[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3504":3,"related-3504":63},{"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,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":62},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。",null,"Tecnología y Ciencias del Agua","2026-09-24T00:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},15,22,18,9,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"农业人工智能","Sentinel-2","遥感","水资源管理","地表水体提取",[32,33],"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",0,"10.24850\u002Fj-tyca-18-03-08",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":6,"card":55,"direction":59,"ingested_from":61},"W7214228825",[40,43,46,49,52],{"name":41,"orcid":42},"Ayoub Benali","https:\u002F\u002Forcid.org\u002F0000-0002-8989-755X",{"name":44,"orcid":45},"Yesma Bendaha","https:\u002F\u002Forcid.org\u002F0000-0002-1347-856X",{"name":47,"orcid":48},"Malika Seddik Bouchouicha","https:\u002F\u002Forcid.org\u002F0009-0001-6092-784X",{"name":50,"orcid":51},"Zakaria Bellahcene","https:\u002F\u002Forcid.org\u002F0000-0003-4353-7871",{"name":53,"orcid":54},"Rachid Rimani","https:\u002F\u002Forcid.org\u002F0000-0002-1923-4312",{"tldr":56,"method":57,"finding":58,"direction":59,"opportunity":60},"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。","农业遥感与作物表型","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。","openalex","2026-09-25T23:30:31.338437Z",{"total":64,"page":21,"page_size":64,"items":65},6,[66,130,170,209,248,292],{"id":67,"title":68,"url":69,"summary":70,"summary_zh":71,"content":9,"source_name":72,"source_url":69,"published_at":73,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":74,"score_detail":75,"sources":82,"tags":84,"search_phrases":87,"slug":90,"view_count":35,"doi":91,"paper":92,"created_at":129},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","Discover Environment","2026-09-11T00:00:00Z",70,{"impact":76,"substance":77,"depth":78,"authority":79,"freshness":80,"relevant":21,"comment":81},12,20,17,13,8,"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。",[83],{"name":72,"url":69},[26,28,85,29,86],"气候适应","降水预测",[88,89],"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","10.1007\u002Fs44274-026-01047-x",{"doi":91,"openalex_id":93,"authors":94,"venue":72,"cited_by_count":35,"oa_url":123,"card":124,"direction":59,"ingested_from":61},"W7212224443",[95,98,100,103,105,108,110,113,115,118,120],{"name":96,"orcid":97},"Pavan Kumar","https:\u002F\u002Forcid.org\u002F0000-0003-3653-8163",{"name":99,"orcid":9},"Megha Paul",{"name":101,"orcid":102},"Prashant K. Srivastava","https:\u002F\u002Forcid.org\u002F0000-0002-4155-630X",{"name":104,"orcid":9},"Manmohan Dobriyal",{"name":106,"orcid":107},"Yogeshwar Singh","https:\u002F\u002Forcid.org\u002F0000-0002-3324-9289",{"name":109,"orcid":9},"Manish Srivastav",{"name":111,"orcid":112},"Ajay Singh","https:\u002F\u002Forcid.org\u002F0000-0003-2933-4058",{"name":114,"orcid":9},"Abu Salim",{"name":116,"orcid":117},"Shams Tabrez Siddiqui","https:\u002F\u002Forcid.org\u002F0000-0002-6567-3383",{"name":119,"orcid":9},"Aasif