[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4172":3,"related-4172":125},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":50,"search_phrases":88,"slug":91,"view_count":92,"doi":93,"paper":94,"created_at":124},4172,"Machine learning reveals distinct drivers of soil organic carbon across the mountain-oasis-desert system of northwest China","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs13021-026-00522-5","The mountain-oasis-desert system (MODS) is a distinctive landscape pattern shaped by interactions between geomorphological configurations and hydrological processes in arid regions. However, most soil organic carbon (SOC) mapping studies treat arid landscapes as homogeneous units, leaving limited quantitative evidence on how SOC patterns and environmental associations differ among MODS subsystems. As a critical ecosystem highly sensitive to climate change and human activities, understanding these responses is essential for regional soil carbon management and ecological restoration. In this study, we developed an ecosystem-based modeling framework in the Hexi Region (HXR) to construct separate SOC prediction models for different subsystems, aiming to investigate the spatiotemporal dynamics of SOC stocks and identify their key driving factors across MODS. The results show that incorporating remote sensing (RS) variables significantly improved model performance, increasing the mean R 2 from 0.51 to 0.58. Among the tested models, XGBoost achieved the best performance, providing an effective tool for SOC mapping in arid regions. Shapley additive explanations (SHAP) analysis of the best-performing XGBoost models identified distinct leading predictors across the MODS, including surface shortwave radiation (SRAD) in mountain and desert ecosystems and the difference vegetation index (DVI) in oasis ecosystems. Furthermore, the partial least squares path model (PLS-PM) revealed contrasting influences of climate change and human activities across ecological subsystems. Climatic factors exerted the strongest influence in the mountainous subsystem, whereas in the oasis subsystem intensive human management became the dominant driver of soil carbon cycling. From 2001 to 2023, SOC stocks in oasis regions increased significantly at a rate of 0.17 t C ha⁻ 1 year⁻ 1 , potentially associated with land-use change and agricultural management. Approximately 19.3% of the study area experienced significant SOC stocks declines. By resolving subsystem-specific SOC patterns and environmental associations, this study advances ecosystem-aware SOC assessment in arid regions. The resulting framework also provides a basis for differentiated carbon management across MODS.","山地-绿洲-荒漠系统（MODS）是干旱区地貌格局与水文过程相互作用形成的独特景观格局。然而，大多数土壤有机碳（SOC）制图研究将干旱区景观视为均质单元，关于MODS各子系统间SOC格局及其环境关联差异的定量证据仍然有限。作为对气候变化和人类活动高度敏感的关键生态系统，理解这些响应对于区域土壤碳管理和生态恢复至关重要。本研究在河西地区（HXR）构建了基于生态系统的建模框架，针对不同子系统分别建立SOC预测模型，旨在探究MODS中SOC储量的时空动态并识别其关键驱动因子。结果表明，引入遥感（RS）变量显著提升了模型性能，平均R²从0.51提高至0.58。在测试的模型中，XGBoost表现最佳，为干旱区SOC制图提供了有效工具。对最优XGBoost模型的SHAP（Shapley加法解释）分析识别出MODS各子系统的不同主导预测因子，其中山地和荒漠生态系统为地表短波辐射（SRAD），绿洲生态系统为差值植被指数（DVI）。此外，偏最小二乘路径模型（PLS-PM）揭示了气候变化和人类活动在各生态子系统中的差异化影响。气候因子在山地子系统中影响最强，而在绿洲子系统中，集约化人类管理成为土壤碳循环的主导驱动因素。2001年至2023年，绿洲区域SOC储量以0.17 t C ha⁻¹ year⁻¹的速率显著增加，这可能与土地利用变化和农业管理有关。约19.3%的研究区域经历了SOC储量的显著下降。通过解析子系统特定的SOC格局及其环境关联，本研究推进了干旱区生态系统感知型SOC评估，所构建的框架也为MODS差异化碳管理提供了依据。",null,"Carbon Balance and Management","2026-10-03T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,9,1,"基于XGBoost与SHAP的干旱区SOC分异驱动研究，方法新颖、数据翔实，对区域碳管理与生态修复有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"机器学习","土壤有机碳","生态修复","遥感监测","干旱区农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[39,44],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":51,"locked":14,"version":52,"method":53,"evidence":54},"classified","2026-10-22.2","rules",{"candidates":55,"agricultural_evidence":58},[56,63,70,75,83],{"code":33,"score":57,"supported":58,"title":59,"abstract":60,"tags":62},15,true,[34],[61,34],"土壤",[28],{"code":40,"score":13,"supported":58,"title":64,"abstract":65,"tags":69},[],[66,67,68],"气候变化","干旱","climate change",[31],{"code":45,"score":21,"supported":58,"title":71,"abstract":73,"tags":74},[72],"machine learning",[],[27],{"code":76,"score":77,"supported":58,"title":78,"abstract":79,"tags":82},"I3",7,[],[80,81],"遥感","remote