[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3561":3,"related-3561":55},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":54},3561,"GIS and Machine Learning Framework for Landslide Susceptibility Mapping: A Raster-Based Approach","https:\u002F\u002Fdoi.org\u002F10.48123\u002Frsgis.1864203","Traditional landslide susceptibility models often rely on statistical methods applied to limited point-based samples, which can limit the spatial continuity of predictions. This study proposes a GIS-integrated, pixel-based machine learning approach that operates directly on raster data to generate continuous landslide susceptibility maps. Implemented in Rwanda, the workflow uses variables derived from a 30 m-resolution digital elevation model (DEM), including slope, aspect, elevation, and curvature, together with auxiliary environmental data such as NDVI, soil type, and distances to hydrological and infrastructural features. Several machine learning algorithms were evaluated, including Random Forest, Support Vector Machine, Logistic Regression, and ensemble approaches. Using only topographic variables, the Stacked Ensemble achieved the highest performance (F1-score = 0.8515; ROC-AUC = 0.9200). When all predictor variables were included, CatBoost achieved the highest performance (F1-score = 0.8860; ROC-AUC = 0.9564). This scalable approach is particularly suitable for landslide susceptibility assessment in data-scarce regions and can contribute to spatial planning and risk reduction efforts in Rwanda and similar regions.","传统的滑坡易发性模型通常依赖统计方法，并应用于有限的点位样本，这可能限制预测的空间连续性。本研究提出了一种集成GIS、基于像素的机器学习方法，直接对栅格数据进行操作，以生成连续的滑坡易发性图。该方法在卢旺达实施，工作流程使用源自30 m分辨率数字高程模型（DEM）的变量，包括坡度、坡向、高程和曲率，并结合NDVI、土壤类型以及距水文和基础设施要素的距离等辅助环境数据。研究评估了多种机器学习算法，包括随机森林、支持向量机、逻辑回归和集成方法。仅使用地形变量时，堆叠集成（Stacked Ensemble）取得了最高性能（F1分数 = 0.8515；ROC-AUC = 0.9200）。当纳入所有预测变量时，CatBoost取得了最高性能（F1分数 = 0.8860；ROC-AUC = 0.9564）。这种可扩展的方法特别适用于数据稀缺地区的滑坡易发性评估，并可为卢旺达及类似地区的空间规划和风险降低工作提供支持。",null,"Turkish Journal of Remote Sensing and GIS","2026-09-24T00:00:00Z","论文",10,false,65,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":22},8,20,17,12,1,"方法新颖、指标扎实的遥感机器学习论文，可为丘陵山区农业风险与空间规划提供参考，但属境外案例、应用面偏窄。",[24],{"name":10,"url":6},[26,27,28,29,30],"数字乡村","农业遥感","机器学习","GIS","滑坡风险",[32,33],"卢旺达 滑坡易发性 机器学习","DEM NDVI 滑坡风险制图","卢旺达滑坡易发性机器学习-3561",0,"10.48123\u002Frsgis.1864203",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":46,"card":47,"direction":51,"ingested_from":53},"W7214227863",[40,43],{"name":41,"orcid":42},"Albert Iradukunda","https:\u002F\u002Forcid.org\u002F0009-0001-6899-7615",{"name":44,"orcid":45},"Kaan Ozgun","https:\u002F\u002Forcid.org\u002F0000-0002-3853-1400","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5606819",{"tldr":48,"method":49,"finding":50,"direction":51,"opportunity":52},"提出GIS集成、基于栅格像元的机器学习框架，生成连续滑坡易发性图。","用30米DEM地形变量、NDVI、土壤等，比较RF、SVM、CatBoost等模","加入全部变量后CatBoost最优，F1=0.886，AUC=0.956，优于仅地形变量。","农业遥感与作物表型","可迁移到农业区滑坡风险评估，结合多时相遥感与作物分布，服务山区耕地安全与规划。","openalex","2026-09-26T23:30:32.763631Z",{"total":56,"page":21,"page_size":56,"items":57},6,[58,126,161,210,239,278],{"id":59,"title":60,"url":61,"summary":62,"summary_zh":63,"content":9,"source_name":64,"source_url":61,"published_at":65,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":66,"score_detail":67,"sources":73,"tags":75,"search_phrases":79,"slug":82,"view_count":35,"doi":83,"paper":84,"created_at":125},3278,"Research