[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2662":3,"related-2662":90},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":36,"classification":37,"search_phrases":63,"slug":66,"view_count":67,"doi":68,"paper":69,"created_at":89},2662,"Annual Gridded Anthropogenic CH4 Emissions Estimation in China (2019–2025) Integrating Multisource Data: SHAP-Based Driver Attribution and Spatio-Temporal Patterns","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183168","Accurately quantifying the spatiotemporal dynamics and driving mechanisms of anthropogenic methane (CH4) emissions (MEs) is of great significance for achieving regional “dual-carbon” goals and global climate collaborative governance. However, existing ME inventories and macro-inversion models generally face bottlenecks such as coarse spatial resolution, lack of data update timeliness, and the inability of traditional static emission factors to capture non-linear responses. To address these issues, this study proposes an annual ME inventory enhancement framework integrating multi-source geographic and remote sensing data. This framework evaluates four advanced machine learning (ML) algorithms, including Random Forest (RF), Categorical Boosting (CB), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM), to construct a 0.1° high-resolution spatial grid of anthropogenic ME in China from 2019 to 2025. Furthermore, it introduces the SHapley Additive exPlanations (SHAP) framework and multi-scale spatial autocorrelation analysis to parse the driving mechanisms and clustering patterns. The results show the following: (1) LGBM exhibits the optimal comprehensive estimation accuracy (R2 = 0.938, RMSE = 3.707 Kt) and robust capability in capturing extreme ME sources (RTop2 = 0.929). (2) SHAP attribution reveals that coal mining and nighttime light (NTL) represent the primary contributing features to ME predictions (with a cumulative contribution of 65.60%), followed by agricultural and pastoral activities (24.98%), and all factors exhibit significant non-linear threshold and step-response characteristics. (3) Regarding spatiotemporal evolution, China’s total anthropogenic ME shows a trend of initial slow increase followed by high-level stabilization; spatially, it presents a “hot in the north, cold in the south” pattern, with extreme high values highly clustered in the Shanxi–Shaanxi–Inner Mongolia energy triangle and its peripheral expansion nodes. This study provides scientific references for formulating tailored, multi-scale, and refined CH4 mitigation strategies.","准确量化人为甲烷（CH₄）排放（MEs）的时空动态与驱动机制，对实现区域“双碳”目标及全球气候协同治理具有重要意义。然而，现有ME清单与宏观反演模型普遍面临空间分辨率粗、数据更新时效性不足、传统静态排放因子难以刻画非线性响应等瓶颈。针对上述问题，本研究提出了一种融合多源地理与遥感数据的年度ME清单增强框架。该框架评估了四种先进机器学习（ML）算法，包括随机森林（RF）、类别提升（CB）、极端梯度提升（XGB）和轻量梯度提升机（LGBM），构建了2019—2025年中国0.1°高分辨率人为ME空间网格。此外，引入SHapley加性解释（SHAP）框架与多尺度空间自相关分析，解析驱动机制与集聚模式。结果表明：（1）LGBM具有最优的综合估算精度（R² = 0.938，RMSE = 3.707 Kt），且在捕捉极端ME源方面表现稳健（RTop2 = 0.929）。（2）SHAP归因揭示，煤炭开采与夜间灯光（NTL）是ME预测的主要贡献特征（累计贡献率65.60%），其次为农牧活动（24.98%），且所有因子均呈现显著的非线性阈值与阶跃响应特征。（3）在时空演变方面，中国人为ME总量呈先缓慢增长后高位稳定的趋势；空间上表现为“北热南冷”格局，极端高值高度集聚于晋陕蒙能源金三角及其外围扩展节点。