[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2427":3,"related-2427":124},{"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":78,"slug":81,"view_count":82,"doi":83,"paper":84,"created_at":123},2427,"Machine learning based precipitation modeling using multi satellite data for climate resilient water resource management in Bundelkhand India","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44274-026-01047-x","Precipitation modeling can be improved by using spatially continuous climate data from satellite remote sensing; nevertheless, incorporating heterogeneous sensor-derived variables and understanding machine learning results continue to be significant hurdles. In this work, a multi-source climatic parameter-based satellite-driven machine learning system for precipitation prediction is presented. The dependent variable was precipitation, and the model inputs were satellite-derived predictors such as land surface temperature, atmospheric moisture, surface pressure, wind speed, relative humidity, soil wetness, and temporal indicators. Convolutional Neural Networks (CNN) and Extreme Gradient Boosting (XGBoost), two sophisticated machine learning models, were used to capture multiscale and nonlinear interactions between precipitation and climate factors. Standard statistical measures were used to evaluate the model's performance, and explicable machine learning methods were used to determine the relative significance of the input variables. The findings suggest that both models make good use of satellite-derived climate data, with CNN demonstrating a great capacity to learn intricate feature interactions and XGBoost demonstrating strong predictive ability. With R2 = 0.77, RMSE = 88.79, as well as MAE = 42.06, XGBoost scored far superior than CNN (R2 = 0.60, RMSE = 120.82, MAE = 73.46). According to the interpretability analysis, the main factors influencing precipitation variability are soil wetness, land surface temperature, and atmospheric moisture. The suggested system supports enhanced hydrological forecasting as well as sustainable water resource management by providing a transparent and scalable method for precipitation prediction, especially in areas with limited data. Overall, the findings show that a scalable and efficient framework for precipitation prediction in semi-arid, data-poor areas may be created by combining interpretable machine learning with multi-source Earth observation data. Graphical Abstract","利用卫星遥感提供的空间连续气候数据可以改进降水建模；然而，整合来自不同传感器的异构变量以及理解机器学习结果仍然是重大难题。本研究提出了一种基于多源气候参数的卫星驱动机器学习降水预测系统。因变量为降水，模型输入为卫星衍生的预测因子，包括地表温度、大气湿度、地表气压、风速、相对湿度、土壤湿度和时间指标。研究采用了两种先进的机器学习模型——卷积神经网络（CNN）和极端梯度提升（XGBoost），以捕捉降水与气候因子之间的多尺度和非线性交互作用。使用标准统计指标评估模型性能，并采用可解释机器学习方法确定输入变量的相对重要性。研究结果表明，两种模型均能有效利用卫星衍生的气候数据，其中CNN展现出学习复杂特征交互的强大能力，XGBoost则表现出强劲的预测性能。XGBoost的R² = 0.77、RMSE = 88.79、MAE = 42.06，显著优于CNN（R² = 0.60、RMSE = 120.82、MAE = 73.46）。可解释性分析表明，影响降水变率的主要因素为土壤湿度、地表温度和大气湿度。所提出的系统为降水预测提供了一种透明且可扩展的方法，有助于增强水文预报和可持续水资源管理，尤其在数据稀缺地区。总体而言，研究结果表明，将可解释机器学习与多源地球观测数据相结合，可为半干旱、数据匮乏地区构建一个可扩展且高效的降水预测框架。