Aftab",{"name":121,"orcid":122},"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":125,"method":126,"finding":127,"direction":59,"opportunity":128},"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。","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。","2026-09-14T23:30:25.935081Z",{"id":131,"title":132,"url":133,"summary":134,"summary_zh":135,"content":9,"source_name":136,"source_url":133,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":137,"score_detail":138,"sources":141,"tags":143,"search_phrases":147,"slug":150,"view_count":35,"doi":151,"paper":152,"created_at":169},3515,"Soil mapping and fertilizer optimization for precision agriculture using artificial intelligence","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs13198-026-03435-1","Soil mapping and fertilizer optimization for precision agriculture using artificial intelligence。International Journal of Systems Assurance Engineering and Management","基于人工智能的精准农业土壤制图与肥料优化。《国际系统保障工程与管理杂志》","International Journal of Systems Assurance Engineering and Management",62,{"impact":76,"substance":139,"depth":17,"authority":79,"freshness":80,"relevant":21,"comment":140},14,"论文探讨AI用于土壤制图与施肥优化，属智慧农业细分方向，但摘要信息有限、影响面偏窄，暂不建议进入每日精选。",[142],{"name":136,"url":133},[144,26,145,28,146],"智慧农业","精准施肥","土壤制图",[148,149],"土壤制图 人工智能 精准施肥","精准农业 肥料优化 AI","土壤制图人工智能精准施肥-3515","10.1007\u002Fs13198-026-03435-1",{"doi":151,"openalex_id":153,"authors":154,"venue":136,"cited_by_count":35,"oa_url":9,"card":163,"direction":167,"ingested_from":61},"W7214144821",[155,158,160],{"name":156,"orcid":157},"Neetu Mittal","https:\u002F\u002Forcid.org\u002F0000-0002-2012-0523",{"name":156,"orcid":159},"https:\u002F\u002Forcid.org\u002F0000-0001-6923-0013",{"name":161,"orcid":162},"Pradeepta Kumar Sarangi","https:\u002F\u002Forcid.org\u002F0000-0003-3827-6208",{"tldr":164,"method":165,"finding":166,"direction":167,"opportunity":168},"利用人工智能进行土壤制图和肥料优化，以支持精准农业。","人工智能方法，用于土壤制图与肥料优化。","AI可提升土壤制图与肥料优化的精准性，促进精准农业。","农业人工智能与决策模型","可探索多源数据融合与实时决策模型，提升肥料推荐的自适应性和可解释性。","2026-09-25T23:30:49.869002Z",{"id":171,"title":172,"url":173,"summary":174,"summary_zh":175,"content":9,"source_name":176,"source_url":173,"published_at":177,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":178,"score_detail":179,"sources":181,"tags":183,"search_phrases":187,"slug":190,"view_count":35,"doi":191,"paper":192,"created_at":208},3509,"Integrating multi-criteria decision-making and remote sensing for wildfire susceptibility assessment of the Lower Ziz Valley oases in Morocco","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44288-026-00735-8","Oasis ecosystems in North Africa are ecologically and economically vital landscapes. Yet they are increasingly threatened by wildfires driven by intensifying climate change and anthropogenic pressures. Despite this urgency, spatially explicit wildfire susceptibility assessments for arid oasis environments remain scarce. This study develops and validates a Fire Susceptibility Index (FSI) for the Lower Ziz Valley oases in southeastern Morocco using an integrated Multi-Criteria Decision-Making (MCDM) and remote sensing framework. Six conditioning factors were selected: Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), proximity to roads and