[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3896":3,"related-3896":105},{"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":18,"tags":20,"primary_topic":24,"secondary_topics":30,"classification":31,"search_phrases":58,"slug":61,"view_count":47,"doi":62,"paper":63,"created_at":104},3896,"Combined Approach to Locate Medieval Fortified Manor Houses in Central Moravia (the Czech Republic)","https:\u002F\u002Fdoi.org\u002F10.1111\u002Farcm.70231","ABSTRACT A systematic prospection of medieval fortified manor houses (FMHs) in Central Moravia (Czech Republic) was conducted with the aim of mapping their distribution and facilitating both further scholarly research and more effective heritage protection by responsible institutions. Given the inherent limitations of individual investigative techniques, a combined methodological framework drawing on historical research, socio‐historical approaches and natural‐science methods was employed. This integrated approach proved effective: of the 123 initially presumed FMHs, 79 were confirmed as having medieval origins, while the remaining 44 sites were shown to be of later date, of uncertain chronology or unfortified. Remote sensing verified a substantial proportion of FMHs recorded in historical sources; however, archaeological research, fieldwalking survey, geophysical survey and the analysis of historical maps also yielded valuable results. The spatial distribution of Central Moravian FMHs, comparable with that of fortified manorial residences elsewhere in Central Europe, reflects their multifunctional character but is primarily conditioned by agricultural suitability, particularly the presence of fertile soils, as well as by territorial constraints imposed by major landholders such as margraves and bishops.","摘要 对捷克共和国中摩拉维亚地区的中世纪设防庄园（fortified manor houses, FMHs）进行了系统性勘察，旨在绘制其分布图，并为后续学术研究以及相关负责机构更有效的遗产保护提供便利。鉴于单一调查技术固有的局限性，本研究采用了一种综合方法框架，融合了历史研究、社会历史学方法及自然科学方法。这一整合性方法被证明是有效的：在最初推测的123处设防庄园中，79处被确认为具有中世纪起源，其余44处则被证明年代较晚、年代不确定或未设防。遥感技术验证了历史文献中记载的相当一部分设防庄园；然而，考古研究、田野调查、地球物理勘探及历史地图分析也取得了有价值的成果。中摩拉维亚设防庄园的空间分布与中欧其他地区的设防领主宅邸相当，反映了其多功能特征，但主要受农业适宜性——尤其是肥沃土壤的存在——以及边疆伯爵和主教等主要土地持有者所施加的领土限制所制约。",null,"Archaeometry","2026-09-30T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该文为考古学论文，研究捷克中部中世纪设防庄园的遥感与多方法勘探，与三农、农业信息化、智慧农业等主题无关，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23],"考古遥感","中世纪庄园","遗产保护",{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":35},"classified","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":39},[37,45,52],{"code":25,"score":38,"supported":39,"title":40,"abstract":41,"tags":44},6,true,[],[42,43],"遥感","remote sensing",[],{"code":46,"score":47,"supported":39,"title":48,"abstract":49,"tags":51},"H2",3,[],[50],"土壤",[],{"code":53,"score":47,"supported":39,"title":54,"abstract":55,"tags":57},"I7",[],[56],"methodological framework",[],[59,60],"中世纪庄园 考古遥感 遗产保护","中世纪庄园 考古遥感","中世纪庄园考古遥感遗产保护-3896","10.1111\u002Farcm.70231",{"doi":62,"openalex_id":64,"authors":65,"venue":10,"cited_by_count":15,"oa_url":6,"card":97,"direction":101,"ingested_from":103},"W7214909131",[66,69,72,75,78,81,84,87,90,92,94],{"name":67,"orcid":68},"Martin Moník","https:\u002F\u002Forcid.org\u002F0000-0001-8793-169X",{"name":70,"orcid":71},"Jakub Novák","https:\u002F\u002Forcid.org\u002F0000-0001-7800-4181",{"name":73,"orcid":74},"Stanislav