[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3561":3,"related-3561":95},{"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,"primary_topic":9,"secondary_topics":31,"classification":32,"search_phrases":70,"slug":73,"view_count":74,"doi":75,"paper":76,"created_at":94},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",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":14,"reason":69},[38,46,51,59,64],{"code":39,"score":40,"supported":41,"title":42,"abstract":44,"tags":45},"I2",15,true,[43],"machine learning",[28,43],[28],{"code":47,"score":20,"supported":41,"title":48,"abstract":49,"tags":50},"I4",[29],[29],[29],{"code":52,"score":53,"supported":41,"title":54,"abstract":55,"tags":58},"H2",6,[],[56,57],"土壤","soil",[],{"code":60,"score":21,"supported":14,"title":61,"abstract":62,"tags":63},"I3",[],[],[27],{"code":65,"score":21,"supported":14,"title":66,"abstract":67,"tags":68},"I6",[],[],[26],"农业相关性需要复核",[71,72],"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",3,"10.48123\u002Frsgis.1864203",{"doi":75,"openalex_id":77,"authors":78,"venue":10,"cited_by_count":85,"oa_url":86,"card":87,"direction":91,"ingested_from":93},"W7214227863",[79,82],{"name":80,"orcid":81},"Albert Iradukunda","https:\u002F\u002Forcid.org\u002F0009-0001-6899-7615",{"name":83,"orcid":84},"Kaan Ozgun","https:\u002F\u002Forcid.org\u002F0000-0002-3853-1400",0,"https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5606819",{"tldr":88,"method":89,"finding":90,"direction":91,"opportunity":92},"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":53,"page":21,"page_size":53,"items":96},[97,196,275,334,399,471],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":104,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":106,"sources":111,"tags":113,"primary_topic":9,"secondary_topics":116,"classification":117,"search_phrases":155,"slug":158,"view_count":85,"doi":159,"paper":160,"created_at":195},4232,"Integrated machine learning and AHP-based framework for spatial delineation of rainwater harvesting potential","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72943-8","Groundwater scarcity and its declining situation in the semi-arid area of Jaipur district, Rajasthan make it imperative to adopt scientific solutions to locate suitable rainwater harvesting sites. This study combines Geographic Information Systems (GIS), Analytical Hierarchy Process (AHP) and machine learning (ML) algorithms for delineating the RWH suitability zones. Eleven biophysical and anthropogenic factors, namely elevation (280–647 m), slope (0–35°), topographic wetness index (TWI), drainage density, soil profile, land use\u002Fland cover (LULC), rainfall (350–700 mm yr⁻ 1 ), hillshade, aspect, lineament density, and proximity to roads, were standardized and incorporated into a spatial database. A georeferenced inventory of 150 locations was divided into training (70%; n = 105) and testing (30%; n = 45) datasets and analyzed using XGBoost, Support Vector Machine (SVM), Gradient Boosting Machine (GBM), CatBoost, and AHP models. Among the evaluated algorithms, XGBoost exhibited the highest predictive performance with a ROC-AUC of 0.78, followed by SVM (0.76), AHP (0.73), CatBoost (0.69), and GBM (0.68). The XGBoost model identified 38.1% (3902.6 km 2 ) of the study area as highly suitable to very highly suitable for RWH implementation, whereas 34.6% (3533.7 km 2 ) and 27.3% (2783.7 km 2 ) were classified as moderate and low-to-very low suitability classes, respectively. Variable importance analysis revealed that rainfall (15.7%), drainage density (15.6%), elevation (11.5%), and TWI (8.8%) were the dominant controls on RWH suitability. The AHP framework showed acceptable consistency (CR \u003C 0.10) and model validation showed an overall accuracy of 88% and a Kappa coefficient of 0.64. The integrated framework successfully identified priority recharge areas in the southeastern lowlands and offers a scalable decision support tool for sustainable groundwater management and water resource planning that is resilient to climate change in semi-arid areas.","拉贾斯坦邦斋浦尔地区半干旱区的地下水稀缺及其持续下降的态势，使得采用科学方法确定适宜的雨水收集地点势在必行。