[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4232":3,"related-4232":128},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":84,"slug":87,"view_count":88,"doi":89,"paper":90,"created_at":127},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。",null,"Scientific Reports","2026-10-03T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,22,17,14,9,1,"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。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业遥感","机器学习","GIS","雨水收集","地下水管理",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":83},[39,48,55,63,71,78],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":47},"I2",18,true,[44],"machine learning",[28,44,46],"decision support",[28],{"code":49,"score":13,"supported":42,"title":50,"abstract":51,"tags":54},"I4",[],[52,29,53],"地理信息","geographic information",[29],{"code":56,"score":21,"supported":42,"title":57,"abstract":58,"tags":62},"H7",[],[59,60,61],"气候变化","干旱","climate change",[],{"code":64,"score":65,"supported":42,"title":66,"abstract":67,"tags":70},"H2",6,[],[68,69],"土壤","soil",[],{"code":72,"score":65,"supported":42,"title":73,"abstract":74,"tags":77},"H3",[],[75,76],"水资源","water resource",[],{"code":79,"score":22,"supported":14,"title":80,"abstract":81,"tags":82},"I3",[],[],[27],"农业相关性需要复核",[85,86],"Jaipur 雨水收集 选址","XGBoost AHP 地下水补给","Jaipur雨水收集选址-4232",0,"10.1038\u002Fs41598-026-72943-8",{"doi":89,"openalex_id":91,"authors":92,"venue":10,"cited_by_count":88,"oa_url":119,"card":120,"direction":124,"ingested_from":126},"W7218709806",[93,96,98,101,103,105,107,109,111,113,116],{"name":94,"orcid":95},"Agradeep Mohanta","https:\u002F\u002Forcid.org\u002F0000-0002-9369-3445",{"name":97,"orcid":9},"Ameet Yadav",{"name":99,"orcid":100},"Dharmendra Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8528-8637",{"name":102,"orcid":9},"Sultan Singh",{"name":104,"orcid":9},"Shuchi Mishra",{"name":106,"orcid":9},"Kanwarpreet Singh",{"name":108,"orcid":9},"Abhishek Sharma",{"name":110,"orcid":9},"Amenjor Senagah",{"name":112,"orcid":9},"Aditya Kumar Tiwary",{"name":114,"orcid":115},"Chandni Thakur","https:\u002F\u002Forcid.org\u002F0000-0001-8976-2738",{"name":117,"orcid":118},"Mohamed A. Mattar","https:\u002F\u002Forcid.org\u002F0000-0002-7506-3036","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-72943-8_reference.pdf",{"tldr":121,"method":122,"finding":123,"direction":124,"opportunity":125},"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。","农业遥感与作物表型","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。","openalex","2026-10-05T23:30:25.173949Z",{"total":65,"page":22,"page_size":65,"items":129},[130,196,275,334,386,464],{"id":131,"title":132,"url":133,"summary":134,"summary_zh":135,"content":9,"source_name":136,"source_url":133,"published_at":137,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":138,"score_detail":139,"sources":143,"tags":145,"primary_topic":9,"secondary_topics":148,"classification":149,"search_phrases":174,"slug":177,"view_count":178,"doi":179,"paper":180,"created_at":195},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。","Turkish Journal of Remote Sensing and GIS","2026-09-24T00:00:00Z",65,{"impact":17,"substance":140,"depth":19,"authority":141,"freshness":17,"relevant":22,"comment":142},20,12,"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。",[144],{"name":136,"url":133},[146,27,28,29,147],"数字乡村","滑坡风险",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":150},{"candidates":151,"agricultural_evidence":14,"reason":83},[152,157,161,165,169],{"code":40,"score":153,"supported":42,"title":154,"abstract":155,"tags":156},15,[44],[28,44],[28],{"code":49,"score":141,"supported":42,"title":158,"abstract":159,"tags":160},[29],[29],[29],{"code":64,"score":65,"supported":42,"title":162,"abstract":163,"tags":164},[],[68,69],[],{"code":79,"score":22,"supported":14,"title":166,"abstract":167,"tags":168},[],[],[27],{"code":170,"score":22,"supported":14,"title":171,"abstract":172,"tags":173},"I6",[],[],[146],[175,176],"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":179,"openalex_id":181,"authors":182,"venue":136,"cited_by_count":88,"oa_url":189,"card":190,"direction":124,"ingested_from":126},"W7214227863",[183,186],{"name":184,"orcid":185},"Albert