图形摘要",null,"Discover Environment","2026-09-11T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"基于多源卫星遥感与可解释机器学习构建降水预测框架，方法对比与结论可靠，对半干旱缺数据区水资源管理有参考价值，但属区域性学术成果，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","遥感","气候适应","水资源管理","降水预测",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":77},[39,48,55,62,70],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":47},"H3",15,true,[44],"water resource",[46,44],"水资源",[30],{"code":49,"score":41,"supported":42,"title":50,"abstract":52,"tags":54},"I2",[51],"machine learning",[53,51],"机器学习",[27],{"code":56,"score":57,"supported":42,"title":58,"abstract":59,"tags":61},"I3",7,[],[28,60],"remote sensing",[28],{"code":63,"score":64,"supported":42,"title":65,"abstract":66,"tags":69},"H2",6,[],[67,68],"土壤","soil",[],{"code":71,"score":72,"supported":42,"title":73,"abstract":74,"tags":76},"H7",4,[],[75],"干旱",[29],"农业相关性需要复核",[79,80],"农业人工智能 水资源管理 气候适应 降水预测","农业人工智能 水资源管理","农业人工智能水资源管理气候适应降水预测-2427",0,"10.1007\u002Fs44274-026-01047-x",{"doi":83,"openalex_id":85,"authors":86,"venue":10,"cited_by_count":82,"oa_url":115,"card":116,"direction":120,"ingested_from":122},"W7212224443",[87,90,92,95,97,100,102,105,107,110,112],{"name":88,"orcid":89},"Pavan Kumar","https:\u002F\u002Forcid.org\u002F0000-0003-3653-8163",{"name":91,"orcid":9},"Megha Paul",{"name":93,"orcid":94},"Prashant K. Srivastava","https:\u002F\u002Forcid.org\u002F0000-0002-4155-630X",{"name":96,"orcid":9},"Manmohan Dobriyal",{"name":98,"orcid":99},"Yogeshwar Singh","https:\u002F\u002Forcid.org\u002F0000-0002-3324-9289",{"name":101,"orcid":9},"Manish Srivastav",{"name":103,"orcid":104},"Ajay Singh","https:\u002F\u002Forcid.org\u002F0000-0003-2933-4058",{"name":106,"orcid":9},"Abu Salim",{"name":108,"orcid":109},"Shams Tabrez Siddiqui","https:\u002F\u002Forcid.org\u002F0000-0002-6567-3383",{"name":111,"orcid":9},"Aasif Aftab",{"name":113,"orcid":114},"Benson Turyasingura","https:\u002F\u002Forcid.org\u002F0000-0003-1325-4483","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44274-026-01047-x.pdf",{"tldr":117,"method":118,"finding":119,"direction":120,"opportunity":121},"用多源卫星数据和机器学习预测印度半干旱区降水，XGBoost优于CNN。","CNN与XGBoost，输入LST、湿度、风速等卫星变量，可解释性分析。","XGBoost预测最佳（R²=0.77），土壤湿度、地表温度、大气水汽最关键。","农业遥感与作物表型","可迁移至其他数据稀缺区，融合多源遥感与可解释AI提升水文预报。","openalex","2026-09-14T23:30:25.935081Z",{"total":64,"page":22,"page_size":64,"items":125},[126,199,255,325,404,454],{"id":127,"title":128,"url":129,"summary":130,"summary_zh":131,"content":9,"source_name":132,"source_url":129,"published_at":133,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":134,"score_detail":135,"sources":139,"tags":141,"primary_topic":9,"secondary_topics":144,"classification":145,"search_phrases":167,"slug":170,"view_count":171,"doi":172,"paper":173,"created_at":198},4881,"Mapping the knowledge structure and evolution of artificial intelligence for water reuse and sustainable water management","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02389-4","Artificial intelligence (AI) has become a powerful instrument to solve complex problems related to sustainable water resource management because it allows creating advanced, data-driven modelling, prediction, and optimization of water systems. Although the studies in this sphere have increased quickly, the global scientific tendencies have not been thoroughly examined. This research paper presents a bibliometric review of the literature about AI applications in green water management that was published from 2015 to 2025. The Scopus database was searched with a structured search strategy on bibliographic data, and 3,280 peer-reviewed articles were analyzed. VOSviewer was used to perform bibliometric mapping and network visualization to investigate the trends in publications, most active journals, most impactful authors, contributions of institutions, country-level partnerships, and research clusters. The findings indicate that the publishing activity has grown tremendously in the last ten years, which suggests that there is a growing interest in AI-based solutions to water quality monitoring, hydrological