Popelka","https:\u002F\u002Forcid.org\u002F0000-0003-2127-2614",{"name":76,"orcid":77},"O. Růžička","https:\u002F\u002Forcid.org\u002F0009-0000-6240-3823",{"name":79,"orcid":80},"Markéta Beitlová","https:\u002F\u002Forcid.org\u002F0000-0002-3935-5824",{"name":82,"orcid":83},"Jan Martínek","https:\u002F\u002Forcid.org\u002F0000-0003-3734-5355",{"name":85,"orcid":86},"Pavel Šlézar","https:\u002F\u002Forcid.org\u002F0000-0001-5502-0701",{"name":88,"orcid":89},"Josef Svoboda","https:\u002F\u002Forcid.org\u002F0000-0003-0402-7879",{"name":91,"orcid":9},"Lukáš Hlubek",{"name":93,"orcid":9},"Tomáš Lehotský",{"name":95,"orcid":96},"David Papajík","https:\u002F\u002Forcid.org\u002F0000-0001-9652-4789",{"tldr":98,"method":99,"finding":100,"direction":101,"opportunity":102},"综合多学科方法系统调查捷克中摩拉维亚中世纪设防庄园，确认79处并分析其分布规律。","历史研究、社会史与遥感、考古、地球物理勘探、历史地图分析相结合。","123处推定庄园中79处确认为中世纪，分布主要受肥沃土壤和大地主领地约束。","农业遥感与作物表型","可借鉴多源遥感与历史GIS结合的方法，研究历史农业聚落与土壤适宜性的长期耦合关系。","openalex","2026-10-01T23:30:28.842686Z",{"total":38,"page":106,"page_size":38,"items":107},1,[108,159,219,330,422,484],{"id":109,"title":110,"url":111,"summary":112,"summary_zh":113,"content":9,"source_name":114,"source_url":111,"published_at":115,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":116,"sources":118,"tags":120,"primary_topic":123,"secondary_topics":124,"classification":125,"search_phrases":137,"slug":140,"view_count":106,"doi":141,"paper":142,"created_at":158},4024,"Mesopotamia Beyond Tells: Documenting Agro-Pastoral Landscapes in the Zagros Piedmont (Kurdistan Region of Iraq)","https:\u002F\u002Fdoi.org\u002F10.1080\u002F00934690.2026.2732748","Agro-pastoral landscapes have long shaped Upper Mesopotamia, yet their dispersed, low-visibility, and often feature-dense archaeological traces remain poorly documented, especially in upland and piedmont zones beyond tell-centred research traditions. This article presents the methodological framework developed by the CArE Project of the Universities Ca’ Foscari Venice and Udine for documenting the rich, endangered agro-pastoral landscapes recorded in the Zagros piedmont of the Kurdistan Region of Iraq. Conceived as a two-year pilot project, CArE integrates diachronic remote sensing, UAV photogrammetry, pedestrian survey, feature-level geodatabase recording, heritage-risk assessment, and targeted OSL sampling. Applied to the area between the towns of Faida and Sheikhan, this workflow enabled the systematic documentation of cairns, enclosures, terraces, walled fields, and modern conflict-related features within a multi-period archaeological continuum. CArE offers a scalable and reproducible model for recording, analysing, and protecting agro-pastoral landscapes increasingly threatened by agriculture, settlement, infrastructure, and extractive development.","农牧景观长期以来塑造了上美索不达米亚，但其分散、低可见度且往往特征密集的考古遗迹仍缺乏充分记录，尤其是在以土丘为中心的研究传统之外的高地和山前地带。本文介绍了威尼斯卡福斯卡里大学和乌迪内大学CArE项目所开发的方法论框架，用于记录伊拉克库尔德斯坦地区扎格罗斯山前地带丰富且濒危的农牧景观。作为一个为期两年的试点项目，CArE整合了历时性遥感、无人机摄影测量、步行调查、遗迹级地理数据库记录、遗产风险评估以及定向光释光（OSL）采样。该工作流程应用于法伊达和谢汗两镇之间的区域，使得在多时期考古连续体中系统记录石堆、围栏、梯田、有墙田地以及与当代冲突相关的遗迹成为可能。