本研究为制定因地制宜、多尺度、精细化CH₄减排策略提供了科学参考。",null,"Remote Sensing","2026-09-15T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,14,9,1,"基于多源遥感与机器学习构建中国0.1°人为甲烷排放网格清单，方法新颖、数据规模大，对农业源排放核算与双碳治理有参考价值，但偏学术、非直接农业应用。",[24],{"name":10,"url":6},[26,27,28,29,30],"农业信息化","机器学习","遥感","甲烷排放","双碳目标",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},"I","digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"partial","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":46,"reason":62},[43,51,57],{"code":44,"score":45,"supported":46,"title":47,"abstract":48,"tags":50},"I2",7,true,[],[27,49],"machine learning",[27],{"code":52,"score":45,"supported":46,"title":53,"abstract":54,"tags":56},"I3",[],[28,55],"remote sensing",[28],{"code":58,"score":21,"supported":14,"title":59,"abstract":60,"tags":61},"I1",[],[],[26],"一级领域明确，二级方向需要细分",[64,65],"农业信息化 双碳目标 机器学习 甲烷排放","农业信息化 双碳目标","农业信息化双碳目标机器学习甲烷排放-2662",5,"10.3390\u002Frs18183168",{"doi":68,"openalex_id":70,"authors":71,"venue":10,"cited_by_count":80,"oa_url":6,"card":81,"direction":87,"ingested_from":88},"W7213229152",[72,75,78],{"name":73,"orcid":74},"Chaokang He","https:\u002F\u002Forcid.org\u002F0009-0005-8014-434X",{"name":76,"orcid":77},"Qinjun Wang","https:\u002F\u002Forcid.org\u002F0000-0001-6084-1889",{"name":79,"orcid":9},"Wenyue Xie",0,{"tldr":82,"method":83,"finding":84,"direction":85,"opportunity":86},"融合多源数据与机器学习构建中国2019-2025年0.1°人为甲烷排放网格，并用SHAP解析驱动机制","随机森林、CatBoost、XGBoost、LightGBM对比，结合SHAP归","LGBM精度最优（R²=0.938），煤炭开采与夜间灯光贡献65.6%，排放呈北热南冷格局。","农业绿色发展与碳","可延伸至农业源甲烷排放的精细网格化与非线性驱动阈值研究，支撑分区减排。","农业遥感与作物表型","openalex","2026-09-16T23:30:28.864720Z",{"total":91,"page":21,"page_size":91,"items":92},6,[93,145,212,289,364,436],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":9,"content":9,"source_name":98,"source_url":96,"published_at":99,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":100,"score_detail":101,"sources":106,"tags":108,"primary_topic":111,"secondary_topics":112,"classification":113,"search_phrases":128,"slug":131,"view_count":91,"doi":132,"paper":133,"created_at":144},1517,"Estimation of Agricultural Vegetation Water Stress Using Feature-Optimized Remote Sensing and Ensemble Machine Learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102536","Estimation of Agricultural Vegetation Water Stress Using Feature-Optimized Remote Sensing and Ensemble Machine Learning。Smart Agricultural Technology","Smart Agricultural Technology","2026-09-01T00:00:00Z",72,{"impact":102,"substance":103,"depth":17,"authority":104,"freshness":45,"relevant":21,"comment":105},15,20,12,"论文提出特征优化遥感与集成机器学习估算农业植被水分胁迫，方法新颖，数据详实，对精准灌溉有参考价值。",[107],{"name":98,"url":96},[109,27,28,110],"智慧农业","作物水分胁迫",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":114},{"candidates":115,"agricultural_evidence":46,"reason":62},[116,120,124],{"code":44,"score":104,"supported":46,"title":117,"abstract":118,"tags":119},[49],[49],[27],{"code":52,"score":104,"supported":46,"title":121,"abstract":122,"tags":123},[55],[55],[28],{"code":58,"score":21,"supported":14,"title":125,"abstract":126,"tags":127},[],[],[109],[129,130],"作物水分胁迫 智慧农业 机器学习 遥感","作物水分胁迫 智慧农业","作物水分胁迫智慧农业机器学习遥感-1517","10.1016\u002Fj.atech.2026.102536",{"doi":132,"openalex_id":134,"authors":135,"venue":98,"cited_by_count":80,"oa_url":96,"card":9,"direction":87,"ingested_from":88},"W7206189125",[136,139,141],{"name":137,"orcid":138},"Ahmed Elbeltagi","https:\u002F\u002Forcid.org\u002F0000-0002-5506-9502",{"name":140,"orcid":9},"Aman Srivastava",{"name":142,"orcid":143},"Abdullah A. Alsumaiei","https:\u002F\u002Forcid.org\u002F0000-0002-9148-3954","2026-09-03T23:30:04.462065Z",{"id":146,"title":147,"url":148,"summary":149,"summary_zh":150,"content":9,"source_name":151,"source_url":148,"published_at":152,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":153,"score_detail":154,"sources":157,"tags":159,"primary_topic":164,"secondary_topics":165,"classification":166,"search_phrases":191,"slug":194,"view_count":80,"doi":195,"paper":196,"created_at":211},5495,"Artificial