on the optimal modeling path for inversion of Pb content in rice leaves based on hyperspectral data of ground objects and machine learning and cross-scale remote sensing monitoring","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10661-026-15959-x","Research on the optimal modeling path for inversion of Pb content in rice leaves based on hyperspectral data of ground objects and machine learning and cross-scale remote sensing monitoring。Environmental Monitoring and Assessment","基于地物高光谱数据与机器学习的稻叶铅含量反演最优建模路径及跨尺度遥感监测研究。环境监测与评估","Environmental Monitoring and Assessment","2026-09-22T00:00:00Z",64,{"impact":17,"substance":68,"depth":69,"authority":70,"freshness":71,"relevant":21,"comment":72},18,16,13,9,"基于地物高光谱与机器学习的水稻叶片铅含量反演建模研究，方法有创新但属细分领域学术进展，公共影响有限。",[74],{"name":64,"url":61},[76,27,77,28,78],"智慧农业","水稻","高光谱遥感",[80,81],"水稻叶片 铅含量 高光谱 反演","稻米 重金属 遥感 监测","水稻叶片铅含量高光谱反演-3278","10.1007\u002Fs10661-026-15959-x",{"doi":83,"openalex_id":85,"authors":86,"venue":64,"cited_by_count":35,"oa_url":9,"card":120,"direction":51,"ingested_from":53},"W7214027889",[87,90,93,96,99,102,104,106,109,112,114,116,118],{"name":88,"orcid":89},"Zhenlong Zhang","https:\u002F\u002Forcid.org\u002F0009-0008-2354-9123",{"name":91,"orcid":92},"Zhe Wang","https:\u002F\u002Forcid.org\u002F0000-0003-1266-7251",{"name":94,"orcid":95},"Chengxia Wang","https:\u002F\u002Forcid.org\u002F0009-0001-0820-2462",{"name":97,"orcid":98},"Wenxue Lin","https:\u002F\u002Forcid.org\u002F0000-0002-8245-9063",{"name":100,"orcid":101},"Jingyan Zhang","https:\u002F\u002Forcid.org\u002F0009-0004-4567-5316",{"name":103,"orcid":9},"Ying Luo",{"name":105,"orcid":9},"Jiaqian Zhang",{"name":107,"orcid":108},"Kai Ye","https:\u002F\u002Forcid.org\u002F0000-0002-2851-6741",{"name":110,"orcid":111},"Yiming Chen","https:\u002F\u002Forcid.org\u002F0000-0002-8121-3109",{"name":113,"orcid":9},"Chaoliang Peng",{"name":115,"orcid":9},"Duan Tian",{"name":117,"orcid":9},"Weihao Wang",{"name":119,"orcid":9},"Jiaxin Liu",{"tldr":121,"method":122,"finding":123,"direction":51,"opportunity":124},"研究基于地面高光谱与机器学习反演水稻叶片铅含量，并探索跨尺度遥感监测的最优建模路径。","地面高光谱数据结合机器学习建模，开展跨尺度遥感监测。","明确了水稻叶片铅含量反演的最优建模路径，实现跨尺度遥感监测。","可探索多尺度遥感数据融合与迁移学习，提升重金属胁迫反演的普适性与精度。","2026-09-23T23:30:19.291361Z",{"id":127,"title":128,"url":129,"summary":130,"summary_zh":9,"content":9,"source_name":131,"source_url":129,"published_at":65,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":132,"score_detail":133,"sources":137,"tags":139,"search_phrases":142,"slug":145,"view_count":35,"doi":146,"paper":147,"created_at":160},3135,"Non-destructive nitrogen estimation in pastures from UAV multispectral imagery using a heterogeneity-driven machine-learning framework","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10453-3","Non-destructive nitrogen estimation in pastures from UAV multispectral imagery using a heterogeneity-driven machine-learning framework。