[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4599":3,"related-4599":102},{"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":74,"slug":77,"view_count":22,"doi":78,"paper":79,"created_at":101},4599,"Reducing redundancy in multi-temporal analysis to improve field-scale detection of crop residue burning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rsase.2026.102310","Accurate field-scale mapping of paddy stubble burning is essential for reliable emission estimation and effective policy intervention. However, current remote sensing approaches often suffer from significant inaccuracies due to the repeated detection of the same field-scale across multi-temporal observations. This leads to systematic overestimation of field-scale and remains insufficiently addressed in existing studies. This study addresses the challenge using multi-temporal remote sensing data and a fuzzy machine-learning technique using the ‘Individual Sample as Mean (ISM)’ training approach. The study was implemented in the Nanakmatta area of Udham Singh Nagar District, Uttarakhand, India. PlanetScope satellite imagery, covering both harvesting and burnt-stubble conditions, was utilised to reduce redundancy. A Modified Possibilistic c -Means (MPCM) classifier, integrated with the ISM approach, was employed to map stubble burning across 13 observation dates during October-November 2025. Peak burning activity was recorded around 23 October 2025, followed by a gradual decline, with no detectable burning on 16 November 2025. The combination of MPCM and ISM effectively minimises inflated estimates of burning events caused by repeated detections of the same burnt areas. Specifically, the ISM training approach handles variability in burning patterns caused by partial combustion, residue mixing, and delayed field preparation. It accounts for class diversity rather than forcing all instances into a single generalised representation. Accuracy assessment using both Mean Membership Difference (MMD) and conventional classification metrics demonstrated the robustness of the proposed framework. A within-class MMD of 0 and a between-class MMD of 0.66 indicated strong class separability, with precision, recall, and F1-score values of 0.775, 0.688, and 0.729, respectively. The proposed framework provides a more reliable and quantitatively validated approach for addressing temporal redundancy and monitoring residue-burning practices across diverse agricultural environments.","准确的田块尺度水稻秸秆焚烧制图对于可靠的排放估算和有效的政策干预至关重要。然而，当前遥感方法常因在多时相观测中重复检测同一田块尺度而导致显著不准确，造成田块尺度的系统性高估，现有研究对此仍未充分解决。本研究利用多时相遥感数据和模糊机器学习技术，采用“个体样本作为均值”（Individual Sample as Mean, ISM）训练方法应对这一挑战。研究在印度北阿坎德邦乌达姆·辛格·纳加尔县的纳纳克马塔地区实施。利用覆盖收割和焚烧后秸秆状况的PlanetScope卫星影像以减少冗余。采用改进的可能性c均值（Modified Possibilistic c-Means, MPCM）分类器，结合ISM方法，对2025年10月至11月期间的13个观测日期进行秸秆焚烧制图。焚烧活动高峰出现在2025年10月23日前后，随后逐渐下降，至2025年11月16日未检测到焚烧。MPCM与ISM的结合有效减少了因重复检测同一焚烧区域而导致的焚烧事件高估。具体而言，ISM训练方法能够处理由不完全燃烧、残茬混合和田间准备延迟引起的焚烧模式变异性，它考虑了类别多样性，而非将所有实例强制归入单一泛化表示。使用平均隶属度差异（Mean Membership Difference, MMD）和传统分类指标进行精度评估，证明了所提框架的稳健性。类内MMD为0，类间MMD为0.66，表明类别可分性强，精确率、召回率和F1分数分别为0.775、0.688和0.729。