Neural Network-Based Prediction and Mapping of Elephant Corridors in West Bengal Using Geospatial and Environmental Variables","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23496876","The fragmentation of forest habitats and increasing anthropogenic pressures have significantly altered elephant movementpatternsinWestBengal,India,resultinginanescalatinghuman-elephantconflict.Accurateidentification and mapping of elephant corridors are essential for landscape-level conservation planning and mitigation.Traditional corridor mapping methods, including expert-based delineation and least-cost path analyses, oftenstruggle to capture the complex and nonlinear relationships between environmental variables influencing elephant movement. This study proposes an Artificial Neural Network (ANN)-based framework to predict potential elephant corridors across West Bengal using remotely sensed and geographic information system (GIS) datasets. The predictor variables included forest cover, normalized difference vegetation index (NDVI), elevation, slope,proximity to water sources, distance from roads, railways, settlements, agricultural land, and historical elephant occurrence records. The ANN model was trained using known elephant movement locations and validated using independent datasets. The predicted suitable surface was integrated into a GIS environment to identify probable movement corridors and prioritize areas for conservation. The proposed approach demonstrates the ability of machine learning to improve corridor prediction compared with conventional GIS-based techniques and provides a decision support tool for forest managers and policymakers.","森林栖息地的破碎化和日益增加的人为压力显著改变了印度西孟加拉邦大象的活动模式，导致人象冲突不断加剧。准确识别和绘制大象廊道对于景观层面的保护规划和冲突缓解至关重要。传统的廊道制图方法，包括基于专家的 delineation（边界划定）和最小成本路径分析，往往难以捕捉影响大象活动的环境变量之间复杂的非线性关系。本研究提出了一种基于人工神经网络（Artificial Neural Network, ANN）的框架，利用遥感数据和地理信息系统（Geographic Information System, GIS）数据集预测西孟加拉邦潜在的大象廊道。预测变量包括森林覆盖、归一化植被指数（Normalized Difference Vegetation Index, NDVI）、海拔、坡度、距水源的邻近度、距道路、铁路、居民点、农田的距离以及历史大象出现记录。ANN模型利用已知的大象活动位置进行训练，并使用独立数据集进行验证。将预测得到的适宜性表面整合到GIS环境中，以识别可能的迁移廊道并确定保护优先区域。所提出的方法展示了机器学习相较于传统基于GIS的技术在改进廊道预测方面的能力，并为森林管理者和政策制定者提供了决策支持工具。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-20T00:00:00Z",70,{"impact":104,"substance":103,"depth":155,"authority":104,"freshness":20,"relevant":21,"comment":156},17,"该研究用人工神经网络结合遥感与GIS预测大象迁徙走廊，方法新颖、数据扎实，对生态保护与乡村人兽冲突治理有参考价值，但属区域性研究，公共影响有限。",[158],{"name":151,"url":148},[160,28,161,162,163],"农业人工智能","GIS","野生动物保护","人兽冲突",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":167},{"candidates":168,"agricultural_evidence":46,"reason":62},[169,174,181,186],{"code":44,"score":13,"supported":46,"title":170,"abstract":171,"tags":173},[],[27,49,172],"decision support",[160],{"code":175,"score":13,"supported":46,"title":176,"abstract":177,"tags":180},"I4",[],[178,161,179],"地理信息","geographic information",[161],{"code":52,"score":182,"supported":46,"title":183,"abstract":184,"tags":185},4,[],[28],[28],{"code":187,"score":21,"supported":14,"title":188,"abstract":189,"tags":190},"H6",[],[],[162],[192,193],"西孟加拉邦 大象走廊","人工神经网络 大象走廊","西孟加拉邦大象走廊-5495","10.5281\u002Fzenodo.23496876",{"doi":195,"openalex_id":197,"authors":198,"venue":151,"cited_by_count":80,"oa_url":148,"card":205,"direction":210,"ingested_from":88},"W7222999966",[199,201,203],{"name":200,"orcid":9},"Bhutia Dechen Doma",{"name":202,"orcid":9},"Swarup Das",{"name":204,"orcid":9},"Mandal Rakesh