[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4749":3,"related-4749":84},{"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":60,"slug":63,"view_count":22,"doi":64,"paper":65,"created_at":83},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。",null,"PNAS Nexus","2026-10-10T00:00:00Z","论文",10,false,82,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,22,19,15,8,1,"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。",[25],{"name":10,"url":6},[27,28,29,30,31],"Sentinel-2","遥感","NDVI","考古遥感","作物标记",{"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},[45,53],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":52},12,true,[],[28,50,51],"remote sensing","multispectral",[29,27,28],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":59},"I2",3,[],[58],"机器学习",[],[61,62],"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":64,"openalex_id":66,"authors":67,"venue":10,"cited_by_count":74,"oa_url":75,"card":76,"direction":80,"ingested_from":82},"W7221319130",[68,71],{"name":69,"orcid":70},"Elias Gravanis","https:\u002F\u002Forcid.org\u002F0000-0002-5331-6661",{"name":72,"orcid":73},"Άθως Αγαπίου","https:\u002F\u002Forcid.org\u002F0000-0001-9106-6766",0,"https:\u002F\u002Facademic.oup.com\u002Fpnasnexus\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fpnasnexus\u002Fpgag336\u002F71838194\u002Fpgag336.pdf",{"tldr":77,"method":78,"finding":79,"direction":80,"opportunity":81},"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。","农业遥感与作物表型","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。","openalex","2026-10-12T23:30:24.489835Z",{"total":85,"page":22,"page_size":85,"items":86},6,[87,139,194,259,320,395],{"id":88,"title":89,"url":90,"summary":91,"summary_zh":92,"content":9,"source_name":93,"source_url":90,"published_at":94,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":95,"score_detail":96,"sources":99,"tags":101,"primary_topic":105,"secondary_topics":106,"classification":107,"search_phrases":121,"slug":124,"view_count":74,"doi":125,"paper":126,"created_at":138},4748,"Study of Territories Using Geoinformatics and Remote Sensing Technologies: Spectral Band Combinations Based on Sentinel-2 Data (A Case Study of Parkent District)","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23297593","This scientific paper analyzes the combination of spectral bands based on data from the European Space Agency's (ESA) Sentinel-2 satellite, using geoinformatics and remote sensing technologies. The Parkent district of the Tashkent region, Republic of Uzbekistan, was selected as the object of study. The research primarily compares the characteristics of the NIR-RED-GREEN (Near-Infrared, Red, Green) and SWIR-NIR-GREEN (Shortwave Infrared, Near-Infrared, Green) band combinations, as well as their advantages in identifying agricultural lands, forest cover, and assessing moisture levels.","本文基于欧洲空间局（ESA）Sentinel-2卫星数据，运用地理信息学与遥感技术，对光谱波段组合进行了分析。研究选取乌兹别克斯坦共和国塔什干州帕尔肯特区作为研究对象。研究主要比较了近红外-红-绿（NIR-RED-GREEN）与短波红外-近红外-绿（SWIR-NIR-GREEN）波段组合的特征，以及二者在识别农业用地、森林覆盖和评估湿度水平方面的优势。