CArE提供了一个可扩展且可重复的模式，用于记录、分析和保护日益受到农业、定居、基础设施和采掘开发威胁的农牧景观。","Journal of Field Archaeology","2026-10-01T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":117},"该文为伊拉克库尔德地区考古景观记录方法研究，属考古学范畴，与三农、农业信息化、智慧农业等主题无直接关联，不建议进入每日精选。",[119],{"name":114,"url":111},[121,21,23,122],"无人机测绘","景观考古",{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},[],{"status":32,"locked":14,"version":33,"method":34,"evidence":126},{"candidates":127,"agricultural_evidence":39},[128,133],{"code":25,"score":129,"supported":39,"title":130,"abstract":131,"tags":132},7,[],[42,43],[121],{"code":53,"score":47,"supported":39,"title":134,"abstract":135,"tags":136},[],[56],[],[138,139],"无人机测绘 景观考古 考古遥感 遗产保护","无人机测绘 景观考古","无人机测绘景观考古考古遥感遗产保护-4024","10.1080\u002F00934690.2026.2732748",{"doi":141,"openalex_id":143,"authors":144,"venue":114,"cited_by_count":15,"oa_url":111,"card":153,"direction":101,"ingested_from":103},"W7213447556",[145,147,149,151],{"name":146,"orcid":9},"F. Simi",{"name":148,"orcid":9},"S. Palalidis",{"name":150,"orcid":9},"Morandi Bonacossi D.",{"name":152,"orcid":9},"C. Tonghini",{"tldr":154,"method":155,"finding":156,"direction":101,"opportunity":157},"提出CArE项目方法框架，系统记录伊拉克库尔德斯坦扎格罗斯山麓的农牧景观。","综合遥感、无人机摄影测量、步行调查、地学数据库、遗产风险评估与OSL测年。","在Faida至Sheikhan间系统记录了石堆、围栏、梯田、石墙田及现代冲突遗迹等多时期遗存。","可将该多源遥感与风险评估框架迁移至其他干旱区农牧景观，并探索自动化特征提取与长期监测。","2026-10-02T23:30:24.389941Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":9,"source_name":165,"source_url":162,"published_at":166,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":168,"sources":175,"tags":177,"primary_topic":181,"secondary_topics":182,"classification":183,"search_phrases":198,"slug":201,"view_count":106,"doi":202,"paper":203,"created_at":218},4749,"Beyond site-specific archaeological prospection: Spectral-geometry reveals cross-site cropmark signals in satellite data","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fpnasnexus\u002Fpgag336","Abstract Remote sensing has long supported archaeological prospection, mainly through the detection of cropmarks, a key archaeological proxy expressed as spectral vegetation anomalies over subsurface features. Yet, cropmark detection is still assumed in the literature to be highly site-specific, governed by local agronomic and environmental conditions. Using multispectral Sentinel-2 data from three European archaeological sites, we show that models trained in one landscape can recover meaningful archaeological proxy signals in other locations. By relying strictly on satellite spectral signatures for training, our models achieve measurable cross-location transferability without incorporating ancillary environmental data. We find that cross-site performance arises not from geographic proximity but from the spectral-geometric similarity of vegetation responses, and that transferability is strongly directional. We quantify this relationship through a Directional Strength Score (DSS), derived from monthly subcluster distances under multiple norms, which captures directional geometric similarity and correlates strongly with machine-learning performance. To keep the analysis grounded in the underlying spectral signal, we relied on architecturally restrained nonlinear classifiers (SVM and constrained XGBoost) and used NDVI-identified phenophases to align training and evaluation with comparable seasonal windows. Taken together, these results demonstrate that partial, spectrally mediated cross-location cropmark detection is feasible and that the underlying vegetation responses exhibit stable spectral structure, with spectral geometry offering a clear interpretive lens on why these signals can transfer across sites. Leveraging globally harmonized satellite data, this approach offers a scalable complement to uneven historical aerial archives and supports systematic regional archaeological prioritization to be deployed within integrated archaeological workflows.","摘要 遥感长期支持考古勘探，主要通过检测作物痕迹（cropmarks）——一种关键的考古代用指标，表现为地下特征上方植被的光谱异常。