[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2776":3,"related-2776":99},{"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":9,"secondary_topics":31,"classification":32,"search_phrases":68,"slug":71,"view_count":72,"doi":73,"paper":74,"created_at":98},2776,"Mapping coastal forest retreat using convolutional neural networks and different satellite imagery","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0357346","Coastal forests are increasingly threatened by saturated soil and elevated salinity levels resulting from sea level rise, saltwater intrusion, and storm surges. In response to rising salinization and flooding, healthy coastal forests that rely on freshwater (both wetland forests and low-elevation upland forests) are transitioning into landscapes dominated by dead or dying trees, known as ghost forests. Situated among salt-tolerant shrubs and grasses, ghost forests eventually become marshes or open water. Here, our main objective was to quantify the dynamics and pathways of these forest landscape conversions, as well as the factors contributing to the changes, which is vital for understanding the progression of coastal ecosystem degradation and forecasting future changes. We focused first on identifying the best method to track forest landscape change by exploring the role of multiple remote sensing indices (i.e., multispectral, bi-seasonal, topographical, and phenological metrics) in enhancing the performance of deep learning models (convolutional neural networks, CNNs) for land cover classification in the coastal plain of North Carolina using surface reflectance of Landsat 8 and Sentinel-2 images. Then, we used the best available data (Landsat 8) to understand long-term change and identify patterns of land cover change from 1985 to 2021. Our study reveals that incorporating phenology and topographical indices enhances the separability of the ghost forests class from all other vegetation classes. In our assessment, the higher-resolution Sentinel-2 data (F1 Score = 96.3) outperformed Landsat images (F1 score = 93.4) for the 2021 co-available year. However, Landsat remains an important tool used due to its long-term data record. Therefore, we used Landsat to determine that 21% of forests were lost between 1985 and 2021, and that the rate of loss is increasing. Between 2010 and 2021, 23,876 ha of forest were converted to marsh, ghost forest, and shrub, which is 1.5 times higher than the 16,968 ha lost between 1985 and 2010. These conversions from forest to ghost forest and marshes were driven primarily by proximity to the channel, salinity, and the increasing rate of relative sea level rise (RSLR), which are the key environmental drivers of observed changes. By quantifying these changes, we highlight regions most vulnerable to environmental stressors, providing a basis for targeted conservation strategies.","沿海森林正日益受到海平面上升、盐水入侵和风暴潮导致的土壤饱和与盐度升高的威胁。为应对不断加剧的盐渍化和洪水，依赖淡水的健康沿海森林（包括湿地森林和低海拔高地森林）正在转变为以死亡或濒死树木为主的景观，即“幽灵森林”（ghost forests）。幽灵森林与耐盐灌木和草本植物交错分布，最终演变为沼泽或开阔水域。本研究的主要目标是量化这些森林景观转换的动态过程和路径，以及促成这些变化的因素，这对于理解沿海生态系统退化的进程和预测未来变化至关重要。我们首先聚焦于确定追踪森林景观变化的最佳方法，通过探索多种遥感指数（即多光谱、双季节、地形和物候指标）在提升深度学习模型（卷积神经网络，CNNs）土地覆盖分类性能中的作用，研究区域为北卡罗来纳州沿海平原，使用Landsat 8和Sentinel-2影像的地表反射率数据。随后，我们使用最佳可用数据（Landsat 8）来理解长期变化并识别1985年至2021年的土地覆盖变化模式。研究表明，纳入物候和地形指数可增强幽灵森林类别与所有其他植被类别的可分性。在我们的评估中，对于2021年两星共存的年份，较高分辨率的Sentinel-2数据（F1分数 = 96.3）优于Landsat影像（F1分数 = 93.4）。然而，Landsat因其长期数据记录仍是一个重要的使用工具。因此，我们使用Landsat确定1985年至2021年间21%的森林已经消失，且消失速率正在加快。2010年至2021年间，23,876公顷森林转换为沼泽、幽灵森林和灌木，比1985年至2010年间损失的16,968公顷高出1.5倍。这些从森林到幽灵森林和沼泽的转换主要由距河道距离、盐度和相对海平面上升（RSLR）速率的增加所驱动，这些是观测到的变化的关键环境驱动因素。