Precision Agriculture","Precision Agriculture",82,{"impact":68,"substance":134,"depth":68,"authority":135,"freshness":13,"relevant":21,"comment":136},22,14,"方法新颖、数据可靠，对草地精准施肥有参考价值，但属细分领域研究，未达重大突破层级。",[138],{"name":131,"url":129},[76,140,27,28,141],"无人机","草地氮素",[143,144],"UAV 多光谱 草地 氮素","Precision Agriculture 氮素估算","UAV多光谱草地氮素-3135","10.1007\u002Fs11119-026-10453-3",{"doi":146,"openalex_id":148,"authors":149,"venue":131,"cited_by_count":35,"oa_url":9,"card":9,"direction":9,"ingested_from":53},"W7213942551",[150,152,155,158],{"name":151,"orcid":9},"Antônio de Oliveira Costa Neto",{"name":153,"orcid":154},"Yiannis Ampatzidis","https:\u002F\u002Forcid.org\u002F0000-0002-3660-3298",{"name":156,"orcid":157},"Andrea Lazzari","https:\u002F\u002Forcid.org\u002F0000-0002-1521-6942",{"name":159,"orcid":9},"Jim Fletcher","2026-09-22T23:30:03.351447Z",{"id":162,"title":163,"url":164,"summary":165,"summary_zh":166,"content":9,"source_name":167,"source_url":164,"published_at":168,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":169,"score_detail":170,"sources":173,"tags":175,"search_phrases":179,"slug":182,"view_count":35,"doi":183,"paper":184,"created_at":209},2791,"Integrating multi-source data and support vector machine to assess the spatio-temporal pattern of land degradation in the Eastern Cape of South Africa","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.indic.2026.101524","Land degradation remains a major environmental challenge, particularly in semi-arid and heterogeneous landscapes, where interactions between vegetation loss and soil exposure are complex and spatially dynamic. This study, therefore, seeks to evaluate the spatial extent of land degradation and drivers over time (2005 - 2025) using Landsat data series and support vector machine (SVM) in the Keiskamma Catchment of South Africa. Degraded land followed a non-monotonic trajectory: it declined from ∼197 km 2 in 2005 to ∼157 km 2 in 2015 (a temporary contraction of 20.3%, consistent with short-term restoration and land-use shifts), before rising sharply and unsustainably to ∼328 km 2 by 2025 (a 108.9% increase relative to 2015, and a net increase of 66.5% over the full two-decade period), largely at the expense of grassland and agricultural land. Furthermore, the findings show that soil-sensitive indicators, particularly BSI and SWIR spectral bands, play a crucial role in determining degraded land. In contrast, vegetation indices such as NDVI contribute less under degraded conditions because degraded areas were severely dominated by exposed soil rather than vegetation. Correlation matrix analysis further reveals a temporal shift from mixed soil–vegetation spectral relationships toward strong soil-dominated reflectance patterns by 2025, indicating advanced degradation stages. Overall, the integration of SVM classification with VIF and SHAP provides a transparent, reliable, and spatially explicit framework for monitoring land degradation. The findings support land degradation neutrality monitoring and provide critical insights for sustainable land-management planning in support of Sustainable Development Goal (SDG) 15.3.","土地退化仍然是一项重大环境挑战，尤其是在半干旱和异质性景观中，植被丧失与土壤裸露之间的相互作用复杂且具有空间动态性。