所提框架为解决时间冗余和监测多样化农业环境中的残茬焚烧行为提供了一种更可靠且经定量验证的方法。",null,"Remote Sensing Applications Society and Environment","2026-10-08T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,21,18,13,9,1,"方法新颖、数据扎实的遥感论文，对秸秆焚烧监测与排放估算有参考价值，但属细分领域技术进展，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","农业面源污染","作物识别","遥感监测","秸秆焚烧",{"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},[45,53,61,68],{"code":33,"score":46,"supported":47,"title":48,"abstract":49,"tags":52},7,true,[],[50,51],"遥感","remote sensing",[30],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":60},"A1",6,[],[58,59],"水稻","paddy",[],{"code":62,"score":63,"supported":47,"title":64,"abstract":65,"tags":67},"I2",4,[],[66],"机器学习",[27],{"code":69,"score":70,"supported":14,"title":71,"abstract":72,"tags":73},"H5",2,[],[],[28,31],[75,76],"PlanetScope 秸秆焚烧 遥感","Uttarakhand 稻田 秸秆焚烧","PlanetScope秸秆焚烧遥感-4599","10.1016\u002Fj.rsase.2026.102310",{"doi":78,"openalex_id":80,"authors":81,"venue":10,"cited_by_count":93,"oa_url":6,"card":94,"direction":98,"ingested_from":100},"W7221040421",[82,85,88,91],{"name":83,"orcid":84},"Anil Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-7177-0817",{"name":86,"orcid":87},"Anamika Palavesam Sarathamani","https:\u002F\u002Forcid.org\u002F0009-0007-4223-7443",{"name":89,"orcid":90},"Ishwari Datt","https:\u002F\u002Forcid.org\u002F0000-0001-9936-2367",{"name":92,"orcid":9},"R.P. Singh",0,{"tldr":95,"method":96,"finding":97,"direction":98,"opportunity":99},"用多时相遥感与模糊机器学习减少重复检测，提升稻田秸秆焚烧田块尺度制图精度。","PlanetScope多时相影像，MPCM分类器结合ISM训练，13期观测。","MPCM+ISM有效抑制重复检测导致的焚烧面积高估，F1达0.729。","农业遥感与作物表型","可将去冗余框架迁移至其他作物残茬焚烧监测，并融合Sentinel-2提升时空覆盖。","openalex","2026-10-10T23:30:31.208858Z",{"total":55,"page":22,"page_size":55,"items":103},[104,176,240,321,390,440],{"id":105,"title":106,"url":107,"summary":108,"summary_zh":109,"content":9,"source_name":110,"source_url":107,"published_at":111,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":112,"score_detail":113,"sources":118,"tags":120,"primary_topic":124,"secondary_topics":125,"classification":126,"search_phrases":138,"slug":141,"view_count":93,"doi":142,"paper":143,"created_at":175},5318,"Lagged Effects and Mechanisms of Central Environmental Inspection Policies on Agricultural Straw Burning: Evidence from Remote Sensing Data in China","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10668-026-08214-3","Lagged Effects and Mechanisms of Central Environmental Inspection Policies on Agricultural Straw Burning: Evidence from Remote Sensing Data in China。Environment Development and Sustainability","中央环保督察政策对农业秸秆焚烧的滞后效应与作用机制：来自中国遥感数据的证据。《环境、发展与可持续性》","Environment Development and Sustainability","2026-10-19T00:00:00Z",84,{"impact":114,"substance":115,"depth":19,"authority":116,"freshness":13,"relevant":22,"comment":117},22,20,14,"基于全国遥感数据评估中央环保督察对秸秆焚烧的滞后效应，数据规模大、方法新颖，对农业环境政策有参考价值，值得进入每日精选。",[119],{"name":110,"url":107},[121,30,122,31,123],"农业政策","卫星遥感","环保督察",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":127},{"candidates":128,"agricultural_evidence":47},[129,134],{"code":33,"score":130,"supported":47,"title":131,"abstract":132,"tags":133},16,[51],[50,51],[122,30],{"code":69,"score":22,"supported":14,"title":135,"abstract":136,"tags":137},[],[],[31],[139,140],"中央环保督察 秸秆焚烧","遥感数据 秸秆焚烧","中央环保督察秸秆焚烧-5318","10.1007\u002Fs10668-026-08214-3",{"doi":142,"openalex_id":144,"authors":145,"venue":110,"cited_by_count":93,"oa_url":9,"card":169,"direction":98,"ingested_from":100},"W7222877438",[146,148,150,152,154,156,158,161,163,165,167],{"name":147,"orcid":9},"Lu Dong",{"name":149,"orcid":9},"Linru Zhang",{"name":151,"orcid":9},"Na Liu",{"name":153,"orcid":9},"Xin Long",{"name":155,"orcid":9},"Ziyi Wang",{"name":157,"orcid":9},"Siyue Yang",{"name":159,"orcid":160},"Jie