[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5177":3,"related-5177":94},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":9,"secondary_topics":32,"classification":33,"search_phrases":59,"slug":62,"view_count":22,"doi":63,"paper":64,"created_at":93},5177,"Long-term associations between land-surface indicators and dust-storm occurrence along the margins of the Taklimakan Desert","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-75251-3","Land-surface change and atmospheric variability jointly shape dust activity in arid regions. We examined land-cover transitions, station dust-storm records, a Sentinel-1 backscatter index, meteorological variables from the fifth-generation European Centre for Medium-Range Weather Forecasts reanalysis (ERA5) and dust diagnostics from the Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) along the margins of the Taklimakan Desert. Within the mapped domain, grassland increased from 9.45% in 1990 to 10.59% in 2023, while barren land decreased from 86.45% to 82.30%. Annual dust-storm-day trends were negative at 21 of 30 stations over available 1990–2024 records, and Sentinel-1 index trends were positive at 22 stations during 2015–2024. Mixed-effects path analysis of 3,804 station-month observations showed that the Sentinel-1 index was negatively associated with modelled dust emission (standardized coefficient = − 0.191; 95% confidence interval: −0.289 to − 0.043). The normalized difference vegetation index (NDVI) and friction velocity had the highest training-set feature importance in the random forest analysis.","地表变化与大气变率共同塑造了干旱地区的沙尘活动。我们沿塔克拉玛干沙漠边缘，研究了土地覆盖转变、台站沙尘暴记录、Sentinel-1后向散射指数、来自欧洲中期天气预报中心第五代再分析资料（ERA5）的气象变量，以及来自现代研究与应用回顾分析第2版（MERRA-2）的沙尘诊断量。在制图范围内，草地面积从1990年的9.45%增加到2023年的10.59%，而裸地面积从86.45%减少到82.30%。在1990—2024年现有记录中，30个台站中有21个台站的年沙尘暴日数呈下降趋势；2015—2024年间，22个台站的Sentinel-1指数呈上升趋势。对3804个台站—月观测值的混合效应路径分析表明，Sentinel-1指数与模拟沙尘排放呈负相关（标准化系数=−0.191；95%置信区间：−0.289至−0.043）。在随机森林分析中，归一化植被指数（NDVI）和摩擦速度在训练集中的特征重要性最高。",null,"Scientific Reports","2026-10-15T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,8,1,"基于多源遥感与30站长期记录，量化地表指标与沙尘暴关联，方法扎实、数据规模可观，对干旱区生态监测有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"NDVI","荒漠化","遥感监测","土地利用","沙尘暴",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":58},[39,47,53],{"code":40,"score":41,"supported":42,"title":43,"abstract":44,"tags":46},"H7",3,true,[],[45],"干旱",[],{"code":48,"score":49,"supported":14,"title":50,"abstract":51,"tags":52},"H6",2,[],[],[30,28],{"code":54,"score":49,"supported":14,"title":55,"abstract":56,"tags":57},"I3",[],[],[27,29],"农业相关性需要复核",[60,61],"塔克拉玛干沙漠 沙尘暴 遥感","Sentinel-1 土地覆盖 沙尘","塔克拉玛干沙漠沙尘暴遥感-5177","10.1038\u002Fs41598-026-75251-3",{"doi":63,"openalex_id":65,"authors":66,"venue":10,"cited_by_count":84,"oa_url":85,"card":86,"direction":90,"ingested_from":92},"W7222086957",[67,69,72,75,77,79,81],{"name":68,"orcid":9},"Yifei Wang",{"name":70,"orcid":71},"Wen Huo","https:\u002F\u002Forcid.org\u002F0000-0002-7861-2424",{"name":73,"orcid":74},"Mayibaier Maihamuti","https:\u002F\u002Forcid.org\u002F0009-0007-4084-5891",{"name":76,"orcid":9},"Fan Yang",{"name":78,"orcid":9},"Chenglong Zhou",{"name":80,"orcid":9},"Xinghua