因此，本研究旨在利用Landsat数据序列和支持向量机（SVM），评估南非Keiskamma集水区2005—2025年间土地退化的空间范围及其驱动因素。退化土地呈非单调变化轨迹：从2005年的约197 km²下降至2015年的约157 km²（暂时收缩20.3%，与短期恢复和土地利用变化相一致），随后急剧且不可持续地上升至2025年的约328 km²（较2015年增加108.9%，在整个二十年期间净增加66.5%），且主要以草地和农用地为代价。此外，研究结果表明，土壤敏感指标，尤其是BSI和SWIR光谱波段，在判定退化土地方面发挥着关键作用。相比之下，NDVI等植被指数在退化条件下贡献较小，因为退化区域严重以裸露土壤为主，而非植被。相关矩阵分析进一步揭示，到2025年，光谱关系由土壤—植被混合关系向强烈的土壤主导反射模式发生时间转变，表明退化已进入后期阶段。总体而言，将SVM分类与VIF和SHAP相结合，为监测土地退化提供了一个透明、可靠且具有空间显式性的框架。研究结果支持土地退化零增长监测，并为支持可持续发展目标（SDG）15.3的可持续土地管理规划提供了关键见解。","Environmental and Sustainability Indicators","2026-09-16T00:00:00Z",77,{"impact":171,"substance":134,"depth":68,"authority":70,"freshness":71,"relevant":21,"comment":172},15,"基于Landsat时序与SVM\u002FSHAP的南非土地退化监测研究，方法透明可复现，对农业遥感与土地退化中性监测有参考价值，但属区域案例、非国内三农直接政策信息。",[174],{"name":167,"url":164},[27,28,176,177,178],"可持续发展","土地退化","遥感监测",[180,181],"可持续发展 农业遥感 土地退化 机器学习","可持续发展 农业遥感","可持续发展农业遥感土地退化机器学习-2791","10.1016\u002Fj.indic.2026.101524",{"doi":183,"openalex_id":185,"authors":186,"venue":167,"cited_by_count":35,"oa_url":203,"card":204,"direction":51,"ingested_from":53},"W7213298151",[187,189,192,195,197,200],{"name":188,"orcid":9},"Mandisa Zameko",{"name":190,"orcid":191},"Kgabo Humphrey Thamaga","https:\u002F\u002Forcid.org\u002F0000-0002-2305-9975",{"name":193,"orcid":194},"Mthunzi Mndela","https:\u002F\u002Forcid.org\u002F0000-0002-2384-6856",{"name":196,"orcid":9},"Matthieu Tshanga",{"name":198,"orcid":199},"Nobert Tafadzwa Mukomberanwa","https:\u002F\u002Forcid.org\u002F0009-0003-1896-9813",{"name":201,"orcid":202},"Mohamed Zhran","https:\u002F\u002Forcid.org\u002F0000-0002-1112-387X","https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2665972726004137\u002Fpdf",{"tldr":205,"method":206,"finding":207,"direction":51,"opportunity":208},"用Landsat与SVM评估南非Keiskamma流域2005-2025年土地退化时空格局。","Landsat时序数据、SVM分类，结合VIF与SHAP做特征解释。","退化面积先降后升，2025年达328km²，土壤光谱指标比NDVI更关键。","可将该SVM-SHAP框架迁移到其他半干旱区，并耦合气候与土地利用驱动做退化预警。","2026-09-17T23:30:36.054539Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":9,"content":215,"source_name":216,"source_url":9,"published_at":217,"category":218,"cover_url":9,"hotness":13,"is_selected":219,"score":220,"score_detail":221,"sources":226,"tags":228,"search_phrases":233,"slug":236,"view_count":237,"doi":9,"paper":9,"created_at":238},2694,"加快农业保险高质量发展实施方案印发——2030年保险深度1.9%、密度1200元\u002F人","https:\u002F\u002Fjcs.moa.gov.cn\u002Fgzdt\u002F202609\u002Ft20260915_6487691.htm","财政部、农业农村部、金融监管总局、国家林草局联合印发《关于加快农业保险高质量发展的实施方案》,到2030年农业保险深度达到1.9%、密度达到1200元\u002F人、科技投入强度达到1%,稻谷、小麦、玉米三大粮食作物覆盖率稳定在90%左右,综合费用率不高于20%。","各省、自治区、直辖市人民政府，新疆生产建设兵团，国务院有关部委、有关直属机构：\n\n经国务院同意，现将《关于加快农业保险高质量发展的实施方案》印发给你们，请抓好贯彻落实。