Tian","https:\u002F\u002Forcid.org\u002F0000-0001-6585-3643",{"name":162,"orcid":9},"Qiyuan Wang",{"name":164,"orcid":9},"Zhanfeng Dong",{"name":166,"orcid":9},"Long Wu",{"name":168,"orcid":9},"Yichen Wang",{"tldr":170,"method":171,"finding":172,"direction":173,"opportunity":174},"利用遥感数据评估中央环保督察政策对秸秆焚烧的滞后效应与作用机制。","基于中国遥感火点数据构建面板，采用滞后效应模型识别政策影响机制。","中央环保督察对秸秆焚烧具有显著但滞后的抑制效应，并存在区域异质性。","农业绿色发展与碳","可结合地块级遥感与农户调查，量化督察滞后期内秸秆离田利用与替代处置的路径。","2026-10-19T23:30:22.693590Z",{"id":177,"title":178,"url":179,"summary":180,"summary_zh":181,"content":9,"source_name":182,"source_url":179,"published_at":183,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":184,"score_detail":185,"sources":187,"tags":189,"primary_topic":193,"secondary_topics":197,"classification":199,"search_phrases":214,"slug":217,"view_count":93,"doi":218,"paper":219,"created_at":239},4897,"Wild boar collision data and satellite computer vision refine habitat suitability mapping across France","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10344-026-02160-1","Abstract Wild boar (Sus scrofa) populations have expanded rapidly across Europe, leading to escalating human-wildlife conflicts (HWCs), notably wildlife-vehicle collisions (WVCs), increased agricultural damage and disease transmission. In continental France these issues are compounded by the species’ ecological adaptability exhibiting increasing overlaps with urbanization and transportation networks. In this study, we leverage time-series environmental data, computer vision and Species Distribution Modeling (SDM) to predict wild boar habitat suitability and investigate its spatiotemporal drivers. We use presence-only data from WVC reports on the national railway and road networks, along with publicly available GBIF observation collections, as complementary occurrence streams in our SDMs, while addressing inherent sampling biases of these datasets with tailored corrections. A key innovation of this study is the integration of national scale, annually updated high-resolution land cover predictors explicitly focused on wild boar resource preference. By fine-tuning a multitemporal Vision Transformer foundational AI model on multispectral satellite remote sensing imagery we capture subtle seasonal phenological differences. Our results highlight clear spatial, seasonal and annual variations in wild boar habitat suitability. The multitemporal SDM pipeline yields meaningful predictions when extrapolating to novel environmental scenarios such as climate extremes. Adding rail and road WVC records to GBIF-based SDMs retained high performance metrics while altering predicted spatial patterns and feature importance distribution. The methodological and ecological insights gained through this study provide additional knowledge for French transportation planning, agriculture and wildlife management. Identifying regions with high seasonal habitat suitability can inform targeted interventions. More broadly, our results demonstrate that advanced, data-driven methods are becoming indispensable for proactively and sustainably addressing HWCs in an increasingly anthropogenic world.","摘要 野猪（Sus scrofa）种群在欧洲迅速扩张，导致人兽冲突（HWCs）不断升级，尤其是野生动物车辆碰撞（WVCs）、农业损害加剧和疾病传播。在法国大陆，该物种的生态适应性使其与城市化和交通网络的重叠日益增加，进一步加剧了这些问题。本研究利用时间序列环境数据、计算机视觉和物种分布模型（SDM）预测野猪栖息地适宜性，并探究其时空驱动因素。我们使用国家铁路和公路网络中WVC报告的存在-only数据，以及公开可用的GBIF观测集合，作为SDM中的互补出现数据流，同时通过针对性校正处理这些数据集固有的采样偏差。本研究的一个关键创新是整合了国家尺度、年度更新的高分辨率土地覆盖预测因子，明确聚焦于野猪的资源偏好。