Yang",{"name":82,"orcid":83},"Ali Mamtimin","https:\u002F\u002Forcid.org\u002F0000-0001-7335-801X",0,"https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75251-3_reference.pdf",{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"分析塔克拉玛干沙漠边缘地表指标与沙尘暴发生的长期关联。","结合土地覆盖、站点沙尘记录、Sentinel-1后向散射、ERA5与MERRA-","站点沙尘日数多呈下降趋势，Sentinel-1指数与模拟沙尘排放显著负相关。","农业遥感与作物表型","可引入多源遥感与机器学习量化地表变化对沙尘的因果贡献，并拓展至绿洲农业防护。","openalex","2026-10-17T23:30:30.235613Z",{"total":95,"page":22,"page_size":95,"items":96},6,[97,146,224,305,371,415],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":104,"score_detail":105,"sources":110,"tags":112,"primary_topic":9,"secondary_topics":115,"classification":116,"search_phrases":129,"slug":132,"view_count":84,"doi":133,"paper":134,"created_at":145},5182,"Land Use Land Cover (LULC) Change Detection in Delhi NCT Using Multi-Sensor Satellite Data and Google Earth Engine","https:\u002F\u002Fdoi.org\u002F10.21275\u002Fsr26903183702","Land Use Land Cover (LULC) change detection is essential for understanding the dynamics of human modified landscapes and for supporting effective land management and urban planning. This study analyses LULC change across the Delhi National Capital Territory over a fifteen-year period, from 2010 to 2025, to assess urban sprawl and its environmental impact in one of India's fastest growing metropolitan regions. Multi temporal Landsat imagery was used as the primary data source, processed on Google Earth Engine, the cloud-based platform that enabled efficient handling and visualisation of large geospatial datasets. Five classes, built up area, agricultural land, vegetation, water, and barren land, were mapped and monitored, and classification accuracy was assessed for both dates. The Normalised Difference Vegetation Index was additionally employed to track vegetation vigour and ecological change. Results reveal a marked expansion of built-up areas alongside a substantial decline in agricultural and vegetated land, driven by peri urban growth along the northwestern and southwestern fringe. NDVI analysis shows rising greenness across the outer belt, reflecting more intensive cultivation on land that remains under crops, a pattern that complements rather than contradicts the measured loss of vegetated area. Combining classification based and an index-based approach provides a robust, scalable framework for LULC monitoring. By revealing where and how urban growth is reshaping the landscape, the study offers a transferable basis for environmental assessment, resource management, and sustainable urban planning in rapidly urbanising regions worldwide.","土地利用\u002F土地覆盖（LULC）变化检测对于理解人类改造景观的动态以及支撑有效的土地管理和城市规划至关重要。本研究分析了德里国家首都辖区在2010年至2025年十五年间的土地利用\u002F土地覆盖变化，以评估印度增长最快的大都市区之一的城市蔓延及其环境影响。研究以多时相Landsat影像作为主要数据源，在Google Earth Engine这一基于云的平台上进行处理，该平台能够高效处理和可视化大型地理空间数据集。研究对建成区、农业用地、植被、水体与裸地五个类别进行了制图和监测，并对两个时相的分类精度进行了评估。此外，研究采用归一化植被指数（NDVI）追踪植被长势与生态变化。结果表明，建成区显著扩张，农业用地和植被用地大幅减少，这一变化主要由西北部和西南部边缘的近郊增长所驱动。NDVI分析显示外围地带的绿度上升，反映出仍处于耕作状态的土地上集约化种植程度提高，这一格局与所测得的植被面积损失相辅相成而非相互矛盾。将基于分类的方法与基于指数的方法相结合，为土地利用\u002F土地覆盖监测提供了一个稳健且可扩展的框架。