Iradukunda","https:\u002F\u002Forcid.org\u002F0009-0001-6899-7615",{"name":187,"orcid":188},"Kaan Ozgun","https:\u002F\u002Forcid.org\u002F0000-0002-3853-1400","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5606819",{"tldr":191,"method":192,"finding":193,"direction":124,"opportunity":194},"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。","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。","2026-09-26T23:30:32.763631Z",{"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":88,"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":41,"depth":206,"authority":207,"freshness":21,"relevant":22,"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":72,"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":35,"method":36,"evidence":223},"classified",{"candidates":224,"agricultural_evidence":42},[225,231,235],{"code":72,"score":41,"supported":42,"title":226,"abstract":227,"tags":230},[76],[228,75,216,76,229],"灌溉","evapotranspiration",[212],{"code":40,"score":22,"supported":14,"title":232,"abstract":233,"tags":234},[],[],[28],{"code":79,"score":22,"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":88,"oa_url":199,"card":268,"direction":273,"ingested_from":126},"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":124,"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":88,"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":41,"substance":18,"depth":41,"authority":13,"freshness":21,"relevant":22,"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":34,"locked":14,"version":35,"method":36,"evidence":294},{"candidates":295,"agricultural_evidence":14,"reason":83},[296,301,305,309,313],{"code":56,"score":20,"supported":42,"title":297,"abstract":299,"tags":300},[298],"drought",[60,298],[],{"code":40,"score":13,"supported":42,"title":302,"abstract":303,"tags":304},[],[28,44,46],[28],{"code":72,"score":21,"supported":42,"title":306,"abstract":307,"tags":308},[],[228,75,216],[],{"code":64,"score":65,"supported":42,"title":310,"abstract":311,"tags":312},[],[68,69],[],{"code":79,"score":22,"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":88,"oa_url":326,"card":327,"direction":331,"ingested_from":126},"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":9,"content":9,"source_name":339,"source_url":337,"published_at":340,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":341,"score_detail":342,"sources":344,"tags":346,"primary_topic":9,"secondary_topics":350,"classification":351,"search_phrases":371,"slug":374,"view_count":375,"doi":376,"paper":377,"created_at":385},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":141,"substance":41,"depth":206,"authority":17,"freshness":21,"relevant":22,"comment":343},"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。",[345],{"name":339,"url":337},[28,347,29,348,349],"遥感","森林防火","风险评估",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":352},{"candidates":353,"agricultural_evidence":14,"reason":83},[354,358,363,367],{"code":40,"score":141,"supported":42,"title":355,"abstract":356,"tags":357},[44],[44],[28],{"code":79,"score":141,"supported":42,"title":359,"abstract":361,"tags":362},[360],"remote sensing",[360],[347],{"code":49,"score":141,"supported":42,"title":364,"abstract":365,"tags":366},[29],[29],[29],{"code":56,"score":22,"supported":14,"title":368,"abstract":369,"tags":370},[],[],[348],[372,373],"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",2,"10.21203\u002Frs.3.rs-11233692\u002Fv1",{"doi":376,"openalex_id":378,"authors":379,"venue":339,"cited_by_count":88,"oa_url":384,"card":9,"direction":124,"ingested_from":126},"W7220368159",[380,382],{"name":381,"orcid":9},"Lucius