settlements, and land cover classified via a U-Net deep learning model (overall accuracy: 95%). Factor weights were determined through the Analytic Hierarchy Process (AHP; CR = 0.09) and aggregated using Weighted Linear Combination (WLC). Land cover (w = 0.30) and NDVI (w = 0.25) emerged as dominant controls, with anthropogenic proximity factors jointly accounting for 31% of the index weight. FSI values ranged from 0.30 to 0.91 (mean = 0.67), with 42.7% of the oasis area (~ 1,707 ha) classified as high susceptibility (FSI ≥ 0.7). Validation against the August 2021 fire event (318 ha) demonstrated strong predictive performance: 96.5% of burned pixels fell within high-risk zones, and mean FSI was significantly higher for burned (0.72) than unburned (0.67) pixels ( p \u003C 0.001), with an AUC of 0.703. Corroborating validation against 60 historical fire records (2009–2024) showed that 98% of events occurred in high or extreme susceptibility zones. The resulting FSI map provides a robust spatial basis for prioritizing fuel management interventions and fire prevention strategies. Its integration into a dynamic geodatabase could further support the development of an early warning system (EWS) for operational wildfire prediction in these irreplaceable oasis landscapes.","北非的绿洲生态系统是具有重要生态和经济价值的景观。然而，日益加剧的气候变化和人为压力所驱动的野火正对其构成越来越大的威胁。尽管形势紧迫，针对干旱绿洲环境的空间显式野火易发性评估仍然匮乏。本研究采用多准则决策（MCDM）与遥感相结合的综合框架，为摩洛哥东南部下济兹河谷绿洲开发并验证了火灾易发性指数（FSI）。选取了六个条件因子：地表温度（LST）、归一化差异植被指数（NDVI）、归一化差异水分指数（NDMI）、道路与居民点邻近度，以及通过U-Net深度学习模型分类的土地覆盖（总体精度：95%）。因子权重通过层次分析法（AHP；CR = 0.09）确定，并采用加权线性组合（WLC）进行聚合。土地覆盖（w = 0.30）和NDVI（w = 0.25）成为主导控制因子，人为邻近因子合计占指数权重的31%。FSI值范围为0.30至0.91（均值 = 0.67），其中42.7%的绿洲面积（约1,707公顷）被归类为高易发性（FSI ≥ 0.7）。针对2021年8月火灾事件（318公顷）的验证表明模型具有较强的预测性能：96.5%的过火像元落在高风险区内，过火像元的FSI均值（0.72）显著高于未过火像元（0.67）（p \u003C 0.001），AUC为0.703。对60条历史火灾记录（2009–2024年）的佐证验证显示，98%的事件发生在高或极高易发性区域内。由此生成的FSI图为优先开展可燃物管理干预和火灾预防策略提供了可靠的空间依据。将其整合至动态地理数据库可进一步支持面向这些不可替代的绿洲景观的业务化野火预测预警系统（EWS）的开发。","Discover Geoscience","2026-09-22T00:00:00Z",73,{"impact":76,"substance":18,"depth":19,"authority":79,"freshness":80,"relevant":21,"comment":180},"方法扎实、验证充分的遥感野火易发性研究，对干旱绿洲农业防灾有参考价值，但属区域性案例，公共影响有限。",[182],{"name":176,"url":173},[26,184,28,185,186],"防灾减灾","野火风险","绿洲农业",[188,189],"摩洛哥 Ziz河谷 绿洲 野火","遥感 野火易发性 评估","摩洛哥Ziz河谷绿洲野火-3509","10.1007\u002Fs44288-026-00735-8",{"doi":191,"openalex_id":193,"authors":194,"venue":176,"cited_by_count":35,"oa_url":202,"card":203,"direction":59,"ingested_from":61},"W7213984877",[195,198,200],{"name":196,"orcid":197},"Rachid Ouachoua","https:\u002F\u002Forcid.org\u002F0000-0002-3194-7585",{"name":199,"orcid":9},"Hamid Benssi",{"name":201,"orcid":9},"Najib Kadiri","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44288-026-00735-8.pdf",{"tldr":204,"method":205,"finding":206,"direction":59,"opportunity":207},"构建遥感与多准则决策融合的绿洲野火易发性指数，并验证其预测精度。","AHP加权线性组合，结合LST、NDVI、NDMI、道路居民点及U-Net土地覆","42.7%绿洲面积高易发，96.5%过火区落于高风险区，AUC达0.703。","可延伸至动态地理数据库与实时早期预警系统，融合气象与人类活动数据。","2026-09-25T23:30:35.200699Z",{"id":210,"title":211,"url":212,"summary":213,"summary_zh":214,"content":9,"source_name":215,"source_url":212,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":216,"score_detail":217,"sources":219,"tags":221,"search_phrases":225,"slug":228,"view_count":35,"doi":229,"paper":230,"created_at":247},3503,"Adversarial