本研究结合地理信息系统（Geographic Information Systems, GIS）、层次分析法（Analytical Hierarchy Process, AHP）和机器学习（Machine Learning, ML）算法，划定雨水收集适宜性分区。研究将11项生物物理和人为因素，即高程（280–647 m）、坡度（0–35°）、地形湿度指数（Topographic Wetness Index, TWI）、河网密度、土壤剖面、土地利用\u002F土地覆被（Land Use\u002FLand Cover, LULC）、降雨量（350–700 mm yr⁻¹）、山体阴影、坡向、线理密度和道路邻近度，进行标准化处理并纳入空间数据库。将150个地理参考位置清单划分为训练集（70%；n = 105）和测试集（30%；n = 45），并采用XGBoost、支持向量机（Support Vector Machine, SVM）、梯度提升机（Gradient Boosting Machine, GBM）、CatBoost和AHP模型进行分析。在评估的算法中，XGBoost表现出最高的预测性能，ROC-AUC为0.78，其次是SVM（0.76）、AHP（0.73）、CatBoost（0.69）和GBM（0.68）。XGBoost模型识别出研究区38.1%（3902.6 km²）的区域为雨水收集高度适宜至极高适宜区，而34.6%（3533.7 km²）和27.3%（2783.7 km²）分别被归类为中度适宜和低至极低适宜等级。变量重要性分析表明，降雨量（15.7%）、河网密度（15.6%）、高程（11.5%）和TWI（8.8%）是雨水收集适宜性的主导控制因素。AHP框架显示出可接受的一致性（CR \u003C 0.10），模型验证显示总体精度为88%，Kappa系数为0.64。该集成框架成功识别了东南部低地的优先补给区，并为半干旱地区可持续地下水管理和应对气候变化的淡水资源规划提供了一种可扩展的决策支持工具。","Scientific Reports","2026-10-03T00:00:00Z",70,{"impact":17,"substance":107,"depth":19,"authority":108,"freshness":109,"relevant":21,"comment":110},22,14,9,"方法扎实、结论可复用的半干旱区雨水收集选址研究，但属区域案例，公共影响有限。",[112],{"name":103,"url":100},[27,28,29,114,115],"雨水收集","地下水管理",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":118},{"candidates":119,"agricultural_evidence":14,"reason":69},[120,126,132,140,144,151],{"code":39,"score":121,"supported":41,"title":122,"abstract":123,"tags":125},18,[43],[28,43,124],"decision support",[28],{"code":47,"score":13,"supported":41,"title":127,"abstract":128,"tags":131},[],[129,29,130],"地理信息","geographic information",[29],{"code":133,"score":109,"supported":41,"title":134,"abstract":135,"tags":139},"H7",[],[136,137,138],"气候变化","干旱","climate change",[],{"code":52,"score":53,"supported":41,"title":141,"abstract":142,"tags":143},[],[56,57],[],{"code":145,"score":53,"supported":41,"title":146,"abstract":147,"tags":150},"H3",[],[148,149],"水资源","water resource",[],{"code":60,"score":21,"supported":14,"title":152,"abstract":153,"tags":154},[],[],[27],[156,157],"Jaipur 雨水收集 选址","XGBoost AHP 地下水补给","Jaipur雨水收集选址-4232","10.1038\u002Fs41598-026-72943-8",{"doi":159,"openalex_id":161,"authors":162,"venue":103,"cited_by_count":85,"oa_url":189,"card":190,"direction":91,"ingested_from":93},"W7218709806",[163,166,168,171,173,175,177,179,181,183,186],{"name":164,"orcid":165},"Agradeep Mohanta","https:\u002F\u002Forcid.org\u002F0000-0002-9369-3445",{"name":167,"orcid":9},"Ameet Yadav",{"name":169,"orcid":170},"Dharmendra Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8528-8637",{"name":172,"orcid":9},"Sultan Singh",{"name":174,"orcid":9},"Shuchi Mishra",{"name":176,"orcid":9},"Kanwarpreet Singh",{"name":178,"orcid":9},"Abhishek Sharma",{"name":180,"orcid":9},"Amenjor Senagah",{"name":182,"orcid":9},"Aditya Kumar Tiwary",{"name":184,"orcid":185},"Chandni Thakur","https:\u002F\u002Forcid.org\u002F0000-0001-8976-2738",{"name":187,"orcid":188},"Mohamed A. Mattar","https:\u002F\u002Forcid.org\u002F0000-0002-7506-3036","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72943-8_reference.pdf",{"tldr":191,"method":192,"finding":193,"direction":91,"opportunity":194},"结合GIS、AHP与多种机器学习算法，划分印度斋浦尔半干旱区雨水收集适宜性分区。","11个生物物理与人为因子，150个样本，XGBoost、SVM、GBM、CatB","XGBoost表现最佳（AUC=0.78），38.1%区域高度适宜，降雨与排水密度为主导因子。","可将该集成框架迁移至其他半干旱农业区，并结合遥感时序数据动态更新适宜性。","2026-10-05T23:30:25.173949Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":201,"content":9,"source_name":202,"source_url":199,"published_at":203,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":204,"score_detail":205,"sources":209,"tags":211,"primary_topic":215,"secondary_topics":220,"classification":221,"search_phrases":239,"slug":242,"view_count":85,"doi":243,"paper":244,"created_at":274},5399,"Spatial