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-11T00:00:00Z",62,{"impact":21,"substance":17,"depth":20,"authority":46,"freshness":97,"relevant":22,"comment":98},9,"基于Sentinel-2多光谱波段组合的遥感应用研究，方法具体、数据来源权威，但研究对象为乌兹别克斯坦地方区域，对国内三农信息化的直接参考价值有限。",[100],{"name":93,"url":90},[102,27,28,103,104],"农业遥感","乌兹别克斯坦","光谱波段",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":108},{"candidates":109,"agricultural_evidence":47},[110,115],{"code":33,"score":111,"supported":47,"title":112,"abstract":113,"tags":114},17,[50],[28,50],[27,102,28],{"code":116,"score":55,"supported":47,"title":117,"abstract":118,"tags":120},"I4",[],[119],"地理信息",[],[122,123],"Sentinel-2 光谱波段 组合","Parkent 遥感 农业用地","Sentinel-2光谱波段组合-4748","10.5281\u002Fzenodo.23297593",{"doi":125,"openalex_id":127,"authors":128,"venue":93,"cited_by_count":74,"oa_url":90,"card":133,"direction":80,"ingested_from":82},"W7221467289",[129,131],{"name":130,"orcid":9},"Xalilov Doniyor",{"name":132,"orcid":9},"Allambergenova Venera",{"tldr":134,"method":135,"finding":136,"direction":80,"opportunity":137},"基于Sentinel-2数据比较NIR-RED-GREEN与SWIR-NIR-GREEN波段组合，用","使用ESA Sentinel-2影像与地理信息学、遥感技术，对比两种光谱波段组合","NIR-RED-GREEN和SWIR-NIR-GREEN组合在识别农业用地、森林覆盖和评估湿度上各有","可进一步量化不同波段组合在干旱区作物分类与土壤湿度反演中的精度差异，并构建自动化优选流程。","2026-10-12T23:30:24.415736Z",{"id":140,"title":141,"url":142,"summary":143,"summary_zh":144,"content":9,"source_name":145,"source_url":142,"published_at":146,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":147,"score_detail":148,"sources":152,"tags":154,"primary_topic":158,"secondary_topics":159,"classification":160,"search_phrases":175,"slug":178,"view_count":74,"doi":179,"paper":180,"created_at":193},4583,"An Efficient Parcel-Center Sampling Strategy for Parcel-Scale Crop Classification Using Multiresolution Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18203463","Parcel-scale crop classification is fundamental to agricultural remote sensing and precision agriculture. The integration of detailed parcel information with medium-spatial-resolution remote sensing data has become an important technical approach to parcel-scale crop classification. For medium-spatial-resolution imagery, the mismatch between parcel boundaries and pixel size makes the parcel–pixel matching strategy a critical step in constructing parcel-level classification features. Existing full-pixels, pixel-center inclusion, and area-weighted strategies generally require identifying pixels associated with each parcel, determining spatial relationships, and performing statistical aggregation. When applied to thousands of parcels across multiple acquisition dates, repeated spatial overlay and multipixel aggregation can become a computational bottleneck in parcel-level feature construction. To address this issue, and assuming sufficient within-parcel feature consistency, a single pixel corresponding to an interior center point or a local window around that point is used to construct parcel-level classification features, thereby reducing the number of pixels involved in spatial matching and feature aggregation. Pringsewu Regency, Lampung Province, Indonesia, which has a highly fragmented parcel pattern, was selected as a case study. Sentinel-2, Landsat-8, Sentinel-1, and topographic data were integrated for parcel-scale crop classification. The results show that the parcel-center sampling strategy substantially reduced the cost of parcel-level feature construction under both the Sentinel-2 and Landsat-8 configurations. Compared with the three multipixel strategies, under the experimental conditions of this study, PCS achieved speedups of approximately 5.2–13.3-fold under Sentinel-2 and 7.3–17.1-fold under Landsat-8. Relative to the full-pixels strategy, OA increased by 0.55 percentage points under the Sentinel-2 configuration and decreased by 1.30 