Malalu",{"name":383,"orcid":9},"Henry Chinthuli","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-11233692\u002Flatest.pdf","2026-10-06T23:30:19.935677Z",{"id":387,"title":388,"url":389,"summary":390,"summary_zh":391,"content":9,"source_name":392,"source_url":389,"published_at":393,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":394,"score_detail":395,"sources":397,"tags":399,"primary_topic":403,"secondary_topics":404,"classification":413,"search_phrases":444,"slug":447,"view_count":375,"doi":448,"paper":449,"created_at":463},3804,"Evaluating Reference Evapotranspiration and Soil Moisture as Predictors for Machine Learning-Based Actual Evapotranspiration Estimation: Model Performance and Explainability","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fatmos17100941","Accurate estimation of actual evapotranspiration (ETa) is essential for sustainable water resources management and agricultural planning. This study investigated how the availability of reference evapotranspiration (ET0) and soil moisture (SM) affects ETa prediction performance and predictor importance using Random Forest (RF), Bagging Trees (BT), Least Squares Boosting (LSBoost), Generalized Additive Models (GAM), and Multiple Linear Regression (MLR). Global solar radiation (Rs), land surface temperature (LST), normalized difference vegetation index (NDVI), and SM were evaluated under two primary scenarios, with and without ET0. Models were developed using 80% of the data, with five-fold cross-validation conducted within the training subset, and final performance was evaluated on an independent 20% test subset. Model interpretability was assessed using SHAP, Permutation Feature Importance (PFI), Partial Dependence Plot (PDP), and temporal signed-SHAP analyses, while an additional SM-ablation experiment quantified the incremental predictive contribution of soil moisture. In Scenario I, ET0 was the dominant predictor, and RF and BT achieved the highest independent-test performance (R2 = 0.875; RMSE = 0.398–0.399 mm day−1). Excluding ET0 reduced predictive performance, with RF, LSBoost, and BT achieving R2 values of approximately 0.80 in Scenario II, while the predictor-importance structure shifted primarily toward Rs, followed by SM, LST, and NDVI. Removal of SM further reduced performance in both scenarios, with substantially greater deterioration when ET0 was unavailable: R2 decreased by 0.025–0.044 in Scenario I and by 0.051–0.099 in Scenario II. Under the SM-excluded Scenario I configuration, which more closely aligned the predictor information with previous ANN- and SAFER-based studies, R2 values ranged from 0.820 to 0.832, indicating that differences in ETa prediction performance cannot be attributed solely to model structure but also depend strongly on predictor information content. Overall, ET0 provides substantial atmospheric-demand information for ETa prediction, whereas Rs assumes the dominant predictive role, and SM provides particularly important complementary information when ET0 is unavailable. The combined performance, ablation, and explainability analyses demonstrate the importance of considering predictor composition together with model structure when developing and comparing ETa estimation approaches.","准确估算实际蒸散发（ETa）对于可持续水资源管理和农业规划至关重要。本研究探讨了参考蒸散发（ET0）和土壤水分（SM）的可用性如何影响ETa预测性能及预测因子重要性，采用了随机森林（RF）、Bagging Trees（BT）、最小二乘提升（LSBoost）、广义加性模型（GAM）和多元线性回归（MLR）方法。在全球太阳辐射（Rs）、地表温度（LST）、归一化差异植被指数（NDVI）和SM的条件下，评估了包含和不包含ET0两种主要情景。模型使用80%的数据进行开发，在训练子集内进行五折交叉验证，最终性能在独立的20%测试子集上评估。模型可解释性通过SHAP、排列特征重要性（PFI）、偏依赖图（PDP）和时间符号SHAP分析进行评估，同时通过额外的SM消融实验量化了土壤水分的增量预测贡献。在情景I中，ET0是主导预测因子，RF和BT取得了最高的独立测试性能（R2 = 0.875；RMSE = 0.398–0.399 mm day−1）。排除ET0降低了预测性能，在情景II中RF、LSBoost和BT的R2值约为0.80，同时预测因子重要性结构主要转向Rs，其次是SM、LST和NDVI。去除SM进一步降低了两种情景下的性能，且在ET0不可用时性能下降幅度更大：情景I中R2下降了0.025–0.044，情景II中下降了0.051–0.099。在排除SM的情景I配置下（该配置使预测因子信息更接近此前的ANN和SAFER研究），R2值范围为0.820至0.832，表明ETa预测性能的差异不能仅归因于模型结构，还强烈依赖于预测因子信息含量。