通过量化这些变化，我们突出了最易受环境胁迫影响的区域，为有针对性的保护策略提供了依据。",null,"PLoS ONE","2026-09-15T00:00:00Z","论文",10,false,82,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,23,14,9,1,"发表于PLoS ONE的研究用CNN结合Landsat与Sentinel-2影像量化海岸森林退化为幽灵森林的过程，方法新颖、数据跨度36年，对沿海生态保护与遥感应用有实质参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"深度学习","遥感监测","海岸防护林","土地覆盖变化","生态退化",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":14,"reason":67},[38,47,54,62],{"code":39,"score":13,"supported":40,"title":41,"abstract":42,"tags":46},"I3",true,[],[43,44,45],"遥感","remote sensing","multispectral",[27],{"code":48,"score":49,"supported":40,"title":50,"abstract":51,"tags":53},"I2",7,[],[26,52],"deep learning",[26],{"code":55,"score":56,"supported":40,"title":57,"abstract":58,"tags":61},"H2",6,[],[59,60],"土壤","soil",[],{"code":63,"score":21,"supported":14,"title":64,"abstract":65,"tags":66},"H6",[],[],[29],"农业相关性需要复核",[69,70],"土地覆盖变化 海岸防护林 深度学习 生态退化","土地覆盖变化 海岸防护林","土地覆盖变化海岸防护林深度学习生态退化-2776",2,"10.1371\u002Fjournal.pone.0357346",{"doi":73,"openalex_id":75,"authors":76,"venue":10,"cited_by_count":88,"oa_url":89,"card":90,"direction":96,"ingested_from":97},"W7213246924",[77,80,83,85],{"name":78,"orcid":79},"Tawakalitu Titilayo Tajudeen","https:\u002F\u002Forcid.org\u002F0000-0003-2405-134X",{"name":81,"orcid":82},"Marcelo Ardón","https:\u002F\u002Forcid.org\u002F0000-0001-7275-2672",{"name":84,"orcid":9},"Mirela Tulbure",{"name":86,"orcid":87},"Katherine L. Martin","https:\u002F\u002Forcid.org\u002F0000-0001-6020-9250",0,"https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle\u002Ffile?id=10.1371\u002Fjournal.pone.0357346&type=printable",{"tldr":91,"method":92,"finding":93,"direction":94,"opportunity":95},"用CNN结合多源遥感指数监测1985-2021年北卡海岸森林退化与幽灵林扩张。","Landsat 8与Sentinel-2影像，多光谱、物候、地形指数，卷积神经网","物候与地形指数提升幽灵林识别；1985-2021年21%森林消失且速率加快，近河道、盐度和海平面上升","农业遥感与作物表型","可迁移该CNN框架到其他海岸带，融合时序Sentinel数据与海平面上升情景预测幽灵林未来扩张。","智慧农业 \u002F 农业物联网","openalex","2026-09-17T23:30:15.391843Z",{"total":56,"page":21,"page_size":56,"items":100},[101,186,251,307,364,419],{"id":102,"title":103,"url":104,"summary":105,"summary_zh":106,"content":9,"source_name":107,"source_url":104,"published_at":108,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":109,"score_detail":110,"sources":114,"tags":116,"primary_topic":120,"secondary_topics":124,"classification":125,"search_phrases":148,"slug":151,"view_count":88,"doi":152,"paper":153,"created_at":185},5576,"Land cover change and soil salinization in Mozambique: A counterfactual analysis over two decades (2001−2022)","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.catena.2026.110691","Soil salinization is a major issue that constrains the sustainable development of agriculture in arid, semi-arid, and coastal lowland areas. It is of great importance for regional land management and climate adaptation to clarify the influence of land cover change on soil salinization. This study aims to quantitatively assess the contribution of land cover change to soil salinization in Mozambique, where both rapid land cover transformation and salinization issues are evident. Firstly, we integrated soil profile electrical conductivity (EC) data, Landsat time-series remote sensing imagery, TerraClimate meteorological data, and the 30 m resolution land cover data, to construct a remote sensing-based EC inversion model for Mozambique. Secondly, we applied a spatially and environmentally constrained counterfactual matching method to quantitatively identify the contributions of different land cover changes on soil salinization trends. Our results reveal that: (1) the spatial distribution of soil salinization in Mozambique exhibits distinct a clear association with proximity to water bodies, with high EC areas primarily concentrated around Lake Malawi in the north and in the coastal regions of Greater Maputo in the south. (2) 26.98% of Mozambique's territory showed a trend of intensifying soil salinization, while 10.88% exhibited a decreasing trend. Areas with intensifying trends are primarily concentrated in the central alluvial plains, localized agricultural development zones, and coastal lowlands. (3) Urbanization was significantly associated with an increasing salinization trend after false discovery rate correction, suggesting that the expansion of impervious surfaces, changes in drainage patterns, and soil compaction may exacerbate localized salt accumulation. Agricultural expansion showed a negative trend difference, consistent with the potential influence of crop cover, tillage, and wet-season leaching, although this association was not significant after false discovery rate correction. The effects of ecological restoration and other factors were not statistically significant. In addition to elucidating the heterogeneous impacts of land cover changes in Mozambique on soil salinization trends, this study also provides methodological guidance and a scientific basis for monitoring\u002Fmanaging soil salinity risks in other coastal lowlands.","土壤盐渍化是制约干旱、半干旱及沿海低地地区农业可持续发展的主要问题。