通过揭示城市增长在何处以及如何重塑景观，本研究为全球快速城市化地区的环境评估、资源管理和可持续城市规划提供了可迁移的基础。","International Journal of Science and Research (IJSR)",62,{"impact":106,"substance":19,"depth":107,"authority":21,"freshness":108,"relevant":22,"comment":109},12,15,9,"方法可迁移的遥感LULC变化检测研究，对快速城市化地区土地管理有参考价值，但属区域案例、非三农核心议题。",[111],{"name":103,"url":100},[27,29,30,113,114],"Google Earth Engine","城市化",[],{"status":117,"locked":14,"version":35,"method":36,"evidence":118},"unclassified",{"candidates":119,"agricultural_evidence":42,"reason":128},[120,124],{"code":54,"score":41,"supported":14,"title":121,"abstract":122,"tags":123},[],[],[113,27,29],{"code":48,"score":22,"supported":14,"title":125,"abstract":126,"tags":127},[],[],[30],"缺少足够的主题证据",[130,131],"德里 土地利用 遥感","Google Earth Engine 城市扩张","德里土地利用遥感-5182","10.21275\u002Fsr26903183702",{"doi":133,"openalex_id":135,"authors":136,"venue":103,"cited_by_count":84,"oa_url":139,"card":140,"direction":90,"ingested_from":92},"W7222341300",[137],{"name":138,"orcid":9},"Neil Rohatgi","https:\u002F\u002Fwww.ijsr.net\u002Farchive\u002Fv15i10\u002FSR26903183702.pdf",{"tldr":141,"method":142,"finding":143,"direction":90,"opportunity":144},"基于多时相Landsat与GEE分析德里国家首都辖区2010-2025年土地利用变化。","多时相Landsat影像、Google Earth Engine平台、五类分类与","建设用地显著扩张，农业与植被用地大幅减少，城郊西北和西南边缘增长驱动。","可结合分类与指数方法构建可迁移框架，拓展至城乡交错带耕地保护与可持续规划研究。","2026-10-17T23:30:31.767409Z",{"id":147,"title":148,"url":149,"summary":150,"summary_zh":151,"content":9,"source_name":152,"source_url":149,"published_at":153,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":104,"score_detail":154,"sources":156,"tags":158,"primary_topic":161,"secondary_topics":167,"classification":172,"search_phrases":198,"slug":201,"view_count":22,"doi":202,"paper":203,"created_at":223},2323,"Land cover transformations in northern Algeria from 2001 to 2021: A MODIS-based spatiotemporal analysis","https:\u002F\u002Fdoi.org\u002F10.30493\u002Fdas.2026.011109","Land use\u002Fland cover (LULC) changes in northern Algeria from 2001 to 2021 were investigated in this research. The assessment utilized the MODIS MCD12Q1 dataset combined with Geographic Information System (GIS) techniques. Substantial landscape transformations were highlighted by the findings. Forests (+47.52%), shrublands (+17.65%), wetlands (+58.64%), and natural vegetation (+465.72%) experienced notable growth, whereas a drop of −14.13% was documented for barren lands by the end of study period. Moderate overall growth was displayed by agricultural lands, despite various fluctuations throughout the timeline. Concurrently, a continuous expansion (+3.90%) driven by escalating anthropogenic pressure was recorded in urban and built-up areas. Regional landscape evolution is clearly shaped by a combination of factors. Climatic variability, ecological succession, land management practices, and human activities collectively drive these observed dynamics. Partial alignment with previously documented vegetation recovery and urban expansion trends in Algeria was demonstrated by comparative literature reviews. However, the moderate spatial resolution (500 m) of the MODIS MCD12Q1 product likely caused several identified data discrepancies. Ultimately, the immense value of remote sensing and GIS approaches for regional environmental monitoring is proven by this project. Achieving better classification accuracy in heterogeneous Mediterranean environments, however, strictly necessitates the use of higher-resolution datasets.","本研究探讨了2001年至2021年阿尔及利亚北部土地利用\u002F土地覆盖（LULC）变化。