percentage points under the Landsat-8 configuration. Across parcel scales, the parcel-center sampling strategy generally maintained classification performance similar to that of the conventional multipixel strategies, and the resulting spatial patterns of the major crops were broadly consistent. Using a parcel-center pixel or local window can therefore retain sufficient classification information while substantially reducing the cost of parcel-level feature construction. This approach provides a simplified solution for efficient parcel-scale crop classification mapping in fragmented agricultural landscapes using medium-resolution imagery.","地块尺度作物分类是农业遥感和精准农业的基础。将详细的地块信息与中空间分辨率遥感数据相结合，已成为地块尺度作物分类的重要技术途径。对于中空间分辨率影像而言，地块边界与像元大小之间的不匹配使得地块—像元匹配策略成为构建地块级分类特征的关键步骤。现有的全像元策略、像元中心包含策略和面积加权策略通常需要识别与每个地块相关的像元、确定空间关系并进行统计聚合。当应用于多个获取日期下的数千个地块时，重复的空间叠加和多像元聚合可能成为地块级特征构建中的计算瓶颈。为解决这一问题，在假设地块内部特征具有足够一致性的前提下，采用与内部中心点相对应的单个像元或该点周围的局部窗口来构建地块级分类特征，从而减少参与空间匹配和特征聚合的像元数量。选取地块格局高度破碎的印度尼西亚楠榜省普林塞乌县作为案例研究区，集成Sentinel-2、Landsat-8、Sentinel-1和地形数据用于地块尺度作物分类。结果表明，在Sentinel-2和Landsat-8两种配置下，地块中心采样策略均大幅降低了地块级特征构建的成本。与三种多像元策略相比，在本研究的实验条件下，PCS在Sentinel-2下实现了约5.2至13.3倍的加速，在Landsat-8下实现了约7.3至17.1倍的加速。相对于全像元策略，总体精度（OA）在Sentinel-2配置下提高了0.55个百分点，在Landsat-8配置下降低了1.30个百分点。在不同地块尺度下，地块中心采样策略总体上保持了与传统多像元策略相似的分类性能，且主要作物的空间格局基本一致。因此，使用地块中心像元或局部窗口能够在保留足够分类信息的同时，大幅降低地块级特征构建的成本。该方法提供了一种简化的解决方案","Remote Sensing","2026-10-09T00:00:00Z",71,{"impact":46,"substance":149,"depth":111,"authority":150,"freshness":21,"relevant":22,"comment":151},21,13,"提出地块中心采样策略，在破碎地块区大幅提速且精度基本持平，方法新颖、结论可靠，对农业遥感工程化有参考价值。",[153],{"name":145,"url":142},[155,27,28,156,157],"智慧农业","作物分类","地块尺度",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":161},{"candidates":162,"agricultural_evidence":47},[163,167],{"code":33,"score":111,"supported":47,"title":164,"abstract":165,"tags":166},[50],[28,50],[27,156,28],{"code":168,"score":169,"supported":47,"title":170,"abstract":171,"tags":174},"I1",7,[],[172,173],"精准农业","precision agriculture",[155],[176,177],"Sentinel-2 地块尺度 作物分类","Pringsewu 遥感 作物制图","Sentinel-2地块尺度作物分类-4583","10.3390\u002Frs18203463",{"doi":179,"openalex_id":181,"authors":182,"venue":145,"cited_by_count":74,"oa_url":142,"card":188,"direction":80,"ingested_from":82},"W7221068088",[183,186],{"name":184,"orcid":185},"Zhihua Wang","https:\u002F\u002Forcid.org\u002F0000-0002-6776-2910",{"name":187,"orcid":9},"Qin Yang",{"tldr":189,"method":190,"finding":191,"direction":80,"opportunity":192},"提出地块中心采样策略，用单像素或局部窗口构建地块级特征，大幅加速地块尺度作物分类。","以印尼Pringsewu为案例，融合Sentinel-2、Landsat-8、S","中心采样较全像素等策略提速5.2–17.1倍，精度基本相当，主要作物空间格局一致。","可探索中心采样在破碎地块、多时相与不同分辨率下的自适应窗口选择及精度-效率权衡机制。","2026-10-10T23:30:27.757031Z",{"id":195,"title":196,"url":197,"summary":198,"summary_zh":199,"content":9,"source_name":200,"source_url":197,"published_at":201,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":202,"score_detail":203,"sources":206,"tags":208,"primary_topic":211,"secondary_topics":212,"classification":213,"search_phrases":235,"slug":238,"view_count":239,"doi":240,"paper":241,"created_at":258},4497,"A SwiGLU enhanced ConvNeXt framework for multispectral Sentinel-2 land use and land cover classification","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-67985-x","Land use and land cover (LCLU) classification from multispectral satellite imagery is important for applications such as urban planning, environmental monitoring, agriculture, and disaster management. Existing