel-2 multispectral data, and vegetation indices. Its Temporal Feature Importance Explainer (TFIExplainer) selects informative polarization–time features, the Multi-Scale Attention Aggregation (MSAA) module enhances spatial representations, and the Spatio-Temporal Feature Encoder (STFE) models long-range spatial dependencies and phenological dynamics; a composite loss improves minority-class and difficult-pixel recognition. On the Xinxiang dataset, TMST achieved an overall accuracy (OA) of 0.8625 and a mean F1-score (mF1) of 0.8329. Module and data-source ablations suggested benefits of the combined modules and multi-source fusion, while a cropland mask reduced non-cropland misclassification. In direct cross-dataset evaluation, models trained on a self-constructed Austrian dataset and tested on the radar-extended Panoptic Agricultural Satellite Time Series (PASTIS-R) dataset showed that TMST outperformed the evaluated baselines under the specified source–target setting. Annual mapping of Xinxiang for 2019–2023, using year-specific samples and independently trained models, provided map-based estimates of regional cropping structures and spatial patterns. Under the evaluated settings, TMST provides an effective approach to crop classification and annually updated crop mapping.","准确的作物制图有助于农业资源管理、产量预测和粮食安全决策。本研究提出了一种时间多尺度时空网络（Temporal Multi-scale Spatio-Temporal Network，TMST），这是一种通过极化—时间特征选择和多尺度时空融合来整合多源遥感时间序列的作物制图方法。TMST结合了Sentinel-1双极化合成孔径雷达（SAR）、Sentinel-2多光谱数据和植被指数。其时间特征重要性解释器（Temporal Feature Importance Explainer，TFIExplainer）用于选择信息量丰富的极化—时间特征，多尺度注意力聚合（Multi-Scale Attention Aggregation，MSAA）模块增强空间表征，时空特征编码器（Spatio-Temporal Feature Encoder，STFE）建模长程空间依赖关系和物候动态；复合损失函数改善了少数类和困难像元的识别。在新乡数据集上，TMST取得了0.8625的总体精度（OA）和0.8329的平均F1分数（mF1）。模块和数据源消融实验表明，组合模块和多源融合具有优势，而耕地掩膜减少了非耕地误分类。在直接的跨数据集评估中，在自行构建的奥地利数据集上训练并在雷达扩展的Panoptic农业卫星时间序列（PASTIS-R）数据集上测试的模型表明，在指定的源—目标设置下，TMST优于所评估的基线方法。使用逐年样本和独立训练的模型对新乡2019—2023年进行年度制图，提供了基于制图的区域种植结构和空间格局估计。在所评估的设置下，TMST为作物分类和年度更新的作物制图提供了一种有效方法。","Agronomy","2026-10-21T00:00:00Z",73,{"impact":234,"substance":169,"depth":235,"authority":20,"freshness":13,"relevant":22,"comment":236},12,17,"提出多源遥感融合的作物制图新方法，方法新颖、实验充分，但属细分技术进展，公共影响有限。",[238],{"name":230,"url":227},[240,241,28,242],"智慧农业","作物制图","SAR",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":246},{"candidates":247,"agricultural_evidence":47},[248,252,259],{"code":33,"score":13,"supported":47,"title":249,"abstract":250,"tags":251},[],[28,50,173],[28],{"code":253,"score":86,"supported":47,"title":254,"abstract":255,"tags":258},"A8",[],[256,257],"粮食安全","food security",[],{"code":260,"score":22,"supported":14,"title":261,"abstract":262,"tags":263},"I1",[],[],[240],[265,266],"Sentinel-1 Sentinel-2 作物分类","TMST 多尺度时空网络","Sentinel-1Sentinel-2作物分类-5571","10.3390\u002Fagronomy16202068",{"doi":268,"openalex_id":270,"authors":271,"venue":230,"cited_by_count":76,"oa_url":227,"card":283,"direction":81,"ingested_from":83},"W7223117203",[272,275,277,280],{"name":273,"orcid":274},"Xi Kan","https:\u002F\u002Forcid.org\u002F0000-0002-4629-9357",{"name":276,"orcid":9},"Wentao Lv",{"name":278,"orcid":279},"Lei