评估采用MODIS MCD12Q1数据集结合地理信息系统（GIS）技术。研究结果凸显了显著的土地景观转变。森林（+47.52%）、灌木地（+17.65%）、湿地（+58.64%）和自然植被（+465.72%）显著增长，而裸地在研究期末则记录了−14.13%的下降。尽管农业用地在时间线上经历了多次波动，但总体上呈现出适度增长。与此同时，城市和建成区因人为压力不断加剧而记录了持续扩张（+3.90%）。区域景观演变显然由多种因素共同塑造。气候变率、生态演替、土地管理实践和人类活动共同驱动了这些观测到的动态。比较文献综述表明，这与阿尔及利亚先前记录的植被恢复和城市扩张趋势部分吻合。然而，MODIS MCD12Q1产品的中等空间分辨率（500米）可能导致了若干已识别的数据差异。最终，本项目证明了遥感和GIS方法在区域环境监测中的巨大价值。然而，要在异质性较强的地中海环境中实现更好的分类精度，严格需要使用更高分辨率的数据集。","DYSONA – Applied Science","2026-09-11T00:00:00Z",{"impact":21,"substance":19,"depth":107,"authority":106,"freshness":108,"relevant":22,"comment":155},"基于MODIS数据的阿尔及利亚北部20年土地覆被变化分析，方法规范、数据翔实，对遥感监测与区域生态评估有参考价值，但属境外区域研究，国内产业影响有限。",[157],{"name":152,"url":149},[159,28,29,30,160],"农业信息化","植被恢复",{"code":162,"slug":163,"name":164,"path":165,"parent_code":166},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis","I",[168],{"code":54,"slug":169,"name":170,"path":171,"parent_code":166},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":173,"locked":14,"version":35,"method":36,"evidence":174},"classified",{"candidates":175,"agricultural_evidence":42},[176,183,189,193],{"code":162,"score":108,"supported":42,"title":177,"abstract":178,"tags":182},[],[179,180,181],"地理信息","GIS","geographic information",[],{"code":54,"score":21,"supported":42,"title":184,"abstract":185,"tags":188},[],[186,187],"遥感","remote sensing",[160,29],{"code":48,"score":49,"supported":14,"title":190,"abstract":191,"tags":192},[],[],[30,28],{"code":194,"score":22,"supported":14,"title":195,"abstract":196,"tags":197},"I1",[],[],[159],[199,200],"农业信息化 土地利用 植被恢复 遥感监测","农业信息化 土地利用","农业信息化土地利用植被恢复遥感监测-2323","10.30493\u002Fdas.2026.011109",{"doi":202,"openalex_id":204,"authors":205,"venue":152,"cited_by_count":84,"oa_url":149,"card":218,"direction":90,"ingested_from":92},"W7212238590",[206,208,211,214,216],{"name":207,"orcid":9},"Bilel Zerouali",{"name":209,"orcid":210},"Richarde Marques da Silva","https:\u002F\u002Forcid.org\u002F0000-0001-6601-5174",{"name":212,"orcid":213},"Nadjem Bailek","https:\u002F\u002Forcid.org\u002F0000-0001-9051-8548",{"name":215,"orcid":9},"Valeriano Carneiro de Lima Silva",{"name":217,"orcid":9},"Celso Augusto Guimarães Santos",{"tldr":219,"method":220,"finding":221,"direction":90,"opportunity":222},"基于MODIS数据分析了2001—2021年阿尔及利亚北部土地覆盖的时空变化。","使用MODIS MCD12Q1数据集结合GIS技术进行LULC分类与变化检测。","森林、灌丛、湿地和自然植被显著增长，裸地减少，建设用地持续扩张。","可引入高分辨率遥感数据提升地中海异质景观分类精度，并耦合气候与人为驱动因子做归因分析。","2026-09-13T23:30:23.070977Z",{"id":225,"title":226,"url":227,"summary":228,"summary_zh":229,"content":9,"source_name":230,"source_url":227,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":232,"sources":235,"tags":237,"primary_topic":9,"secondary_topics":241,"classification":242,"search_phrases":275,"slug":278,"view_count":84,"doi":279,"paper":280,"created_at":304},5577,"Assessing Land Use and Land Cover Change in the Jamanxim River Region (Brazilian Amazon) from 2015 to 2025 Using CBERS-4\u002FPAN