阐明土地覆盖变化对土壤盐渍化的影响，对区域土地管理和气候适应具有重要意义。本研究旨在定量评估土地覆盖变化对莫桑比克土壤盐渍化的贡献，该国土地覆盖转型迅速且盐渍化问题突出。首先，我们整合了土壤剖面电导率（EC）数据、Landsat时间序列遥感影像、TerraClimate气象数据以及30 m分辨率土地覆盖数据，构建了基于遥感的莫桑比克EC反演模型。其次，我们采用空间与环境约束的反事实匹配方法，定量识别不同土地覆盖变化对土壤盐渍化趋势的贡献。研究结果表明：（1）莫桑比克土壤盐渍化的空间分布与水体邻近性呈现明显的关联，高EC区域主要集中于北部的马拉维湖周边以及南部大马普托沿海地区。（2）莫桑比克26.98%的国土面积呈现土壤盐渍化加剧趋势，而10.88%呈现减轻趋势。加剧趋势区域主要集中于中部冲积平原、局部农业开发区及沿海低地。（3）经错误发现率校正后，城市化与盐渍化加剧趋势显著相关，表明不透水面扩张、排水格局改变及土壤压实可能加剧局部盐分累积。农业扩张呈现负向趋势差异，与作物覆盖、耕作及湿季淋洗的潜在影响一致，但该关联经错误发现率校正后不显著。生态恢复及其他因素的影响在统计上不显著。本研究不仅阐明了莫桑比克土地覆盖变化对土壤盐渍化趋势的异质性影响，还为其他沿海低地土壤盐渍化风险的监测与管理提供了方法学指导和科学依据。","CATENA","2026-10-20T00:00:00Z",79,{"impact":111,"substance":112,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":113},16,22,"该研究基于遥感与反事实匹配方法，定量评估土地覆盖变化对盐渍化的贡献，方法新颖、结论可靠，对沿海低地盐渍化监测具有参考价值，但属境外区域研究，国内政策与产业影响有限。",[115],{"name":107,"url":104},[27,117,118,29,119],"莫桑比克","土壤盐渍化","盐分反演",{"code":55,"slug":60,"name":121,"path":122,"parent_code":123},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":126,"locked":14,"version":34,"method":35,"evidence":127},"classified",{"candidates":128,"agricultural_evidence":40},[129,133,137,144],{"code":55,"score":19,"supported":40,"title":130,"abstract":131,"tags":132},[60],[59,60],[],{"code":39,"score":49,"supported":40,"title":134,"abstract":135,"tags":136},[],[43,44],[27],{"code":138,"score":56,"supported":40,"title":139,"abstract":140,"tags":143},"H7",[],[141,142],"气候适应","干旱",[],{"code":63,"score":21,"supported":14,"title":145,"abstract":146,"tags":147},[],[],[29],[149,150],"莫桑比克 土壤盐渍化 遥感","土地覆盖变化 盐渍化 反事实分析","莫桑比克土壤盐渍化遥感-5576","10.1016\u002Fj.catena.2026.110691",{"doi":152,"openalex_id":154,"authors":155,"venue":107,"cited_by_count":88,"oa_url":104,"card":180,"direction":94,"ingested_from":97},"W7223069171",[156,158,160,162,165,167,170,173,175,177],{"name":157,"orcid":9},"Yue Li",{"name":159,"orcid":9},"Mengfei Shi",{"name":161,"orcid":9},"Fei Zhang",{"name":163,"orcid":164},"Brian Alan Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1911-3585",{"name":166,"orcid":9},"Gowhar Meraj",{"name":168,"orcid":169},"Jaime Carlos Macuácua","https:\u002F\u002Forcid.org\u002F0000-0002-4822-6098",{"name":171,"orcid":172},"Pankaj Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5264-3951",{"name":174,"orcid":9},"Yuanfang Chai",{"name":176,"orcid":9},"Hongtao Xu",{"name":178,"orcid":179},"Xu Ma","https:\u002F\u002Forcid.org\u002F0000-0003-0644-7498",{"tldr":181,"method":182,"finding":183,"direction":94,"opportunity":184},"量化莫桑比克2001-2022年土地覆盖变化对土壤盐渍化的贡献。","融合EC剖面、Landsat时序与气候数据反演EC，并用空间环境约束的反事实匹配","26.98%区域盐渍化加剧；城市化显著关联盐渍化上升，农业扩张关联不显著。","可将反事实匹配框架迁移至其他滨海低地，并引入作物类型与灌溉制度细化农业扩张的盐渍化效应。","2026-10-22T11:20:42.713789Z",{"id":187,"title":188,"url":189,"summary":190,"summary_zh":191,"content":9,"source_name":192,"source_url":189,"published_at":193,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":194,"score_detail":195,"sources":200,"tags":202,"primary_topic":9,"secondary_topics":206,"classification":207,"search_phrases":226,"slug":229,"view_count":88,"doi":230,"paper":231,"created_at":250},5010,"Analysis of Land Cover Change Using Support Vector Machine Algorithm on Satellite Imagery (Case Study: Mining Area of IWIP).","https:\u002F\u002Fdoi.org\u002F10.58602\u002Fitsecs.v4i4.388","Unsupervised mining activities and the lack of proper management of the environment can bring very serious ecological effects. One of the worst is large-scale land cover change. This paper investigates the land cover changes in the mining area of PT Indonesia Weda Bay Industrial Park (IWIP), Weda Bay Nickel (WBN) area, and measures the performance of the Support Vector Machine technique of land cover classification using satellite imagery. This research is a quantitative study based on a remote sensing technique and spatial analysis in a GIS environment. Multi-temporal satellite images, Landsat-7 (2010), Landsat-8 (2014), and Sentinel-2 (2019 and 2025) were processed to land cover classes (vegetation, open land, cloud) based on the spectral indices NDVI, NDBI, and BSI. Through the post-classification comparison method, land cover changes were detected. The overall change from 2010 to 2025 is quite