通过在多光谱卫星遥感影像上微调多时相视觉Transformer基础AI模型，我们捕捉到了细微的季节物候差异。我们的结果突出了野猪栖息地适宜性在空间、季节和年际上的明显变化。多时相SDM流程在推断至气候极端等新型环境情景时产生了有意义的预测。将铁路和公路WVC记录添加到基于GBIF的SDM中，在保持高性能指标的同时改变了预测的空间格局和特征重要性分布。本研究获得的方法学和生态学见解为法国交通规划、农业和野生动物管理提供了额外知识。识别具有高季节性栖息地适宜性的区域可为针对性干预提供依据。更广泛地说，我们的结果表明，在日益受到人类影响的世界中，先进的数据驱动方法正成为前瞻性和可持续地应对人兽冲突不可或缺的手段。","European Journal of Wildlife Research","2026-10-13T00:00:00Z",81,{"impact":19,"substance":114,"depth":19,"authority":116,"freshness":21,"relevant":22,"comment":186},"该研究将卫星遥感与计算机视觉用于野猪栖息地建模，方法新颖、数据规模大，对交通规划与农业野生动物管理有参考价值，但属法国区域研究，国内产业影响有限。",[188],{"name":182,"url":179},[27,30,190,191,192],"栖息地评估","野生动物管理","人兽冲突",{"code":62,"slug":194,"name":195,"path":196,"parent_code":37},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[198],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":200},{"candidates":201,"agricultural_evidence":47},[202,209],{"code":62,"score":203,"supported":47,"title":204,"abstract":206,"tags":208},15,[205],"computer vision",[207,205],"计算机视觉",[27],{"code":33,"score":13,"supported":47,"title":210,"abstract":211,"tags":213},[],[50,51,212],"multispectral",[30],[215,216],"法国 野猪 栖息地 遥感","野猪 车辆碰撞 卫星影像","法国野猪栖息地遥感-4897","10.1007\u002Fs10344-026-02160-1",{"doi":218,"openalex_id":220,"authors":221,"venue":182,"cited_by_count":93,"oa_url":179,"card":234,"direction":98,"ingested_from":100},"W7221702437",[222,225,227,230,232],{"name":223,"orcid":224},"Adrian Meyer","https:\u002F\u002Forcid.org\u002F0000-0002-8652-1477",{"name":226,"orcid":9},"Théo Reibel",{"name":228,"orcid":229},"Кevin Мorelle","https:\u002F\u002Forcid.org\u002F0000-0001-9041-6541",{"name":231,"orcid":9},"Mathias Kneubühler",{"name":233,"orcid":9},"Denis Jordan",{"tldr":235,"method":236,"finding":237,"direction":98,"opportunity":238},"融合野猪碰撞数据与卫星视觉模型，预测法国野猪栖息地适宜性及其时空驱动因素。","时间序列环境数据、Vision Transformer卫星影像、物种分布模型与G","栖息地适宜性呈明显时空变化，加入碰撞记录改变预测格局与特征重要性。","可将碰撞数据与遥感表型结合，拓展至其他野生动物-农业冲突的时空预警与决策。","2026-10-14T23:30:27.244673Z",{"id":241,"title":242,"url":243,"summary":244,"summary_zh":245,"content":9,"source_name":246,"source_url":243,"published_at":247,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":248,"score_detail":249,"sources":251,"tags":253,"primary_topic":257,"secondary_topics":263,"classification":266,"search_phrases":294,"slug":297,"view_count":22,"doi":298,"paper":299,"created_at":320},4808,"Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1898342","Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.","农业病害是种植者面临的重大问题，会对果实和叶片造成严重损害，导致产量损失。因此，开发植物病害早期检测系统是一个至关重要的问题。本研究提出了一种基于深度学习的新型混合模型，用于植物病害的检测与分割，具体针对苹果园中的苹果黑星病和葡萄园中的霜霉病。该早期病害检测系统的开发使用了2023年5月至2024年12月期间通过无人机在土耳其泰基尔达省农业区域采集的多光谱影像数据。数据集包含3625幅苹果园图像和5625幅葡萄园图像。所用DJI Phantom 4多光谱无人机配备五个光谱波段（蓝、绿、红、红边和近红外），用于捕捉光谱丰富度和时间变化过程。本研究提出了一种专门开发的深度学习架构，用于基于时间序列的多光谱无人机影像病害检测与分割。植物随时间的变化提供了关于植物病害发生的重要信息。因此，本研究使用时间序列从植物随时间的变化中提取特征。所提出的模型架构专门设计以利用时间序列信息，从而能够稳健地跟踪作物健康状况随时间的变化。使用苹果病害数据集训练的模型达到了82.05%的平均交并比（IoU）值，而使用葡萄园病害数据集训练的模型达到了79.67%的IoU值。研究结果凸显了将无人机获取的多光谱时间序列数据与先进深度学习模型相结合，在精准农业中实现可扩展、准确且及时的植物病害检测方面的有效性。