Imagery","https:\u002F\u002Fdoi.org\u002F10.29150\u002Fjhrs.v16i4.269068","Land use and land cover (LULC) changes in the Amazon are among the main drivers of biodiversity loss, ecosystem degradation, and the intensification of climate change. This study aimed to analyze the multitemporal dynamics of LULC around the Jamanxim River, Pará, Brazilian Amazon, between 2015 and 2025, using high-resolution imagery from the CBERS-4\u002FPAN satellite. The study area covers 492.74 km², including part of the Jamanxim National Forest, a conservation unit under strong pressure from agricultural expansion and logging activities. The methodology included geometric correction of the images, Gram–Schmidt pansharpening, and supervised classification with the Random Forest algorithm, validated with historical imagery from Google Earth Pro. Thematic maps of land use and cover were generated, and performance metrics such as overall accuracy, omission and commission errors, and F1-scores were assessed. The results indicated a significant reduction in forest cover, from 412.28 km² in 2015 to 355.47 km² in 2025 (–13.78%). Non-vegetated areas increased by 132.47%, while agricultural areas expanded by 54.97%. The forest and water body classes showed high accuracy (F1-score > 0.95), while confusion persisted between agricultural and bare soil classes. Overall accuracy remained above 90% across all years, with the highest performance recorded in 2020 (96.31%). These results highlight the potential of CBERS-4\u002FPAN imagery for monitoring multitemporal changes in tropical forest landscapes. At the same time, they reveal the intensification of deforestation and the growing threats to conservation in the Amazon, reinforcing the importance of remote sensing for environmental management and policy support.","亚马逊地区的土地利用与土地覆盖（LULC）变化是生物多样性丧失、生态系统退化以及气候变化加剧的主要驱动因素之一。本研究旨在利用CBERS-4\u002FPAN卫星的高分辨率影像，分析2015年至2025年间巴西亚马孙州雅曼辛河（Jamanxim River）周边土地利用与土地覆盖的多时相动态。研究区面积为492.74 km²，包括雅曼辛国家森林（Jamanxim National Forest）的一部分，该保护区正面临农业扩张和采伐活动的强烈压力。研究方法包括影像几何校正、Gram–Schmidt全色锐化以及基于随机森林（Random Forest）算法的监督分类，并利用Google Earth Pro的历史影像进行验证。研究生成了土地利用与覆盖专题图，并评估了总体精度、漏分误差与错分误差以及F1分数等性能指标。结果表明，森林覆盖显著减少，从2015年的412.28 km²降至2025年的355.47 km²（–13.78%）。无植被区域增加了132.47%，农业区域扩张了54.97%。森林和水体类别表现出较高精度（F1分数 > 0.95），而农业类别与裸土类别之间仍存在混淆。各年份总体精度均保持在90%以上，其中2020年性能最高（96.31%）。这些结果凸显了CBERS-4\u002FPAN影像在监测热带森林景观多时相变化方面的潜力，同时揭示了亚马逊地区森林砍伐的加剧以及保护面临的日益增长的威胁，进一步强调了遥感在环境管理和政策支持中的重要性。","Journal of Hyperspectral Remote Sensing","2026-10-20T00:00:00Z",{"impact":19,"substance":18,"depth":233,"authority":106,"freshness":108,"relevant":22,"comment":234},17,"该研究利用CBERS-4\u002FPAN影像量化亚马逊保护区十年间森林减少13.78%，方法规范、结论可靠，对遥感监测与生态保护有参考价值，但地域性强、与国内三农直接关联有限。",[236],{"name":230,"url":227},[29,30,238,239,240],"森林保护","亚马逊","CBERS-4",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":243},{"candidates":244,"agricultural_evidence":42,"reason":274},[245,252,256,262,268],{"code":48,"score":246,"supported":42,"title":247,"abstract":248,"tags":251},7,[],[249,250],"生物多样性","biodiversity",[30],{"code":54,"score":246,"supported":42,"title":253,"abstract":254,"tags":255},[],[186,187],[29],{"code":40,"score":95,"supported":42,"title":257,"abstract":258,"tags":261},[],[259,260],"气候变化","climate