然而，文献中仍普遍认为作物痕迹检测高度依赖于具体遗址，受当地农艺和环境条件制约。利用来自三个欧洲考古遗址的多光谱Sentinel-2数据，我们表明在一个景观中训练的模型可以在其他地点恢复有意义的考古代用信号。通过严格依赖卫星光谱特征进行训练，我们的模型在不纳入辅助环境数据的情况下实现了可测量的跨地点迁移能力。我们发现，跨遗址性能并非源于地理邻近性，而是源于植被响应的光谱-几何相似性，并且迁移能力具有强烈的方向性。我们通过方向强度评分（Directional Strength Score, DSS）量化这一关系，该评分基于多种范数下的逐月子簇距离推导而来，捕捉方向性几何相似性并与机器学习性能强烈相关。为使分析立足于底层光谱信号，我们采用架构受限的非线性分类器（SVM和约束XGBoost），并使用NDVI识别的物候期来对齐训练和评估，使其处于可比较的季节窗口内。综合来看，这些结果表明，部分、以光谱为中介的跨地点作物痕迹检测是可行的，且底层植被响应表现出稳定的光谱结构，光谱几何为理解这些信号为何能够跨遗址迁移提供了清晰的解释视角。利用全球协调的卫星数据，该方法为不均衡的历史航空档案提供了可扩展的补充，并支持在综合考古工作流程中部署系统性的区域考古优先级排序。","PNAS Nexus","2026-10-10T00:00:00Z",82,{"impact":169,"substance":170,"depth":171,"authority":172,"freshness":173,"relevant":106,"comment":174},18,22,19,15,8,"PNAS Nexus 论文，用 Sentinel-2 多光谱数据证明作物标记信号可跨遗址迁移，方法新颖、结论可靠，对农业遥感与考古信息化有参考价值，但属细分领域突破，未达全国性产业事件层级。",[176],{"name":165,"url":162},[178,42,179,21,180],"Sentinel-2","NDVI","作物标记",{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},[],{"status":32,"locked":14,"version":33,"method":34,"evidence":184},{"candidates":185,"agricultural_evidence":39},[186,192],{"code":25,"score":187,"supported":39,"title":188,"abstract":189,"tags":191},12,[],[42,43,190],"multispectral",[179,178,42],{"code":193,"score":47,"supported":39,"title":194,"abstract":195,"tags":197},"I2",[],[196],"机器学习",[],[199,200],"Sentinel-2 作物标记 考古","遥感 光谱几何 跨遗址","Sentinel-2作物标记考古-4749","10.1093\u002Fpnasnexus\u002Fpgag336",{"doi":202,"openalex_id":204,"authors":205,"venue":165,"cited_by_count":15,"oa_url":212,"card":213,"direction":101,"ingested_from":103},"W7221319130",[206,209],{"name":207,"orcid":208},"Elias Gravanis","https:\u002F\u002Forcid.org\u002F0000-0002-5331-6661",{"name":210,"orcid":211},"Άθως Αγαπίου","https:\u002F\u002Forcid.org\u002F0000-0001-9106-6766","https:\u002F\u002Facademic.oup.com\u002Fpnasnexus\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fpnasnexus\u002Fpgag336\u002F71838194\u002Fpgag336.pdf",{"tldr":214,"method":215,"finding":216,"direction":101,"opportunity":217},"用Sentinel-2多光谱数据证明作物标记模型可跨遗址迁移，且迁移性由光谱几何相似性决定。","Sentinel-2多光谱、SVM与约束XGBoost、NDVI物候对齐、方向强","跨遗址作物标记检测可行，迁移性源于植被光谱几何相似而非地理邻近，且具方向性。","可将光谱几何迁移性指标引入作物表型与病害遥感，构建跨区域可迁移的植被异常检测模型。","2026-10-12T23:30:24.489835Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":224,"content":9,"source_name":225,"source_url":222,"published_at":226,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":227,"score_detail":228,"sources":232,"tags":234,"primary_topic":240,"secondary_topics":241,"classification":246,"search_phrases":302,"slug":305,"view_count":15,"doi":306,"paper":307,"created_at":329},5582,"AI-Based RGB Imaging and 14-Channel Multispectral Food Quality Scanner","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85255","Food-quality assessment plays an important role in food safety, agricultural processing, storage, and supply-chain management. Conventional inspection methods depend on visual judgement or laboratory-based testing, which may require considerable time, specialised equipment, and manual effort. Recent developments in computer