deep learning based approaches have improved LCLU; however, most of them utilize only the red, green, and blue (RGB) bands of multispectral sentinel-2 imagery, thereby underutilizing the complementary spectral information available in the near-infrared (NIR), short-wave infrared (SWIR), and derived spectral indices such as normalized difference built-up Index (NDBI), Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI). In this work, we propose a convolutional neural network (CNN), SwigNeXT, based on a modified ConvNeXt architecture for the classification of multispectral Sentinel-2 imagery using spectral band combinations which are RGB, NIR–Red–Green, SWIR–NIR–Red, and derived index combination NDBI–NDVI–NDWI rather than using only the RGB. The SwigNeXT incorporates SwiGLU-based gated feature modulation to improve spectral spatial feature representation. The final classification is obtained by ensembling the predictions of the three spectral band combinations and the derived index combination. Experimental results show that the proposed ensemble framework achieved an overall accuracy of 99.19% with a Kappa coefficient ( \\(\\kappa \\) ) of 0.9909, outperforming conventional CNNs, transfer learning based CNNs and transformer based approaches. A gradient based SHapley Additive exPlanations framework was further integrated to analyse spatial and spectral feature contributions. The proposed framework was further validated on Sentinel-2 imagery from the Delhi–NCR region, to examine its applicability under geographically distinct real world imaging conditions.","多光谱卫星影像的土地利用与土地覆盖（LCLU）分类对城市规划、环境监测、农业和灾害管理等应用具有重要意义。现有的基于深度学习的方法改进了LCLU分类；然而，大多数方法仅利用多光谱Sentinel-2影像的红、绿、蓝（RGB）波段，从而未能充分利用近红外（NIR）、短波红外（SWIR）以及归一化差异建成区指数（NDBI）、归一化差异植被指数（NDVI）和归一化差异水体指数（NDWI）等衍生光谱指数中可用的互补光谱信息。在本研究中，我们提出了一种基于改进ConvNeXt架构的卷积神经网络（CNN）——SwigNeXT，用于多光谱Sentinel-2影像分类，采用RGB、NIR–Red–Green、SWIR–NIR–Red等光谱波段组合以及NDBI–NDVI–NDWI衍生指数组合，而非仅使用RGB。SwigNeXT引入了基于SwiGLU的门控特征调制，以改进光谱空间特征表示。最终分类通过集成三种光谱波段组合和衍生指数组合的预测结果获得。实验结果表明，所提出的集成框架达到了99.19%的总体精度，Kappa系数（\\(\\kappa\\)）为0.9909，优于传统CNN、基于迁移学习的CNN以及基于Transformer的方法。进一步集成了基于梯度的SHapley加性解释框架，以分析空间和光谱特征贡献。所提出的框架在德里–NCR地区的Sentinel-2影像上进一步验证，以检验其在地理上不同的真实成像条件下的适用性。","Scientific Reports","2026-10-07T00:00:00Z",81,{"impact":17,"substance":18,"depth":17,"authority":204,"freshness":97,"relevant":22,"comment":205},14,"提出融合SwiGLU门控与多光谱波段组合的ConvNeXt集成框架，在Sentinel-2土地利用分类上达99.19%精度，方法新颖且对农业遥感监测有实用价值。",[207],{"name":200,"url":197},[155,209,28,29,210],"农业人工智能","土地利用",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":214},{"candidates":215,"agricultural_evidence":47},[216,220,226,231],{"code":33,"score":150,"supported":47,"title":217,"abstract":218,"tags":219},[51],[51],[29,28],{"code":54,"score":169,"supported":47,"title":221,"abstract":222,"tags":225},[],[223,224],"深度学习","deep learning",[209],{"code":227,"score":22,"supported":14,"title":228,"abstract":229,"tags":230},"H6",[],[],[210],{"code":168,"score":22,"supported":14,"title":232,"abstract":233,"tags":234},[],[],[155],[236,237],"Sentinel-2 多光谱 土地覆盖分类","ConvNeXt SwiGLU 遥感分类","Sentinel-2多光谱土地覆盖分类-4497",2,"10.1038\u002Fs41598-026-67985-x",{"doi":240,"openalex_id":242,"authors":243,"venue":200,"cited_by_count":74,"oa_url":251,"card":252,"direction":257,"ingested_from":82},"W7220869344",[244,246,248],{"name":245,"orcid":9},"Neeraj Kumar",{"name":247,"orcid":9},"Navin Rajpal",{"name":249,"orcid":250},"Pramod Kumar