sensing",[30],{"code":84,"score":22,"supported":14,"title":85,"abstract":86,"tags":87},"H6",[],[],[29],[89,90],"河西地区 土壤有机碳 机器学习","山地-绿洲-荒漠 遥感 碳储量","河西地区土壤有机碳机器学习-4172",2,"10.1186\u002Fs13021-026-00522-5",{"doi":93,"openalex_id":95,"authors":96,"venue":10,"cited_by_count":116,"oa_url":6,"card":117,"direction":121,"ingested_from":123},"W7219075005",[97,99,102,104,107,109,112,114],{"name":98,"orcid":9},"Y. Chen",{"name":100,"orcid":101},"Haiyang Xi","https:\u002F\u002Forcid.org\u002F0000-0003-3158-8161",{"name":103,"orcid":9},"Meng Zhu",{"name":105,"orcid":106},"Wenju Cheng","https:\u002F\u002Forcid.org\u002F0000-0002-1822-5668",{"name":108,"orcid":9},"Yulian Hao",{"name":110,"orcid":111},"Linbo Qu","https:\u002F\u002Forcid.org\u002F0009-0007-4669-8407",{"name":113,"orcid":9},"Zhehui Wang",{"name":115,"orcid":9},"Bin Wang",0,{"tldr":118,"method":119,"finding":120,"direction":121,"opportunity":122},"构建基于生态系统的机器学习框架，预测西北荒漠-绿洲-山地系统土壤有机碳并识别各子系统驱动因子。","XGBoost、SHAP、PLS-PM，结合遥感变量与2001-2023年多源数","遥感变量提升模型R²至0.58；山地和沙漠由辐射主导，绿洲由人类管理主导，绿洲碳储量年增0.17 t","农业遥感与作物表型","可延伸研究绿洲农业管理措施对土壤碳的长期影响，并开发子系统自适应的碳监测与决策模型。","openalex","2026-10-04T23:30:24.631460Z",{"total":126,"page":22,"page_size":126,"items":127},6,[128,216,310,376,480,563],{"id":129,"title":130,"url":131,"summary":132,"summary_zh":133,"content":9,"source_name":134,"source_url":131,"published_at":135,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":136,"score_detail":137,"sources":142,"tags":144,"primary_topic":148,"secondary_topics":154,"classification":157,"search_phrases":192,"slug":195,"view_count":116,"doi":196,"paper":197,"created_at":215},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy","2026-10-21T00:00:00Z",77,{"impact":17,"substance":138,"depth":139,"authority":140,"freshness":13,"relevant":22,"comment":141},21,17,13,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[143],{"name":134,"url":131},[145,27,30,146,147],"智慧农业","土壤墒情","冬小麦",{"code":149,"slug":150,"name":151,"path":152,"parent_code":153},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[155,156],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"status":51,"locked":14,"version":52,"method":53,"evidence":158},{"candidates":159,"agricultural_evidence":58},[160,166,170,174,179,186],{"code":149,"score":161,"supported":58,"title":162,"abstract":164,"tags":165},26,[163,150],"winter wheat",[151,163,150],[147],{"code":33,"score":57,"supported":58,"title":167,"abstract":168,"tags":169},[34],[61,34],[146],{"code":45,"score":57,"supported":58,"title":171,"abstract":172,"tags":173},[72],[27,72],[27],{"code":76,"score":13,"supported":58,"title":175,"abstract":176,"tags":178},[],[80,81,177],"multispectral",[30],{"code":180,"score":126,"supported":58,"title":181,"abstract":182,"tags":185},"H3",[],[183,184],"灌溉","irrigation",[],{"code":187,"score":188,"supported":58,"title":189,"abstract":190,"tags":191},"I1",4,[],[145],[145],[193,194],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":196,"openalex_id":198,"authors":199,"venue":134,"cited_by_count":116,"oa_url":131,"card":209,"direction":214,"ingested_from":123},"W7223156204",[200,203,205,207],{"name":201,"orcid":202},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":204,"orcid":9},"Yi Zhang",{"name":206,"orcid":9},"WEI Lei",{"name":208,"orcid":9},"Chengcai Zhang",{"tldr":210,"method":211,"finding":212,"direction":121,"opportunity":213},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z",{"id":217,"title":218,"url":219,"summary":220,"summary_zh":221,"content":9,"source_name":222,"source_url":219,"published_at":223,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":224,"score_detail":225,"sources":229,"tags":231,"primary_topic":234,"secondary_topics":238,"classification":241,"search_phrases":286,"slug":289,"view_count":92,"doi":290,"paper":291,"created_at":309},4575,"A review of remote sensing for agricultural drought: technologies, indices, modelling advances and future prospects","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15481603.2026.2738981","Agricultural drought is a complex hazard that jeopardises food security and progress toward the Sustainable Development Goals. We systematically reviewed peer-reviewed English-language literature published between 2015 and 2025, focusing on Remote