prediction, optimization of wastewater treatment, and smart water management system. China, the United States and India became the most productive nations with the University of Chinese Academy of Sciences and Beijing normal university as some of the top contributing institutions. The analysis of the key words co-occurrence (dominant research themes) was based on machine learning, water-quality prediction, hydrological modelling, remote sensing, and decision-support systems. The co-citation analysis has shown the core studies in machine learning algorithms, including random forests, neural networks, and boosting algorithms, which underpin the present studies in this field. Overall, the results depict the growing role of AI technologies to enhance the effectiveness of water resources management and wastewater treatment. This research offers a clear insight into the intellectual framework and the future research perspective of AI-based environmentally sustainable water management which can be of great value to researchers, policymakers, and practitioners who would wish to come up with innovative and data-based water management solutions.","人工智能（AI）已成为解决可持续水资源管理相关复杂问题的有力工具，因为它能够构建先进的数据驱动模型，实现水系统的预测与优化。尽管该领域的研究迅速增加，但全球科学趋势尚未得到充分审视。本文对2015年至2025年间发表的关于人工智能在绿色水资源管理中应用的文献进行了文献计量学综述。采用结构化检索策略对Scopus数据库中的文献数据进行检索，共分析了3，280篇同行评审论文。使用VOSviewer进行文献计量制图和网络可视化，以探究发文趋势、最活跃期刊、最具影响力作者、机构贡献、国家层面合作及研究聚类。研究结果表明，过去十年间发文活动急剧增长，表明基于人工智能的水质监测、水文预测、废水处理优化和智能水管理系统解决方案日益受到关注。中国、美国和印度成为最高产国家，中国科学院和北京师范大学为贡献最多的机构之一。关键词共现分析（主导研究主题）基于机器学习、水质预测、水文建模、遥感和决策支持系统。共被引分析揭示了机器学习算法的核心研究，包括随机森林、神经网络和提升算法，这些构成了该领域当前研究的基础。总体而言，研究结果描绘了人工智能技术在提升水资源管理和废水处理效能方面日益增长的作用。本研究为基于人工智能的环境可持续水资源管理的知识框架和未来研究视角提供了清晰见解，对希望提出创新性和数据驱动型水资源管理方案的研究人员、政策制定者和实践者具有重要价值。","Discover Artificial Intelligence","2026-10-12T00:00:00Z",67,{"impact":17,"substance":136,"depth":137,"authority":20,"freshness":21,"relevant":22,"comment":138},18,16,"基于3280篇文献的AI水资源管理文献计量综述，方法规范、结论有参考价值，但属学术综述类，产业与政策落地性有限。",[140],{"name":132,"url":129},[27,28,142,30,143],"文献计量","智慧水务",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":146},{"candidates":147,"agricultural_evidence":14,"reason":77},[148,153,157,161],{"code":49,"score":136,"supported":42,"title":149,"abstract":151,"tags":152},[150],"artificial intelligence",[53,51,150],[27],{"code":40,"score":57,"supported":42,"title":154,"abstract":155,"tags":156},[],[46,44],[30],{"code":56,"score":57,"supported":42,"title":158,"abstract":159,"tags":160},[],[28,60],[28],{"code":162,"score":57,"supported":42,"title":163,"abstract":164,"tags":166},"I7",[],[142,165],"bibliometric",[142],[168,169],"AI 水资源管理 文献计量","人工智能 再生水 可持续水管理","AI水资源管理文献计量-4881",2,"10.1007\u002Fs44163-026-02389-4",{"doi":172,"openalex_id":174,"authors":175,"venue":132,"cited_by_count":82,"oa_url":190,"card":191,"direction":197,"ingested_from":122},"W7221506022",[176,179,182,184,186,188],{"name":177,"orcid":178},"Narendra Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5578-3255",{"name":180,"orcid":181},"Mangey Ram Nagar","https:\u002F\u002Forcid.org\u002F0000-0003-3635-3548",{"name":183,"orcid":9},"Isha Dharsandia",{"name":185,"orcid":9},"Ananya Tiwari",{"name":187,"orcid":9},"Santosh Kumar Mishra",{"name":189,"orcid":9},"Mohit Kumar","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44163-026-02389-4.pdf",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"对2015-2025年AI用于水回用与可持续水管理的3280篇文献做文献计量分析，梳理知识结构与演化","Scopus检索3280篇同行评议文献，用VOSviewer做共现与共被引网络可","发文量十年激增，中国、美国、印度领先；主题聚焦机器学习、水质预测、水文建模、遥感与决策支持。","农业人工智能与决策模型","可将AI水管理方法迁移至农业灌溉与面源污染场景，构建农业水-肥-碳协同的智能决策模型。","智慧农业 \u002F 农业物联网","2026-10-14T23:30:10.246538Z",{"id":200,"title":201,"url":202,"summary":203,"summary_zh":204,"content":9,"source_name":205,"source_url":202,"published_at":206,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":207,"score_detail":208,"sources":210,"tags":212,"primary_topic":9,"secondary_topics":214,"classification":215,"search_phrases":231,"slug":234,"view_count":82,"doi":235,"paper":236,"created_at":254},4680,"Groundwater Potential Mapping in Northwestern Nigeria: A Comparison of the Analytic Hierarchy Process and Galileo-Enhanced CAT-XGB","https:\u002F\u002Fdoi.org\u002F10.31223\u002Fx5mv5h","Global water scarcity intensifies the need for high-resolution groundwater assessment tools, yet traditional approaches struggle to reconcile qualitative expert weights with the extensive spatial coverage offered by remote sensing data. This study presents a comparative framework evaluating expert-driven Multi-Criteria Decision Analysis (a ten-layer Analytic Hierarchy Process (AHP)) against data-driven ensemble machine learning for groundwater potential mapping in the geologically complex terrain of Northwestern Nigeria. Standard thematic layers were integrated with embeddings from a pretrained remote sensing foundation model to train ensemble classifiers, with groundwater potential validated against Vertical Electrical Sounding (VES) data. The foundation-model-enhanced CAT-XGB ensemble achieved notable predictive performance, consistently outperforming standalone tree-based classifiers and traditional AHP. Spatial difference mapping revealed that the enhanced ensemble captured critical, localized hydrogeological anomalies smoothed over by expert-driven weighting. Bridging heuristic decision-making with foundation-model-enhanced machine learning significantly improves spatial precision and reliability, potentially providing a field-validated tool for optimizing borehole siting and sustainable aquifer management in data-scarce, geologically complex regions.","全球水资源短缺加剧了对高分辨率地下水评估工具的需求，然而传统方法难以在定性专家权重与遥感数据所提供的广泛空间覆盖之间取得协调。本研究提出一个比较框架，在尼日利亚西北部地质复杂地形区，评估专家驱动的多准则决策分析（十层层次分析法（AHP））与数据驱动的集成机器学习在地下水潜力制图中的表现。研究将标准主题图层与预训练遥感基础模型的嵌入特征相结合以训练集成分类器，并利用垂直电测深（VES）数据对地下水潜力进行验证。经基础模型增强的CAT-XGB集成模型取得了显著的预测性能，持续优于独立的树基分类器和传统AHP。空间差异制图揭示，增强集成模型捕捉到了被专家驱动权重所平滑化的关键局部水文地质异常。将启发式决策与基础模型增强的机器学习相衔接，显著提升了空间精度与可靠性，有望为数据稀缺、地质复杂区域优化钻孔选址和可持续含水层管理提供一种经野外验证的工具。","OpenAlex","2026-10-09T00:00:00Z",69,{"impact":17,"substance":18,"depth":136,"authority":17,"freshness":57,"relevant":22,"comment":209},"将遥感基础模型与集成机器学习用于尼日利亚西北部地下水潜力制图，方法新颖、有实地验证，对缺水地区灌溉与水资源管理有参考价值，但属区域案例研究，公共影响有限。",[211],{"name":205,"url":202},[27,53,28,30,213],"地下水潜力",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":216},{"candidates":217,"agricultural_evidence":14,"reason":77},[218,222,226],{"code":49,"score":21,"supported":42,"title":219,"abstract":220,"tags":221},[],[53,51],[27,53],{"code":56,"score":57,"supported":42,"title":223,"abstract":224,"tags":225},[],[28,60],[28],{"code":40,"score":227,"supported":42,"title":228,"abstract":229,"tags":230},5,[],[46],[213,30],[232,233],"尼日利亚 地下水潜力 遥感","CAT-XGB 地下水 制图","尼日利亚地下水潜力遥感-4680","10.31223\u002Fx5mv5h",{"doi":235,"openalex_id":237,"authors":238,"venue":9,"cited_by_count":82,"oa_url":248,"card":249,"direction":120,"ingested_from":122},"W7221088011",[239,241,243,245],{"name":240,"orcid":9},"Joseph Osumeje",{"name":242,"orcid":9},"Sachet Utekar",{"name":244,"orcid":9},"Morli Li",{"name":246,"orcid":247},"Daniel