\n\n财政部 农业农村部\n\n金融监管总局 国家林草局\n\n2026 年 9 月 8 日\n\n**关于加快农业保险高质量发展的实施方案**\n\n为进一步加快农业保险高质量发展，稳定农户收益，服务保障国家粮食安全和农业生产能力，经国务院同意，制定本实施方案。\n\n一、总体要求\n\n坚持以习近平新时代中国特色社会主义思想为指导，深入贯彻党的二十大和二十届历次全会精神，认真落实四中全会部署，全面贯彻习近平总书记关于“三农”工作的重要论述，完整准确全面贯彻新发展理念，加快构建新发展格局，着力推动高质量发展，遵循政府引导、市场运作、自主自愿、协同推进、改革创新的原则，充分发挥农业保险在价格、补贴、保险“三位一体”农业支持政策体系中的重要一环作用。\n\n到 2030 年，基本建成与农户风险保障需求相契合、与现代农业发展相适应、中央与地方分工负责的多层次农业保险体系，总体达到国际先进水平，实现补贴有效率、产业有保障、农民得实惠、机构可持续的多赢格局，政策更加普惠，发展更加均衡。农业保险深度（保费\u002F第一产业增加值）达到 1.9%，农业保险密度（保费\u002F第一产业就业人数）达到 1200 元\u002F人，农业保险科技投入强度（农业保险机构科技创新投入\u002F保费）达到 1%。稻谷、小麦、玉米三大粮食作物农业保险覆盖率稳定在 90%左右，提升特色农业保险对特色农业产业的保障水平，更好发挥富农强农作用。农业保险综合费用率不高于 20%。\n\n二、聚焦农业保险发展重点\n\n**（一）健全多层次农业保险体系。**坚持中央与地方共同推动、各部门分工负责，构建复合、多元、多层次的农业保险体系。加强对关系国计民生和粮食安全的大宗农产品以及地方特色农业的保障，稳步推进物化成本保险、完全成本保险、收入保险等险种发展，加强对小农户和农民合作社、家庭农场等新型农业经营主体的保障，强化对防止返贫致贫对象的支持。建立健全投保人、直保端、再保端等多方参与的风险分散链条，发挥好大灾风险准备金作用。\n\n**（二）增强种植业农产品风险保障。**加强主粮、棉花、油料、糖料、橡胶等大宗农产品风险保障，提高区域间农业保险发展均衡性，完善省以下保费分担机制。逐步降低产粮大县农业保险县级保费补贴承担比例，推动扩大稻谷、小麦、玉米、大豆完全成本保险和种植收入保险投保面积。完善对马铃薯、油菜、花生、甜菜、青稞等农产品以及稻谷、小麦、玉米制种的保险支持保障。\n\n**（三）促进养殖业保险规范发展。**完善养殖企业和养殖场（户）养殖保险模式，采用电子耳标、生物识别等技术加强养殖数量监控。动态调整能繁母猪、育肥猪、奶牛等养殖业保险保障水平，鼓励根据不同养殖方式提供差异化风险保障方案。做好牦牛、藏系羊等涉藏特定品种保险支持保障。\n\n**（四）推动林草保险提质增效。**坚持预防与保障并重，与现代林草业发展相适应，推动构建林草综合保险体系。完善公益林保险和商品林保险政策，探索适合相关林业保险险种特点的承保理赔模式。保险机构要合理确定森林保险防灾减损费用计提比例，据实列支。鼓励保险机构开展草原、湿地、国家公园、碳汇等保险试点，丰富林草保险产品。\n\n**（五）支持地方特色发展。**鼓励各地结合实际制定特色农业保险发展政策，加强相关资金统筹，加大支持力度，扩大保险范围，积极发展蔬菜、水果、肉牛、肉羊、禽类、渔业、林下经济等特色农业保险。\n\n**（六）完善产品供给体系。**健全“政策险+商业险”、“基本险+补充险”的农业保险产品供给体系。鼓励各地结合实际在物化成本保险等提供基本保险保障的险种基础上，设计开发相关补充保险，形成更高保障。鼓励各地因地制宜发展农业气象指数保险。支持保险机构发展商业性农业保险，开发便利农户投保的综合型保险保障方案。\n\n**（七）推广“农业保险+”模式。**深化农业保险与信贷、担保、期货等金融工具协同，探索保单质押、联合分担风险等模式。发挥农业保险增信功能，提高投保农户信用等级，促进涉农数据、科技、资产等要素资源融合，引导加大金融资源投入。\n\n**（八）逐步拓宽服务领域。**鼓励保险机构根据农业发展需要以市场化方式提供覆盖农林牧渔、涉农产业上下游、农民人身安全等方面风险的保险产品，探索开展农产品加工、仓储、运输、质量保险及高标准农田工程质量保险，为农业对外合作提供保险服务。鼓励地方和保险机构提供大棚、农房、农机、仓库等农业生产设施设备保险，以及农业绿色发展、智慧农业、民族村寨等领域保险。\n\n三、优化农业保险运行机制\n\n**（九）优化完善承保管理。**财政、发展改革、农业农村、保险监管、林业草原等部门及保险机构加强信息互通，共享农（林）地确权、流转、目标价格补贴面积以及农产品成本调查、畜禽存出栏量、病死猪无害化处理等农业生产经营数据。逐步推行“一户一单”承保模式。保险监管部门指导保险机构制定农业保险精准承保规范，提升可操作性。保险机构应加强农业保险承保精准性管理，开展验标和承保信息审核，集体投保类业务逐步提高抽查验标比例，规模经营主体投保类业务实现全部验标。\n\n**（十）加强财政补贴管理。**强化保费补贴资金管理，加强补贴资金所涉投保信息与农业生产经营数据、历史投保数据的比对核验，提高财政资金使用效益。及时向保险机构拨付保费补贴资金，优化资金拨付方式。鼓励各地实行省级财政部门与保险机构省级分公司“省级对省级”结算等模式。\n\n**（十一）完善查勘定损制度。**农业农村、保险监管、林业草原等部门结合当地种植、养殖、林业生产实际，指导保险机构制定分类或分险种查勘定损操作规范，明确查勘、抽样、定损等工作流程和标准。农业农村、林业草原等部门配合做好灾后查勘和灾损核定工作。\n\n**（十二）提升理赔服务质效。**保险监管部门指导保险机构制定完善农业保险理赔实施规范，提升理赔效率和精准度。保险机构应完善基层服务网络，简化手续、优化流程、赔款到户，建立农业大灾快速理赔响应机制，针对重大自然灾害和事故合理预付部分赔偿金，支持农户恢复生产。保险机构应通过银行转账等非现金方式将保险赔款直接支付给被保险人。\n\n**（十三）鼓励开展风险减量管理。**健全风险减量管理机制，增强事前防灾减灾、事中救灾减损、事后及时赔付相结合的一体化服务能力，推动农业保险从单一事后理赔向全流程风险管理转型。保险机构可与农业农村、林业草原、气象等领域社会化服务机构合作，开展防灾减损工作。\n\n**（十四）健全监督管理机制。**健全农业保险领域常态化监督机制，财政、农业农村、保险监管、林业草原等部门加强联动，加大监督力度。对虚构虚增保险标的、虚假理赔、骗取套取保费补贴等违法违规行为，加大打击和惩戒力度，依法依规予以处理。\n\n四、夯实农业保险发展基础\n\n**（十五）强化信息化支撑。**持续推进全国农业保险数据信息系统、全国农业保险信息管理平台建设。统一农业保险数据标准，加强部门间、中央与地方间农业保险数据信息共享。加快推动农业保险行业数字化转型，促进业务流程智能化、标准化。\n\n**（十六）推进风险区划工作。**推进三大粮食作物、主要畜产品等重要农产品保险风险区划工作，适时发布风险区划结果和保险费率参考。探索开展地方特色农业保险风险区划工作。\n\n**（十七）加强科技应用。