Sensing (RS)-driven agricultural drought monitoring and prediction. Eligible studies were identified from the Web of Science and Scopus databases (last searched in August 2025); review articles, duplicates, and irrelevant studies were excluded, resulting in 181 articles. This review critically examined the evolution of sensors, drought indices, modelling approaches, and emerging technologies used to assess agricultural drought across diverse agro-ecological regions. Specifically, we (1) systematically evaluated the use of optical, thermal, and microwave RS platforms, along with satellite-based, model-based, and reanalysis products for agricultural drought monitoring; (2) reviewed widely used RS-based drought indices, including single indices grouped into nine categories, as well as composite indices; (3) reviewed software or programming languages applied; (4) assessed the progression of modelling approaches from traditional statistical and time-series methods to machine learning (ML) and deep learning (DL) frameworks; and (5) examined validation strategies applied to agricultural drought assessment. The analysis reveals a growing research interest in this topic, with a strong geographic concentration in Asia, particularly China. Optical and thermal platforms (e.g. MODIS and Landsat) dominate the literature (~54%) due to their accessibility, followed by satellite-derived precipitation products (17%), while microwave soil-moisture missions remain underutilized (~7%). Regarding RS-based indices, most studies employed more than one index: 44% analysed multiple individual indices, 51% used composite indices (either alone or in combination with individual indices), and only 5% relied on a single index. Vegetation indices, such as NDVI, remain workhorses; however, their sensitivity to soil background effects and canopy saturation has driven increased adoption of thermal composites (e.g. VHI), as well as adaptive weighting schemes and principal component analysis-based approaches. Moreover, computational tools used in drought research can be broadly grouped into geospatial and RS platforms for large-scale data processing and analysis (e.g. QGIS, GEE), and general-purpose programming languages (e.g. R, Python) for model development and advanced analytics. Regarding the methodology, statistical and time-series approaches account for 64% of the reviewed studies, followed by ML models (20%) and DL methods (15%), while explainable artificial intelligence (XAI) remains nascent. Techniques, such as random forests, support vector machines, and CNN and LSTM architectures, generally outperform traditional models but require large training datasets and raise concerns related to interpretability and ethics. In terms of validation, hydro-climatic indices such as SPI and SPEI are most commonly used (32%), followed by crop yield and yield anomaly data (19%). This review further identifies key research gaps across sensors, indices, and modelling approaches and proposes a roadmap for developing equitable, interpretable, and resilient agricultural drought monitoring systems. Emerging opportunities include context-aware and interpretable AI, multi-sensor and multi-scale data fusion across optical, thermal, and microwave domains, integration of physiologically meaningful indicators such as sun-induced chlorophyll fluorescence (SIF), robust uncertainty quantification, and the development of hybrid and physics-informed modelling frameworks.","农业干旱是一种复杂的灾害，威胁粮食安全和可持续发展目标的实现。我们系统综述了2015年至2025年间发表的同行评议英文文献，聚焦于遥感（RS）驱动的农业干旱监测与预测。符合条件的研究通过Web of Science和Scopus数据库检索确定（最后检索时间为2025年8月）；综述文章、重复文献及不相关研究被排除，最终纳入181篇文献。本综述批判性地审视了用于评估不同农业生态区农业干旱的传感器、干旱指数、建模方法及新兴技术的演变。具体而言，我们（1）系统评估了光学、热红外和微波遥感平台，以及基于卫星、基于模型和再分析产品在农业干旱监测中的应用；（2）综述了广泛使用的基于遥感的干旱指数，包括归为九类的单一指数以及复合指数；（3）综述了所应用的软件或编程语言；（4）评估了建模方法从传统统计和时间序列方法向机器学习（ML）和深度学习（DL）框架的演进；（5）考察了应用于农业干旱评估的验证策略。分析显示，该主题的研究兴趣日益增长，地理上高度集中于亚洲，尤其是中国。光学和热红外平台（如MODIS和Landsat）因其可获取性在文献中占主导地位（约54%），其次是卫星降水产品（17%），而微波土壤水分任务仍未得到充分利用（约7%）。在基于遥感的指数方面，大多数研究采用了不止一种指数：44%分析了多个单一指数，51%使用了复合指数（单独使用或与单一指数结合使用），仅5%依赖单一指数。植被指数（如NDVI）仍是主力工具；然而，其对土壤背景效应和冠层饱和的敏感性推动了热红外复合指数（如VHI）以及自适应权重方案和基于主成分分析的方法得到更多采用。