C. Jones","https:\u002F\u002Forcid.org\u002F0000-0002-8701-4506","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15434\u002Fdownload\u002F26756\u002F",{"tldr":250,"method":251,"finding":252,"direction":120,"opportunity":253},"对比专家驱动AHP与遥感基础模型增强的CAT-XGB集成，用于尼日利亚西北部地下水潜力制图。","十层AHP与预训练遥感基础模型嵌入训练CAT-XGB集成，用垂直电测深数据验证。","基础模型增强的CAT-XGB集成预测性能优于传统AHP和独立树模型，能捕捉局部水文地质异常。","可探索遥感基础模型嵌入与专家知识融合，提升数据稀缺复杂区地下水等农业水资源评估精度。","2026-10-11T23:30:30.328869Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":260,"content":9,"source_name":261,"source_url":258,"published_at":262,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":263,"score_detail":264,"sources":267,"tags":269,"primary_topic":9,"secondary_topics":272,"classification":273,"search_phrases":296,"slug":299,"view_count":171,"doi":300,"paper":301,"created_at":324},4031,"DEVELOPMENT OF A DELTA-BASED XGBOOST MODEL FOR FORECASTING RESERVOIR STORAGE DYNAMICS","https:\u002F\u002Fdoi.org\u002F10.48081\u002Fbtouen3.2026\u002F91-113","Accurately forecasting reservoir water volumes is crucial for climate change adaptation, drought mitigation, and provides a basis for energy planning and management, particularly in continental basins, where hydrological variability poses challenges to traditional modeling. In turn, reduced reservoir inflows limit the water available to hydroelectric power plants for optimal hydroelectric generation. To address this issue, we propose a novel delta-based learning framework using extreme gradient boosting (XGBoost) that forecasts daily volume increments (ΔV) rather than total water volume. The proposed model represents a novel solution where standard machine learning approaches often struggle to capture short-term dynamics due to non-stationary trends in absolute water volume data. The model integrates meteorological and hydrological characteristics of the ERA5 reanalysis lag, is trained on 2019–2022 data, tested on 2023–2025 data, and is adapted to regional specificities. The results demonstrate exceptional performance: the reconstructed volume achieved an R² of 0.983, a Nash–Sutcliffe efficiency (NSE) of 0.983, and a Kling–Gupta efficiency (KGE) of 0.984. Most importantly, the delta-model-based approach reduced the root mean square error (RMSE) by 16 % compared to the baseline direct volume forecasting method, effectively eliminating systematic trend leakage. Performance analysis confirmed the physical dominance of delays in water volume and precipitation integrals. This study confirms that differential dynamics modeling significantly improves the stability and interpretability of forecasts, offering a reproducible and reliable tool. Keywords: reservoir forecasting, delta-based learning, hydrological machine learning, XGBoost, ERA5 reanalysis, multi-horizon prediction, remote sensing, predictive modeling.","准确预测水库水量对于适应气候变化、缓解干旱至关重要，并为能源规划与管理提供依据，尤其是在大陆性流域，水文变异性对传统建模构成挑战。反过来，水库入库流量的减少限制了水电站可用于优化水力发电的水量。为解决这一问题，我们提出了一种基于增量学习的新框架，采用极端梯度提升（XGBoost）预测每日水量增量（ΔV），而非总水量。该模型代表了一种新颖的解决方案，因为标准机器学习方法往往因绝对水量数据中的非平稳趋势而难以捕捉短期动态。该模型整合了ERA5再分析滞后项的气象和水文特征，在2019—2022年数据上训练，在2023—2025年数据上测试，并适应区域特异性。结果表明其性能卓越：重建水量的R²为0.983，纳什—萨特克利夫效率（NSE）为0.983，克林—古普塔效率（KGE）为0.984。最重要的是，基于增量模型的方法与基线直接水量预测方法相比，将均方根误差（RMSE）降低了16%，有效消除了系统性趋势泄漏。性能分析证实了水量和降水积分滞后的物理主导性。本研究证实，差分动态建模显著提高了预测的稳定性和可解释性，提供了一种可重复且可靠的工具。