Kumar",{"tldr":206,"method":207,"finding":208,"direction":87,"opportunity":209},"用人工神经网络结合遥感与GIS变量预测并制图西孟加拉邦大象迁徙廊道。","ANN模型，输入遥感与GIS环境变量及历史象群出现记录，GIS集成制图。","ANN能刻画环境变量非线性关系，廊道预测优于传统GIS方法，可作决策支持工具。","可将ANN廊道预测与人类活动、农田冲突热点耦合，探索农业景观中野生动物通道与作物保护的协同规划。","农业人工智能与决策模型","2026-10-21T23:30:43.936453Z",{"id":213,"title":214,"url":215,"summary":216,"summary_zh":217,"content":9,"source_name":218,"source_url":215,"published_at":219,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":220,"score_detail":221,"sources":226,"tags":228,"primary_topic":232,"secondary_topics":233,"classification":234,"search_phrases":272,"slug":275,"view_count":80,"doi":276,"paper":277,"created_at":288},5403,"RS-GIS Based Dss (Decision Support System) for Land evaluation and Land resource management – (case study Amol District)","https:\u002F\u002Fdoi.org\u002F10.71500\u002Fthesis.2026.519222","Creating a proper planting pattern according to land talent identification, cannot be achieved without considering socioeconomic conditions and detailed holistic. This issue is considered by development of rice which is one of the main world’s most important agricultural products in rural areas and ensures their food security. In the country rice is considered as a strategic plant. This is among sustainable resources of area and attention to its development and expanding its cultivation causes farmers’ confidence and ensures economic stability of the region. On the other hand, crop insurance is same for all land, because statistical information on agricultural lands are most obtained through traditional methods based on the opinion of experts and individuals and collect this information always accompanied with error. Accordingly annually huge costs are paid for insured loss of agricultural lands Thus land evaluation, identification and resolution of land based on its capabilities by taking the capacity of the soil and environmental risks into account is essential for land management. This study presents a spatial decision support system (SDSS) to land evaluation and identification of suitable areas for rice cultivation in the studied area. After gathering data and field studies, various layers of criteria affecting decisions were created in GIS environment. Development of multi-criteria decision-making techniques (MCDM) is done using Analytical Hierarchy Process AHP, fuzzy logic and artificial neural networks. The comparison and integration of models (model compilation and standardization of fuzzy AHP, FAHP, fuzzy standardization and FAHP) was also carried out. To review and matching between fitness maps obtained from different models and the observed value of kappa coefficient was calculated. Neural network model with kappa coefficient 0.65 has highest fitness coefficient among land suitability class and the harvest amount and this due to the performance value in determining the classes is predictable in this model. After that, Fuzzy standardization compilation models and FAHP and Fuzzy standardization and AHP with Kappa coefficient of 0.54 and 0.51 respectively showed highest agreement between the land suitability classes and performance. The majority of lands located on non-prone class have high slope and if cultivation increase risk of soil erosion. Investigating area under rice plantation (paddy fields) with very prone and prone lands in different styles showed that almost the majority of this area is currently devoted to rice cultivation. Although neural network model showed higher accuracy than other models, but this assessment model requires data on rice yield and collecting performance rate required accuracy, cost and much time and sometimes land management and environmental hazards affects it.","根据土地适宜性识别来制定合理的种植模式，离不开对社会经济条件和详细整体性因素的考量。