Gong","https:\u002F\u002Forcid.org\u002F0000-0001-6429-267X",{"name":281,"orcid":282},"Linglong Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-8863-9911",{"tldr":284,"method":285,"finding":286,"direction":81,"opportunity":287},"提出TMST网络，融合SAR与多光谱时序数据实现作物制图。","Sentinel-1\u002F2时序、极化-时序特征选择、多尺度注意力与时空编码器。","新乡OA达0.8625，多源融合与模块组合有效，跨数据集优于基线。","可探索极化-时序特征选择在跨区域迁移与少样本作物制图中的泛化能力。","2026-10-22T11:20:39.359881Z",{"id":290,"title":291,"url":292,"summary":293,"summary_zh":294,"content":9,"source_name":94,"source_url":292,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":295,"score_detail":296,"sources":298,"tags":300,"primary_topic":304,"secondary_topics":309,"classification":311,"search_phrases":328,"slug":331,"view_count":76,"doi":332,"paper":333,"created_at":343},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。",67,{"impact":46,"substance":169,"depth":235,"authority":234,"freshness":13,"relevant":22,"comment":297},"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[299],{"name":94,"url":292},[240,301,302,28,303],"农业人工智能","产量预测","可解释性",{"code":305,"slug":306,"name":307,"path":308,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[310],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":312},{"candidates":313,"agricultural_evidence":47},[314,320,324],{"code":305,"score":234,"supported":47,"title":315,"abstract":317,"tags":319},[316],"computer vision",[318],"计算机视觉",[301],{"code":33,"score":46,"supported":47,"title":321,"abstract":322,"tags":323},[],[28,50],[302,28],{"code":260,"score":22,"supported":14,"title":325,"abstract":326,"tags":327},[],[],[240],[329,330],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":332,"openalex_id":334,"authors":335,"venue":94,"cited_by_count":76,"oa_url":292,"card":338,"direction":81,"ingested_from":83},"W7223114002",[336],{"name":337,"orcid":9},"Kadiatou Barry",{"tldr":339,"method":340,"finding":341,"direction":81,"opportunity":342},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":345,"title":346,"url":347,"summary":348,"summary_zh":349,"content":9,"source_name":350,"source_url":347,"published_at":351,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":352,"sources":354,"tags":356,"primary_topic":360,"secondary_topics":366,"classification":368,"search_phrases":394,"slug":397,"view_count":76,"doi":398,"paper":399,"created_at":441},5567,"Capturing Spatial Heterogeneity Using UAV-Derived Multispectral Phenotypes and Random Regression Models Improves Genetic Evaluation in Alfalfa Breeding Trials","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.10.14.759249","Spatial heterogeneity is a major source of environmental noise in field trials, reducing genetic evaluation accuracy. Conventional spatial correction methods use field layout and plot proximity but often fail to capture in-season dynamics or leverage temporal data from high-throughput phenotyping. We hypothesized that longitudinal UAV-derived multispectral measurements could characterize field-scale environmental heterogeneity and improve genetic evaluation in breeding trials. Multispectral imagery was collected throughout the growing season across eight alfalfa trials in New York and New Mexico (20222023). Vegetation indices were evaluated for heritability and association with biomass yield using univariate and multi-trait models. Longitudinal measurements were modeled with random regression (RR) to estimate plot-specific permanent environmental effects (PEE), incorporated into genomic mixed models within a two-stage framework. Model performance was compared with conventional autoregressive (AR) and baseline (no correction) models using metrics of consistency and accuracy of estimated genetic effects across replicates. Vegetation