Heterogeneity and Nonlinear Environmental Associations of Positive Climatic Moisture Deficit with Implications for Sustainable Water Resource Assessment: A Case Study of Anyang","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu182010595","Positive climatic moisture deficit (CMD+) characterizes the seasonal imbalance between precipitation supply and atmospheric water demand, yet its spatial heterogeneity and associations with environmental and human-related factors remain insufficiently understood. Taking Anyang, China, as a case study, we calculated annual CMD+ for 2000–2020 using 1 km monthly precipitation and potential evapotranspiration data and applied an extreme gradient boosting (XGBoost)–SHapley Additive exPlanations (SHAP) framework to the corresponding long-term mean fields to examine climatological spatial heterogeneity. Five predictors were considered, including elevation, normalized difference vegetation index (NDVI), irrigation fraction, built-up fraction, and population density. Nested spatial-block cross-validation showed good model generalization. Long-term mean CMD+ was generally lower in the western mountainous area and higher across the central and eastern plains. The digital elevation model (DEM) accounted for 66.10% of the normalized mean absolute SHAP importance, followed by NDVI (13.47%) and irrigation fraction (9.72%). A DEM-excluded sensitivity model retained a spatial cross-validated R2 of 0.781, compared with 0.898 for the full model. SHAP dependence analysis revealed pronounced nonlinear responses, with primary local model response transition points at approximately 297.1 m for DEM, 0.812 for NDVI, and 23.1% for irrigation fraction. The strongest pairwise SHAP interaction occurred between NDVI and irrigation fraction, accounting for 21.87% of total pairwise interaction strength. These results show that the spatial heterogeneity of CMD+ in Anyang is closely associated with topographic background, while vegetation status and irrigated agriculture provide additional nonlinear and interactive explanatory information. The identified spatial patterns and model-response transitions provide spatial information for understanding regional climatic moisture deficits and for subsequent sustainable water resource assessment.","正向气候水分亏缺（CMD+）刻画了降水供给与大气水分需求之间的季节性失衡，但其空间异质性及其与环境因素和人为因素的关联仍缺乏充分认识。以中国安阳为案例区，本研究利用1 km月降水量与潜在蒸散量数据计算了2000—2020年的年CMD+，并将极端梯度提升（XGBoost）—SHapley加性解释（SHAP）框架应用于相应的长期均值场，以考察气候态空间异质性。研究考虑了5个预测因子，包括高程、归一化植被指数（NDVI）、灌溉面积比例、建成区比例和人口密度。嵌套空间分块交叉验证表明模型具有良好的泛化能力。长期平均CMD+总体表现为西部山区较低、中部和东部平原较高。数字高程模型（DEM）占归一化平均绝对SHAP重要性的66.10%，其次为NDVI（13.47%）和灌溉面积比例（9.72%）。剔除DEM的敏感性模型保持了0.781的空间交叉验证R²，而完整模型为0.898。SHAP依赖分析揭示了显著的非线性响应，主要局部模型响应转变点分别约为DEM 297.1 m、NDVI 0.812和灌溉面积比例23.1%。最强的成对SHAP交互作用出现在NDVI与灌溉面积比例之间，占总成对交互强度的21.87%。结果表明，安阳CMD+的空间异质性与地形背景密切相关，而植被状况和灌溉农业提供了额外的非线性和交互解释信息。