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",77,{"impact":130,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":250},"该研究提出基于多光谱时序影像的新型深度学习模型，实现果园与葡萄园病害早期检测，数据规模大、方法新颖，对精准农业病害预警具有参考价值。",[252],{"name":246,"url":243},[254,255,27,30,256],"智慧农业","无人机","病害预警",{"code":258,"slug":259,"name":260,"path":261,"parent_code":262},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[264,265],{"code":62,"slug":194,"name":195,"path":196,"parent_code":37},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":267},{"candidates":268,"agricultural_evidence":47},[269,277,283,287],{"code":258,"score":270,"supported":47,"title":271,"abstract":273,"tags":276},17,[272],"apple",[274,275,272],"苹果","葡萄",[],{"code":62,"score":203,"supported":47,"title":278,"abstract":280,"tags":282},[279],"deep learning",[281,279],"深度学习",[27],{"code":33,"score":17,"supported":47,"title":284,"abstract":285,"tags":286},[212],[212],[30],{"code":288,"score":46,"supported":47,"title":289,"abstract":290,"tags":293},"I1",[],[291,292],"精准农业","precision agriculture",[254],[295,296],"苹果黑星病 无人机 多光谱","葡萄园 霜霉病 深度学习","苹果黑星病无人机多光谱-4808","10.15832\u002Fankutbd.1898342",{"doi":298,"openalex_id":300,"authors":301,"venue":246,"cited_by_count":93,"oa_url":313,"card":314,"direction":319,"ingested_from":100},"W7221558726",[302,305,308,310],{"name":303,"orcid":304},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":306,"orcid":307},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":309,"orcid":9},"Fatih Sinan Bir",{"name":311,"orcid":312},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":315,"method":316,"finding":317,"direction":98,"opportunity":318},"提出一种基于无人机多光谱时序影像的深度学习混合模型，实现苹果黑星病和葡萄霉病的早期检测与分割。","DJI Phantom 4多光谱无人机采集时序影像，构建时序深度学习分割模型。","苹果病IoU达82.05%，葡萄病达79.67%，验证多光谱时序数据有效性。","可探索多作物、多病害的时序多光谱通用模型，并融合气象与地面数据提升早期预警能力。","智慧农业 \u002F 农业物联网","2026-10-13T23:30:10.242467Z",{"id":322,"title":323,"url":324,"summary":325,"summary_zh":326,"content":9,"source_name":327,"source_url":324,"published_at":328,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":329,"score_detail":330,"sources":333,"tags":335,"primary_topic":338,"secondary_topics":339,"classification":341,"search_phrases":364,"slug":367,"view_count":368,"doi":369,"paper":370,"created_at":389},3550,"Asymmetric Vegetation Responses to Flood Exposure in the Chi River Basin: A Multi-Temporal Remote Sensing and Machine Learning Investigation","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsym18101606","Flooding and drought alternate in many tropical floodplains, but how vegetation responds to both hazards over multiple years remains poorly quantified. We examined vegetation–flood associations in the Chi River Basin, Northeast Thailand, drawing on Sentinel-2 imagery from 2020, 2023, and 2024, flood records from 2017, 2018, 2021, and 2022, and machine learning methods across 230,911 point-based spatial units. Nine forms of asymmetry emerged from the analysis. The most striking was recovery asymmetry: areas that flooded at least twice between 2017 and 2022 gained vegetation during 2020–2023 (mean NDVI change = +0.0270), whereas areas with little or no flood exposure lost vegetation (mean change = −0.0430). This gap was statistically significant (Cohen’s d = 0.5586, p \u003C 0.001) and suggests that repeated flooding may buffer vegetation against subsequent drought. Agricultural land declined less (−0.0316) than forest (−0.0937; ANOVA F = 1717.7, p \u003C 0.001). Baseline vegetation condition, measured as NDVI in 2020, contributed 32.9% to model importance, more than twice the contribution of elevation (14.5%). Spectral indices together accounted for 76.6% of importance, compared with 23.5% for topographic variables. The 2023 El Niño year produced the largest difference between high-flood and low-flood areas (+0.0364); because only one year per ENSO phase was available, we treat this as a case-based comparison rather