此外，干旱研究中使用的计算工具可大致分为用于大规模数据处理和分析的地理空间与遥感平台（如QGIS、GEE），以及用于模型开发的通用编程语言（如R、Python）。","GIScience & Remote Sensing","2026-10-08T00:00:00Z",81,{"impact":19,"substance":18,"depth":226,"authority":20,"freshness":227,"relevant":22,"comment":228},19,8,"系统综述181篇文献，梳理遥感干旱监测的传感器、指数与建模进展，方法学价值高，但属学术综述，产业落地影响有限。",[230],{"name":222,"url":219},[145,232,27,30,233],"粮食安全","农业干旱",{"code":76,"slug":235,"name":236,"path":237,"parent_code":49},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[239,240],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"status":51,"locked":14,"version":52,"method":53,"evidence":242},{"candidates":243,"agricultural_evidence":58},[244,248,253,260,266,270,277,282],{"code":76,"score":57,"supported":58,"title":245,"abstract":246,"tags":247},[81],[80,81],[30],{"code":40,"score":20,"supported":58,"title":249,"abstract":251,"tags":252},[250],"drought",[67,250],[],{"code":45,"score":13,"supported":58,"title":254,"abstract":255,"tags":259},[],[256,27,72,257,258],"深度学习","deep learning","artificial intelligence",[27],{"code":261,"score":77,"supported":58,"title":262,"abstract":263,"tags":265},"A8",[],[232,264],"food security",[232],{"code":33,"score":126,"supported":58,"title":267,"abstract":268,"tags":269},[],[61,34],[],{"code":271,"score":272,"supported":58,"title":273,"abstract":274,"tags":276},"D",3,[],[275],"水产",[],{"code":84,"score":272,"supported":58,"title":278,"abstract":279,"tags":281},[],[280],"农业生态",[],{"code":187,"score":22,"supported":14,"title":283,"abstract":284,"tags":285},[],[],[145],[287,288],"遥感 农业干旱 监测","GIScience Remote Sensing 干旱指数","遥感农业干旱监测-4575","10.1080\u002F15481603.2026.2738981",{"doi":290,"openalex_id":292,"authors":293,"venue":222,"cited_by_count":116,"oa_url":303,"card":304,"direction":214,"ingested_from":123},"W7221081979",[294,297,300],{"name":295,"orcid":296},"Fatemeh Saba","https:\u002F\u002Forcid.org\u002F0000-0001-6171-155X",{"name":298,"orcid":299},"Nima Ahmadian","https:\u002F\u002Forcid.org\u002F0000-0003-3676-1840",{"name":301,"orcid":302},"Olena Dubovyk","https:\u002F\u002Forcid.org\u002F0000-0002-7338-3167","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F15481603.2026.2738981?needAccess=true",{"tldr":305,"method":306,"finding":307,"direction":121,"opportunity":308},"系统综述2015-2025年遥感农业干旱监测与预测的传感器、指数、建模及验证进展。","基于Web of Science与Scopus的181篇文献系统综述，涵盖光学\u002F","光学热红外平台占主导，微波土壤水分利用不足；复合指数与机器学习建模成为趋势。","微波土壤水分数据融合与深度学习干旱预测模型在数据稀缺区验证是潜在研究空白。","2026-10-10T23:30:14.933078Z",{"id":311,"title":312,"url":313,"summary":314,"summary_zh":315,"content":9,"source_name":316,"source_url":313,"published_at":317,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":318,"score_detail":319,"sources":321,"tags":323,"primary_topic":325,"secondary_topics":326,"classification":328,"search_phrases":355,"slug":358,"view_count":22,"doi":359,"paper":360,"created_at":375},3772,"Integrating Vegetation Health Indices and Machine Learning for Early Prediction of Agricultural Drought","https:\u002F\u002Fdoi.org\u002F10.1080\u002F02626667.2026.2740781","Agricultural drought threatens food security across Nigeria’s Sahel, yet spatially explicit machine-learning-based prediction remains limited in the region. This study developed a spatiotemporal drought monitoring and prediction framework for Yobe State (2000–2025) integrating seven remote-sensing indicators; NDVI, EVI, VCI, TCI, SMI, LST, and rainfall within Google Earth Engine at 3 km resolution. A persistent north–south drought gradient emerged across all indicators, with northern local government areas exhibiting chronic vegetation stress, soil moisture deficit, and elevated surface temperatures throughout the study period. Three machine learning models; LSTM, Random Forest, and XGBoost were trained on Vegetation Health Index-derived drought severity classes. XGBoost achieved the highest predictive performance (accuracy = 86.9%; Kappa = 0.829; RMSE = 2.26), with rainfall and vegetation condition as dominant predictors. All three models converge on the northern LGAs as the highest-risk zone by 2030, supporting targeted early warning deployment and climate-smart agricultural investment across the Sahel.","农业干旱威胁着尼日利亚萨赫勒地区的粮食安全，但该地区基于机器学习且具有空间显式特征的预测研究仍然有限。本研究在Google Earth Engine平台上，以3 km分辨率构建了约贝州（2000—2025年）的时空干旱监测与预测框架，集成了七种遥感指标：归一化植被指数（NDVI）、增强植被指数（EVI）、植被条件指数（VCI）、温度条件指数（TCI）、土壤水分指数（SMI）、地表温度（LST）和降雨量。所有指标均呈现出持续的南北干旱梯度，北部地方政府辖区在整个研究期内表现出长期的植被胁迫、土壤水分亏缺和地表温度升高。