所识别的空间格局和模型响应转变点为理解区域气候水分亏缺及后续可持续水资源评估提供了空间信息。","Sustainability","2026-10-19T00:00:00Z",64,{"impact":17,"substance":121,"depth":206,"authority":207,"freshness":109,"relevant":21,"comment":208},16,13,"以安阳为案例，用遥感与XGBoost-SHAP揭示气候水分亏缺的空间异质性，方法有新意、结论可靠，但属区域案例研究，公共影响有限。",[210],{"name":202,"url":199},[27,28,212,213,214],"灌溉管理","水资源评估","气候干旱",{"code":145,"slug":216,"name":217,"path":218,"parent_code":219},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[],{"status":222,"locked":14,"version":34,"method":35,"evidence":223},"classified",{"candidates":224,"agricultural_evidence":41},[225,231,235],{"code":145,"score":121,"supported":41,"title":226,"abstract":227,"tags":230},[149],[228,148,216,149,229],"灌溉","evapotranspiration",[212],{"code":39,"score":21,"supported":14,"title":232,"abstract":233,"tags":234},[],[],[28],{"code":60,"score":21,"supported":14,"title":236,"abstract":237,"tags":238},[],[],[27],[240,241],"安阳 气候水分亏缺 遥感","XGBoost SHAP 水资源评估","安阳气候水分亏缺遥感-5399","10.3390\u002Fsu182010595",{"doi":243,"openalex_id":245,"authors":246,"venue":202,"cited_by_count":85,"oa_url":199,"card":268,"direction":273,"ingested_from":93},"W7222973420",[247,249,252,255,258,260,262,264,266],{"name":248,"orcid":9},"Yan Li",{"name":250,"orcid":251},"Xiaohua Yang","https:\u002F\u002Forcid.org\u002F0000-0001-8387-5213",{"name":253,"orcid":254},"Dehui Bian","https:\u002F\u002Forcid.org\u002F0000-0001-6921-1875",{"name":256,"orcid":257},"Qi Wang","https:\u002F\u002Forcid.org\u002F0000-0002-3156-9246",{"name":259,"orcid":9},"Lequn Gu",{"name":261,"orcid":9},"Ailing Zhang",{"name":263,"orcid":9},"Wei Gao",{"name":265,"orcid":9},"Wenjie Qi",{"name":267,"orcid":9},"Yayun Ma",{"tldr":269,"method":270,"finding":271,"direction":91,"opportunity":272},"以安阳为例，用XGBoost-SHAP分析2000—2020年气候水分亏缺的空间异质性及其环境关联。","1 km月降水与潜在蒸散数据计算CMD+，结合XGBoost-SHAP与嵌套空间","CMD+西部山区低、中东部平原高；高程贡献66.1%，NDVI与灌溉比例呈显著非线性交互。","可引入多源遥感与作物种植结构，探究CMD+非线性阈值对灌溉需水与水资源配置的传导机制。","数字乡村与农业信息化","2026-10-20T23:30:23.927575Z",{"id":276,"title":277,"url":278,"summary":279,"summary_zh":280,"content":9,"source_name":281,"source_url":278,"published_at":282,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":283,"score_detail":284,"sources":286,"tags":288,"primary_topic":9,"secondary_topics":292,"classification":293,"search_phrases":317,"slug":320,"view_count":85,"doi":9,"paper":321,"created_at":333},4668,"CONNECTING FLOODWATER, RAINFALL AND RESERVOIR DATA TO INTELLIGENT WATER REDISTRIBUTION FOR DROUGHT-RESILIENT RESOURCE MANAGEMENT - (AQUA RESCUE)","https:\u002F\u002Fijerst.org\u002Findex.php\u002Fijerst\u002Farticle\u002Fview\u002F4739","Many regions of India face floods and droughts in the same year, sometimes within a few hundred kilometres of each other. During a heavy monsoon spell, reservoirs in one basin release large volumes of water to protect their dams, and much of this water flows to the sea, while districts in a neighbouring basin run short of drinking and irrigation water a few months later. The data that could help manage this imbalance, including rainfall records, reservoir storage, river gauge levels and flood extents, is collected by different agencies and is rarely analysed together. This paper presents Aqua Rescue, a data pipeline and decision support system that connects these sources to plan the redistribution of surplus water to drought-prone areas. The pipeline ingests daily rainfall from rain gauge networks and gridded products, reservoir levels and releases from water resources department bulletins, river discharge from gauging stations, groundwater levels from observation wells and flood extent maps derived from satellite radar imagery. Each source is cleaned, converted to common units and mapped to a shared spatial framework of basins, sub-basins, reservoirs and districts. A curated data warehouse keeps both the daily history and the current state of every reservoir and district, and data quality checks catch missing bulletins, unit errors and sudden unrealistic jumps in storage values. Machine learning models use this curated data in three ways. A Long Short-Term Memory network forecasts reservoir inflows for the next fourteen days from recent rainfall, upstream discharge and catchment soil moisture. A