Patch and Camouflage Attacks on Aerial Object Detection: A Geometry-Aware Review","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26196057","Uncrewed aerial vehicles increasingly rely on on-board deep object detectors for applications such as surveillance, delivery, agriculture, and traffic monitoring. The vulnerability of these detectors to adversarial patches has therefore become a practical safety concern. Research on adversarial patch and camouflage attacks against aerial object detection has expanded rapidly, yet existing reviews consider aerial systems only as one application domain among many and do not examine the unique geometric conditions of aerial imagery. This review surveys adversarial patch and camouflage attacks, together with the corresponding defense mechanisms, for aerial, UAV, and remote sensing object detection. The literature is organized using a taxonomy based on two dimensions: the physical medium of the perturbation and the application domain it targets. Existing methods are then compared with respect to physical robustness, evaluation datasets and detectors, threat models, and their treatment of viewpoint variation. A recurring observation across the literature is that viewpoint variation is represented primarily through object scale, while explicit modeling of viewing geometry remains limited. This trend is closely linked to the characteristics of the aerial datasets used for evaluation, which typically provide realistic imagery but limited geometric information. Consequently, questions concerning viewpoint-dependent placement, degradation, and naturalness remain only partially explored. The review concludes by identifying the major research gaps, future directions, and deployment challenges that are likely to shape the next generation of aerial adversarial attack and defense research.","无人驾驶飞行器（UAV）在监视、配送、农业和交通监测等应用中日益依赖机载深度目标检测器。因此，这些检测器对对抗性补丁的脆弱性已成为一个实际的安全问题。针对空中目标检测的对抗性补丁与伪装攻击研究迅速扩展，然而现有综述仅将空中系统视为众多应用领域之一，并未考察航空影像独特的几何条件。本综述考察了针对空中、无人机及遥感目标检测的对抗性补丁与伪装攻击以及相应的防御机制。文献按照基于两个维度的分类体系进行组织：扰动的物理介质及其所针对的应用领域。随后，现有方法在物理鲁棒性、评估数据集与检测器、威胁模型以及其对视角变化的处理方面进行了比较。文献中反复出现的一个观察是，视角变化主要通过目标尺度来表示，而对观察几何的显式建模仍然有限。这一趋势与用于评估的航空数据集的特征密切相关，这些数据集通常提供真实影像但几何信息有限。因此，关于视角依赖的放置、退化及自然性的问题仅得到部分探讨。本综述最后指出了可能塑造下一代空中对抗攻击与防御研究的主要研究空白、未来方向及部署挑战。","Sensors",67,{"impact":80,"substance":77,"depth":78,"authority":79,"freshness":20,"relevant":21,"comment":218},"系统梳理航空与无人机目标检测的对抗补丁与伪装攻击及防御，指出视角几何建模不足的研究空白，对农业遥感与无人机应用安全有参考价值。",[220],{"name":215,"url":212},[222,26,223,28,224],"无人机","目标检测","对抗攻击",[226,227],"无人机 对抗补丁 目标检测","航空图像 对抗攻击","无人机对抗补丁目标检测-3503","10.3390\u002Fs26196057",{"doi":229,"openalex_id":231,"authors":232,"venue":215,"cited_by_count":35,"oa_url":212,"card":242,"direction":59,"ingested_from":61},"W7214217753",[233,236,239],{"name":234,"orcid":235},"Sandesh Shrestha","https:\u002F\u002Forcid.org\u002F0000-0001-5298-4468",{"name":237,"orcid":238},"K. T. Y. Mahima","https:\u002F\u002Forcid.org\u002F0000-0003-4975-9408",{"name":240,"orcid":241},"Asanka