研究以植被健康指数（VHI）衍生的干旱严重程度等级为标签，训练了三种机器学习模型：长短期记忆网络（LSTM）、随机森林（Random Forest）和极端梯度提升（XGBoost）。XGBoost取得了最高的预测性能（准确率=86.9%；Kappa=0.829；RMSE=2.26），其中降雨量和植被状况为主要预测因子。三种模型一致预测，到2030年北部地方政府辖区将成为最高风险区，这为萨赫勒地区有针对性的预警部署和气候智慧型农业投资提供了依据。","Hydrological Sciences Journal","2026-09-28T00:00:00Z",80,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":227,"relevant":22,"comment":320},"基于多源遥感与机器学习构建萨赫勒地区农业干旱早期预警框架，方法扎实、结论明确，对干旱监测预警有参考价值。",[322],{"name":316,"url":313},[145,27,30,233,324],"预警系统",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},[327],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":329},{"candidates":330,"agricultural_evidence":58},[331,335,339,343,347,351],{"code":45,"score":57,"supported":58,"title":332,"abstract":333,"tags":334},[72],[27,72],[27],{"code":40,"score":20,"supported":58,"title":336,"abstract":337,"tags":338},[250],[67,250],[],{"code":261,"score":126,"supported":58,"title":340,"abstract":341,"tags":342},[],[232,264],[],{"code":33,"score":126,"supported":58,"title":344,"abstract":345,"tags":346},[],[61,34],[],{"code":76,"score":188,"supported":58,"title":348,"abstract":349,"tags":350},[],[80],[30],{"code":187,"score":22,"supported":14,"title":352,"abstract":353,"tags":354},[],[],[145],[356,357],"尼日利亚 萨赫勒 农业干旱","XGBoost 植被健康指数 干旱预测","尼日利亚萨赫勒农业干旱-3772","10.1080\u002F02626667.2026.2740781",{"doi":359,"openalex_id":361,"authors":362,"venue":316,"cited_by_count":116,"oa_url":9,"card":370,"direction":214,"ingested_from":123},"W7214639469",[363,366,368],{"name":364,"orcid":365},"Gbolahan S. Badru","https:\u002F\u002Forcid.org\u002F0000-0003-4020-6356",{"name":367,"orcid":9},"Shakirudeen Odunuga",{"name":369,"orcid":9},"Michael Adebisi Adeyemi",{"tldr":371,"method":372,"finding":373,"direction":121,"opportunity":374},"基于多源遥感与机器学习构建尼日利亚萨赫勒地区农业干旱早期预测框架。","GEE整合NDVI、EVI、VCI等7个指标，用LSTM、随机森林、XGBoos","XGBoost预测精度最高（86.9%），北部LGAs为2030年前最高风险区。","可探索多模型集成与迁移学习，将干旱预警框架推广至其他萨赫勒地区并耦合作物产量预测。","2026-09-29T23:30:09.236357Z",{"id":377,"title":378,"url":379,"summary":380,"summary_zh":381,"content":9,"source_name":382,"source_url":379,"published_at":383,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":384,"score_detail":385,"sources":388,"tags":390,"primary_topic":394,"secondary_topics":395,"classification":400,"search_phrases":451,"slug":454,"view_count":116,"doi":455,"paper":456,"created_at":479},5483,"Soil Salinity under Climate Change in Pakistan: Emerging Challenges and Sustainable Management Approaches for Agriculture","https:\u002F\u002Fdoi.org\u002F10.71317\u002Fkjard.2.10.2026.883","Soil salinity is a major constraint to agricultural productivity, soil health, and food security in Pakistan, particularly under changing climatic conditions. Rising temperatures, increased evapotranspiration, irregular precipitation, droughts, flooding, and sea-level rise can intensify salt accumulation and alter soil–water interactions. This review examines the emerging challenges associated with climate change and soil salinity in Pakistan, focusing on their impacts on soil properties, crop physiology, agricultural production, and rural livelihoods. It discusses the mechanisms of soil salinity and sodicity, their spatial distribution, and the interactions among climate variability, irrigation practices, groundwater quality, and secondary salinization. Furthermore, sustainable management approaches are evaluated, including gypsum application, organic amendments, integrated nutrient management, efficient irrigation, drainage improvement, and appropriate leaching strategies. Climate-resilient approaches, such as conventional crop breeding, modern biotechnology, halophyte utilization, plant growth-promoting microorganisms, and mycorrhizal associations, are also explored. The review highlights the potential of remote sensing, geographic information systems, precision agriculture, and predictive modelling to support salinity monitoring and site-specific management. Despite these opportunities, important challenges remain, including insufficient long-term monitoring, limited region-specific data, economic constraints, and gaps in farmer awareness and institutional coordination. Addressing these challenges requires integrated research, effective agricultural policies, improved extension services, and collaboration among researchers, policymakers, and farming communities. Prioritizing locally adapted, economically feasible, and environmentally sustainable interventions can strengthen agricultural resilience, restore salt-affected soils, and protect freshwater resources. Overall, integrating climate adaptation with sustainable soil and water management is essential for maintaining agricultural productivity and improving long-term food security in Pakistan.","土壤盐渍化是制约巴基斯坦农业生产力、土壤健康和粮食安全的主要因素，在气候变化条件下尤为突出。