gradient boosting model estimates the water demand of each district for drinking, irrigation and industry using population, cropping pattern and temperature data. A drought risk score is computed from the Standardised Precipitation Index, groundwater decline and storage deficit. The forecast surplus and the estimated deficits are then passed to a linear programming optimiser that recommends how much water to move through existing canals, link channels and pumping schemes while respecting capacity, flood cushion and minimum environmental flow constraints.","印度许多地区在同一年内既遭遇洪水又面临干旱，有时两者相距仅几百公里。在季风强降水期间，一个流域的水库为保护大坝而泄放大量水量，其中大部分流入海洋，而邻近流域的各区在几个月后却面临饮用水和灌溉用水短缺。可用于管理这种失衡的数据——包括降雨记录、水库蓄水量、河流水位和洪水范围——由不同机构分别收集，鲜有综合分析。本文提出Aqua Rescue，一个数据管道与决策支持系统，将上述来源连接起来，以规划将盈余水重新分配至易旱地区。该管道摄入来自雨量计网络和格点产品的日降雨量、水资源部门公报中的水库水位与泄放量、水文站的河流流量、观测井的地下水位，以及由卫星雷达影像提取的洪水范围图。每个数据源均经过清洗、转换为统一单位，并映射至流域、子流域、水库和区的共享空间框架。一个经过整理的数据仓库保存每个水库和区的每日历史记录与当前状态，数据质量检查可捕捉公报缺失、单位错误以及蓄水量值的突然非现实跳变。机器学习模型以三种方式使用这些整理后的数据。长短期记忆网络（Long Short-Term Memory network）根据近期降雨、上游流量和流域土壤湿度预报未来十四天的水库入库流量。梯度提升模型（gradient boosting model）利用人口、种植模式和温度数据估算各区的生活、灌溉和工业需水量。干旱风险评分由标准化降水指数（Standardised Precipitation Index）、地下水下降量和蓄水亏缺计算得出。随后，预报盈余量与估算亏缺量被输入线性规划优化器，该优化器在尊重输水能力、防洪库容和最小环境流量约束的前提下，推荐通过现有渠道、连接河道和泵站方案输送多少水量。","International Journal of Engineering Research and Science & Technology","2026-10-08T00:00:00Z",77,{"impact":121,"substance":107,"depth":121,"authority":13,"freshness":109,"relevant":21,"comment":285},"面向印度流域的水数据融合与智能调配决策支持系统，方法链条完整、数据源多元，对农业抗旱与水资源管理有参考价值，但属境外区域性研究，公共影响层级有限。",[287],{"name":281,"url":278},[27,28,289,290,291],"智慧水利","水资源调度","抗旱减灾",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":294},{"candidates":295,"agricultural_evidence":14,"reason":69},[296,301,305,309,313],{"code":133,"score":108,"supported":41,"title":297,"abstract":299,"tags":300},[298],"drought",[137,298],[],{"code":39,"score":13,"supported":41,"title":302,"abstract":303,"tags":304},[],[28,43,124],[28],{"code":145,"score":109,"supported":41,"title":306,"abstract":307,"tags":308},[],[228,148,216],[],{"code":52,"score":53,"supported":41,"title":310,"abstract":311,"tags":312},[],[56,57],[],{"code":60,"score":21,"supported":14,"title":314,"abstract":315,"tags":316},[],[],[27],[318,319],"Aqua Rescue 水资源调度","印度 洪水 干旱 水库调度","AquaRescue水资源调度-4668",{"doi":9,"openalex_id":322,"authors":323,"venue":281,"cited_by_count":85,"oa_url":326,"card":327,"direction":331,"ingested_from":93},"W7221299254",[324],{"name":325,"orcid":9},"Mr. R. Ramu,  Golla Indu Prasanna,  Mallavalap Divya Reddy,  Boddapati Manjunadh,  Pembarthi Rohith","https:\u002F\u002Fijerst.org\u002Findex.php\u002Fijerst\u002Farticle\u002Fdownload\u002F4739\u002F4377",{"tldr":328,"method":329,"finding":330,"direction":331,"opportunity":332},"构建Aqua Rescue数据管道与决策系统，将洪水、降雨和水库数据整合，优化调水以缓解干旱。","整合多源数据，用LSTM预测入库流量、梯度提升估需水、线性规划优化调水。","系统能连接分散数据，预测盈余与亏缺，在约束下推荐跨区调水方案。","智慧农业 \u002F 农业物联网","可探索实时物联网数据同化与多目标优化，提升跨流域调水的动态响应与公平性。","2026-10-11T23:30:15.965738Z",{"id":335,"title":336,"url":337,"summary":338,"summary_zh":339,"content":9,"source_name":340,"source_url":337,"published_at":341,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":342,"score_detail":343,"sources":345,"tags":347,"primary_topic":351,"secondary_topics":356,"classification":357,"search_phrases":376,"slug":379,"view_count":380,"doi":381,"paper":382,"created_at":398},4588,"Integrating terrestrial and marine remote sensing indicators to estimate subnational economic output","https:\u002F\u002Fdoi.org\u002F10.1080\u002F01431161.2026.2743115","Subnational economic data remain scarce across much of the Global South, particularly in fragmented island and coastal geographies, thereby constraining the capacity of researchers and