indices showed moderate to high heritability, with GNDVI consistently outperforming NDVI and NDRE. Both univariate and multi-trait analyses revealed substantial spatial variability, particularly in New Mexico trials. RR-derived PEE captured field-scale spatial patterns and improved genetic signal recovery relative to baseline and AR models, with the largest gains under strong spatial heterogeneity and comparable performance where variability was limited. The RR framework improved reproducibility of genetic effect estimates across independent field subsets without compromising agreement with full-trial evaluations. These findings show that integrating UAV data via random regression enhances genetic signal recovery and selection accuracy, with broader potential for precision agriculture and biosensor-driven crop management.","空间异质性是田间试验中环境噪声的主要来源，会降低遗传评估的准确性。传统空间校正方法利用田间布局和小区邻近性，但往往无法捕捉生育期内的动态变化，也未能充分利用高通量表型分析产生的时间序列数据。我们假设，基于无人机（UAV）的纵向多光谱测量能够表征田块尺度的环境异质性，并改善育种试验中的遗传评估。在2022—2023年纽约州和新墨西哥州的8个紫花苜蓿试验中，于整个生长季收集了多光谱影像。采用单性状和多性状模型评估了植被指数的遗传力及其与生物量产量的关联。纵向测量数据采用随机回归（RR）建模，以估计小区特异性永久环境效应（PEE），并在两阶段框架中将其纳入基因组混合模型。利用重复间估计遗传效应的一致性和准确性指标，将模型性能与传统的自回归（AR）模型和基线（无校正）模型进行比较。植被指数表现出中到高的遗传力，其中GNDVI始终优于NDVI和NDRE。单性状和多性状分析均揭示了显著的空间变异，尤其在新墨西哥州的试验中更为明显。RR衍生的PEE捕捉到了田块尺度的空间格局，相对于基线模型和AR模型改善了遗传信号的恢复，在强空间异质性条件下增益最大，而在变异有限时性能相当。RR框架提高了遗传效应估计在独立田间子集间的可重复性，同时未损害与全试验评估的一致性。这些结果表明，通过随机回归整合UAV数据可增强遗传信号恢复和选择准确性，在精准农业和生物传感器驱动的作物管理方面具有更广泛的潜力。","bioRxiv (Cold Spring Harbor Laboratory)","2026-10-20T00:00:00Z",{"impact":17,"substance":98,"depth":17,"authority":234,"freshness":21,"relevant":22,"comment":353},"该研究利用无人机多光谱表型与随机回归模型校正田间空间异质性，显著提升苜蓿育种遗传评估精度，方法新颖、数据覆盖两州八组试验，对智慧育种有实质参考价值。",[355],{"name":350,"url":347},[240,357,358,28,359],"无人机","育种","紫花苜蓿",{"code":361,"slug":362,"name":363,"path":364,"parent_code":365},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[367],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":369},{"candidates":370,"agricultural_evidence":47},[371,378,382,389],{"code":361,"score":372,"supported":47,"title":373,"abstract":375,"tags":377},15,[374],"alfalfa",[376,374],"苜蓿",[359],{"code":33,"score":234,"supported":47,"title":379,"abstract":380,"tags":381},[173],[173],[28],{"code":260,"score":383,"supported":47,"title":384,"abstract":385,"tags":388},7,[],[386,387],"精准农业","precision agriculture",[240],{"code":390,"score":118,"supported":47,"title":391,"abstract":392,"tags":393},"C4",[],[376],[359],[395,396],"无人机 多光谱 苜蓿 育种","随机回归 空间异质性 遗传评估","无人机多光谱苜蓿育种-5567","10.64898\u002F2026.10.14.759249",{"doi":398,"openalex_id":400,"authors":401,"venue":350,"cited_by_count":76,"oa_url":347,"card":436,"direction":81,"ingested_from":83},"W7223083966",[402,405,408,411,414,416,418,421,424,427,430,433],{"name":403,"orcid":404},"Dinesh Ghimire","https:\u002F\u002Forcid.org\u002F0009-0008-2281-1396",{"name":406,"orcid":407},"Ranjita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-6116-7611",{"name":409,"orcid":410},"Karl H. Kunze","https:\u002F\u002Forcid.org\u002F0000-0003-4548-1808",{"name":412,"orcid":413},"Felipe Sabadin","https:\u002F\u002Forcid.org\u002F0000-0003-2937-1465",{"name":415,"orcid":9},"Julie Hansen",{"name":417,"orcid":9},"Christopher Pierce",{"name":419,"orcid":420},"Liam Wickes-Do","https:\u002F\u002Forcid.org\u002F0009-0003-2927-4590",{"name":422,"orcid":423},"Nicholas Santantonio","https:\u002F\u002Forcid.org\u002F0000-0002-4351-4023",{"name":425,"orcid":426},"Ian