气温升高、蒸散加剧、降水不规律、干旱、洪水以及海平面上升可能加剧盐分积累并改变土壤—水相互作用。本文综述了巴基斯坦气候变化与土壤盐渍化相关的新兴挑战，重点关注其对土壤性质、作物生理、农业生产和农村生计的影响。文章讨论了土壤盐渍化和钠质化的机制、其空间分布，以及气候变率、灌溉实践、地下水质量和次生盐渍化之间的相互作用。此外，评估了可持续管理途径，包括施用石膏、有机改良、综合养分管理、高效灌溉、排水改良和适宜的淋洗策略。还探讨了气候韧性方法，如常规作物育种、现代生物技术、盐生植物利用、植物促生微生物和菌根共生。本文强调了遥感、地理信息系统、精准农业和预测建模在支持盐渍化监测和因地制宜管理方面的潜力。尽管存在这些机遇，重要挑战依然存在，包括长期监测不足、区域特定数据有限、经济制约以及农民意识和制度协调方面的差距。应对这些挑战需要综合研究、有效的农业政策、改进的推广服务以及研究人员、政策制定者和农业社区之间的协作。优先采取适应当地、经济可行且环境可持续的干预措施，可增强农业韧性、修复盐渍化土壤并保护淡水资源。总体而言，将气候适应与可持续水土管理相结合，对于维持巴基斯坦农业生产力和改善长期粮食安全至关重要。","Kashmir Journal of Academic Research and Development","2026-10-20T00:00:00Z",66,{"impact":140,"substance":19,"depth":57,"authority":386,"freshness":227,"relevant":22,"comment":387},12,"综述性论文，系统梳理气候变化下巴基斯坦土壤盐渍化成因与可持续治理路径，兼具遥感与精准农业视角，对盐碱地治理议题有参考价值，但属区域性综述、非突破性成果。",[389],{"name":382,"url":379},[66,391,30,392,393],"盐碱地治理","智慧灌溉","土壤盐渍化",{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},[396,397],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":180,"slug":184,"name":398,"path":399,"parent_code":37},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"status":51,"locked":14,"version":52,"method":53,"evidence":401},{"candidates":402,"agricultural_evidence":58},[403,408,412,418,422,426,432,439,445],{"code":40,"score":19,"supported":58,"title":404,"abstract":405,"tags":407},[68],[66,406,67,68],"气候适应",[66],{"code":33,"score":57,"supported":58,"title":409,"abstract":410,"tags":411},[34],[61,34],[391],{"code":180,"score":13,"supported":58,"title":413,"abstract":414,"tags":417},[],[183,415,184,416],"水资源","evapotranspiration",[392],{"code":76,"score":77,"supported":58,"title":419,"abstract":420,"tags":421},[],[80,81],[30],{"code":261,"score":126,"supported":58,"title":423,"abstract":424,"tags":425},[],[232,264],[],{"code":187,"score":126,"supported":58,"title":427,"abstract":428,"tags":431},[],[429,430],"精准农业","precision agriculture",[],{"code":433,"score":126,"supported":58,"title":434,"abstract":435,"tags":438},"I4",[],[436,437],"地理信息","geographic information",[],{"code":440,"score":272,"supported":58,"title":441,"abstract":442,"tags":444},"F3",[],[443],"养分管理",[],{"code":446,"score":272,"supported":58,"title":447,"abstract":448,"tags":450},"J1",[],[449],"农业政策",[],[452,453],"巴基斯坦 土壤盐渍化","盐碱地 遥感监测","巴基斯坦土壤盐渍化-5483","10.71317\u002Fkjard.2.10.2026.883",{"doi":455,"openalex_id":457,"authors":458,"venue":382,"cited_by_count":116,"oa_url":379,"card":474,"direction":121,"ingested_from":123},"W7222999158",[459,461,463,465,467,469,472],{"name":460,"orcid":9},"Asifa Naz",{"name":462,"orcid":9},"Muhammad Abu Baker Siddiq",{"name":464,"orcid":9},"Syed Asghar Hussain Shah",{"name":466,"orcid":9},"Shahrish Nawaz",{"name":468,"orcid":9},"Muhmmad Irfan",{"name":470,"orcid":471},"Rizwana Kausar","https:\u002F\u002Forcid.org\u002F0000-0002-1339-3312",{"name":473,"orcid":9},"Muhammad Nouman Khalid",{"tldr":475,"method":476,"finding":477,"direction":121,"opportunity":478},"综述气候变化下巴基斯坦土壤盐渍化的挑战与可持续管理途径。","文献综述，整合盐渍化机制、空间分布及遥感GIS与预测模型应用。","需将气候适应与水土管理结合，优先本地化、经济可行的干预措施。","可填补长期盐渍化监测与区域数据空白，发展遥感+预测模型的精准分区治理。","2026-10-21T23:30:23.059448Z",{"id":481,"title":482,"url":483,"summary":484,"summary_zh":485,"content":9,"source_name":486,"source_url":483,"published_at":487,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":488,"score_detail":489,"sources":492,"tags":494,"primary_topic":498,"secondary_topics":499,"classification":502,"search_phrases":517,"slug":520,"view_count":116,"doi":521,"paper":522,"created_at":562},5178,"Spatial Modeling of Topsoil Total Carbon and Texture from Spectral Characteristics of Bare Soil Surface Images of Landsat 5\u002F8 Using Machine Learning","https:\u002F\u002Fdoi.org\u002F10.1134\u002Fs1064229326601228","— This study examines the possibility for detecting bare soil surface (BSS), using remote sensing data and for applying this approach to model texture and