vision, multispectral sensing, and artificial intelligence (AI) provide opportunities for automated, non-destructive food-quality assessment. This paper reviews the application of RGB imaging, multispectral sensing, machine learning, and deep learning for fruit-ripeness estimation, surfacedefect detection, grain classification, and food-authenticity assessment. The reviewed literature demonstrates that RGB imaging can extract visible features such as colour, shape, and texture, whereas multispectral sensing provides wavelength-dependent information associated with food characteristics. Published studies have reported promising results in tomato-ripeness classification, apple-defect detection, rice-grain analysis, and honey-adulteration screening. Based on these findings, a compact food-quality scanner integrating an RGB camera, a 14-channel multispectral sensor, controlled illumination, and an embedded processing unit is proposed. The review discusses sensor integration, data preprocessing, feature fusion, classification methods, evaluation metrics, and implementation challenges. It also identifies the need for broader datasets, standardised illumination, independent validation, and resource-efficient AI models to improve the reliability of portable food-inspection systems.","食品质量评估在食品安全、农产品加工、储运和供应链管理中发挥着重要作用。传统检测方法依赖人工目视判断或实验室检测，往往需要较长时间、专用设备和人工投入。近年来，计算机视觉、多光谱传感和人工智能（AI）的发展为自动化、无损食品质量评估提供了新的机遇。本文综述了RGB成像、多光谱传感、机器学习和深度学习在果实成熟度估计、表面缺陷检测、谷物分类和食品真实性评估中的应用。所综述的文献表明，RGB成像能够提取颜色、形状和纹理等可见特征，而多光谱传感则可提供与食品特性相关的波长依赖信息。已发表研究在番茄成熟度分类、苹果缺陷检测、稻米籽粒分析和蜂蜜掺假筛查等方面取得了良好结果。基于上述研究结果，本文提出一种集成了RGB相机、14通道多光谱传感器、受控照明和嵌入式处理单元的紧凑型食品质量扫描仪。综述讨论了传感器集成、数据预处理、特征融合、分类方法、评价指标和实现挑战，并指出需要更广泛的数据集、标准化照明、独立验证和资源高效的AI模型，以提高便携式食品检测系统的可靠性。","International Journal for Research in Applied Science and Engineering Technology","2026-10-21T00:00:00Z",65,{"impact":187,"substance":169,"depth":229,"authority":230,"freshness":13,"relevant":106,"comment":231},16,9,"综述性论文，提出集成RGB与14通道多光谱的便携食品质量扫描仪方案，方法框架清晰但缺乏自有实验数据，属细分领域技术进展，可作参考但非重大突破。",[233],{"name":225,"url":222},[235,236,237,238,239],"智慧农业","农业人工智能","无损检测","多光谱成像","食品质量检测",{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},[242],{"code":193,"slug":243,"name":244,"path":245,"parent_code":29},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":32,"locked":14,"version":33,"method":34,"evidence":247},{"candidates":248,"agricultural_evidence":39},[249,253,263,270,277,284,291,297],{"code":25,"score":187,"supported":39,"title":250,"abstract":251,"tags":252},[190],[190],[238],{"code":193,"score":13,"supported":39,"title":254,"abstract":255,"tags":262},[],[256,196,257,258,259,260,261],"深度学习","计算机视觉","machine learning","deep learning","artificial intelligence","computer vision",[236],{"code":264,"score":129,"supported":39,"title":265,"abstract":266,"tags":269},"E4",[],[267,268],"食品安全","food safety",[237],{"code":271,"score":38,"supported":39,"title":272,"abstract":273,"tags":276},"A1",[],[274,275],"稻米","rice",[],{"code":278,"score":38,"supported":39,"title":279,"abstract":280,"tags":283},"B1",[],[281,282],"番茄","tomato",[],{"code":285,"score":38,"supported":39,"title":286,"abstract":287,"tags":290},"B2",[],[288,289],"苹果","apple",[],{"code":292,"score":47,"supported":39,"title":293,"abstract":294,"tags":296},"E1",[],[295],"农产品加工",[],{"code":298,"score":106,"supported":14,"title":299,"abstract":300,"tags":301},"I1",[],[],[235],[303,304],"RGB成像 