Soni","https:\u002F\u002Forcid.org\u002F0000-0003-0632-5044","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-67985-x_reference.pdf",{"tldr":253,"method":254,"finding":255,"direction":80,"opportunity":256},"提出SwiGLU增强的ConvNeXt框架，融合多光谱波段与指数集成分类Sentinel-2土地利用","改进ConvNeXt加SwiGLU门控，用RGB、NIR、SWIR及NDVI\u002FN","集成框架总体精度99.19%、Kappa 0.9909，优于CNN、迁移学习和Transformer","可探索多光谱指数组合与门控机制在作物精细分类及跨区域迁移中的泛化能力。","智慧农业 \u002F 农业物联网","2026-10-09T23:30:12.234854Z",{"id":260,"title":261,"url":262,"summary":263,"summary_zh":264,"content":9,"source_name":265,"source_url":262,"published_at":266,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":267,"score_detail":268,"sources":271,"tags":273,"primary_topic":276,"secondary_topics":277,"classification":284,"search_phrases":300,"slug":303,"view_count":239,"doi":304,"paper":305,"created_at":319},4365,"An Index-Based Algorithm for Detecting Water Soil Erosion Indicators from Sentinel-2 Multispectral Data and Its Verification on Field Data of Rostov Oblast and Krasnodar Krai","https:\u002F\u002Fdoi.org\u002F10.23947\u002F2587-8999-2026-10-3-49-57","Introduction . The paper presents the development and testing of an index-based algorithm for detecting indicators of soil erosion by water from Sentinel-2 remote sensing data, considered as the first practical stage in constructing a hybrid physics-based mass-transport model with neural-network parameter identification. Materials and Methods . The algorithm relies on joint analysis of time series of the Normalized Difference Vegetation Index (NDVI) and the Bare Soil Index (BSI), followed by spatial change detection (ΔBSI) with threshold filtering at the 90th percentile. The algorithm was first validated on synthetic data and then applied to real Sentinel-2 imagery for two test sites – the Kamensky District of Rostov Oblast and the vicinity of Moldovanskoye village, Krymsky District, Krasnodar Krai – covering 10 dates within 2024. Results. The algorithm is shown to consistently identify spatially localised zones of increasing bare-soil exposure. Discussion . A key limitation – the inability to distinguish erosion-related exposure from ordinary agrotechnical bare soil — is discussed, along with directions for resolving it (digital elevation model overlay, multi-year analysis). Conclusion . An index-based algorithm for detecting indicators of water-induced soil erosion from Sentinel-2 multispectral time series was developed and validated. Verification on synthetic data and application to two real test areas in southern Russia confirmed its operability while demonstrating the need to separate erosion-related changes from agricultural soil exposure in subsequent model development.","引言。本文介绍了一种基于指数的算法开发与测试，该算法用于从Sentinel-2遥感数据中检测水蚀土壤侵蚀指标，被视为构建基于物理的质量输运混合模型并结合神经网络参数辨识的第一个实践阶段。材料与方法。该算法依赖于对归一化植被指数（NDVI）和裸土指数（BSI）时间序列的联合分析，随后进行空间变化检测（ΔBSI），并在第90百分位数处进行阈值滤波。该算法首先在合成数据上进行了验证，然后应用于两个测试点的真实Sentinel-2影像——罗斯托夫州卡缅斯基区和克拉斯诺达尔边疆区克里姆斯克区摩尔多瓦诺夫斯科耶村附近——覆盖2024年内的10个日期。结果。结果表明，该算法能够一致地识别出裸土暴露增加的空间局部区域。讨论。讨论了关键局限性——无法区分与侵蚀相关的裸土暴露和普通农技作业造成的裸土——以及解决该问题的方向（叠加数字高程模型、多年分析）。结论。开发并验证了一种基于指数的算法，用于从Sentinel-2多光谱时间序列中检测水蚀土壤侵蚀指标。