total soil carbon in the topsoil. The study area comprises agricultural fields within the North Caucasus Federal Agricultural Research Center in the northeastern spurs of the Stavropol Upland. Landsat 5\u002F8 imagery and spectral indices (NDVI, NBR2, and BSI) were used to classify BSS. Optimal discrimination of BSS from green and non-photosynthetic vegetation was achieved, using a BSI threshold of >0.18 (F1-score = 0.98). Spatial modeling of topsoil properties was conducted by comparing five regression models (Linear Regression, K-Nearest Neighbors, Random Forest, Extreme Gradient Boosting, and Cubist). A linear regression model demonstrated the highest performance; key predictors included the mean and standard deviation of SWIR2. The model exhibits strong predictive capability for sand, silt, clay, and total carbon (adjusted R 2 = 0.82, 0.75, 0.78, and 0.74, respectively). The topsoil is characterized by the range of clay content from 5 to 30%, of silt content from 15 to 60%, of sand content from 20 to 80%, and of total carbon from 0.5 to 3%. Predictive maps of texture and total carbon derived from BSS reveal considerable local heterogeneity, with soils consisting of Chernozems and Phaeozems, influenced by parent rock variability. The modeling results highlight the high predictive power of the BSS spectral characteristics, even when used as a single predictor for digital soil mapping.","本研究探讨了利用遥感数据检测裸露土壤表面（BSS）的可能性，并将该方法应用于表层土壤质地和总碳的建模。研究区包括位于斯塔夫罗波尔高地东北支脉的北高加索联邦农业研究中心内的农田。利用Landsat 5\u002F8影像和光谱指数（NDVI、NBR2和BSI）对BSS进行分类。当BSI阈值>0.18时，实现了BSS与绿色植被及非光合植被的最优区分（F1分数=0.98）。通过比较五种回归模型（线性回归、K近邻、随机森林、极端梯度提升和Cubist）对表层土壤属性进行了空间建模。线性回归模型表现出最高的性能；关键预测变量包括SWIR2的均值和标准差。该模型对砂粒、粉粒、黏粒和总碳表现出较强的预测能力（调整R²分别为0.82、0.75、0.78和0.74）。表层土壤的黏粒含量范围为5%至30%，粉粒含量为15%至60%，砂粒含量为20%至80%，总碳含量为0.5%至3%。基于BSS生成的质地和总碳预测图揭示了显著的局部异质性，土壤由黑钙土和暗色始成土组成，受母岩变异性的影响。建模结果凸显了BSS光谱特征的高预测能力，即使仅作为数字土壤制图的单一预测变量使用亦然。","Eurasian Soil Science","2026-10-15T00:00:00Z",69,{"impact":386,"substance":490,"depth":17,"authority":140,"freshness":227,"relevant":22,"comment":491},20,"方法新颖、结论可靠，但属区域尺度研究，公共影响有限，适合作为技术类精选。",[493],{"name":486,"url":483},[27,80,495,496,497],"土壤碳","Landsat","数字土壤制图",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[500,501],{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},{"code":76,"slug":235,"name":236,"path":237,"parent_code":49},{"status":51,"locked":14,"version":52,"method":53,"evidence":503},{"candidates":504,"agricultural_evidence":58},[505,509,513],{"code":33,"score":20,"supported":58,"title":506,"abstract":507,"tags":508},[34],[61,34],[],{"code":45,"score":21,"supported":58,"title":510,"abstract":511,"tags":512},[72],[],[27],{"code":76,"score":227,"supported":58,"title":514,"abstract":515,"tags":516},[],[80,81],[496,80],[518,519],"Landsat 裸土 土壤碳","北高加索 土壤质地 遥感","Landsat裸土土壤碳-5178","10.1134\u002Fs1064229326601228",{"doi":521,"openalex_id":523,"authors":524,"venue":486,"cited_by_count":116,"oa_url":9,"card":557,"direction":121,"ingested_from":123},"W7222107492",[525,528,531,534,537,540,543,546,548,551,554],{"name":526,"orcid":527},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":529,"orcid":530},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":532,"orcid":533},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":535,"orcid":536},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":538,"orcid":539},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":541,"orcid":542},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":544,"orcid":545},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":547,"orcid":9},"A. E. Shatunov",{"name":549,"orcid":550},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":552,"orcid":553},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":555,"orcid":556},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":558,"method":559,"finding":560,"direction":121,"opportunity":561},"用Landsat 5\u002F8裸土光谱指数识别裸土并机器学习建模表层土壤质地与全碳。","Landsat 5\u002F8影像、NDVI\u002FNBR2\u002FBSI指数、五种回归模型对比。","BSI阈值0.18识别裸土F1达0.98，线性回归最优，SWIR2均值与标准差为关键预测因子。","可探索多时相裸土合成与深度学习模型，提升数字土壤制图精度与跨区域迁移能力。","2026-10-17T23:30:31.485949Z",{"id":564,"title":565,"url":566,"summary":567,"summary_zh":568,"content":9,"source_name":569,"source_url":566,"published_at":487,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":570,"score_detail":571,"sources":573,"tags":575,"primary_topic":578,"secondary_topics":579,"classification":581,"search_phrases":620,"slug":623,"view_count":22,"doi":624,"paper":625,"created_at":636},5086,"Artificial