change",[],{"code":263,"score":41,"supported":42,"title":264,"abstract":265,"tags":267},"H2",[],[266],"soil",[],{"code":269,"score":41,"supported":42,"title":270,"abstract":271,"tags":273},"I7",[],[272],"研究方法",[],"多个产业证据相当，需要确认主归属",[276,277],"CBERS-4 亚马逊 土地利用","Jamanxim 森林覆盖 遥感","CBERS-4亚马逊土地利用-5577","10.29150\u002Fjhrs.v16i4.269068",{"doi":279,"openalex_id":281,"authors":282,"venue":230,"cited_by_count":84,"oa_url":227,"card":299,"direction":90,"ingested_from":92},"W7223141286",[283,286,288,291,294,297],{"name":284,"orcid":285},"Ubiratan Joaquim da Silva","https:\u002F\u002Forcid.org\u002F0000-0001-7995-6416",{"name":287,"orcid":9},"Gabriel Henrique Santos Silva",{"name":289,"orcid":290},"Juarez Antonio da Silva","https:\u002F\u002Forcid.org\u002F0000-0002-2898-0309",{"name":292,"orcid":293},"Anderson Luiz Ribeiro de Paiva","https:\u002F\u002Forcid.org\u002F0000-0003-3475-1454",{"name":295,"orcid":296},"Leidjane Maria Maciel de Oliveira","https:\u002F\u002Forcid.org\u002F0000-0003-1251-6998",{"name":298,"orcid":9},"Sylvana Melo dos Santos",{"tldr":300,"method":301,"finding":302,"direction":90,"opportunity":303},"用CBERS-4\u002FPAN影像分析亚马逊Jamanxim河流域2015-2025年土地利用变化。","几何校正、Gram-Schmidt融合、随机森林监督分类，Google Eart","森林覆盖减少13.78%，农业扩张54.97%，裸地增132.47%，总体精度超90%。","可探索中巴地球资源卫星在热带森林退化监测中的业务化应用与多源数据融合。","2026-10-22T11:20:42.901761Z",{"id":306,"title":307,"url":308,"summary":309,"summary_zh":310,"content":9,"source_name":311,"source_url":308,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":84,"score_detail":312,"sources":314,"tags":316,"primary_topic":319,"secondary_topics":324,"classification":326,"search_phrases":348,"slug":351,"view_count":84,"doi":352,"paper":353,"created_at":370},5485,"Integrating machine learning and geospatial technologies for spatio-temporal analysis of urban expansion and land use transformation in Gambella Town, Ethiopia","https:\u002F\u002Fdoi.org\u002F10.1371\u002Fjournal.pone.0360419","Rapid urbanization and the associated expansion of built-up areas are transforming land resources, ecosystem functions, and the spatial structure of cities. Distinguishing urban growth, urban expansion, and urban sprawl is essential for understanding the processes and patterns of urban transformation and supporting sustainable urban planning. This study integrates machine learning and geospatial technologies to analyze spatio-temporal land use and land cover (LULC) dynamics and urban expansion in Gambella Town, Ethiopia. Multi-temporal Landsat satellite images from 2005, 2015, and 2025 were processed using remote sensing techniques and a supervised machine learning approach based on the Random Forest (RF) classifier. Six major LULC classes were identified: Agricultural Land, Bush with Grass, Built-Up Area, Bare Land, Forest Land, and Water Bodies. The classification achieved overall accuracies of 90%, 90%, and 89% for 2005, 2015, and 2025, respectively. The results revealed substantial land transformation and rapid physical urban expansion, with the built-up area increasing from 93 ha (2.0%) in 2005–1,956 ha (41.3%) in 2025. This expansion was