significant. The vegetation cover decreased from 91.2% to 84.3%, while open land increased from less than 1% to 11.4%. The greatest changes were observed in 2019 and 2025, suggesting that mining activities and related industry development have speed up A lot. The Support Vector Machine algorithm reached excellent classification accuracy over the different periods (97.47%, 96.67%, 89.52%, 95.12% in the cases of 2010 2014 2019 and 2025 respectively), and the results were supported by the high Kappa agreement scores (ranging from 0.84 to 0.96). The low difference between training and testing accuracy indicates a strong generalization without any sign of the model getting overfitted to the training data. The work highlights that Support Vector Machine algorithm, is a very good and reliable method for detecting land cover change in mining areas, where patterns are both complex as well as dynamic.","无监督的采矿活动和缺乏适当的环境管理可能带来非常严重的生态影响。其中最严重的影响之一是大规模的土地覆盖变化。本文研究了PT Indonesia Weda Bay Industrial Park（IWIP）矿区、Weda Bay Nickel（WBN）地区的土地覆盖变化，并评估了利用卫星影像进行土地覆盖分类的支持向量机（Support Vector Machine）技术的性能。本研究是一项基于遥感技术和GIS环境下空间分析的定量研究。多时相卫星影像Landsat-7（2010年）、Landsat-8（2014年）和Sentinel-2（2019年和2025年）基于光谱指数NDVI、NDBI和BSI被处理为土地覆盖类别（植被、裸地、云）。通过分类后比较法，检测了土地覆盖变化。2010年至2025年的总体变化相当显著。植被覆盖从91.2%下降至84.3%，而裸地从不足1%增加至11.4%。最大的变化出现在2019年和2025年，表明采矿活动及相关产业发展已大幅加速。支持向量机算法在不同时期均达到了优异的分类精度（2010年、2014年、2019年和2025年分别为97.47%、96.67%、89.52%、95.12%），且结果得到了高Kappa一致性系数的支持（范围为0.84至0.96）。训练精度与测试精度之间的低差异表明模型具有较强的泛化能力，没有出现过拟合训练数据的迹象。该研究强调，支持向量机算法是一种非常好且可靠的方法，可用于检测采矿区域的土地覆盖变化，因为这些区域的模式既复杂又动态。","Journal of Information Technology Software Engineering and Computer Science (ITSECS)","2026-10-13T00:00:00Z",66,{"impact":196,"substance":197,"depth":111,"authority":13,"freshness":198,"relevant":21,"comment":199},12,20,8,"以SVM结合多时相卫星影像量化IWIP镍矿区2010—2025年植被与裸地变化，方法可靠、数据扎实，对矿区生态遥感监测有参考价值，但属区域案例研究，公共影响有限。",[201],{"name":192,"url":189},[27,203,29,204,205],"矿区生态","支持向量机","镍矿开采",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":208},{"candidates":209,"agricultural_evidence":14,"reason":67},[210,218,222],{"code":211,"score":20,"supported":40,"title":212,"abstract":213,"tags":217},"I4",[],[214,215,216],"空间分析","GIS","spatial analysis",[],{"code":39,"score":49,"supported":40,"title":219,"abstract":220,"tags":221},[],[43,44],[27],{"code":63,"score":72,"supported":14,"title":223,"abstract":224,"tags":225},[],[],[29,203],[227,228],"IWIP 矿区 土地覆盖","Sentinel-2 镍矿 遥感","IWIP矿区土地覆盖-5010","10.58602\u002Fitsecs.v4i4.388",{"doi":230,"openalex_id":232,"authors":233,"venue":192,"cited_by_count":88,"oa_url":244,"card":245,"direction":94,"ingested_from":97},"W7221684953",[234,236,238,241],{"name":235,"orcid":9},"Efraim Julian Soma",{"name":237,"orcid":9},"Winsy Christo Deilan Weki",{"name":239,"orcid":240},"Rillya Arundaa","https:\u002F\u002Forcid.org\u002F0009-0008-4979-5525",{"name":242,"orcid":243},"Mahardika Inra Takaendengan","https:\u002F\u002Forcid.org\u002F0000-0001-8622-7537","https:\u002F\u002Fejournal.techcart-press.com\u002Findex.php\u002Fitsecs\u002Farticle\u002Fdownload\u002F388\u002F338",{"tldr":246,"method":247,"finding":248,"direction":94,"opportunity":249},"用SVM分类多时相卫星影像，分析印尼IWIP矿区2010-2025年土地覆盖变化。","Landsat-7\u002F8与Sentinel-2影像，NDVI\u002FNDBI\u002FBSI指数","植被从91.2%降至84.3%，裸地升至11.4%，SVM精度89.5%-97.5%，Kappa 0","可将SVM与深度学习结合，提升多云热带矿区影像分类鲁棒性并做变化驱动力归因。","2026-10-15T23:30:32.156647Z",{"id":252,"title":253,"url":254,"summary":255,"summary_zh":256,"content":9,"source_name":257,"source_url":254,"published_at":258,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":88,"score_detail":259,"sources":261,"tags":263,"primary_topic":265,"secondary_topics":270,"classification":271,"search_phrases":282,"slug":285,"view_count":21,"doi":286,"paper":287,"created_at":306},4513,"Spatio-temporal assessment of mining-induced environmental changes using remote sensing: a case study of the Talcher Coalfield, Angul District, India","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-74815-7","This study evaluates the spatio-temporal impacts of coal mining on environmental conditions in the Talcher coalfield region, India, using multi-temporal Landsat data (2000, 2014, and 2023) at 30 m resolution. Land use land cover (LULC) was derived using supervised classification (Maximum