Intelligence for Environmental Sustainability and Climate Change Mitigation: Recent Advances, Challenges, and Future Perspectives","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23399627","Abstract Climate change and environmental degradation have emerged as two of the most pressing global challenges of the twenty-first century, threatening ecosystems, biodiversity, human health, and sustainable development. Artificial Intelligence (AI) has transformed environmental research and management by enabling advanced data analytics, real-time monitoring, predictive modeling, and intelligent decision-support systems. This review critically examines the applications of AI in addressing environmental and climate-related challenges, including climate forecasting, air and water quality monitoring, biodiversity conservation, precision agriculture, renewable energy optimization, carbon emission assessment, waste management, and disaster risk reduction. Furthermore, The review also identifies current research gaps and highlights future opportunities for developing transparent, energy-efficient, and explainable AI systems that support evidence-based environmental decisionmaking. It concludes that AI has become a transformative tool for accelerating progress toward climate change mitigation, environmental sustainability, and the achievement of the United Nations Sustainable Development Goals (SDGs). Strengthening interdisciplinary collaboration, responsible AI governance, and policy support will be essential to maximize the environmental benefits of AI while minimizing its ecological footprint. Keywords: Artificial Intelligence; Climate Change; Environmental Sustainability; Machine Learning; Deep Learning; Remote Sensing; Internet of Things; Renewable Energy; Biodiversity Conservation; Sustainable Development Goals.","摘要 气候变化和环境退化已成为二十一世纪最紧迫的全球性挑战之一，威胁着生态系统、生物多样性、人类健康和可持续发展。人工智能（AI）通过实现先进的数据分析、实时监测、预测建模和智能决策支持系统，改变了环境研究与管理的方式。本文综述批判性地考察了AI在应对环境和气候相关挑战中的应用，包括气候预测、空气和水质监测、生物多样性保护、精准农业、可再生能源优化、碳排放评估、废物管理和灾害风险降低。此外，本综述还指出了当前的研究空白，并强调了未来开发透明、节能且可解释的AI系统的机遇，以支持基于证据的环境决策。文章得出结论，AI已成为加速气候变化减缓、环境可持续发展以及实现联合国可持续发展目标（SDGs）的变革性工具。加强跨学科合作、负责任的AI治理和政策支持，对于最大化AI的环境效益并同时最小化其生态足迹至关重要。关键词：人工智能；气候变化；环境可持续性；机器学习；深度学习；遥感；物联网；可再生能源；生物多样性保护；可持续发展目标。","Zenodo (CERN European Organization for Nuclear Research)",70,{"impact":19,"substance":17,"depth":57,"authority":386,"freshness":21,"relevant":22,"comment":572},"综述性论文，覆盖AI在气候预测、精准农业、遥感监测等方向的应用，与农业信息化相关但偏宏观综述，增量有限。",[574],{"name":569,"url":566},[145,576,577,66,30],"农业人工智能","可持续发展",{"code":45,"slug":46,"name":47,"path":48,"parent_code":49},[580],{"code":40,"slug":41,"name":42,"path":43,"parent_code":37},{"status":51,"locked":14,"version":52,"method":53,"evidence":582},{"candidates":583,"agricultural_evidence":58},[584,588,592,596,600,607,613],{"code":45,"score":19,"supported":58,"title":585,"abstract":586,"tags":587},[258],[256,27,72,257,258],[576],{"code":40,"score":57,"supported":58,"title":589,"abstract":590,"tags":591},[68],[66,68],[66],{"code":187,"score":77,"supported":58,"title":593,"abstract":594,"tags":595},[],[429,430],[145],{"code":76,"score":77,"supported":58,"title":597,"abstract":598,"tags":599},[],[80,81],[30],{"code":601,"score":126,"supported":58,"title":602,"abstract":603,"tags":606},"H4",[],[604,605],"碳排放","carbon emission",[],{"code":84,"score":126,"supported":58,"title":608,"abstract":609,"tags":612},[],[610,611],"生物多样性","biodiversity",[],{"code":614,"score":126,"supported":58,"title":615,"abstract":616,"tags":619},"I5",[],[617,618],"物联网","internet of things",[],[621,622],"AI 气候变化","人工智能 环境可持续","AI气候变化-5086","10.5281\u002Fzenodo.23399627",{"doi":624,"openalex_id":626,"authors":627,"venue":569,"cited_by_count":116,"oa_url":566,"card":630,"direction":214,"ingested_from":123},"W7222092855",[628],{"name":629,"orcid":9},"Deepmala Suryavanshi",{"tldr":631,"method":632,"finding":633,"direction":634,"opportunity":635},"综述AI在气候变化缓解与环境可持续领域的应用进展、挑战与未来方向。","文献综述，涵盖机器学习、深度学习、遥感、物联网等技术应用。","AI已成为推动气候减缓与可持续发展目标实现的变革性工具。","农业绿色发展与碳","可聚焦可解释、低能耗AI在农业碳减排与精准环境决策中的落地研究。","2026-10-16T23:30:15.059867Z"]