水稻作为世界最重要的农产品之一，其发展在农村地区受到重视，并保障了当地的粮食安全。在我国，水稻被视为战略作物。水稻是区域可持续资源之一，关注其发展并扩大种植面积能够增强农民信心，保障区域经济稳定。另一方面，作物保险对所有土地采取统一标准，因为农业用地的统计信息大多基于专家和个人意见通过传统方法获取，且此类信息的采集始终伴随着误差。因此，每年为农业用地保险损失支付巨额费用。有鉴于此，土地评价、识别及基于土地能力的土地问题解决，必须将土壤容量和环境风险纳入考量，这对土地管理至关重要。本研究提出了一种空间决策支持系统（SDSS），用于研究区域的土地评价和水稻适宜种植区识别。在收集数据和实地调研之后，于GIS环境中创建了影响决策的各准则图层。多准则决策技术（MCDM）的开发采用了层次分析法（AHP）、模糊逻辑和人工神经网络。同时进行了模型的比较与集成（模型编制与模糊AHP标准化、FAHP、模糊标准化与FAHP）。为审查和匹配不同模型获得的适宜性图件，计算了观测值与kappa系数。神经网络模型的kappa系数为0.65，在土地适宜性等级与产量之间具有最高的拟合系数，这归因于该模型在确定等级方面的性能值具有可预测性。其后，模糊标准化编制模型与FAHP、模糊标准化与AHP的kappa系数分别为0.54和0.51，在土地适宜性等级与产量之间表现出最高的一致性。位于非适宜等级的大多数土地具有高坡度，若扩大种植将增加土壤侵蚀风险。对不同适宜性等级下水稻种植区（稻田）的调查……","Test","2026-10-19T00:00:00Z",50,{"impact":222,"substance":223,"depth":102,"authority":224,"freshness":222,"relevant":21,"comment":225},8,16,3,"案例研究有一定方法参考价值，但来源不明、地域局限，不足以进入每日精选。",[227],{"name":218,"url":215},[229,28,161,230,231],"决策支持系统","水稻种植","土地评价",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":235},{"candidates":236,"agricultural_evidence":46,"reason":62},[237,241,245,254,261,268],{"code":44,"score":104,"supported":46,"title":238,"abstract":239,"tags":240},[172],[172],[229],{"code":175,"score":104,"supported":46,"title":242,"abstract":243,"tags":244},[161],[161],[161],{"code":246,"score":13,"supported":46,"title":247,"abstract":248,"tags":253},"A1",[],[249,250,251,252],"水稻","稻田","rice","paddy",[230],{"code":255,"score":91,"supported":46,"title":256,"abstract":257,"tags":260},"A8",[],[258,259],"粮食安全","food security",[],{"code":262,"score":91,"supported":46,"title":263,"abstract":264,"tags":267},"H2",[],[265,266],"土壤","soil",[],{"code":52,"score":21,"supported":14,"title":269,"abstract":270,"tags":271},[],[],[28],[273,274],"Amol District 水稻 土地适宜性","RS-GIS 决策支持系统 土地评价","AmolDistrict水稻土地适宜性-5403","10.71500\u002Fthesis.2026.519222",{"doi":276,"openalex_id":278,"authors":279,"venue":218,"cited_by_count":80,"oa_url":215,"card":283,"direction":210,"ingested_from":88},"W7222963628",[280],{"name":281,"orcid":282},"Zeinab Maddahi","https:\u002F\u002Forcid.org\u002F0000-0002-2824-2736",{"tldr":284,"method":285,"finding":286,"direction":87,"opportunity":287},"构建基于RS-GIS的空间决策支持系统，评估伊朗Amol地区水稻种植适宜性。","GIS叠加多准则决策、AHP、模糊逻辑与人工神经网络，用Kappa系数验证。","神经网络模型Kappa系数0.65最高，土地适宜性与产量吻合最好。","可将该SDSS与实时遥感、作物保险定损结合，发展动态土地适宜性监测。","2026-10-20T23:30:40.596410Z",{"id":290,"title":291,"url":292,"summary":293,"summary_zh":294,"content":9,"source_name":295,"source_url":292,"published_at":296,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":297,"score_detail":298,"sources":300,"tags":302,"primary_topic":306,"secondary_topics":307,"classification":308,"search_phrases":338,"slug":341,"view_count":80,"doi":342,"paper":343,"created_at":363},5166,"Application of the SCS–CN Method Integrated with GIS and Remote Sensing for Watershed Runoff Estimation: A Review","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fijecc\u002F2026\u002Fv16i105735","Accurate estimation of runoff is crucial for watershed planning, soil and water conservation, flood mitigation, and the management of ungauged watersheds. The Soil Conservation Service Curve Number (SCS-CN) method has been extensively used because of its minimal input requirements and its ability to model the spatial influence of land use, soil properties, and hydrologic soil groups. This review compiles applications of the GIS-based SCS-CN method reported for watersheds in semi-arid and monsoon-affected countries