M. Ray","https:\u002F\u002Forcid.org\u002F0000-0003-2056-536X",{"name":428,"orcid":429},"Michael A. Gore","https:\u002F\u002Forcid.org\u002F0000-0001-6896-8024",{"name":431,"orcid":432},"Virginia Mae Moore","https:\u002F\u002Forcid.org\u002F0000-0001-7888-3366",{"name":434,"orcid":435},"Kelly R. Robbins","https:\u002F\u002Forcid.org\u002F0000-0001-9522-9585",{"tldr":437,"method":438,"finding":439,"direction":81,"opportunity":440},"用无人机多光谱时序表型和随机回归模型校正田间空间异质性，提升苜蓿育种遗传评估精度。","八项苜蓿试验的无人机多光谱植被指数，随机回归估计小区永久环境效应并嵌入基因组混合","随机回归提取的环境效应能捕捉田块尺度空间格局，在强异质性下显著提升遗传信号恢复与选择准确性。","可将无人机时序表型与随机回归框架推广到其他作物育种试验，并探索多源遥感与基因组选择的联合建模。","2026-10-22T11:20:32.655394Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":9,"source_name":94,"source_url":445,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":448,"score_detail":449,"sources":452,"tags":454,"primary_topic":458,"secondary_topics":464,"classification":471,"search_phrases":503,"slug":506,"view_count":76,"doi":507,"paper":508,"created_at":519},5552,"INTEGRATING IoT, REMOTE SENSING, AND ARTIFICIAL INTELLIGENCE FOR SMART IRRIGATION: A REVIEW OF ARCHITECTURES, METHODS, AND CHALLENGES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23531020","This research paper reviews the integration of Internet of Things (IoT), remote sensing, and Artificial Intelligence (AI) in smart irrigation systems. It discusses system architectures, intelligent irrigation techniques, automated water management, key challenges, and future research opportunities to improve water-use efficiency and promote sustainable agriculture.","本文综述了物联网（Internet of Things, IoT）、遥感与人工智能（Artificial Intelligence, AI）在智能灌溉系统中的融合应用，探讨了系统架构、智能灌溉技术、自动化水资源管理、关键挑战及未来研究方向，以提升用水效率并促进可持续农业发展。",75,{"impact":17,"substance":169,"depth":450,"authority":234,"freshness":21,"relevant":22,"comment":451},16,"系统综述物联网、遥感与AI融合的智能灌溉架构与方法，属智慧农业细分领域有实质增量的国际综述，值得入选。",[453],{"name":94,"url":445},[301,455,28,456,457],"农业物联网","智慧灌溉","节水农业",{"code":459,"slug":460,"name":461,"path":462,"parent_code":463},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[465,470],{"code":466,"slug":467,"name":468,"path":469,"parent_code":37},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":472},{"candidates":473,"agricultural_evidence":47},[474,480,487,491,496],{"code":459,"score":19,"supported":47,"title":475,"abstract":476,"tags":479},[460],[477,478,460],"灌溉","水资源",[456,457],{"code":466,"score":17,"supported":47,"title":481,"abstract":483,"tags":486},[482],"IoT",[484,485,482],"物联网","internet of things",[455],{"code":33,"score":372,"supported":47,"title":488,"abstract":489,"tags":490},[50],[28,50],[28],{"code":305,"score":234,"supported":47,"title":492,"abstract":494,"tags":495},[493],"artificial intelligence",[493],[301],{"code":497,"score":86,"supported":47,"title":498,"abstract":499,"tags":502},"H8",[],[500,501],"可持续农业","sustainable agriculture",[],[504,505],"IoT 遥感 AI 智能灌溉","农业人工智能 农业物联网 智慧灌溉 节水农业","IoT遥感AI智能灌溉-5552","10.5281\u002Fzenodo.23531020",{"doi":507,"openalex_id":509,"authors":510,"venue":94,"cited_by_count":76,"oa_url":445,"card":513,"direction":517,"ingested_from":83},"W7223090389",[511],{"name":512,"orcid":9},"Patil",{"tldr":514,"method":515,"finding":516,"direction":517,"opportunity":518},"综述物联网、遥感与人工智能融合的智能灌溉系统架构、方法与挑战。","文献综述，梳理IoT、遥感与AI集成的系统架构与智能灌溉技术。","融合三者可提升用水效率并推动可持续农业，但仍面临关键挑战。","智慧农业 \u002F 农业物联网","可针对多源数据融合的实时灌溉决策模型与边缘部署开展实证研究。","2026-10-22T11:20:18.028252Z"]