在合成数据上的验证以及在俄罗斯南部两个真实测试区域的应用证实了其可操作性，同时表明在后续模型开发中有必要将与侵蚀相关的变化与农业裸土暴露区分开来。","COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES","2026-10-05T00:00:00Z",70,{"impact":46,"substance":269,"depth":111,"authority":150,"freshness":21,"relevant":22,"comment":270},20,"提出基于NDVI与BSI时序的土壤水蚀指标遥感识别算法，并在俄罗斯南部两个试验区验证，方法有新意但属区域尺度研究，对国内农业遥感监测有参考价值。",[272],{"name":265,"url":262},[155,27,29,274,275],"遥感监测","土壤侵蚀",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[278],{"code":279,"slug":280,"name":281,"path":282,"parent_code":283},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":40,"locked":14,"version":41,"method":42,"evidence":285},{"candidates":286,"agricultural_evidence":47},[287,291,296],{"code":33,"score":269,"supported":47,"title":288,"abstract":289,"tags":290},[51],[28,50,51],[29,27,274],{"code":279,"score":204,"supported":47,"title":292,"abstract":293,"tags":295},[280],[294,280],"土壤",[],{"code":168,"score":22,"supported":14,"title":297,"abstract":298,"tags":299},[],[],[155],[301,302],"Sentinel-2 土壤侵蚀 遥感","罗斯托夫州 克拉斯诺达尔 土壤侵蚀","Sentinel-2土壤侵蚀遥感-4365","10.23947\u002F2587-8999-2026-10-3-49-57",{"doi":304,"openalex_id":306,"authors":307,"venue":265,"cited_by_count":74,"oa_url":262,"card":314,"direction":80,"ingested_from":82},"W7220651513",[308,311],{"name":309,"orcid":310},"V. A. Blagin","https:\u002F\u002Forcid.org\u002F0009-0003-3239-6150",{"name":312,"orcid":313},"V. A. Beraia","https:\u002F\u002Forcid.org\u002F0009-0006-2270-5011",{"tldr":315,"method":316,"finding":317,"direction":80,"opportunity":318},"开发基于Sentinel-2时序NDVI与BSI指数的水土流失指标检测算法，并在俄罗斯南部实地验证。","联合NDVI与BSI时序，用ΔBSI阈值（90百分位）检测裸土变化，合成与真实数","算法能稳定识别裸土暴露增加区域，但无法区分侵蚀与农事裸土，需DEM和多年度分析。","可融合DEM与多年度时序，构建区分侵蚀与农事裸土的分类模型，并接入神经网络参数识别。","2026-10-07T23:30:29.080156Z",{"id":321,"title":322,"url":323,"summary":324,"summary_zh":325,"content":9,"source_name":326,"source_url":323,"published_at":327,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":328,"score_detail":329,"sources":332,"tags":334,"primary_topic":337,"secondary_topics":338,"classification":339,"search_phrases":365,"slug":368,"view_count":369,"doi":370,"paper":371,"created_at":394},4025,"Remote estimation of plastic distribution in California agriculture using Sentinel-2 imagery: a case study","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1927646","Global application of agricultural plastic mulch is increasing. While these films offer benefits for crop production, they also are a large source of plastic waste and pollution in both terrestrial and aquatic systems. The current scale of global mulch application and its deleterious impacts are unclear. Current estimates of agricultural plastic use remain limited by field-specific growing patterns and data limitations. Satellite spectroscopy may offer a means to reduce this uncertainty and model agricultural plastic use on large spatial and temporal scales, though temporally variable crop canopy growth and spectrally diverse plastic targets complicate this approach. To build toward improved plasticulture estimates, this study presents an interpretable, spectral-based classification of bulk plastic use in a California agricultural site using Sentinel-2 imagery. In situ reflectance measurements of soil and white, green, and black plastic mulch endmembers were collected using a Spectra Vista Corporation HR-1024i Spectroradiometer from 350–2500 nm. A combination of field observations and high spatial resolution NearMap imagery (n = 416 spectra) were compiled and divided into 60% training and 40% testing data using a stratified sampling approach. Informed by field reflectance data, mixture analyses, and Sentinel-2 reflectance imagery, an empirical decision tree classification was parameterized to classify dark and bright plastic debris