than a general ENSO response. Threshold analysis identified two distinct values: an operational cut-off at NDVI = 0.05 (overall accuracy 82.67%) and an ecological transition around 0.25–0.30. Spatial clustering was weak but significant (Moran’s I = 0.2179, p \u003C 0.001). Spatial block cross-validation gave lower accuracy (0.597) than random cross-validation (0.627), pointing to spatial autocorrelation in the data. High-flood areas had 1.67 times the vulnerability index of low-flood areas (0.4306 vs. 0.2573). These patterns support differentiated management: elevation-based zoning, warning systems calibrated to local flood regimes, and focused interventions at hotspots.","在许多热带洪泛平原，洪水与干旱交替发生，但植被如何在多年间同时响应这两种灾害，仍缺乏充分的定量研究。我们以泰国东北部栖河（Chi River）流域为研究区，考察植被与洪水的关联，数据来源包括2020年、2023年和2024年的Sentinel-2影像，2017年、2018年、2021年和2022年的洪水记录，并采用机器学习方法，覆盖230 911个基于点的空间单元。分析中出现了九种不对称形式。其中最显著的是恢复不对称：2017—2022年间至少发生两次洪水的区域，在2020—2023年间植被增加（NDVI平均变化=+0.0270），而洪水暴露很少或没有洪水暴露的区域则植被减少（平均变化=−0.0430）。这一差异具有统计显著性（Cohen’s d=0.5586，p\u003C0.001），表明反复洪水可能缓冲植被对随后干旱的响应。农田的下降幅度（−0.0316）小于森林（−0.0937；ANOVA F=1717.7，p\u003C0.001）。以2020年NDVI衡量的基线植被状况对模型重要性的贡献为32.9%，是海拔贡献（14.5%）的两倍多。光谱指数合计占重要性的76.6%，而地形变量占23.5%。2023年厄尔尼诺年（El Niño year）高洪水区与低洪水区之间的差异最大（+0.0364）；由于每个ENSO相位仅有1年数据，我们将其视为基于个案的比较，而非一般性的ENSO响应。阈值分析识别出两个不同的值：操作性截断值为NDVI=0.05（总体精度82.67%），生态过渡值约为0.25~0.30。空间聚类较弱但显著（Moran’s I=0.2179，p\u003C0.001）。空间分块交叉验证的精度（0.597）低于随机交叉验证（0.627），表明数据中存在空间自相关。高洪水区的脆弱性指数是低洪水区的1.67倍（0.4306对0.2573）。这些格局支持差异化治理：基于海拔的分区、根据当地洪水情势校准的预警系统，以及在热点区域的重点干预。","Symmetry","2026-09-25T00:00:00Z",70,{"impact":331,"substance":114,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":332},8,"基于Sentinel-2与机器学习的多时相洪涝-植被响应研究，数据规模大、结论具体，对农业遥感与灾害风险管理有参考价值，但属区域案例研究，公共影响有限。",[334],{"name":327,"url":324},[254,27,30,336,337],"洪涝灾害","植被恢复",{"code":62,"slug":194,"name":195,"path":196,"parent_code":37},[340],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":342},{"candidates":343,"agricultural_evidence":47},[344,349,353,360],{"code":62,"score":203,"supported":47,"title":345,"abstract":347,"tags":348},[346],"machine learning",[66,346],[27],{"code":33,"score":13,"supported":47,"title":350,"abstract":351,"tags":352},[51],[],[337,30],{"code":354,"score":46,"supported":47,"title":355,"abstract":356,"tags":359},"H7",[],[357,358],"干旱","drought",[336],{"code":288,"score":22,"supported":14,"title":361,"abstract":362,"tags":363},[],[],[254],[365,366],"湄公河支流 流域 遥感 洪水","Sentinel-2 NDVI 洪涝 植被","湄公河支流流域遥感洪水-3550",3,"10.3390\u002Fsym18101606",{"doi":369,"openalex_id":371,"authors":372,"venue":327,"cited_by_count":93,"oa_url":324,"card":384,"direction":98,"ingested_from":100},"W7214283372",[373,375,378,381],{"name":374,"orcid":9},"Jiradech Majandang",{"name":376,"orcid":377},"Patiwat Littidej","https:\u002F\u002Forcid.org\u002F0000-0002-1024-547X",{"name":379,"orcid":380},"Benjamabhorn Pumhirunroj","https:\u002F\u002Forcid.org\u002F0009-0009-6607-5594",{"name":382,"orcid":383},"D. C. Slack","https:\u002F\u002Forcid.org\u002F0000-0003-0324-2163",{"tldr":385,"method":386,"finding":387,"direction":98,"opportunity":388},"利用多时相遥感和机器学习揭示泰国湄公河支流流域植被对洪水的非对称响应。","Sentinel-2影像、洪水记录与机器学习，分析23万个空间单元。","重复洪水区植被增加，低洪水区减少，表明洪水可缓冲干旱影响。","可探索洪水-干旱交替下植被恢复机制，并开发基于阈值的差异化预警系统。","2026-09-26T23:30:29.514361Z",{"id":391,"title":392,"url":393,"summary":394,"summary_zh":9,"content":9,"source_name":395,"source_url":9,"published_at":396,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":184,"score_detail":397,"sources":399,"tags":401,"primary_topic":403,"secondary_topics":404,"classification":405,"search_phrases":426,"slug":429,"view_count":63,"doi":9,"paper":430,"created_at":439},3248,"Crop recommendation in precision agriculture: a systematic literature review of methods, trends, and challenges（精准农业中的作物推荐：方法、趋势与挑战系统综述）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37471110","MDPI 发表精准农业作物推荐方法系统综述：从183项研究中严格筛选129篇发表于2020-2026年的文章，使用PRISMA协议进行综合分析。