Likelihood Algorithm), while vegetation dynamics and thermal characteristics were assessed using the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST). In addition, atmospheric column densities were incorporated to analyze key atmospheric pollutants SO₂, NO₂, and CO and to assess air quality variations associated with mining activities. The integrated assessment highlights substantial environmental changes associated with mining and land-use transformation. The LULC analysis (2000–2023) reveals a decline in forest cover (41.33% to 37.37%) and agricultural land (45.62% to 45.04%), accompanied by an increase in built-up areas (6.84% to 8.54%) and mining areas (2.12% to 4.94%), indicating intensified anthropogenic pressure. LST and NDVI analyses (2014–2023) show changes in surface thermal conditions and vegetation characteristics. LST results indicate higher maximum and mean temperatures in mining and built-up areas, with changes between 2014 and 2023 varying among land-use classes, with mining areas showing the highest thermal values, where mean summer LST increased from 42.97 °C (2014) to 46.28 °C (2023), and mean winter LST increased from 38.67 °C to 41.81 °C. NDVI analysis indicates a decline in maximum NDVI values over the study period. The results show a spatial association between LULC changes, NDVI, and LST, with areas of mining and built-up expansion generally corresponding to lower NDVI and higher surface temperatures. Analysis of satellite-derived atmospheric column densities indicates higher SO₂, NO₂, and CO values in mining and industrial regions, with higher values observed during winter.","本研究利用30 m分辨率的多时相Landsat数据（2000年、2014年和2023年），评估了印度塔尔切尔煤田地区煤矿开采对环境条件的时空影响。土地利用\u002F土地覆盖（LULC）通过监督分类（最大似然算法）获得，植被动态和热特征则分别采用归一化差异植被指数（NDVI）和地表温度（LST）进行评估。此外，研究还引入大气柱密度以分析主要大气污染物SO₂、NO₂和CO，并评估与采矿活动相关的空气质量变化。综合评估揭示了与采矿和土地利用转型相关的显著环境变化。LULC分析（2000—2023年）显示，森林覆盖面积（从41.33%降至37.37%）和农业用地（从45.62%降至45.04%）减少，而建成区面积（从6.84%增至8.54%）和采矿区域面积（从2.12%增至4.94%）增加，表明人为压力加剧。LST和NDVI分析（2014—2023年）显示地表热条件和植被特征发生变化。LST结果表明，采矿区和建成区的最高温度和平均温度较高，2014年至2023年的变化因土地利用类型而异，其中采矿区的热值最高，夏季平均LST从42.97 °C（2014年）升至46.28 °C（2023年），冬季平均LST从38.67 °C升至41.81 °C。NDVI分析表明，研究期内最大NDVI值下降。结果表明，LULC变化、NDVI和LST之间存在空间关联，采矿和建成区扩张区域通常对应较低的NDVI和较高的地表温度。卫星反演的大气柱密度分析表明，采矿和工业区域的SO₂、NO₂和CO值较高，且冬季观测值更高。","Scientific Reports","2026-10-07T00:00:00Z",{"impact":88,"substance":88,"depth":88,"authority":88,"freshness":88,"relevant":88,"comment":260},"该研究聚焦印度煤矿区环境遥感监测，与三农、农业信息化、智慧农业等主题无直接关联，不建议进入每日精选。",[262],{"name":257,"url":254},[27,264,203,29],"地表温度",{"code":39,"slug":266,"name":267,"path":268,"parent_code":269},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":126,"locked":14,"version":34,"method":35,"evidence":272},{"candidates":273,"agricultural_evidence":40},[274,278],{"code":39,"score":13,"supported":40,"title":275,"abstract":276,"tags":277},[44],[],[264,27],{"code":63,"score":72,"supported":14,"title":279,"abstract":280,"tags":281},[],[],[29,203],[283,284],"Talcher 煤田 遥感","Landsat NDVI LST 矿区","Talcher煤田遥感-4513","10.1038\u002Fs41598-026-74815-7",{"doi":286,"openalex_id":288,"authors":289,"venue":257,"cited_by_count":88,"oa_url":300,"card":301,"direction":94,"ingested_from":97},"W7220855962",[290,292,294,297],{"name":291,"orcid":9},"Sk Riyajul Islam",{"name":293,"orcid":9},"Shilpa Pakhira",{"name":295,"orcid":296},"Abhilash Gogineni","https:\u002F\u002Forcid.org\u002F0000-0002-8350-468X",{"name":298,"orcid":299},"Regasa Yadeta Sembeta","https:\u002F\u002Forcid.org\u002F0000-0002-9686-3155","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-74815-7_reference.pdf",{"tldr":302,"method":303,"finding":304,"direction":94,"opportunity":305},"基于多时相Landsat遥感评估印度煤矿区2000-2023年环境变化。","Landsat多时相数据、最大似然监督分类、NDVI、LST及SO₂\u002FNO₂\u002FC","采矿与建设用地扩张导致林地耕地减少，矿区夏季均温升至46.28°C，NDVI下降，污染物冬季偏高。","可借鉴其多指标遥感框架，研究矿区周边农田退化与作物表型响应，构建农业环境风险监测模型。","2026-10-09T23:30:27.643699Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":9,"source_name":257,"source_url":310,"published_at":313,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":88,"score_detail":314,"sources":316,"tags":318,"primary_topic":9,"secondary_topics":320,"classification":321,"search_phrases":333,"slug":336,"view_count":337,"doi":338,"paper":339,"created_at":363},4231,"CrossCD-Eval: a