**保险机构应加大科技投入强度，合理应用无人机、遥感、物联网、人工智能、区块链、云计算等技术工具，提高保险服务精准度。鼓励保险机构探索开发农业灾害风险模型。制定农业保险科技应用规范或标准。保险机构应开展承保理赔信息实名校验和身份认证。\n\n**（十八）加强遴选管理。**按照适度竞争原则，结合服务能力、风控能力合理确定农业保险承保机构。各省份根据保费规模等因素统筹确定承保机构数量，承保机构一经确定应保持相对稳定，服务有效期一般不少于 3 年。开展承保机构绩效评价，强化绩效评价结果应用，做好承保机构动态调整工作。审慎评估农业保险市场环境和保险机构服务能力，加强经营资格管理，优化准入退出机制。\n\n**（十九）健全政策法规。**适应农业保险发展态势和高质量发展需要，推动适时修订《农业保险条例》，进一步加强农业保险法治建设。\n\n五、健全农业保险大灾风险分散机制\n\n**（二十）完善大灾风险准备金管理。**科学设置农业保险各险种大灾风险准备金计提比例，完善大灾风险准备金触发使用标准。保险机构按照独立运作、因地制宜、分级管理、统筹使用的原则，加强大灾风险准备金使用规范性管理，进一步发挥大灾风险准备金作用。\n\n**（二十一）大力发展农业再保险。**按照约定分保和市场化分保相结合的发展模式，健全农业再保险制度。完善约定分保机制和流程，优化大灾超赔保障。鼓励发展商业性再保险，逐步提高市场化业务比重。推动完善农业再保险机构治理机制，提高运行规范性和发展可持续性。\n\n**（二十二）健全风险分散机制。**研究建立农业保险大灾风险基金，完善农业保险大灾风险分散链条。加强农业保险赔付资金与政府救灾资金协同运用。\n\n六、做好组织实施工作\n\n各地区、各有关部门要高度重视农业保险工作，夯实工作基础，形成工作合力，更好满足“三农”主体风险保障需求。各省级人民政府加强组织领导，统筹推进本行政区域内农业保险规划发展、资源统筹、政策宣传等各项工作，发挥农业保险工作小组作用，组织有关部门和保险机构加强协同配合，确保各项任务落实见效。各有关部门按职责分工做好政策设计、资金安排、监督管理等工作。保险机构切实提高服务质效，可根据业务需要设立协保员，为承保理赔等服务提供便利。","农业农村部计划财务司 2026年9月8日","2026-09-08T00:00:00Z","政策",true,92,{"impact":222,"substance":223,"depth":224,"authority":171,"freshness":56,"relevant":21,"comment":225},28,24,19,"四部门联合印发的全国性农业保险高质量发展实施方案，明确2030年保险深度1.9%、密度1200元\u002F人等量化目标，条款与数据详实，权威性和政策影响力突出，值得进入每日精选。",[227],{"name":216,"url":213},[26,27,229,230,231,232],"粮食安全","农业保险","风险区划","财政补贴",[234,235],"农业保险 农业遥感 数字乡村 粮食安全","农业保险 农业遥感","农业保险农业遥感数字乡村粮食安全-2694",2,"2026-09-17T00:04:35.464456Z",{"id":240,"title":241,"url":242,"summary":243,"summary_zh":244,"content":9,"source_name":245,"source_url":242,"published_at":168,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":246,"score_detail":247,"sources":249,"tags":251,"search_phrases":255,"slug":258,"view_count":21,"doi":259,"paper":260,"created_at":277},2681,"Forest encroachment prediction using multi-temporal satellite data and machine learning: a case study of Bandipur National Park, India","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-70597-0","Abstract Forest encroachment poses a significant threat to protected forest ecosystems due to increasing human activities, including infrastructure development, agricultural expansion, and settlement growth. Continuous monitoring is therefore essential for effective conservation planning and sustainable forest management. This study presents an artificial intelligence-based framework for forest encroachment prediction in Bandipur National Park, India, using multi-temporal Sentinel- 2 satellite imagery integrated with topographic, land-cover, and anthropogenic variables. Multi temporal Normalized Difference Vegetation Index (NDVI) and Normalized Burn Ratio (NBR) were combined with elevation, slope, aspect, forest and water masks, and distance-to-road and distance-to-settlement variables. Three predictive models, namely Random Forest (RF), MultiLayer Perceptron (MLP), and a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture, were comparatively evaluated. RF achieved the highest classification accuracy of 94.17%, followed by MLP at 91.50% and CNN–LSTM at 78.69%. Future projections for 2026 and 2030 indicated