总体而言，ET0为ETa预测提供了大量大气需求信息，而Rs承担了主导预测作用，SM在ET0不可用时提供了特别重要的补充信息。综合性能、消融和可解释性分析表明，在开发和比较ETa估算方法时，需将预测因子组成与模型结构一并考虑。","Atmosphere","2026-09-27T00:00:00Z",73,{"impact":141,"substance":18,"depth":41,"authority":207,"freshness":17,"relevant":22,"comment":396},"方法对比与可解释性分析扎实，对农业水资源管理和灌溉决策有参考价值，但属专业论文，公共影响有限。",[398],{"name":392,"url":389},[400,27,28,401,402],"智慧农业","土壤墒情","蒸散发估算",{"code":72,"slug":216,"name":217,"path":218,"parent_code":219},[405,408],{"code":64,"slug":69,"name":406,"path":407,"parent_code":219},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"code":40,"slug":409,"name":410,"path":411,"parent_code":412},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":222,"locked":14,"version":35,"method":36,"evidence":414},{"candidates":415,"agricultural_evidence":42},[416,421,425,429,435,440],{"code":72,"score":19,"supported":42,"title":417,"abstract":418,"tags":420},[229],[75,419,229],"蒸散发",[],{"code":64,"score":153,"supported":42,"title":422,"abstract":423,"tags":424},[69],[68,69],[401],{"code":40,"score":21,"supported":42,"title":426,"abstract":427,"tags":428},[44],[],[28],{"code":430,"score":178,"supported":42,"title":431,"abstract":432,"tags":434},"J1",[],[433],"农业规划",[],{"code":436,"score":22,"supported":14,"title":437,"abstract":438,"tags":439},"I1",[],[],[400],{"code":79,"score":22,"supported":14,"title":441,"abstract":442,"tags":443},[],[],[27],[445,446],"参考蒸散发 土壤水分 机器学习","ET0 实际蒸散发 随机森林","参考蒸散发土壤水分机器学习-3804","10.3390\u002Fatmos17100941",{"doi":448,"openalex_id":450,"authors":451,"venue":392,"cited_by_count":88,"oa_url":389,"card":457,"direction":461,"ingested_from":126},"W7214588993",[452,455],{"name":453,"orcid":454},"Halil Karahan","https:\u002F\u002Forcid.org\u002F0000-0001-5346-5686",{"name":456,"orcid":9},"Devrim Alkaya",{"tldr":458,"method":459,"finding":460,"direction":461,"opportunity":462},"评估ET0与土壤湿度对机器学习估算实际蒸散的影响及可解释性。","用RF、BT、LSBoost、GAM、MLR结合SHAP、PFI、PDP及SM消","ET0主导预测，缺失时Rs主导且SM补充价值显著增大。","农业人工智能与决策模型","可探索缺ET0条件下融合遥感与土壤湿度的可解释ETa估算框架。","2026-09-29T23:30:57.729880Z",{"id":465,"title":466,"url":467,"summary":468,"summary_zh":469,"content":9,"source_name":470,"source_url":467,"published_at":393,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":471,"score_detail":472,"sources":474,"tags":476,"primary_topic":479,"secondary_topics":480,"classification":481,"search_phrases":534,"slug":537,"view_count":521,"doi":538,"paper":539,"created_at":560},3677,"A stocktake of opportunities and knowledge gaps in advancing digital agriculture in Quebec","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04697-2","Abstract Sustainable development has become a key priority for the agricultural sector, both globally and in Quebec. Digital agriculture, as an important component of sustainable agricultural systems, represents a promising pathway toward achieving sustainable development goals. However, despite the recognized benefits of digital agriculture, the opportunities, limitations, and research gaps associated with its contribution to sustainable development in Quebec remain insufficiently understood. This study applies a systematic tracking approach to identify applications of digital technologies in Quebec’s agricultural sector and evaluate their potential contributions to provincial sustainable development objectives while highlighting gaps and opportunities for their enhanced deployment. A total of 59 peer-reviewed publications and grey literature reports were identified and analyzed. Overall, 14 categories of digital technologies were documented within Quebec’s agricultural sector. Their representation in the scientific literature was primarily concentrated in three dominant categories: web\u002Fmobile applications and software (31%), machine learning and sensors (14%), and satellite technologies (13%). The identified digital technologies have significant potential to support sustainable development objectives in Quebec