G. Perera","https:\u002F\u002Forcid.org\u002F0000-0003-4021-3943",{"tldr":243,"method":244,"finding":245,"direction":59,"opportunity":246},"综述无人机与遥感目标检测中的对抗补丁与伪装攻击及防御，并提出几何感知分类体系。","基于扰动介质与应用领域的分类法，比较物理鲁棒性、数据集、威胁模型与视角处理。","现有研究多以目标尺度代替视角变化，缺乏显式视角几何建模，因数据集几何信息有限。","可构建含视角几何标注的农业航拍数据集，研究视角依赖的对抗补丁放置与自然性防御。","2026-09-25T23:30:31.219576Z",{"id":249,"title":250,"url":251,"summary":252,"summary_zh":253,"content":9,"source_name":254,"source_url":251,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":255,"score_detail":256,"sources":259,"tags":261,"search_phrases":264,"slug":267,"view_count":35,"doi":268,"paper":269,"created_at":291},3495,"Remote Sensing and GIS in Modern Drought Assessment: Bridging Conventional Methods and Emerging Technologies","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fjgeesi\u002F2026\u002Fv30i91123","Drought is a complex and recurring hydroclimatic hazard that affects agricultural production, water resources, ecosystems and socioeconomic development. Effective drought assessment requires approaches capable of capturing its spatial and temporal variability and its multiple dimensions. This review examines the evolution of drought assessment from conventional drought indices to integrated approaches based on remote sensing and Geographic Information Systems (GIS), with an emphasis on their applications, strengths, limitations and emerging developments. Conventional indices, including the Standardized Precipitation Index (SPI), Standardized Precipitation Evapotranspiration Index (SPEI), Palmer Drought Severity Index (PDSI), Reconnaissance Drought Index (RDI) and Percent of Normal Precipitation Index (PNPI), remain widely used because of their established methodologies and long-term applicability. However, their dependence on meteorological observations can limit spatial characterisation and the representation of vegetation, soil moisture and other land-surface responses. Remote sensing provides spatially extensive and repeated observations of vegetation condition, land surface temperature, soil moisture, evapotranspiration and water-related conditions, enabling the development of satellite-derived drought indicators and indices. GIS further facilitates the integration, spatial analysis, visualisation, and mapping of drought-related information from multiple sources. The review also discusses hybrid approaches that combine climate-based indices with satellite-derived indicators, as well as drought monitoring platforms and multi-source assessment frameworks. Despite substantial advances, challenges remain regarding cloud contamination, differences in spatial and temporal resolution, data continuity, ground-based validation and uncertainty associated with multi-source datasets. Emerging machine learning, deep learning and artificial intelligence approaches offer opportunities for integrating heterogeneous datasets and improving drought characterisation and early warning. Overall, the integration of conventional observations, remote sensing, GIS and advanced analytical approaches provides a promising framework for more comprehensive drought monitoring and risk assessment under increasing climate variability and change.","干旱是一种复杂且反复出现的水文气候灾害，影响农业生产、水资源、生态系统和社会经济发展。