policymakers to monitor local economic conditions. This study proposes and empirically evaluates a four-proxy remote sensing framework for subnational gross domestic product (GDP) estimation. The framework extends the established Night-time Lights (NTL)–Normalised Difference Vegetation Index (NDVI)–Forest Loss (FL) approach by incorporating sea surface Chlorophyll-a (CHLA) as a marine fisheries proxy. This achieves full proxy coverage across the non-agriculture, forestry, and fisheries sector through NTL, agriculture through NDVI, forestry through FL, and marine fisheries through CHLA. The empirical analysis employs Multiscale Geographically Weighted Regression (MGWR) and pooled ordinary least squares (OLS) across 102 regencies and cities in Sulawesi and Maluku, eastern Indonesia, over 2015–2024, with a province-level panel extending to 2002–2024. The stepwise MGWR R2 rises from 0.468 (NTL only) to 0.543 (NTL, NDVI, and FL) to 0.561 (full model), with a pooled Pearson correlation of 0.760. CHLA is positive and significant at both spatial scales after conditioning on all terrestrial proxies, confirmed by OLS coefficients of 0.029 at the regency\u002Fcity level and 0.148 at the province level, significant at the 0.1% and 1% levels respectively. All proxy relationships replicate in direction and significance across scales and over the 23-year panel. The framework provides a freely replicable tool for subnational economic monitoring in data-scarce coastal and island settings, with direct applicability to marine-dependent primary sector economies globally.","在全球南方的大部分地区，尤其是碎片化的岛屿和沿海地理区域，地方经济数据仍然稀缺，从而制约了研究者和政策制定者监测地方经济状况的能力。本研究提出并实证评估了一个用于地方国内生产总值（GDP）估算的四代理变量遥感框架。该框架在已有的夜间灯光（NTL）—归一化植被指数（NDVI）—森林损失（FL）方法基础上，引入海表叶绿素a（CHLA）作为海洋渔业代理变量。由此实现了对非农、林业和渔业部门的代理变量全覆盖：NTL对应非农部门，NDVI对应农业，FL对应林业，CHLA对应海洋渔业。实证分析采用多尺度地理加权回归（MGWR）和混合普通最小二乘法（OLS），覆盖印度尼西亚东部苏拉威西和马鲁古的102个县和市，时间范围为2015—2024年，并辅以延伸至2002—2024年的省级面板数据。逐步MGWR的R²从0.468（仅NTL）升至0.543（NTL、NDVI和FL）再升至0.561（全模型），混合皮尔逊相关系数为0.760。在控制所有陆地代理变量后，CHLA在两个空间尺度上均为正向且显著，OLS系数在县\u002F市级为0.029、省级为0.148，分别在0.1%和1%水平上显著。所有代理变量关系在不同尺度和23年面板期间在方向和显著性上均得到重复验证。该框架为数据稀缺的沿海和岛屿地区的地方经济监测提供了一个可自由复制的工具，并可直接适用于全球依赖海洋的初级产业经济体。","International Journal of Remote Sensing","2026-10-09T00:00:00Z",81,{"impact":121,"substance":107,"depth":121,"authority":108,"freshness":109,"relevant":21,"comment":344},"将叶绿素a纳入遥感代理框架估算次国家级GDP，方法新颖、数据扎实，对数据稀缺沿海岛屿地区的农业与渔业经济监测有直接参考价值。",[346],{"name":340,"url":337},[26,27,348,349,350],"遥感监测","渔业经济","GDP估算",{"code":60,"slug":352,"name":353,"path":354,"parent_code":355},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":222,"locked":14,"version":34,"method":35,"evidence":358},{"candidates":359,"agricultural_evidence":41},[360,366,372],{"code":60,"score":206,"supported":41,"title":361,"abstract":363,"tags":365},[362],"remote sensing",[364,362],"遥感",[27,348],{"code":367,"score":74,"supported":41,"title":368,"abstract":369,"tags":371},"D",[],[370],"渔业",[],{"code":65,"score":21,"supported":14,"title":373,"abstract":374,"tags":375},[],[],[26],[377,378],"苏拉威西 马鲁古 遥感 GDP","叶绿素a 海洋渔业 遥感","苏拉威西马鲁古遥感GDP-4588",2,"10.1080\u002F01431161.2026.2743115",{"doi":381,"openalex_id":383,"authors":384,"venue":340,"cited_by_count":85,"oa_url":9,"card":393,"direction":91,"ingested_from":93},"W7221189467",[385,388,390],{"name":386,"orcid":387},"Laurenz Thiele","https:\u002F\u002Forcid.org\u002F0009-0009-9294-1337",{"name":389,"orcid":9},"Amanus Khalifafilardy