agriculture through improved pesticide monitoring, soil health assessment and conservation, fertilizer management optimization, water-use efficiency, and biodiversity conservation. Collectively, these technologies could be combined in 65 distinct ways to support sustainable development goals; however, only 54% of this potential is currently being exploited in Quebec. This highlights substantial opportunities for expanding the role of digital agriculture in addressing sustainability challenges. The study also reveals important knowledge gaps, particularly regarding the social dimensions influencing the diffusion and adoption of digital technologies in agriculture. A limited understanding of the factors affecting Quebec farmers’ adoption decisions remains a major barrier to maximizing the benefits of digital agriculture. Addressing these social and behavioral dimensions will be essential for accelerating the transition toward more sustainable, digitally enabled agricultural systems in Quebec.","摘要 可持续发展已成为全球及魁北克农业部门的重要优先事项。数字农业作为可持续农业系统的重要组成部分，是实现可持续发展目标的一条充满前景的路径。然而，尽管数字农业的益处已得到认可，但其对魁北克可持续发展所作贡献的机遇、局限及研究空白仍未被充分理解。本研究采用系统性追踪方法，识别数字技术在魁北克农业部门中的应用，评估其对省级可持续发展目标的潜在贡献，同时揭示其加强部署的空白与机遇。共识别并分析了59篇同行评审出版物和灰色文献报告。总体而言，魁北克农业部门中记录到14类数字技术。其在科学文献中的呈现主要集中在三个主导类别：网络\u002F移动应用程序与软件（31%）、机器学习与传感器（14%）以及卫星技术（13%）。所识别的数字技术通过改善农药监测、土壤健康评估与保护、肥料管理优化、水资源利用效率以及生物多样性保护，具有支持魁北克农业可持续发展目标的显著潜力。总体而言，这些技术可以65种不同方式组合以支持可持续发展目标；然而，魁北克目前仅开发利用了其中54%的潜力。这凸显了扩大数字农业在应对可持续性挑战方面作用的重大机遇。本研究还揭示了重要的知识空白，特别是影响数字技术在农业中扩散与采纳的社会维度方面。对影响魁北克农民采纳决策的因素了解有限，仍是最大化数字农业效益的主要障碍。解决这些社会与行为维度对于加速魁北克向更可持续、数字化赋能的农业系统转型至关重要。","Discover Sustainability",78,{"impact":206,"substance":18,"depth":41,"authority":207,"freshness":21,"relevant":22,"comment":473},"基于59篇文献的系统梳理，量化了魁北克数字农业技术类别与可持续目标支撑潜力，指出仅54%潜力被利用及农户采纳的社会维度研究缺口，对区域数字农业政策有参考价值。",[475],{"name":470,"url":467},[477,400,27,28,478],"数字农业","农业可持续发展",{"code":40,"slug":409,"name":410,"path":411,"parent_code":412},[],{"status":222,"locked":14,"version":35,"method":36,"evidence":482},{"candidates":483,"agricultural_evidence":42},[484,489,494,501,508,512,519,526,530],{"code":436,"score":206,"supported":42,"title":485,"abstract":487,"tags":488},[486],"digital agriculture",[477,486],[477,400],{"code":40,"score":490,"supported":42,"title":491,"abstract":492,"tags":493},7,[],[28,44],[28],{"code":495,"score":65,"supported":42,"title":496,"abstract":497,"tags":500},"F3",[],[498,499],"肥料","fertilizer",[],{"code":502,"score":65,"supported":42,"title":503,"abstract":504,"tags":507},"F4",[],[505,506],"农药","pesticide",[],{"code":64,"score":65,"supported":42,"title":509,"abstract":510,"tags":511},[],[68,69],[],{"code":513,"score":65,"supported":42,"title":514,"abstract":515,"tags":518},"H6",[],[516,517],"生物多样性","biodiversity",[],{"code":520,"score":521,"supported":42,"title":522,"abstract":523,"tags":525},"H8",4,[],[524],"可持续农业",[478],{"code":72,"score":178,"supported":42,"title":527,"abstract":528,"tags":529},[],[75],[],{"code":79,"score":22,"supported":14,"title":531,"abstract":532,"tags":533},[],[],[27],[535,536],"魁北克 数字农业","魁北克 农业技术 应用","魁北克数字农业-3677","10.1007\u002Fs43621-026-04697-2",{"doi":538,"openalex_id":540,"authors":541,"venue":470,"cited_by_count":88,"oa_url":467,"card":555,"direction":273,"ingested_from":126},"W7214562996",[542,544,547,550,552],{"name":543,"orcid":9},"Sambiani D. Y. Tindjiete",{"name":545,"orcid":546},"Terence Épule Épule","https:\u002F\u002Forcid.org\u002F0000-0002-5756-382X",{"name":548,"orcid":549},"Daniel Etongo","https:\u002F\u002Forcid.org\u002F0000-0002-8237-0843",{"name":551,"orcid":9},"Changhui Peng",{"name":553,"orcid":554},"Paul Célicourt","https:\u002F\u002Forcid.org\u002F0000-0001-9297-6593",{"tldr":556,"method":557,"finding":558,"direction":273,"opportunity":559},"系统盘点魁北克数字农业技术应用及其对可持续发展的贡献与知识空白。","系统追踪59篇同行评议与灰色文献，归类14类数字技术并评估组合潜力。","技术可65种组合支撑可持续发展目标，但仅54%潜力被利用，社会采纳因素研究不足。","可深入研究农户数字技术采纳的社会行为因素，填补魁北克及类似地区扩散机制的研究空白。","2026-09-28T23:30:36.987716Z"]