from soil and crop (accuracy = 0.982, kappa coefficient = 0.973, macro-averaged F1-score = 0.967). Modeled agricultural plastic distributions were then retrieved through a time series of Sentinel-2 imagery over Santa Maria, CA, from April 2023 to January 2025, elucidating patterns in plastic application and crop canopy growth without the need for prior knowledge of field growing and management patterns. These results are encouraging for the utility of optical remote sensing in modeling plastic use patterns and identifying contamination hotspots throughout California and, potentially, similarly mulched agroecological systems.","全球农业塑料地膜的应用日益增加。尽管这些薄膜为作物生产带来了益处，但它们同时也是陆地和水生系统中塑料废弃物和污染的重要来源。目前全球地膜应用的规模及其有害影响尚不明确。当前对农业塑料使用量的估算仍受限于特定田块的种植模式和数据局限性。卫星光谱学可能为减少这种不确定性并在大时空尺度上模拟农业塑料使用提供一种手段，尽管作物冠层的时序变化和光谱多样的塑料目标使这一方法变得复杂。为推进对塑料农业（plasticulture）估算的改进，本研究利用Sentinel-2影像，对加利福尼亚州一个农业站点的大宗塑料使用进行了可解释的、基于光谱的分类。使用Spectra Vista Corporation HR-1024i光谱辐射仪在350–2500 nm范围内采集了土壤以及白色、绿色和黑色塑料地膜端元的原位反射率测量数据。结合野外观测和高空间分辨率NearMap影像（n = 416条光谱），采用分层抽样方法将数据分为60%训练集和40%测试集。在野外反射率数据、混合分析及Sentinel-2反射率影像的指导下，参数化了一棵经验决策树分类器，以从土壤和作物中分类暗色和亮色塑料残膜（精度 = 0.982，kappa系数 = 0.973，宏平均F1分数 = 0.967）。随后通过2023年4月至2025年1月期间覆盖加利福尼亚州圣玛丽亚的Sentinel-2影像时间序列，反演了模拟的农业塑料分布，阐明了塑料施用和作物冠层生长的模式，而无需事先了解田块种植和管理模式。这些结果令人鼓舞，表明光学遥感在模拟加利福尼亚州乃至其他类似覆膜农业生态系统的塑料使用模式和识别污染热点方面具有实用价值。","Frontiers in Remote Sensing","2026-10-01T00:00:00Z",78,{"impact":330,"substance":18,"depth":17,"authority":150,"freshness":97,"relevant":22,"comment":331},16,"该研究利用Sentinel-2影像实现农膜分布遥感估算，方法新颖、精度高，对农业面源污染监测有参考价值，但属区域案例，影响范围有限。",[333],{"name":326,"url":323},[155,27,28,335,336],"农膜污染","加州农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":340},{"candidates":341,"agricultural_evidence":47},[342,346,350,355,361],{"code":33,"score":21,"supported":47,"title":343,"abstract":344,"tags":345},[],[28,50],[27,28],{"code":279,"score":85,"supported":47,"title":347,"abstract":348,"tags":349},[],[294,280],[],{"code":227,"score":55,"supported":47,"title":351,"abstract":352,"tags":354},[],[353],"农业生态",[],{"code":356,"score":55,"supported":47,"title":357,"abstract":358,"tags":360},"J3",[],[359],"全球农业",[],{"code":168,"score":22,"supported":14,"title":362,"abstract":363,"tags":364},[],[],[155],[366,367],"Sentinel-2 农膜 遥感","加州 农业塑料 遥感监测","Sentinel-2农膜遥感-4025",4,"10.3389\u002Ffrsen.2026.1927646",{"doi":370,"openalex_id":372,"authors":373,"venue":326,"cited_by_count":74,"oa_url":323,"card":389,"direction":80,"ingested_from":82},"W7215027304",[374,376,378,381,383,386],{"name":375,"orcid":9},"Eva Scrivner",{"name":377,"orcid":9},"Dexter Hamilton",{"name":379,"orcid":380},"Daniel J. Sousa","https:\u002F\u002Forcid.org\u002F0000-0002-1632-1955",{"name":382,"orcid":9},"Margot Mattson",{"name":384,"orcid":385},"Nicholas E. Williams","https:\u002F\u002Forcid.org\u002F0000-0003-4013-9296",{"name":387,"orcid":388},"Seeta A. Sistla","https:\u002F\u002Forcid.org\u002F0000-0002-6345-462X",{"tldr":390,"method":391,"finding":392,"direction":80,"opportunity":393},"利用Sentinel-2影像和实地光谱，分类并制图加州农业塑料覆盖分布。","Sentinel-2影像、实地光谱与决策树分类，结合高分辨率影像验证。","决策树分类精度达0.982，可无需先验知识反演塑料覆盖时空格局。","可扩展至全球地膜污染热点监测，并融合多源遥感提升复杂作物区塑料识别。","2026-10-02T23:30:24.457168Z",{"id":396,"title":397,"url":398,"summary":399,"summary_zh":400,"content":9,"source_name":401,"source_url":398,"published_at":402,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":403,"score_detail":404,"sources":406,"tags":408,"primary_topic":411,"secondary_topics":417,"classification":419,"search_phrases":436,"slug":439,"view_count":55,"doi":440,"paper":441,"created_at":451},3838,"Forecasting