Yunus",{"name":391,"orcid":392},"Rahmatia","https:\u002F\u002Forcid.org\u002F0009-0009-7550-9243",{"tldr":394,"method":395,"finding":396,"direction":91,"opportunity":397},"提出融合陆地与海洋遥感指标的四代理框架，估算印尼东部次国家级GDP。","用夜间灯光、NDVI、森林损失与叶绿素a，结合MGWR和OLS分析102个县市。","加入叶绿素a后模型R²从0.543升至0.561，海洋渔业代理显著提升经济估算精度。","可将海洋遥感代理拓展至其他沿海地区，并耦合渔业产量与贸易数据验证经济监测普适性。","2026-10-10T23:30:28.117529Z",{"id":400,"title":401,"url":402,"summary":403,"summary_zh":404,"content":9,"source_name":202,"source_url":402,"published_at":405,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":406,"sources":408,"tags":410,"primary_topic":414,"secondary_topics":418,"classification":419,"search_phrases":446,"slug":449,"view_count":380,"doi":450,"paper":451,"created_at":470},4435,"Land Use Change, Flood Exposure, and Vegetation Stress in the Chi River Basin, Northeast Thailand: A Multi-Temporal Remote Sensing and Machine Learning Assessment","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu181910188","Climate change has intensified hydrological extremes in Southeast Asia, yet the relationships between land use change, flood exposure, and vegetation stress remain poorly understood in tropical floodplain environments. This study assessed land use dynamics, flood exposure, and vegetation stress in the Upper Chi River Basin, Northeast Thailand, using multi-temporal remote sensing datasets spanning 2015–2024, official land use data from the Land Development Department (LDD), and machine learning approaches, including Random Forest classification of binary flood occurrence, SHAP analysis, and spatial statistics. Agricultural land dominated the landscape (84.2% in 2023), with 11.0% land use change occurring between 2015 and 2023, primarily agricultural conversion from forest (38.6% of Forest Area converted) and water body (30.0% of Water Body converted). Flood frequency was highest in areas classified as Water Bodies (0.38 events) and Agricultural Areas (0.55 events), while Forest Areas showed the greatest resilience (0.05 events). Random Forest classification of flood occurrence achieved an overall accuracy of 0.920 and AUC-ROC of 0.905, with DEM emerging as the dominant predictor in both Random Forest importance (0.435) and mean absolute SHAP (0.308). Vegetation stress affected 21.1% of the basin, with 59.2% of points showing an NDVI decline greater than 0.02 and 33.3% falling below the VCI \u003C 0.4 drought threshold. Four sensitivity classes were identified: Low (66.4%), Moderate (19.2%), High (12.4%), and Very High (2.0%), with Very High Sensitivity concentrated along the Chi River corridor in low-lying areas (mean DEM = 146.0 m). Moran’s I confirmed strong spatial clustering of flood frequency (I = 0.787) and sensitivity class (I = 0.534), highlighting the need for spatial statistical approaches. The findings support elevation-based land use zoning, forest conservation, and climate-resilient agricultural practices to enhance flood resilience and contribute to Sustainable Development Goals 2 (Zero Hunger), 11 (Sustainable Cities), 13 (Climate Action), and 15 (Life on Land).","气候变化加剧了东南亚的水文极端事件，但在热带洪泛平原环境中，土地利用变化、洪水暴露与植被胁迫之间的关系仍缺乏深入认识。本研究利用2015—2024年多时相遥感数据集、泰国土地发展厅（LDD）的官方土地利用数据以及机器学习方法（包括对二元洪水发生事件的随机森林分类、SHAP分析和空间统计），评估了泰国东北部奇河上游流域的土地利用动态、洪水暴露和植被胁迫。农业用地在景观中占主导地位（2023年为84.2%），2015—2023年间土地利用变化率为11.0%，主要表现为农业用地扩张导致的林地转换（38.6%的林地面积被转换）和水体转换（30.0%的水体面积被转换）。洪水频率在水体分类区域（0.38次）和农业用地分类区域（0.55次）最高，而林地表现出最强的恢复力（0.05次）。洪水发生事件的随机森林分类总体精度达到0.920，AUC-ROC为0.905，其中DEM在随机森林重要性（0.435）和平均绝对SHAP值（0.308）中均为最主要的预测因子。植被胁迫影响了流域21.1%的区域，59.2%的样点NDVI下降幅度超过0.02，33.3%的样点低于VCI \u003C 0.4的干旱阈值。研究识别出四个敏感性等级：低敏感（66.4%）、中等敏感（19.2%）、高敏感（12.4%）和极高敏感（2.0%），其中极高敏感区集中在奇河沿岸低洼地带（平均DEM = 146.0 m）。Moran's I证实了洪水频率（I = 0.787）和敏感性等级（I = 0.534）具有强烈的空间聚集性，凸显了空间统计方法的必要性。