关键词：水库预测，增量学习，水文机器学习，XGBoost，ERA5再分析，多步预测，遥感，预测建模。","Bulletin of Toraighyrov University Energetics series","2026-09-30T00:00:00Z",72,{"impact":17,"substance":265,"depth":136,"authority":17,"freshness":21,"relevant":22,"comment":266},22,"提出基于增量的XGBoost水库蓄水量预测新方法，精度高且可复现，对农业水资源与水电调度有参考价值，但属专业论文、影响面有限。",[268],{"name":261,"url":258},[27,28,30,270,271],"水库调度","水文预报",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":274},{"candidates":275,"agricultural_evidence":14,"reason":77},[276,284,288,292],{"code":71,"score":277,"supported":42,"title":278,"abstract":279,"tags":283},9,[],[280,75,281,282],"气候变化","climate change","drought",[],{"code":49,"score":57,"supported":42,"title":285,"abstract":286,"tags":287},[],[53,51],[27],{"code":56,"score":57,"supported":42,"title":289,"abstract":290,"tags":291},[],[28,60],[28],{"code":40,"score":22,"supported":14,"title":293,"abstract":294,"tags":295},[],[],[30],[297,298],"XGBoost 水库蓄水量 预测","ERA5 再分析 水文预报","XGBoost水库蓄水量预测-4031","10.48081\u002Fbtouen3.2026\u002F91-113",{"doi":300,"openalex_id":302,"authors":303,"venue":261,"cited_by_count":82,"oa_url":258,"card":319,"direction":120,"ingested_from":122},"W7215046343",[304,307,310,313,316],{"name":305,"orcid":306},"Aliya Aubakirova","https:\u002F\u002Forcid.org\u002F0009-0004-6925-6714",{"name":308,"orcid":309},"Alexandr V. Neftissov","https:\u002F\u002Forcid.org\u002F0000-0003-4079-2025",{"name":311,"orcid":312},"Mukhtar Orazbay","https:\u002F\u002Forcid.org\u002F0009-0001-4994-6484",{"name":314,"orcid":315},"Andrii O. Biloshchytskyi","https:\u002F\u002Forcid.org\u002F0000-0001-9548-1959",{"name":317,"orcid":318},"Tetyana Honcharenko","https:\u002F\u002Forcid.org\u002F0000-0003-2577-6916",{"tldr":320,"method":321,"finding":322,"direction":195,"opportunity":323},"提出基于增量学习的XGBoost模型预测水库日蓄水量增量，提升短期动态预报精度。","XGBoost增量学习框架，融合ERA5再分析气象水文滞后特征，2019-202","重建水量R²、NSE、KGE均达0.983以上，RMSE较直接预测降低16%，消除趋势泄漏。","可将增量学习框架迁移至农业灌溉水库与作物需水耦合预测，探索多尺度滞后特征与可解释性。","2026-10-02T23:30:26.711539Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":9,"source_name":331,"source_url":328,"published_at":332,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":333,"score_detail":334,"sources":336,"tags":338,"primary_topic":341,"secondary_topics":346,"classification":356,"search_phrases":375,"slug":378,"view_count":171,"doi":379,"paper":380,"created_at":403},3504,"WaterFormer-MS: A multi-stream deep learning framework for surface water segmentation from satellite imagery","https:\u002F\u002Fdoi.org\u002F10.24850\u002Fj-tyca-18-03-08","Accurate mapping of surface water bodies is essential for dam monitoring, irrigation planning, and sustainable water resource management. Conventional methods based on spectral indices, such as NDWI, can face challenges in complex environments due to spectral ambiguity, seasonal variability, and urban or vegetated surfaces. Deep learning approaches such as U-Net and DeepLabv3+ have improved water-body segmentation; however, accurately delineating fine boundaries and detecting small water bodies remain challenging. To address these limitations, this study proposes WaterFormer-MS, a multi-stream deep learning framework for surface water segmentation from Sentinel-2 imagery. The architecture integrates spectral, geometric, and contextual information through dedicated processing streams and combines the extracted features using a convolutional fusion module enhanced with CBAM attention. This design aims to improve feature representation and support accurate water-body delineation. The proposed model was trained and evaluated using Sentinel-2 imagery from a publicly available Kaggle dataset containing diverse land-cover conditions, including urban, vegetated, and agricultural environments. At 300 epochs, WaterFormer-MS achieved an overall accuracy of 97.4%, a precision of 93.2%, a recall of 94.2%, an F1-score of 93.7%, and an IoU of 89.7%. Within the experimental framework, WaterFormer-MS