such as India, Saudi Arabia, Afghanistan, China, Iraq, and Ethiopia. The reviewed literature employed rainfall data, land-use\u002Fland-cover data, soil maps, hydrologic soil groups, digital elevation models, and watershed morphometry to calculate curve numbers and direct runoff. The reported CN values varied substantially, from about 40 under dry conditions to more than 90 under urban, rocky, agricultural, or poorly infiltrating conditions. Runoff estimates ranged from relatively low values in arid catchments to more than 1,300 mm per year in high-rainfall watersheds. Several studies reported high R2 correlations between observed and estimated runoff, typically ranging from 0.73 to 0.98. Important limitations identified in the review include the sensitivity of results to the choice of curve number, antecedent moisture condition, initial abstraction assumption, land-use classification, soil-group assignment, rainfall representation, and the lack of observed discharge data. The overall design of the SCS-CN method and its integration with RS and GIS offer a practical approach to assessing spatial runoff and prioritising watersheds, but the method requires local calibration, uncertainty analysis, and validation against observed rainfall–runoff data.","径流的准确估算对于流域规划、水土保持、洪水缓解以及无资料流域的管理至关重要。土壤保持服务曲线数（SCS-CN）方法因其输入需求少、能够模拟土地利用、土壤性质和水文土壤组的空间影响而被广泛使用。本综述汇编了基于GIS的SCS-CN方法在半干旱和受季风影响国家（如印度、沙特阿拉伯、阿富汗、中国、伊拉克和埃塞俄比亚）流域的应用报道。所综述的文献利用降雨数据、土地利用\u002F土地覆盖数据、土壤图、水文土壤组、数字高程模型和流域形态计量来计算曲线数和直接径流。报道的CN值差异很大，从干旱条件下的约40到城市、岩石、农业或入渗不良条件下的90以上不等。径流估算值从干旱集水区的相对较低值到高降雨流域的年径流量超过1300 mm不等。多项研究报告了观测径流与估算径流之间的高R²相关性，通常在0.73至0.98之间。本综述识别出的重要局限性包括：结果对曲线数选择、前期土壤湿润条件、初始损失假设、土地利用分类、土壤组赋值、降雨代表性以及缺乏实测流量数据的敏感性。SCS-CN方法的总体设计及其与遥感和GIS的集成，为评估空间径流和流域优先排序提供了一种实用方法，但该方法需要本地校准、不确定性分析，并依据实测降雨—径流数据进行验证。","International Journal of Environment and Climate Change","2026-10-16T00:00:00Z",63,{"impact":222,"substance":17,"depth":223,"authority":104,"freshness":20,"relevant":21,"comment":299},"综述系统梳理了GIS与遥感集成的SCS-CN径流估算方法及其局限，对农业信息化中的流域水资源与水土保持管理有参考价值，但属方法综述、影响面有限，未达每日精选门槛。",[301],{"name":295,"url":292},[28,161,303,304,305],"水土保持","流域管理","水文模型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":309},{"candidates":310,"agricultural_evidence":46,"reason":62},[311,315,319,323,327,333],{"code":52,"score":104,"supported":46,"title":312,"abstract":313,"tags":314},[55],[28],[28],{"code":175,"score":104,"supported":46,"title":316,"abstract":317,"tags":318},[161],[161],[161],{"code":262,"score":91,"supported":46,"title":320,"abstract":321,"tags":322},[],[265,266],[],{"code":187,"score":182,"supported":46,"title":324,"abstract":325,"tags":326},[],[303],[303],{"code":328,"score":224,"supported":46,"title":329,"abstract":330,"tags":332},"H7",[],[331],"干旱",[],{"code":334,"score":21,"supported":14,"title":335,"abstract":336,"tags":337},"H3",[],[],[305],[339,340],"SCS-CN GIS 遥感 径流估算","水土保持 水文模型 流域管理 遥感","SCS-CNGIS遥感径流估算-5166","10.9734\u002Fijecc\u002F2026\u002Fv16i105735",{"doi":342,"openalex_id":344,"authors":345,"venue":295,"cited_by_count":80,"oa_url":292,"card":358,"direction":87,"ingested_from":88},"W7222632567",[346,348,350,352,354,356],{"name":347,"orcid":9},"Sudhir Lad",{"name":349,"orcid":9},"R. D. Bansod",{"name":351,"orcid":9},"Bhaupatil Gavit",{"name":353,"orcid":9},"Sachin Nandgude",{"name":355,"orcid":9},"Shailendra Gadge",{"name":357,"orcid":9},"Mahesh