有效的干旱评估需要能够捕捉其时空变异性和多维特征的方法。本文综述了干旱评估从传统干旱指数到基于遥感与地理信息系统（GIS）的综合方法的演变，重点探讨其应用、优势、局限性和新兴发展。传统指数，包括标准化降水指数（SPI）、标准化降水蒸散指数（SPEI）、帕尔默干旱强度指数（PDSI）、侦察干旱指数（RDI）和降水距平百分率指数（PNPI），因其方法成熟且具有长期适用性而仍被广泛使用。然而，这些指数对气象观测的依赖可能限制其空间表征能力以及对植被、土壤水分和其他陆面响应的刻画。遥感提供了对植被状况、地表温度、土壤水分、蒸散量及与水相关状况的大范围重复观测，使得卫星衍生的干旱指标和指数得以发展。GIS进一步促进了多来源干旱相关信息的整合、空间分析、可视化和制图。本文还讨论了将基于气候的指数与卫星衍生指标相结合的混合方法，以及干旱监测平台和多源评估框架。尽管取得了实质性进展，但在云污染、时空分辨率差异、数据连续性、地面验证以及多源数据集相关的不确定性方面仍存在挑战。新兴的机器学习、深度学习和人工智能方法为整合异质数据集、改进干旱表征和预警提供了机遇。总体而言，在气候变异性和变化日益加剧的背景下，传统观测、遥感、GIS和先进分析方法的整合为更全面的干旱监测和风险评估提供了一个有前景的框架。","Journal of Geography Environment and Earth Science International",66,{"impact":76,"substance":19,"depth":257,"authority":76,"freshness":80,"relevant":21,"comment":258},16,"综述系统梳理遥感与GIS在干旱评估中的应用演进，方法学价值明确，但属综述类论文、非国内落地事件，影响力有限。",[260],{"name":254,"url":251},[144,26,28,262,263],"GIS","干旱监测",[265,266],"遥感 GIS 干旱评估","卫星遥感 干旱指数","遥感GIS干旱评估-3495","10.9734\u002Fjgeesi\u002F2026\u002Fv30i91123",{"doi":268,"openalex_id":270,"authors":271,"venue":254,"cited_by_count":35,"oa_url":251,"card":286,"direction":59,"ingested_from":61},"W7214156857",[272,274,276,278,280,282,284],{"name":273,"orcid":9},"V. Dhanalakshmi",{"name":275,"orcid":9},"N. Manikandan",{"name":277,"orcid":9},"V. S. Jinsy",{"name":279,"orcid":9},"K. V. Sumesh",{"name":281,"orcid":9},"P. Nideesh",{"name":283,"orcid":9},"P. S. Manju",{"name":285,"orcid":9},"N. Gopika",{"tldr":287,"method":288,"finding":289,"direction":59,"opportunity":290},"综述了从传统干旱指数到遥感、GIS及AI集成的现代干旱评估方法演进。","文献综述，对比SPI、SPEI等传统指数与遥感、GIS及混合方法。","遥感与GIS弥补传统指数空间局限，但云污染、分辨率差异和验证仍是挑战。","可探索多源遥感与机器学习融合的干旱早期预警，重点解决数据不确定性与地面验证。","2026-09-25T23:30:30.576065Z",{"id":293,"title":294,"url":295,"summary":296,"summary_zh":297,"content":9,"source_name":298,"source_url":295,"published_at":299,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":255,"score_detail":300,"sources":302,"tags":304,"search_phrases":308,"slug":311,"view_count":35,"doi":312,"paper":313,"created_at":335},3475,"Cross-sensor urban land-cover characterization using hyperspectral and multispectral satellite imagery","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1908768","Introduction This study establishes a cross-sensor urban remote sensing baseline for future urban digital-intelligence applications by integrating separately classified and validated multispectral (Landsat, Sentinel-2) and hyperspectral (PRISMA) imagery using a common sampling and evaluation framework. Methods Eight land-cover classes — Dense Urban Area, Medium Urban Area, Sparse Urban Area, Tree Cover, Grass, Cropland, Bare Area, and Water — were mapped using Random Forest, Support Vector Machine (SVM), Gradient Boosting Machine, K-Nearest Neighbor, and Classification and Regression Tree algorithms. Performance was evaluated across all three sensors using overall accuracy, Cohen’s kappa, macro-averaged and class-wise F1-scores, class-area composition, spectral profile, Fisher scores, pairwise separability metrics, and principal component analysis (PCA). Results Results demonstrated clear sensor-dependent differences in urban representation and classification accuracy. Sentinel-2 