研究结果支持基于海拔的土地利用分区、森林保护以及气候适应性农业实践，以增强洪水恢复力，并助力实现可持续发展目标2（零饥饿）、11（可持续城市）、13（气候行动）和15（陆地生物）。","2026-10-07T00:00:00Z",{"impact":17,"substance":107,"depth":121,"authority":207,"freshness":109,"relevant":21,"comment":407},"基于多时相遥感与机器学习的流域土地利用—洪涝—植被胁迫评估，方法扎实、数据翔实，对农业防灾与气候韧性有参考价值，但属区域性研究，公共影响有限。",[409],{"name":202,"url":402},[26,28,348,411,412,413],"土地利用","洪涝风险","植被胁迫",{"code":355,"slug":415,"name":416,"path":417,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":420,"locked":14,"version":34,"method":35,"evidence":421},"partial",{"candidates":422,"agricultural_evidence":41,"reason":445},[423,427,431,436,441],{"code":39,"score":40,"supported":41,"title":424,"abstract":425,"tags":426},[43],[28,43],[28],{"code":60,"score":40,"supported":41,"title":428,"abstract":429,"tags":430},[362],[364,362],[348],{"code":133,"score":109,"supported":41,"title":432,"abstract":433,"tags":435},[],[136,434,137,138,298],"气候适应",[],{"code":437,"score":21,"supported":14,"title":438,"abstract":439,"tags":440},"H6",[],[],[411],{"code":65,"score":21,"supported":14,"title":442,"abstract":443,"tags":444},[],[],[26],"一级领域明确，二级方向需要细分",[447,448],"泰国 Chi River 流域 遥感","土地利用变化 洪涝暴露 植被胁迫","泰国ChiRiver流域遥感-4435","10.3390\u002Fsu181910188",{"doi":450,"openalex_id":452,"authors":453,"venue":202,"cited_by_count":85,"oa_url":402,"card":465,"direction":91,"ingested_from":93},"W7220850940",[454,456,459,462],{"name":455,"orcid":9},"Jiradech Majandang",{"name":457,"orcid":458},"Patiwat Littidej","https:\u002F\u002Forcid.org\u002F0000-0002-1024-547X",{"name":460,"orcid":461},"Benjamabhorn Pumhirunroj","https:\u002F\u002Forcid.org\u002F0009-0009-6607-5594",{"name":463,"orcid":464},"D. C. Slack","https:\u002F\u002Forcid.org\u002F0000-0003-0324-2163",{"tldr":466,"method":467,"finding":468,"direction":91,"opportunity":469},"用多时相遥感和机器学习评估泰国栖河流域土地利用变化、洪水暴露与植被胁迫的关系。","2015–2024年多时相遥感、LDD土地利用数据、随机森林、SHAP与空间统计","农地占84.2%，洪水频发于农地和水体，21.1%流域植被受胁迫，DEM是洪水主导因子。","可结合高分辨率时序遥感与作物模型，量化洪水胁迫对热带平原农业产量的级联影响。","2026-10-08T23:30:29.519607Z",{"id":472,"title":473,"url":474,"summary":475,"summary_zh":9,"content":9,"source_name":476,"source_url":474,"published_at":477,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":478,"score_detail":479,"sources":481,"tags":483,"primary_topic":9,"secondary_topics":486,"classification":487,"search_phrases":506,"slug":509,"view_count":380,"doi":510,"paper":511,"created_at":519},4308,"GIS, Remote Sensing and Machine Learning Applications for Forest Fire Mapping, Susceptibility Assessment and Risk Analysis: A Systematic Review","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11233692\u002Fv1","GIS, Remote Sensing and Machine Learning Applications for Forest Fire Mapping, Susceptibility Assessment and Risk Analysis: A Systematic Review。Research Square","Research Square","2026-10-05T00:00:00Z",63,{"impact":20,"substance":121,"depth":206,"authority":17,"freshness":109,"relevant":21,"comment":480},"系统综述梳理遥感与机器学习在森林火灾制图与风险评估中的应用，对林业信息化与防灾有参考价值，但属综述类论文、来源为预印本平台，权威性一般。",[482],{"name":476,"url":474},[28,364,29,484,485],"森林防火","风险评估",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":488},{"candidates":489,"agricultural_evidence":14,"reason":69},[490,494,498,502],{"code":39,"score":20,"supported":41,"title":491,"abstract":492,"tags":493},[43],[43],[28],{"code":60,"score":20,"supported":41,"title":495,"abstract":496,"tags":497},[362],[362],[364],{"code":47,"score":20,"supported":41,"title":499,"abstract":500,"tags":501},[29],[29],[29],{"code":133,"score":21,"supported":14,"title":503,"abstract":504,"tags":505},[],[],[484],[507,508],"森林火灾 遥感 机器学习","GIS 森林火险 评估","森林火灾遥感机器学习-4308","10.21203\u002Frs.3.rs-11233692\u002Fv1",{"doi":510,"openalex_id":512,"authors":513,"venue":476,"cited_by_count":85,"oa_url":518,"card":9,"direction":91,"ingested_from":93},"W7220368159",[514,516],{"name":515,"orcid":9},"Lucius Malalu",{"name":517,"orcid":9},"Henry Chinthuli","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-11233692\u002Flatest.pdf","2026-10-06T23:30:19.935677Z"]