研究表明集成学习方法（特别是随机森林和XGBoost）在各种农业数据集的预测性能上具有强大能力；支持向量机、决策树、k近邻等传统ML方法仍被广泛使用；同时CNN和LSTM被用于遥感和时间相关农业分析。最常用的数据集来源是Kaggle，典型输入包括土壤养分（NPK）、土壤pH、天气条件和NDVI、EVI等卫星指数。研究主要研究空白：有限的实时部署、低多数据源集成、低跨区域验证、低模型可解释性。研究表明可扩展、可解释的AI系统对农业实际应用具有重要意义。","MDPI","2026-09-22T00:00:00Z",{"impact":19,"substance":114,"depth":19,"authority":20,"freshness":13,"relevant":22,"comment":398},"基于PRISMA的129篇文献系统综述，梳理作物推荐主流方法与四大研究空白，对农业AI落地有参考价值。",[400],{"name":395,"url":393},[254,27,66,402,30],"作物推荐",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":406},{"candidates":407,"agricultural_evidence":47},[408,412,416,422],{"code":288,"score":115,"supported":47,"title":409,"abstract":410,"tags":411},[291,292],[291],[254],{"code":33,"score":63,"supported":47,"title":413,"abstract":414,"tags":415},[],[50],[30],{"code":417,"score":368,"supported":47,"title":418,"abstract":419,"tags":421},"H2",[],[420],"土壤",[],{"code":62,"score":70,"supported":14,"title":423,"abstract":424,"tags":425},[],[],[27,66],[427,428],"精准农业 作物推荐 系统综述","XGBoost 随机森林 作物推荐","精准农业作物推荐系统综述-3248",{"doi":9,"openalex_id":9,"authors":431,"venue":9,"cited_by_count":93,"oa_url":9,"card":432,"direction":436,"ingested_from":438},[],{"tldr":433,"method":434,"finding":435,"direction":436,"opportunity":437},"系统综述129篇2020-2026年文献，梳理精准农业作物推荐的方法、趋势与挑战。","PRISMA协议系统综述，分析183项研究筛选出的129篇文献。","集成学习（随机森林、XGBoost）表现最强，主要空白为实时部署、多源集成、跨区域验证与可解释性。","农业人工智能与决策模型","可探索可解释、可跨区域泛化的实时作物推荐系统，并融合多源遥感与物联网数据。","agent","2026-09-23T00:04:33.331160Z",{"id":441,"title":442,"url":443,"summary":444,"summary_zh":445,"content":9,"source_name":446,"source_url":443,"published_at":447,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":448,"score_detail":449,"sources":451,"tags":453,"primary_topic":457,"secondary_topics":458,"classification":465,"search_phrases":485,"slug":488,"view_count":55,"doi":489,"paper":490,"created_at":504},3174,"Remote sensing and geospatial modeling for the detection of war-induced land use abandonment, soil disturbance, and degradation in Sumy region of Ukraine: a systematic review","https:\u002F\u002Fdoi.org\u002F10.31548\u002Fzemleustriy2026.03.015","The full-scale military invasion of Ukraine has caused multidimensional transformations of agricultural landscapes, land cover, and ecosystems. The Sumy region, located along the northeastern border with the Russian Federation, is a critical region that has suffered from intense fighting, prolonged artillery shelling, and ongoing border clashes during the study period from 2022 to May 2026. This paper systematically evaluates the application of remote sensing and geospatial modeling techniques to detect, quantify, and monitor war-induced land abandonment, as well as physical land cover disturbances, chemical contamination, and broader environmental degradation in this theater of war. Combining recent scientific publications on the war in Ukraine and comparative global examples (Syria, Iraq, and Sudan), the effectiveness of integrating multi-sensor