achieved higher values than the other proposed variants. Comparisons with conventional NDWI-based approaches and published deep learning methods suggest competitive performance; however, these comparisons should be interpreted cautiously because datasets, preprocessing procedures, training protocols, and evaluation settings may differ. The results support the potential of the proposed framework for surface water segmentation and environmental monitoring applications in diverse remote sensing scenarios.","准确绘制地表水体分布对于大坝监测、灌溉规划和水资源可持续管理至关重要。基于NDWI等光谱指数的传统方法在复杂环境中可能因光谱模糊性、季节性变化以及城市或植被覆盖地表而面临挑战。U-Net和DeepLabv3+等深度学习方法改善了水体分割效果，但精确描绘精细边界和检测小型水体仍然具有挑战性。为解决这些局限，本研究提出WaterFormer-MS，一种用于Sentinel-2影像地表水分割的多流深度学习框架。该架构通过专门的处理流整合光谱、几何和上下文信息，并利用经CBAM注意力增强的卷积融合模块将提取的特征进行融合。该设计旨在改善特征表征并支持精确的水体描绘。所提模型使用来自公开Kaggle数据集的Sentinel-2影像进行训练和评估，该数据集包含城市、植被和农业环境等多种土地覆盖条件。在300个训练轮次时，WaterFormer-MS取得了97.4%的总体精度、93.2%的精确率、94.2%的召回率、93.7%的F1分数和89.7%的IoU。在实验框架内，WaterFormer-MS取得了高于其他所提变体的数值。与传统基于NDWI的方法及已发表的深度学习方法进行比较，结果表明其性能具有竞争力；然而，这些比较应谨慎解读，因为数据集、预处理流程、训练方案和评估设置可能存在差异。研究结果支持所提框架在多样化遥感场景中用于地表水分割和环境监测应用的潜力。","Tecnología y Ciencias del Agua","2026-09-24T00:00:00Z",74,{"impact":41,"substance":265,"depth":136,"authority":13,"freshness":277,"relevant":22,"comment":335},"提出多流深度学习框架用于卫星影像地表水提取，精度指标明确，对灌溉规划与水资源监测有参考价值，但属方法类论文，产业影响有限。",[337],{"name":331,"url":328},[27,339,28,30,340],"Sentinel-2","地表水体提取",{"code":49,"slug":342,"name":343,"path":344,"parent_code":345},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[347,352],{"code":40,"slug":348,"name":349,"path":350,"parent_code":351},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"code":56,"slug":353,"name":354,"path":355,"parent_code":345},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":357,"locked":14,"version":35,"method":36,"evidence":358},"classified",{"candidates":359,"agricultural_evidence":42},[360,366,371],{"code":49,"score":41,"supported":42,"title":361,"abstract":363,"tags":365},[362],"deep learning",[364,362],"深度学习",[27],{"code":40,"score":13,"supported":42,"title":367,"abstract":368,"tags":370},[],[369,46,348,44],"灌溉",[30],{"code":56,"score":21,"supported":42,"title":372,"abstract":373,"tags":374},[],[28,60],[339,28],[376,377],"WaterFormer-MS 地表水 分割","Sentinel-2 水体提取 深度学习","WaterFormer-MS地表水分割-3504","10.24850\u002Fj-tyca-18-03-08",{"doi":379,"openalex_id":381,"authors":382,"venue":331,"cited_by_count":82,"oa_url":328,"card":398,"direction":120,"ingested_from":122},"W7214228825",[383,386,389,392,395],{"name":384,"orcid":385},"Ayoub Benali","https:\u002F\u002Forcid.org\u002F0000-0002-8989-755X",{"name":387,"orcid":388},"Yesma Bendaha","https:\u002F\u002Forcid.org\u002F0000-0002-1347-856X",{"name":390,"orcid":391},"Malika Seddik Bouchouicha","https:\u002F\u002Forcid.org\u002F0009-0001-6092-784X",{"name":393,"orcid":394},"Zakaria Bellahcene","https:\u002F\u002Forcid.org\u002F0000-0003-4353-7871",{"name":396,"orcid":397},"Rachid Rimani","https:\u002F\u002Forcid.org\u002F0000-0002-1923-4312",{"tldr":399,"method":400,"finding":401,"direction":120,"opportunity":402},"提出多流深度学习框架WaterFormer-MS，从Sentinel-2影像中精准分割地表水体。","多流架构融合光谱、几何与上下文特征，CBAM注意力卷积融合，Sentinel-2","300轮训练下总体精度97.4%、IoU 89.7%，优于NDWI及对比深度学习方法。","可探索多流框架在农业灌溉水体与小型水塘精细提取中的迁移，并引入时序Sentinel-2提升季节鲁棒性。","2026-09-25T23:30:31.338437Z",{"id":405,"title":406,"url":407,"summary":408,"summary_zh":9,"content":9,"source_name":409,"source_url":407,"published_at":410,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":411,"score_detail":412,"sources":415,"tags":417,"primary_topic":9,"secondary_topics":420,"classification":421,"search_phrases":441,"slug":444,"view_count":22,"doi":445,"paper":446,"created_at":453},2054,"Quantifying