Patil",{"tldr":359,"method":360,"finding":361,"direction":87,"opportunity":362},"综述GIS与遥感集成的SCS-CN法在半干旱与季风区流域径流估算的应用。","汇总印度、中国等国文献，用降雨、土地利用、土壤图、DEM与流域形态计算CN和径流","CN约40至90以上，年径流差异大，R²多在0.73至0.98，但结果对CN与前期湿度等敏感。","可研究CN本地化校准与不确定性量化，并结合实测径流验证，提升无资料流域径流估算可靠性。","2026-10-17T23:30:28.373754Z",{"id":365,"title":366,"url":367,"summary":368,"summary_zh":369,"content":9,"source_name":370,"source_url":367,"published_at":371,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":372,"score_detail":373,"sources":376,"tags":378,"primary_topic":381,"secondary_topics":382,"classification":383,"search_phrases":416,"slug":419,"view_count":21,"doi":420,"paper":421,"created_at":435},5074,"QISHLOQ XO‘JALIGI OLIY TA’LIM MUASSASALARIDA MAXSUS FANLARNI O‘QITISHDA “SMART AGRICULTURE” TEXNOLOGIYALARIDAN FOYDALANISH METODIKASI","https:\u002F\u002Fdoi.org\u002F10.67547\u002Ffanistiqbollari.2026.876","The article examines a methodology for integrating Smart Agriculture technologies into the teaching of specialized subjects at agricultural higher education institutions. The study analyzes the didactic potential of the Internet of Things, sensor monitoring, GIS, remote sensing, artificial intelligence, smart irrigation and digital data analytics.","本文探讨了将智慧农业技术融入农业高等院校专业课程教学的方法论。研究分析了物联网、传感器监测、地理信息系统、遥感、人工智能、智能灌溉和数字数据分析在教学中的潜力。","Ta limda Istiqbolli Izlanishlar xalqaro ilmiy metodik jurnal","2026-10-15T00:00:00Z",49,{"impact":222,"substance":19,"depth":374,"authority":91,"freshness":222,"relevant":21,"comment":375},13,"乌兹别克语论文探讨智慧农业技术融入农业高校专业教学的路径，属农业信息化人才培养方向，但为境外一般期刊、影响面有限，暂不宜进入每日精选。",[377],{"name":370,"url":367},[109,160,379,28,380],"物联网","农业教育",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":384},{"candidates":385,"agricultural_evidence":46,"reason":62},[386,391,395,401,407,411],{"code":58,"score":102,"supported":46,"title":387,"abstract":389,"tags":390},[388],"smart agriculture",[109,388],[109],{"code":52,"score":45,"supported":46,"title":392,"abstract":393,"tags":394},[],[28,55],[28],{"code":396,"score":45,"supported":46,"title":397,"abstract":398,"tags":400},"I5",[],[379,399],"internet of things",[379],{"code":334,"score":91,"supported":46,"title":402,"abstract":403,"tags":406},[],[404,405],"灌溉","irrigation",[],{"code":175,"score":91,"supported":46,"title":408,"abstract":409,"tags":410},[],[178,161],[],{"code":44,"score":182,"supported":46,"title":412,"abstract":413,"tags":415},[],[414],"artificial intelligence",[160],[417,418],"农业人工智能 农业教育 智慧农业 物联网","农业人工智能 农业教育","农业人工智能农业教育智慧农业物联网-5074","10.67547\u002Ffanistiqbollari.2026.876",{"doi":420,"openalex_id":422,"authors":423,"venue":370,"cited_by_count":80,"oa_url":427,"card":428,"direction":434,"ingested_from":88},"W7221997102",[424],{"name":425,"orcid":426},"O'G'ILOY SADULLO QIZI SHAMSIYEV","https:\u002F\u002Forcid.org\u002F0009-0003-4706-6488","https:\u002F\u002Ffanistiqbollari.uz\u002Fstorage\u002Farticle876.pdf",{"tldr":429,"method":430,"finding":431,"direction":432,"opportunity":433},"研究将智慧农业技术融入农业高校专业课程教学的方法论。","分析物联网、传感器、GIS、遥感、AI等技术的教学潜力。","智慧农业技术可有效支撑农业专业课程的教学方法设计。","数字乡村与农业信息化","可实证检验该教学法对学生技能与就业的影响，并开发配套课程资源。","智慧农业 \u002F 农业物联网","2026-10-16T23:30:07.890026Z",{"id":437,"title":438,"url":439,"summary":440,"summary_zh":441,"content":9,"source_name":442,"source_url":439,"published_at":443,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":444,"score_detail":445,"sources":447,"tags":449,"primary_topic":452,"secondary_topics":453,"classification":454,"search_phrases":478,"slug":481,"view_count":21,"doi":482,"paper":483,"created_at":499},4825,"Multi-Source Remote Sensing Fusion and Deep Learning for Intelligent Precision Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206434","The fusion of multi-source remote sensing data and deep learning technology