unified framework with domain-aware feature normalization for cross-domain remote sensing change detection","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-70914-7","Abstract Change detection (CD) in remote sensing imagery is essential for monitoring urban growth, land-use transformation, and environmental dynamics. However, cross-domain change detection remains challenging due to distribution shifts caused by differences in geographic regions, spatial resolutions, sensor\u002Facquisition conditions, temporal periods, and annotation protocols. This paper introduces CrossCD-Eval, a unified framework for evaluating the generalization of deep learning-based change detection models under in-domain, cross-domain, and few-shot domain adaptation settings. Five recent models, namely GLAFormer 1 , Change-Mamba 2 , EHCTNet 3 , ELGC-Net 4 , and STNet 5 , are evaluated using CLCD, HRSCD, and LEVIR-CD. To reduce representation-level domain mismatch, we propose a Domain-Aware Feature Normalization (DAFN) module that aligns source and target feature statistics as a lightweight feature-level adaptation component. Experimental results show that all models achieve strong in-domain performance but degrade under cross-domain transfer, confirming the impact of domain shift. DAFN improves cross-domain and few-shot adaptation performance, with larger gains observed under more challenging source–target shifts. Repeated 10-shot experiments over five random target-sample selections further show that DAFN improves adaptation stability, reducing IoU standard deviation by up to 22.7%. An additional ablation and baseline-comparison study demonstrates that the observed gains are not solely due to preprocessing. Compared with full preprocessing, AdaBN, adversarial feature alignment, and the instance-normalization-based CrossCDNet baseline, DAFN provides additional feature-level adaptation benefits, especially when combined with strong backbones such as STNet.","摘要 遥感影像中的变化检测（CD）对于监测城市扩张、土地利用转变和环境动态至关重要。然而，由于地理区域、空间分辨率、传感器\u002F采集条件、时间段和标注协议差异所导致的分布偏移，跨域变化检测仍然具有挑战性。本文提出CrossCD-Eval，一个用于评估基于深度学习的变化检测模型在域内、跨域和少样本域适应设置下泛化能力的统一框架。使用CLCD、HRSCD和LEVIR-CD对五个近期模型进行了评估，即GLAFormer 1、Change-Mamba 2、EHCTNet 3、ELGC-Net 4和STNet 5。为减少表示层面的域不匹配，我们提出域感知特征归一化（DAFN）模块，作为轻量级特征级适应组件，对齐源域和目标域的特征统计量。实验结果表明，所有模型均取得较强的域内性能，但在跨域迁移时性能下降，证实了域偏移的影响。DAFN提升了跨域和少样本适应性能，在更具挑战性的源-目标偏移下增益更大。在五次随机目标样本选择上重复进行的10-shot实验进一步表明，DAFN提升了适应稳定性，将IoU标准差最多降低22.7%。额外的消融和基线对比研究表明，所观察到的增益并非仅由预处理所致。与完整预处理、AdaBN、对抗特征对齐以及基于实例归一化的CrossCDNet基线相比，DAFN提供了额外的特征级适应收益，尤其是与STNet等强骨干网络结合时。","2026-10-03T00:00:00Z",{"impact":88,"substance":88,"depth":88,"authority":88,"freshness":88,"relevant":88,"comment":315},"属遥感变化检测通用方法研究，未涉及农业场景，与三农及农业信息化主题不相关。",[317],{"name":257,"url":310},[26,27,319],"变化检测",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":322},{"candidates":323,"agricultural_evidence":14,"reason":67},[324,329],{"code":39,"score":325,"supported":40,"title":326,"abstract":327,"tags":328},15,[44],[43,44],[27],{"code":48,"score":49,"supported":40,"title":330,"abstract":331,"tags":332},[],[26,52],[26],[334,335],"CrossCD-Eval 跨域变化检测","遥感变化检测 域自适应","CrossCD-Eval跨域变化检测-4231",3,"10.1038\u002Fs41598-026-70914-7",{"doi":338,"openalex_id":340,"authors":341,"venue":257,"cited_by_count":88,"oa_url":357,"card":358,"direction":94,"ingested_from":97},"W7218559287",[342,345,348,351,354],{"name":343,"orcid":344},"Menna M. Elkholy","https:\u002F\u002Forcid.org\u002F0000-0003-4475-5424",{"name":346,"orcid":347},"Hala M. Ebied","https:\u002F\u002Forcid.org\u002F0000-0001-9843-842X",{"name":349,"orcid":350},"Mohamed F. Tolba","https:\u002F\u002Forcid.org\u002F0000-0003-3104-6418",{"name":352,"orcid":353},"Marwa S. Moustafa","https:\u002F\u002Forcid.org\u002F0000-0003-3805-9668",{"name":355,"orcid":356},"Dina Elsayad","https:\u002F\u002Forcid.org\u002F0000-0003-3934-7637","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-70914-7.pdf",{"tldr":359,"method":360,"finding":361,"direction":94,"opportunity":362},"提出统一框架CrossCD-Eval评估跨域遥感变化检测，并设计DAFN模块提升跨域泛化。","在CLCD、HRSCD、LEVIR-CD上评测五种模型，提出域感知特征归一化DA","模型域内表现强但跨域下降，DAFN提升跨域与少样本适应，IoU标准差最多降22.7%。","可将DAFN用于农业跨区域\u002F跨传感器作物变化监测，探索轻量域适应与少样本迁移。","2026-10-05T23:30:25.083737Z",{"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":88,"score_detail":372,"sources":374,"tags":376,"primary_topic":9,"secondary_topics":379,"classification":380,"search_phrases":395,"slug":398,"view_count":399,"doi":400,"paper":401,"created_at":418},3798,"Debris