improved spatial characterization of heterogeneous urban surfaces through enhanced spatial resolution and red-edge information. PRISMA produced the highest classification performance, with SVM achieving an overall accuracy of 91.26% and a macro-averaged F1-score of 89.72%. However, this advantage was class-specific rather than uniform across all urban-density classes. Spectral-profile and PCA analysis showed hyperspectral observations substantially improved separability between Medium and Sparse Urban classes (spectral angle: 0.54° Landsat, 1.58° Sentinel-2, 4.11° PRISMA). PRISMA classifications also allocated substantially less area to Sparse Urban Area and more to Bare Area than the multispectral classifications. Discussion This redistribution may reflect improved discrimination of mixed peri-urban surfaces but cannot be considered more accurate without an independent concurrent area-wide reference map. The findings do not establish universal sensor superiority; rather classification outcomes depend jointly on sensor properties, acquisition timing, preprocessing, class definitions, and classifier choice, supporting a complementary interpretation of multispectral and hyperspectral observations.","引言 本研究通过在一个统一的采样与评估框架下，整合分别分类并验证的多光谱（Landsat、Sentinel-2）和高光谱（PRISMA）影像，为未来城市数字智能应用建立了一个跨传感器城市遥感基线。方法 采用随机森林、支持向量机（SVM）、梯度提升机、K近邻以及分类与回归树算法，对八类土地覆盖类型——密集城市区、中等城市区、稀疏城市区、乔木覆盖、草地、农田、裸地和水体——进行制图。利用总体精度、Cohen's kappa系数、宏平均及各类别F1分数、类别面积组成、光谱剖面、Fisher得分、成对可分性指标和主成分分析（PCA），在三种传感器上评估了分类性能。结果 结果表明，城市表征和分类精度存在明显的传感器依赖性差异。Sentinel-2通过增强的空间分辨率和红边信息，改善了对异质城市地表的空间刻画。PRISMA取得了最高的分类性能，其中SVM的总体精度达到91.26%，宏平均F1分数为89.72%。然而，这一优势具有类别特异性，而非在所有城市密度类别上均匀体现。光谱剖面和PCA分析表明，高光谱观测显著改善了中等城市区与稀疏城市区之间的可分性（光谱角：Landsat为0.54°，Sentinel-2为1.58°，PRISMA为4.11°）。与多光谱分类相比，PRISMA分类还将显著更少的面积划为稀疏城市区，而将更多面积划为裸地。讨论 这种面积重分配可能反映了对城乡过渡带混合地表判别能力的提升，但在缺乏独立的同期全域参考图的情况下，不能认为其更为准确。研究结果并未确立某种传感器的普遍优越性；相反，分类结果共同取决于传感器特性、获取时间、预处理、类别定义和分类器选择，这支持对多光谱与高光谱观测进行互补性解读。","Frontiers in Remote Sensing","2026-09-23T00:00:00Z",{"impact":80,"substance":77,"depth":78,"authority":79,"freshness":80,"relevant":21,"comment":301},"跨传感器城市土地覆盖分类研究，方法扎实、结论审慎，对农业遥感与国土监测有参考价值，但属专业论文而非产业级事件。",[303],{"name":298,"url":295},[26,28,305,306,307],"土地覆盖分类","高光谱遥感","城市遥感",[309,310],"PRISMA 高光谱 城市土地覆盖","Sentinel-2 Landsat 城市分类","PRISMA高光谱城市土地覆盖-3475","10.3389\u002Ffrsen.2026.1908768",{"doi":312,"openalex_id":314,"authors":315,"venue":298,"cited_by_count":35,"oa_url":328,"card":329,"direction":334,"ingested_from":61},"W7214084535",[316,318,320,322,325],{"name":317,"orcid":9},"Sawaid Abbas",{"name":319,"orcid":9},"Zohaib",{"name":321,"orcid":9},"Nawai Habib",{"name":323,"orcid":324},"Faisal Mueen Qamer","https:\u002F\u002Forcid.org\u002F0000-0003-0434-652X",{"name":326,"orcid":327},"Majid Nazeer","https:\u002F\u002Forcid.org\u002F0000-0002-7631-1599","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1908768\u002Fpdf",{"tldr":330,"method":331,"finding":332,"direction":59,"opportunity":333},"用统一框架对比Landsat、Sentinel-2与PRISMA在城市土地覆盖分类中的表现。","随机森林、SVM等五种分类器，结合光谱剖面、Fisher分数与PCA评估三传感器","PRISMA高光谱分类精度最高（SVM达91.26%），但优势因城市密度类别而异。","可探索多源遥感互补融合与跨传感器迁移学习，提升混合地表分类的鲁棒性。","智慧农业 \u002F 农业物联网","2026-09-25T23:30:11.302770Z"]