多光谱 食品质量","14通道 多光谱 扫描仪","RGB成像多光谱食品质量-5582","10.22214\u002Fijraset.2026.85255",{"doi":306,"openalex_id":308,"authors":309,"venue":225,"cited_by_count":15,"oa_url":222,"card":322,"direction":328,"ingested_from":103},"W7223139905",[310,312,314,316,318,320],{"name":311,"orcid":9},"Eshwari Take",{"name":313,"orcid":9},"Avanish Raut",{"name":315,"orcid":9},"Vedant Joshi",{"name":317,"orcid":9},"Shravani Akolkar",{"name":319,"orcid":9},"R. M. Gharat",{"name":321,"orcid":9},"Shruti Dive",{"tldr":323,"method":324,"finding":325,"direction":326,"opportunity":327},"综述RGB与多光谱成像结合AI的食品品质无损检测，并提出一款集成14通道多光谱传感器的紧凑型扫描仪方","综述RGB成像、多光谱传感与机器学习\u002F深度学习在食品检测中的应用，并提出传感器集","RGB与多光谱融合在番茄成熟度、苹果缺陷、稻米分类和蜂蜜掺假检测中表现良好。","农业人工智能与决策模型","可研究多源光谱特征融合与轻量化模型，构建标准化数据集和便携设备独立验证体系。","数字乡村与农业信息化","2026-10-22T11:20:48.684398Z",{"id":331,"title":332,"url":333,"summary":334,"summary_zh":335,"content":9,"source_name":336,"source_url":333,"published_at":226,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":337,"score_detail":338,"sources":341,"tags":343,"primary_topic":347,"secondary_topics":353,"classification":361,"search_phrases":390,"slug":393,"view_count":15,"doi":394,"paper":395,"created_at":421},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",80,{"impact":229,"substance":170,"depth":169,"authority":339,"freshness":13,"relevant":106,"comment":340},14,"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。",[342],{"name":336,"url":333},[235,236,344,345,346],"农业遥感","氮素监测","紫花苜蓿",{"code":348,"slug":349,"name":350,"path":351,"parent_code":352},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[354,355],{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},{"code":356,"slug":357,"name":358,"path":359,"parent_code":360},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed","C",{"status":32,"locked":14,"version":33,"method":34,"evidence":362},{"candidates":363,"agricultural_evidence":39},[364,369,375,381,386],{"code":25,"score":169,"supported":39,"title":365,"abstract":367,"tags":368},[366],"hyperspectral",[42,43,366],[344],{"code":348,"score":172,"supported":39,"title":370,"abstract":372,"tags":374},[371],"alfalfa",[373,371],"苜蓿",[346],{"code":356,"score":13,"supported":39,"title":376,"abstract":377,"tags":380},[],[378,373,379],"饲草","forage",[346],{"code":193,"score":13,"supported":39,"title":382,"abstract":383,"tags":385},[],[256,196,258,259,384],"decision support",[236],{"code":298,"score":106,"supported":14,"title":387,"abstract":388,"tags":389},[],[],[235],[391,392],"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":394,"openalex_id":396,"authors":397,"venue":336,"cited_by_count":15,"oa_url":333,"card":416,"direction":101,"ingested_from":103},"W7223154576",[398,400,402,404,406,409,411,414],{"name":399,"orcid":9},"Shuai Fu",{"name":401,"orcid":9},"Yunhao Li",{"name":403,"orcid":9},"Chunli Miao",{"name":405,"orcid":9},"Jie Liu",{"name":407,"orcid":408},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":410,"orcid":9},"Yongjia