Flow Susceptibility Mapping Using Explainable Deep Learning in Eastern Hindukush Pakistan","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fesp.70419","ABSTRACT Debris flows are among the most destructive geomorphological hazards in mountainous regions, causing damage to human settlements, infrastructure and ecosystems. The Eastern Hindu Kush region of Pakistan is particularly vulnerable due to steep topography, intense monsoonal precipitation, active tectonics and increasing anthropogenic disturbance. This study develops an integrated debris flow susceptibility assessment framework by combining convolutional neural networks (CNN) with SHapley Additive exPlanations (SHAP). A total of 13 conditioning factors representing topographic, hydrological, geological, environmental and anthropogenic characteristics were prepared using GIS and remote sensing datasets at a spatial resolution of 30 × 30 m. The CNN model demonstrated strong predictive performance, achieving an area under the curve (AUC) of 0.94, overall accuracy (ACC) of 0.86, precision of 0.84, recall of 0.88, an F1‐score of 0.86 and a Kappa coefficient of 0.71. The resulting susceptibility map identified approximately 26.3% of the study area as high to very high susceptibility zones, predominantly concentrated along steep river valleys and highly dissected mountainous terrain. The susceptibility map was further validated by debris flow density analysis, which showed hazard density increasing from 0 events\u002Fkm 2 in very low zones to 0.048 events\u002Fkm 2 in very high zones, with most historical debris flow events concentrated within the very high susceptibility class. SHAP analysis identified slope, NDVI, rainfall, distance to roads and distance to streams as the most influential conditioning factors controlling debris flow occurrence. The proposed CNN–SHAP framework provides a robust and interpretable approach for regional‐scale debris flow susceptibility assessment, with applicability to similar mountainous environments. These findings provide valuable information for hazard mitigation, infrastructure planning and land‐use management in data‐scarce mountain regions.","泥石流是山区最具破坏性的地貌灾害之一，会对人类聚居地、基础设施和生态系统造成损害。巴基斯坦东兴都库什地区由于地形陡峭、季风降水强烈、构造活动活跃以及人为干扰日益加剧，尤为脆弱。本研究通过将卷积神经网络（CNN）与SHapley加法解释（SHAP）相结合，构建了一个综合性的泥石流易发性评估框架。利用GIS和遥感数据集，以30×30 m的空间分辨率制备了代表地形、水文、地质、环境和人为特征的13个 conditioning factors（孕灾因子）。CNN模型表现出较强的预测性能，曲线下面积（AUC）达到0.94，总体精度（ACC）为0.86，精确率为0.84，召回率为0.88，F1分数为0.86，Kappa系数为0.71。所得易发性图识别出约26.3%的研究区域为高至极高易发性区，主要集中于陡峭的河谷和高度切割的山地地形。易发性图进一步通过泥石流密度分析得到验证，结果显示灾害密度从极低区的0 events\u002Fkm²增加到极高区的0.048 events\u002Fkm²，且大多数历史泥石流事件集中在极高易发性类别内。SHAP分析识别出坡度、NDVI、降雨量、距道路距离和距河流距离是控制泥石流发生的最具影响力的孕灾因子。所提出的CNN–SHAP框架为区域尺度泥石流易发性评估提供了一种稳健且可解释的方法，适用于类似的山区环境。这些发现为数据稀缺山区的灾害减缓、基础设施规划和土地利用管理提供了有价值的信息。","Earth Surface Processes and Landforms","2026-09-27T00:00:00Z",{"impact":88,"substance":88,"depth":88,"authority":88,"freshness":88,"relevant":88,"comment":373},"泥石流易发性遥感与深度学习研究，属地质灾害领域，与三农、农业信息化无直接关联，不建议进入每日精选。",[375],{"name":370,"url":367},[26,377,27,378],"SHAP","地质灾害",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":381},{"candidates":382,"agricultural_evidence":14,"reason":67},[383,387,391],{"code":48,"score":13,"supported":40,"title":384,"abstract":385,"tags":386},[52],[],[377,26],{"code":39,"score":49,"supported":40,"title":388,"abstract":389,"tags":390},[],[43,44],[27],{"code":211,"score":337,"supported":40,"title":392,"abstract":393,"tags":394},[],[215],[],[396,397],"东兴都库什 泥石流 易发性","CNN SHAP 泥石流","东兴都库什泥石流易发性-3798",4,"10.1002\u002Fesp.70419",{"doi":400,"openalex_id":402,"authors":403,"venue":370,"cited_by_count":88,"oa_url":412,"card":413,"direction":94,"ingested_from":97},"W7214538761",[404,407,409],{"name":405,"orcid":406},"Kashif Ullah","https:\u002F\u002Forcid.org\u002F0000-0003-2880-0977",{"name":408,"orcid":9},"Xi Chen",{"name":410,"orcid":411},"Tie