relatively limited encroachment under RF and MLP, with maximum projected areas of 1.27 km² (0.15%) and 0.64 km² (0.07%), respectively. In contrast, CNN–LSTM projected substantially larger encroached areas of 115.76 km² (13.24%) in 2026 and 71.94 km² (8.23%) in 2030. Overall, RF demonstrated the strongest and most consistent classification performance under the adopted experimental framework, indicating its potential for supporting forest monitoring, encroachment hotspot identification, and evidencebased conservation planning.","摘要 森林侵占对受保护森林生态系统构成重大威胁，其驱动因素包括基础设施建设、农业扩张和聚落增长等日益加剧的人类活动。因此，持续监测对于有效的保护规划和可持续森林管理至关重要。本研究提出了一种基于人工智能的森林侵占预测框架，以印度班迪普尔国家公园为研究区，利用多时相Sentinel-2卫星影像，并结合地形、土地覆盖和人为变量。研究将多时相归一化植被指数（NDVI）和归一化燃烧比（NBR）与高程、坡度、坡向、森林和水体掩膜以及距道路距离和距聚落距离等变量相结合。研究对比评估了三种预测模型，即随机森林（RF）、多层感知机（MLP）以及混合卷积神经网络—长短期记忆网络（CNN–LSTM）架构。RF取得了最高的分类精度，为94.17%，其次是MLP的91.50%和CNN–LSTM的78.69%。2026年和2030年的未来预测表明，在RF和MLP下森林侵占相对有限，最大预测面积分别为1.27 km²（0.15%）和0.64 km²（0.07%）。相比之下，CNN–LSTM预测的侵占面积要大得多，2026年为115.76 km²（13.24%），2030年为71.94 km²（8.23%）。总体而言，在所采用的实验框架下，RF表现出最强且最一致的分类性能，表明其具有支持森林监测、侵占热点识别和循证保护规划的潜力。","Scientific Reports",79,{"impact":171,"substance":134,"depth":68,"authority":135,"freshness":13,"relevant":21,"comment":248},"基于多时相Sentinel-2与机器学习预测森林侵占，方法对比扎实、结论明确，对农业遥感与生态监测有参考价值。",[250],{"name":245,"url":242},[27,28,252,253,254],"NDVI","生态监测","森林保护",[256,257],"农业遥感 机器学习 森林保护 生态监测","农业遥感 机器学习","农业遥感机器学习森林保护生态监测-2681","10.1038\u002Fs41598-026-70597-0",{"doi":259,"openalex_id":261,"authors":262,"venue":245,"cited_by_count":35,"oa_url":242,"card":271,"direction":276,"ingested_from":53},"W7213307679",[263,265,267,269],{"name":264,"orcid":9},"Pushpa B. R",{"name":266,"orcid":9},"H. R. Chaitanya",{"name":268,"orcid":9},"Chandhana U. Shankar",{"name":270,"orcid":9},"R. Sudarshan",{"tldr":272,"method":273,"finding":274,"direction":51,"opportunity":275},"用多时相Sentinel-2影像和机器学习预测印度Bandipur国家公园的森林侵占。","Sentinel-2多时相NDVI\u002FNBR结合地形、土地覆盖和人为变量，比较RF","RF分类精度最高达94.17%，预测2026和2030年侵占面积有限，CNN-LSTM预测值显著偏大","可探索多源遥感与深度学习融合提升侵占预测精度，并推广到其他保护区或农业扩张监测。","农业人工智能与决策模型","2026-09-16T23:30:46.701925Z",{"id":279,"title":280,"url":281,"summary":282,"summary_zh":283,"content":9,"source_name":284,"source_url":281,"published_at":285,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":286,"score_detail":287,"sources":289,"tags":291,"search_phrases":295,"slug":298,"view_count":35,"doi":299,"paper":300,"created_at":329},2425,"GIS-Based Multi-Criteria Modelling of Soil Erosion Susceptibility Using AHP in Ikere-Ekiti, Southwestern Nigeria","https:\u002F\u002Fdoi.org\u002F10.54536\u002Fajgt.v5i1.8103","Soil erosion remains a critical environmental challenge in tropical regions, particularly in areas experiencing rapid land-use change and geomorphic instability. This study presents a GIS-based multi-criteria modelling approach for assessing soil erosion susceptibility in Ikere-Ekiti, Southwestern Nigeria. Twelve conditioning factors-land use\u002Fland cover (LULC), slope, aspect, elevation, drainage density, soil type, rainfall, Normalized