Cotton Productivity in the Mil-Mugan Economic Region using Climate Variables and Remote Sensing Data","https:\u002F\u002Fdoi.org\u002F10.52171\u002Fherald.342","Satellite imagery is considered as one of the most valuable and functional data sources for evaluating and forecasting production in agricultural systems. This study aims to forecast productivity in cotton fields within the Mil-Mugan economic region by incorporating vegetation indices and climatic variables. NDVI indicators were derived from Sentinel-2 data, temperature (T) was obtained from ERA5-Land data, and precipitation (R) was collected from the CHIRPS database. The data were analyzed using Google Earth Engine, ArcGIS Pro, and Python environments, consolidating them into an integrated temporal-spatial dimension. The correlation and regression analysis assessed the link among NDVI, temperature, precipitation, and productivity, leading to the development of a multivariate model. The findings derived from the model indicate that NDVI is the primary factor influencing productivity. The model developed for one region was implemented in the other three locations, and the correlation between the actual and predicted indicators was assessed using R² and RMSE metrics. The results indicate that the model's forecast accuracy fluctuates within the 90% range, considered appropriate for predicting regional cotton yield. The study's findings are significant for enhancing operational monitoring and planning of agrotechnical decisions with satellite data.","卫星影像被认为是评估和预测农业系统产量最有价值且最实用的数据来源之一。本研究旨在通过整合植被指数与气候变量，预测米尔-穆甘经济区棉田的生产力。NDVI指标源自Sentinel-2数据，温度（T）取自ERA5-Land数据，降水（R）来自CHIRPS数据库。数据在Google Earth Engine、ArcGIS Pro和Python环境中进行分析，并将其整合为统一的时空维度。通过相关性与回归分析评估了NDVI、温度、降水与生产力之间的关系，进而构建了多变量模型。模型结果表明，NDVI是影响生产力的主要因素。将为某一区域开发的模型应用于其他三个地点，并使用R²和RMSE指标评估实际值与预测值之间的相关性。结果表明，模型的预测精度在90%范围内波动，被认为适用于预测区域棉花产量。本研究结果对于利用卫星数据加强农艺决策的业务化监测与规划具有重要意义。","Herald of the Azerbaijan Engineering Academy","2026-09-29T00:00:00Z",63,{"impact":21,"substance":269,"depth":330,"authority":13,"freshness":97,"relevant":22,"comment":405},"基于Sentinel-2与气候变量的棉花产量预测模型，方法扎实、精度达90%，但属区域案例研究，公共影响有限。",[407],{"name":401,"url":398},[155,409,410,28,29],"产量预测","棉花",{"code":412,"slug":413,"name":414,"path":415,"parent_code":416},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[418],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":420},{"candidates":421,"agricultural_evidence":47},[422,427,432],{"code":412,"score":20,"supported":47,"title":423,"abstract":425,"tags":426},[424],"cotton",[410,424],[410],{"code":33,"score":428,"supported":47,"title":429,"abstract":430,"tags":431},11,[50],[],[29,409,28],{"code":168,"score":22,"supported":14,"title":433,"abstract":434,"tags":435},[],[],[155],[437,438],"Mil-Mugan 棉花 遥感","Sentinel-2 NDVI 棉花产量","Mil-Mugan棉花遥感-3838","10.52171\u002Fherald.342",{"doi":440,"openalex_id":442,"authors":443,"venue":401,"cited_by_count":74,"oa_url":398,"card":446,"direction":80,"ingested_from":82},"W7214748696",[444],{"name":445,"orcid":9},"B.H. Babashli",{"tldr":447,"method":448,"finding":449,"direction":80,"opportunity":450},"结合Sentinel-2 NDVI与气候变量，构建多元模型预测米尔-穆甘地区棉花产量。","Sentinel-2 NDVI、ERA5-Land温度、CHIRPS降水，GEE","NDVI是产量主控因子，模型跨区预测精度约90%，可用于区域估产。","可引入多时相NDVI与机器学习，提升跨区域迁移性和极端气候下的估产鲁棒性。","2026-09-30T23:30:27.786044Z"]