data, including optical (Sentinel-2, Landsat), synthetic aperture radar (SAR; Sentinel-1), thermal, and very high resolution (VHR; Maxar, WorldView) platforms, as well as advanced machine and deep learning algorithms (Random Forest, Deep Learning) and time series analysis (FANTA, two-period curve approximation), is assessed. The results of the study show that while geospatial modeling is an indispensable tool for rapid, large-scale, and non-contact damage assessment in active conflict settings, significant critical research gaps remain, namely separating short-term cessation of agricultural use from actual land abandonment caused by war, verifying such facts in the face of a severe shortage of reliable ground data, and managing sensitive geospatial information. This systematic review highlights existing methodological gaps and outlines future perspectives needed to build a harmonized spatial monitoring system capable of guiding post-conflict recovery and environmental remediation based on actual remote sensing data at the regional scale.Received: 01.07.2026;Accepted:26.08.2026;","乌克兰遭受的大规模军事入侵已导致农业景观、土地覆盖和生态系统发生多维转变。苏梅州位于乌克兰与俄罗斯联邦东北部接壤的边境沿线，是一个关键地区，在研究期间（2022年至2026年5月）遭受了激烈战斗、长期炮击以及持续边境冲突的影响。本文系统评估了遥感与地理空间建模技术在探测、量化和监测该战区战争导致的土地撂荒、土地覆盖物理扰动、化学污染及更广泛环境退化方面的应用。结合近期关于乌克兰战争的科学出版物及全球比较案例（叙利亚、伊拉克和苏丹），本文评估了多传感器数据整合的有效性，包括光学（Sentinel-2、Landsat）、合成孔径雷达（SAR；Sentinel-1）、热红外及甚高分辨率（VHR；Maxar、WorldView）平台，以及先进的机器学习和深度学习算法（随机森林、深度学习）和时间序列分析（FANTA、两期曲线近似）。研究结果表明，尽管地理空间建模是在活跃冲突环境中进行快速、大规模、非接触式损害评估不可或缺的工具，但仍存在重要的关键研究空白，即如何区分农业利用的短期中止与战争导致的实际土地撂荒，如何在严重缺乏可靠地面数据的情况下核实此类事实，以及如何管理敏感的地理空间信息。本系统综述指出了现有的方法论空白，并勾勒了未来前景，以构建一个协调的空间监测系统，从而基于区域尺度上的实际遥感数据指导冲突后恢复和环境修复。收稿日期：2026年7月1日；接受日期：2026年8月26日；","Zemleustrìj kadastr ì monìtorìng zemelʹ","2026-09-21T00:00:00Z",75,{"impact":19,"substance":115,"depth":270,"authority":17,"freshness":331,"relevant":22,"comment":450},"系统综述遥感与地理空间建模在战区耕地撂荒与土壤退化识别中的应用，方法体系与数据源梳理扎实，对农业遥感监测有参考价值，但属境外冲突场景研究，国内落地关联度有限。",[452],{"name":446,"url":443},[27,454,30,455,456],"土地退化","耕地撂荒","冲突农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[459,460],{"code":62,"slug":194,"name":195,"path":196,"parent_code":37},{"code":417,"slug":461,"name":462,"path":463,"parent_code":464},"soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":40,"locked":14,"version":41,"method":42,"evidence":466},{"candidates":467,"agricultural_evidence":47},[468,472,476,480],{"code":33,"score":203,"supported":47,"title":469,"abstract":470,"tags":471},[51],[50,51],[30],{"code":62,"score":13,"supported":47,"title":473,"abstract":474,"tags":475},[],[281,66,279],[27],{"code":417,"score":331,"supported":47,"title":477,"abstract":478,"tags":479},[461],[],[],{"code":481,"score":22,"supported":14,"title":482,"abstract":483,"tags":484},"H1",[],[],[454],[486,487],"乌克兰 苏梅州 遥感 耕地撂荒","Sentinel-1 合成孔径雷达 土地退化监测","乌克兰苏梅州遥感耕地撂荒-3174","10.31548\u002Fzemleustriy2026.03.015",{"doi":489,"openalex_id":491,"authors":492,"venue":446,"cited_by_count":93,"oa_url":443,"card":499,"direction":98,"ingested_from":100},"W7213890485",[493,495,497],{"name":494,"orcid":9},"V. Bogdanets",{"name":496,"orcid":9},"Ye. Berezhniak",{"name":498,"orcid":9},"D. Brovko",{"tldr":500,"method":501,"finding":502,"direction":98,"opportunity":503},"系统综述遥感与地理空间建模在乌克兰苏梅地区检测战争导致的土地弃耕、土壤扰动与退化的应用。","综述多源遥感（Sentinel-2\u002F1、Landsat、VHR）与机器学习、时间","遥感是冲突区快速非接触损害评估的关键工具，但区分短期停耕与真正弃耕、地面数据匮乏及敏感信息管理仍是重","可研究多源时序遥感与弱监督学习结合，构建冲突区弃耕识别与地面验证缺失下的不确定性量化框架。","2026-09-22T23:30:23.289241Z"]