Difference Vegetation Index (NDVI), geology, rainfall erosivity (R-factor), soil erodibility (K-factor), and Topographic Wetness Index (TWI)-were integrated using an Analytic Hierarchy Process (AHP) framework. Spatial datasets derived from ASTER DEM, Landsat 8 imagery, soil and geological maps, and rainfall records were standardized and weighted using pairwise comparison, with model consistency validated (CR = 0.06). A weighted overlay model was employed to generate erosion susceptibility zones. Results indicate that low and moderate susceptibility zones dominate (90.48%), while high and very high-risk areas account for 4.50% and 0.03%, respectively. High-risk zones are strongly associated with steep slopes, high drainage density, sparse vegetation, and erodible soils. The study demonstrates the robustness of GIS-based multi-criteria modelling in erosion prediction and provides a decision-support framework for sustainable land management in tropical environments.","土壤侵蚀仍然是热带地区面临的严峻环境挑战，尤其是在土地利用快速变化和地貌不稳定的区域。本研究提出了一种基于GIS的多准则建模方法，用于评估尼日利亚西南部伊凯雷-埃基蒂（Ikere-Ekiti）地区的土壤侵蚀敏感性。研究整合了12个条件因子——土地利用\u002F土地覆盖（LULC）、坡度、坡向、高程、河网密度、土壤类型、降雨量、归一化植被指数（NDVI）、地质、降雨侵蚀力（R因子）、土壤可蚀性（K因子）和地形湿度指数（TWI），并采用层次分析法（AHP）框架进行分析。来自ASTER DEM、Landsat 8影像、土壤与地质图及降雨记录的空间数据集经过标准化处理，并通过成对比较法赋权，模型一致性得到验证（CR = 0.06）。采用加权叠加模型生成侵蚀敏感性分区。结果表明，低度和中度敏感区占主导地位（90.48%），而高风险区和极高风险区分别占4.50%和0.03%。高风险区与陡坡、高河网密度、稀疏植被和易蚀土壤密切相关。本研究证明了基于GIS的多准则建模在侵蚀预测中的稳健性，并为热带环境下的可持续土地管理提供了决策支持框架。","American Journal of Geospatial Technology","2026-09-12T00:00:00Z",62,{"impact":17,"substance":68,"depth":171,"authority":70,"freshness":17,"relevant":21,"comment":288},"基于GIS与AHP的土壤侵蚀敏感性建模研究，方法规范、结论可靠，对热带地区土地管理与农业生态保护有参考价值，但属区域性案例研究，公共影响有限。",[290],{"name":284,"url":281},[26,292,293,29,294],"遥感","土壤侵蚀","水土保持",[296,297],"土壤侵蚀 数字乡村 水土保持 遥感","土壤侵蚀 数字乡村","土壤侵蚀数字乡村水土保持遥感-2425","10.54536\u002Fajgt.v5i1.8103",{"doi":299,"openalex_id":301,"authors":302,"venue":284,"cited_by_count":35,"oa_url":323,"card":324,"direction":51,"ingested_from":53},"W7212388696",[303,305,308,311,314,317,319,321],{"name":304,"orcid":9},"Samuel Fatile",{"name":306,"orcid":307},"Elochukwu Moka","https:\u002F\u002Forcid.org\u002F0000-0001-6089-1392",{"name":309,"orcid":310},"Olaniran Emmanuel Aluko","https:\u002F\u002Forcid.org\u002F0000-0002-8750-1742",{"name":312,"orcid":313},"Ugonna C. Nkwunonwo","https:\u002F\u002Forcid.org\u002F0000-0002-6944-0675",{"name":315,"orcid":316},"Seyi F. Olatoyinbo","https:\u002F\u002Forcid.org\u002F0000-0002-6859-9350",{"name":318,"orcid":9},"Ndukwe Emmanuel Chiemelu",{"name":320,"orcid":9},"Peter Damulak DAKUNG",{"name":322,"orcid":9},"Mark Fredrick OCHOLI","https:\u002F\u002Fjournals.e-palli.com\u002Fhome\u002Findex.php\u002Fajgt\u002Farticle\u002Fdownload\u002F8103\u002F4012",{"tldr":325,"method":326,"finding":327,"direction":51,"opportunity":328},"用GIS与AHP多准则模型评估尼日利亚Ikere-Ekiti地区土壤侵蚀敏感性并划分风险区。","整合12个因子，基于AHP加权叠加，数据来自ASTER DEM、Landsat ","低与中度敏感区占90.48%，高与极高风险区仅4.53%，高风险与陡坡、高排水密度、稀疏植被和易蚀土","可引入机器学习或时序遥感提升AHP权重客观性，并验证侵蚀风险与作物产量的空间关联。","2026-09-14T23:30:24.740002Z"]