Hu",{"name":412,"orcid":413},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":415,"orcid":9},"吴彩霞",{"tldr":417,"method":418,"finding":419,"direction":101,"opportunity":420},"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":423,"title":424,"url":425,"summary":426,"summary_zh":427,"content":9,"source_name":428,"source_url":425,"published_at":226,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":429,"score_detail":430,"sources":434,"tags":436,"primary_topic":439,"secondary_topics":440,"classification":441,"search_phrases":459,"slug":462,"view_count":15,"doi":463,"paper":464,"created_at":483},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",73,{"impact":187,"substance":431,"depth":432,"authority":339,"freshness":13,"relevant":106,"comment":433},20,17,"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。",[435],{"name":428,"url":425},[235,437,42,438],"作物制图","SAR",{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},[],{"status":32,"locked":14,"version":33,"method":34,"evidence":442},{"candidates":443,"agricultural_evidence":39},[444,448,455],{"code":25,"score":13,"supported":39,"title":445,"abstract":446,"tags":447},[],[42,43,190],[42],{"code":449,"score":38,"supported":39,"title":450,"abstract":451,"tags":454},"A8",[],[452,453],"粮食安全","food security",[],{"code":298,"score":106,"supported":14,"title":456,"abstract":457,"tags":458},[],[],[235],[460,461],"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":463,"openalex_id":465,"authors":466,"venue":428,"cited_by_count":15,"oa_url":425,"card":478,"direction":101,"ingested_from":103},"W7223117203",[467,470,472,475],{"name":468,"orcid":469},"Xi Kan","https:\u002F\u002Forcid.org\u002F0000-0002-4629-9357",{"name":471,"orcid":9},"Wentao Lv",{"name":473,"orcid":474},"Lei Gong","https:\u002F\u002Forcid.org\u002F0000-0001-6429-267X",{"name":476,"orcid":477},"Linglong Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-8863-9911",{"tldr":479,"method":480,"finding":481,"direction":101,"opportunity":482},"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":485,"title":486,"url":487,"summary":488,"summary_zh":489,"content":9,"source_name":490,"source_url":487,"published_at":226,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":491,"score_detail":492,"sources":494,"tags":496,"primary_topic":499,"secondary_topics":500,"classification":502,"search_phrases":517,"slug":520,"view_count":15,"doi":521,"paper":522,"created_at":532},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。","Zenodo (CERN European Organization for Nuclear Research)",67,{"impact":173,"substance":431,"depth":432,"authority":187,"freshness":13,"relevant":106,"comment":493},"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。",[495],{"name":490,"url":487},[235,236,497,42,498],"产量预测","可解释性",{"code":193,"slug":243,"name":244,"path":245,"parent_code":29},[501],{"code":25,"slug":26,"name":27,"path":28,"parent_code":29},{"status":32,"locked":14,"version":33,"method":34,"evidence":503},{"candidates":504,"agricultural_evidence":39},[505,509,513],{"code":193,"score":187,"supported":39,"title":506,"abstract":507,"tags":508},[261],[257],[236],{"code":25,"score":173,"supported":39,"title":510,"abstract":511,"tags":512},[],[42,43],[497,42],{"code":298,"score":106,"supported":14,"title":514,"abstract":515,"tags":516},[],[],[235],[518,519],"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":521,"openalex_id":523,"authors":524,"venue":490,"cited_by_count":15,"oa_url":487,"card":527,"direction":101,"ingested_from":103},"W7223114002",[525],{"name":526,"orcid":9},"Kadiatou Barry",{"tldr":528,"method":529,"finding":530,"direction":101,"opportunity":531},"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"]