Liu","https:\u002F\u002Forcid.org\u002F0000-0002-6879-4818","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1002\u002Fesp.70419",{"tldr":414,"method":415,"finding":416,"direction":94,"opportunity":417},"用CNN结合SHAP绘制巴基斯坦东兴都库什泥石流易发性图并解释关键因子。","CNN模型+SHAP，基于GIS与遥感13个30米条件因子。","高易发区占26.3%，坡度、NDVI、降雨、道路与河流距离最关键。","可将CNN-SHAP框架迁移至山区农业灾害风险与耕地安全评估，弥补数据稀缺区研究空白。","2026-09-29T23:30:30.418175Z",{"id":420,"title":421,"url":422,"summary":423,"summary_zh":424,"content":9,"source_name":425,"source_url":422,"published_at":426,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":88,"score_detail":427,"sources":429,"tags":431,"primary_topic":9,"secondary_topics":435,"classification":436,"search_phrases":455,"slug":458,"view_count":72,"doi":459,"paper":460,"created_at":474},3671,"CLOUD-BASED MULTI-TEMPORAL SAR-OPTICAL FUSION USING RANDOM FOREST FOR GEOSPATIAL INTELLIGENCE MONITORING OF KIPP IKN NUSANTARA","https:\u002F\u002Fdoi.org\u002F10.21163\u002Fgt_2027.221.08","The development of Indonesia's new capital (IKN) Nusantara drives dramatic land-cover transformation across a strategic 17,599-hectare area under the persistent cloud cover of Kalimantan, where optical remote sensing alone is insufficient for continuous monitoring.This study proposes a cloud-based multi-temporal SAR-optical fusion approach using Random Forest classification for geospatial-intelligence (GEOINT) monitoring of the Core Government Area (KIPP) of IKN.Using Google Earth Engine, we processed 70 Sentinel-1 GRD and 52 Sentinel-2 images for 2022 and 61 and 81 images for 2024, building a 12-band fusion stack (SAR backscatter VV, VH, VV\u002FVH; optical B2, B3, B4, B8, B11, B12; and NDVI, NDBI, NDWI).Six experiments compared SAR-only, optical-only, and fusion configurations.The Random Forest fusion achieved 88.89% overall accuracy and 0.8609 kappa for 2022 and 85.12% and 0.8127 for 2024 (assessed against ESA WorldCover 2021 class definitions; see Section 2.7), outperforming SAR-only (63.20%) and optical-only (86.44%).Change detection revealed 899.64 ha of direct vegetation-to-built-up conversion, a 60% expansion of built-up area driven by IKN construction.This is the first cloud-based multi-temporal fusion framework applied to KIPP IKN monitoring, with implications for spatial planning, security surveillance, and environmental compliance.","印度尼西亚新首都（IKN）努山塔拉的开发，在加里曼丹持续云覆盖下推动了一个战略性的17,599公顷区域发生剧烈的土地覆盖转变，仅依靠光学遥感不足以实现持续监测。本研究提出了一种基于云的多时相SAR-光学融合方法，采用随机森林分类对IKN核心政府区（KIPP）进行地理空间情报（GEOINT）监测。利用Google Earth Engine，我们处理了2022年的70景Sentinel-1 GRD和52景Sentinel-2影像，以及2024年的61景和81景影像，构建了一个12波段融合数据集（SAR后向散射VV、VH、VV\u002FVH；光学B2、B3、B4、B8、B11、B12；以及NDVI、NDBI、NDWI）。六组实验比较了仅SAR、仅光学和融合配置。随机森林融合在2022年达到88.89%的总体精度和0.8609的kappa系数，2024年为85.12%和0.8127（依据ESA WorldCover 2021类别定义进行评估；见第2.7节），优于仅SAR（63.20%）和仅光学（86.44%）。变化检测揭示了899.64公顷的植被直接转为建成区，IKN建设推动建成区面积扩张60%。这是首个应用于KIPP IKN监测的基于云的多时相融合框架，对空间规划、安全监控和环境合规具有重要意义。","Geographia Technica","2026-09-26T00:00:00Z",{"impact":88,"substance":88,"depth":88,"authority":88,"freshness":88,"relevant":88,"comment":428},"该研究聚焦印尼新首都建设的遥感监测，属地理空间情报领域，与三农、农业信息化、智慧农业等主题无直接关联，故不进入每日精选。",[430],{"name":425,"url":422},[432,27,29,433,434],"随机森林","SAR光学融合","空间规划",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":437},{"candidates":438,"agricultural_evidence":14,"reason":67},[439,443,447,451],{"code":39,"score":49,"supported":40,"title":440,"abstract":441,"tags":442},[],[43,44],[27],{"code":63,"score":21,"supported":14,"title":444,"abstract":445,"tags":446},[],[],[29],{"code":48,"score":21,"supported":14,"title":448,"abstract":449,"tags":450},[],[],[432],{"code":211,"score":21,"supported":14,"title":452,"abstract":453,"tags":454},[],[],[434],[456,457],"Sentinel-1 Sentinel-2 融合","土地覆盖变化 SAR光学融合 空间规划 遥感监测","Sentinel-1Sentinel-2融合-3671","10.21163\u002Fgt_2027.221.08",{"doi":459,"openalex_id":461,"authors":462,"venue":425,"cited_by_count":88,"oa_url":468,"card":469,"direction":94,"ingested_from":97},"W7214434955",[463,465],{"name":464,"orcid":9},"Fajar Sidik Suganda",{"name":466,"orcid":467},"Asep Adang Supriyadi","https:\u002F\u002Forcid.org\u002F0000-0003-1103-6669","https:\u002F\u002Ftechnicalgeography.org\u002Fpdf\u002F1_2027\u002F08_suganda.pdf",{"tldr":470,"method":471,"finding":472,"direction":94,"opportunity":473},"提出云端多时相SAR-光学融合与随机森林方法，监测印尼新首都核心区土地覆盖变化。","Google Earth Engine处理Sentinel-1\u002F2影像，构建12","融合分类精度达88.89%，检测到899.64公顷植被转建设用地，建成区扩张60%。","可迁移至多云农业区作物监测，探索融合特征优化与跨区域泛化能力。","2026-09-28T23:30:27.951741Z"]