Thermoregulation in Niche Construction of Apis mellifera as an Extended Phenotype to Map the Selection Pressure of Volatile Climate Using Hybrid CNN Bi-LSTM Architecture and Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10938207\u002Fv1","Quantifying Thermoregulation in Niche Construction of Apis mellifera as an Extended Phenotype to Map the Selection Pressure of Volatile Climate Using Hybrid CNN Bi-LSTM Architecture and Remote Sensing。Research Square","Research Square","2026-09-08T00:00:00Z",52,{"impact":21,"substance":413,"depth":41,"authority":64,"freshness":277,"relevant":22,"comment":414},14,"以混合CNN-BiLSTM与遥感量化蜜蜂巢域构建的热调节，方法新颖但属预印本、应用面窄，适合主题聚合而非每日精选。",[416],{"name":409,"url":407},[418,27,28,419,29],"智慧农业","蜜蜂",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":422},{"candidates":423,"agricultural_evidence":14,"reason":77},[424,428,432,437],{"code":56,"score":17,"supported":42,"title":425,"abstract":426,"tags":427},[60],[60],[28],{"code":71,"score":22,"supported":14,"title":429,"abstract":430,"tags":431},[],[],[29],{"code":433,"score":22,"supported":14,"title":434,"abstract":435,"tags":436},"I1",[],[],[418],{"code":49,"score":22,"supported":14,"title":438,"abstract":439,"tags":440},[],[],[27],[442,443],"农业人工智能 智慧农业 气候适应 蜜蜂","农业人工智能 智慧农业","农业人工智能智慧农业气候适应蜜蜂-2054","10.21203\u002Frs.3.rs-10938207\u002Fv1",{"doi":445,"openalex_id":447,"authors":448,"venue":409,"cited_by_count":82,"oa_url":452,"card":9,"direction":120,"ingested_from":122},"W7211926390",[449],{"name":450,"orcid":451},"M. R. K. Pathan","https:\u002F\u002Forcid.org\u002F0009-0002-1943-7942","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10938207\u002Flatest.pdf","2026-09-10T23:30:24.223473Z",{"id":455,"title":456,"url":457,"summary":458,"summary_zh":459,"content":9,"source_name":460,"source_url":457,"published_at":461,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":333,"score_detail":462,"sources":464,"tags":466,"primary_topic":469,"secondary_topics":470,"classification":471,"search_phrases":498,"slug":501,"view_count":82,"doi":502,"paper":503,"created_at":513},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",{"impact":17,"substance":265,"depth":136,"authority":17,"freshness":13,"relevant":22,"comment":463},"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[465],{"name":460,"url":457},[418,27,467,28,468],"粮食安全","气候分析",{"code":49,"slug":342,"name":343,"path":344,"parent_code":345},[],{"status":357,"locked":14,"version":35,"method":36,"evidence":472},{"candidates":473,"agricultural_evidence":42},[474,478,485,490,494],{"code":49,"score":277,"supported":42,"title":475,"abstract":476,"tags":477},[150],[],[27],{"code":479,"score":480,"supported":42,"title":481,"abstract":482,"tags":484},"I5",3,[],[483],"农业传感",[],{"code":486,"score":22,"supported":14,"title":487,"abstract":488,"tags":489},"A8",[],[],[467],{"code":433,"score":22,"supported":14,"title":491,"abstract":492,"tags":493},[],[],[418],{"code":56,"score":22,"supported":14,"title":495,"abstract":496,"tags":497},[],[],[28],[499,500],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":502,"openalex_id":504,"authors":505,"venue":460,"cited_by_count":82,"oa_url":457,"card":508,"direction":195,"ingested_from":122},"W7223111766",[506],{"name":507,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":509,"method":510,"finding":511,"direction":120,"opportunity":512},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","2026-10-22T11:21:02.682497Z"]