has been increasingly applied in precision agriculture. This review focuses on the perception–decision–execution framework and summarizes the current application status, technical routes, and development trends of multi-source remote sensing data fusion and deep learning in precision agriculture. It examines the complementary advantages of multimodal data such as optical, thermal infrared (TIR), Light Detection and Ranging (LiDAR), and synthetic aperture radar (SAR) in characterizing crop physiological traits and structural characteristics. At the algorithmic level, this review analyzes the evolution of deep learning architectures from single convolutional neural networks (CNNs) to spatiotemporal fusion networks (STFNs), Transformer-based architectures, and emerging state-space models, with emphasis on their capabilities for heterogeneous feature extraction and cross-modal information integration. This review discusses the transformation mechanism from intelligent perception to executable decision-making and explores the application effectiveness of prescription maps and variable-rate task technology in improving resource utilization. This review proposes forward-looking views on core bottlenecks such as model generalization, physical interpretability, and edge computing. This review not only provides a theoretical analysis of precision agriculture but also provides academic recommendations for the development of intelligent agricultural equipment in the future.","多源遥感数据与深度学习技术的融合已在精准农业中得到日益广泛的应用。本文以“感知—决策—执行”框架为主线，综述了多源遥感数据融合与深度学习在精准农业中的应用现状、技术路线与发展趋势。文章考察了光学、热红外（TIR）、激光雷达（LiDAR）和合成孔径雷达（SAR）等多模态数据在表征作物生理性状与结构特征方面的互补优势。在算法层面，本文分析了深度学习架构从单一卷积神经网络（CNN）向时空融合网络（STFN）、基于Transformer的架构以及新兴状态空间模型的演进，重点探讨了其在异构特征提取与跨模态信息整合方面的能力。本文讨论了从智能感知到可执行决策的转化机制，并探究了处方图与变量作业技术在提升资源利用率方面的应用效果。针对模型泛化能力、物理可解释性与边缘计算等核心瓶颈，本文提出了前瞻性观点。本文不仅为精准农业提供了理论分析，也为未来智能农业装备的发展提供了学术建议。","Sensors","2026-10-12T00:00:00Z",78,{"impact":17,"substance":103,"depth":17,"authority":19,"freshness":222,"relevant":21,"comment":446},"系统综述多源遥感融合与深度学习在精准农业中的感知—决策—执行框架，方法脉络清晰、前瞻性强，对智慧农业装备研发有参考价值。",[448],{"name":442,"url":439},[109,160,450,28,451],"精准农业","多源数据融合",{"code":32,"slug":33,"name":34,"path":35,"parent_code":9},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":455},{"candidates":456,"agricultural_evidence":46,"reason":62},[457,462,468,472],{"code":58,"score":223,"supported":46,"title":458,"abstract":460,"tags":461},[459],"precision agriculture",[450,459],[109,450],{"code":44,"score":102,"supported":46,"title":463,"abstract":465,"tags":467},[464],"deep learning",[466,464],"深度学习",[160],{"code":52,"score":102,"supported":46,"title":469,"abstract":470,"tags":471},[55],[28,55],[28],{"code":396,"score":45,"supported":46,"title":473,"abstract":474,"tags":477},[],[475,476],"边缘计算","edge computing",[451],[479,480],"多源遥感 深度学习 精准农业","Transformer 遥感 作物表型","多源遥感深度学习精准农业-4825","10.3390\u002Fs26206434",{"doi":482,"openalex_id":484,"authors":485,"venue":442,"cited_by_count":80,"oa_url":439,"card":494,"direction":87,"ingested_from":88},"W7221565940",[486,489,492],{"name":487,"orcid":488},"Zhen Ma","https:\u002F\u002Forcid.org\u002F0000-0003-4377-9651",{"name":490,"orcid":491},"Xiyuan Chen","https:\u002F\u002Forcid.org\u002F0000-0002-1770-8529",{"name":493,"orcid":9},"Cundeng Wang",{"tldr":495,"method":496,"finding":497,"direction":87,"opportunity":498},"综述多源遥感融合与深度学习在精准农业感知-决策-执行框架中的应用与趋势。","综述光学、热红外、LiDAR、SAR融合及CNN到Transformer、状态空","多模态融合与先进深度学习架构可提升作物感知与处方图决策，但泛化性、可解释性和边缘计算仍是瓶颈。","可探索轻量化状态空间模型与物理约束融合，提升跨区域泛化及边缘端实时决策能力。","2026-10-13T23:30:24.008972Z"]