accompanied by major transformations of surrounding land resources, particularly the conversion of Bush with Grass and other open areas to built-up land. Agricultural land increased from 634 ha (13.4%) to 1,750 ha (36.9%), whereas Bush with Grass declined from 3,375 ha (71.1%) to 652 ha (13.7%). Socio-economic information collected from 277 respondents indicated that population growth, rural–urban migration, housing demand, employment opportunities, and infrastructure development were major drivers of urban expansion. The study distinguishes urban expansion, represented by the increase in built-up land, from urban sprawl, which refers to the spatial pattern and form of outward urban development. The integration of Random Forest classification and GIS-based spatial analysis provides valuable evidence of land transformation, vegetation loss, and increasing pressure on urban services, supporting more sustainable urban planning and land management in Gambella Town.","快速城市化及与之相关的建成区扩张正在改变土地资源、生态系统功能和城市空间结构。区分城市增长（urban growth）、城市扩张（urban expansion）和城市蔓延（urban sprawl），对于理解城市转型的过程与格局、支撑可持续城市规划至关重要。本研究融合机器学习与地理空间技术，分析埃塞俄比亚甘贝拉镇（Gambella Town）土地利用与土地覆盖（LULC）的时空动态及城市扩张。采用遥感技术和基于随机森林（RF）分类器的监督机器学习方法，处理了2005年、2015年和2025年的多时相Landsat卫星影像。研究识别出六类主要LULC类型：农业用地、灌草地、建成区、裸地、林地和水体。2005年、2015年和2025年的分类总体精度分别为90%、90%和89%。结果表明，土地发生了显著转变，城市实体空间快速扩张，建成区面积从2005年的93公顷（2.0%）增至2025年的1,956公顷（41.3%）。这一扩张伴随着周边土地资源的重大转变，尤其是灌草地及其他开阔地被转化为建成用地。农业用地从634公顷（13.4%）增至1,750公顷（36.9%），而灌草地则从3,375公顷（71.1%）降至652公顷（13.7%）。从277名受访者收集的社会经济信息表明，人口增长、城乡迁移、住房需求、就业机会和基础设施建设是城市扩张的主要驱动因素。本研究将城市扩张（以建成用地增加为表征）与城市蔓延（指城市向外发展的空间格局与形态）加以区分。随机森林分类与基于GIS的空间分析的融合，为土地转变、植被丧失及城市服务压力加剧提供了有价值的证据，有助于甘贝拉镇实现更可持续的城市规划与土地管理。","PLoS ONE",{"impact":84,"substance":84,"depth":84,"authority":84,"freshness":84,"relevant":84,"comment":313},"研究聚焦埃塞俄比亚城市扩张与土地利用变化，属城市地理与遥感应用，与三农、农业信息化主题无直接关联，不建议进入每日精选。",[315],{"name":311,"url":308},[317,29,30,318],"机器学习","城市扩张",{"code":320,"slug":321,"name":322,"path":323,"parent_code":166},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[325],{"code":162,"slug":163,"name":164,"path":165,"parent_code":166},{"status":173,"locked":14,"version":35,"method":36,"evidence":327},{"candidates":328,"agricultural_evidence":42},[329,334,340,344],{"code":320,"score":107,"supported":42,"title":330,"abstract":332,"tags":333},[331],"machine learning",[317,331],[317],{"code":162,"score":108,"supported":42,"title":335,"abstract":336,"tags":339},[],[337,180,338],"空间分析","spatial analysis",[],{"code":54,"score":246,"supported":42,"title":341,"abstract":342,"tags":343},[],[186,187],[29],{"code":48,"score":22,"supported":14,"title":345,"abstract":346,"tags":347},[],[],[30],[349,350],"Gambella Town 城市扩张","Random Forest 土地利用分类","GambellaTown城市扩张-5485","10.1371\u002Fjournal.pone.0360419",{"doi":352,"openalex_id":354,"authors":355,"venue":311,"cited_by_count":84,"oa_url":308,"card":365,"direction":90,"ingested_from":92},"W7223022155",[356,359,361,363],{"name":357,"orcid":358},"Kanenus Fufa Dararo","https:\u002F\u002Forcid.org\u002F0009-0007-5747-1558",{"name":360,"orcid":9},"Goanar Jal Dup",{"name":362,"orcid":9},"Weyesa Merga Chemeda",{"name":364,"orcid":9},"Shankar Karuppannan",{"tldr":366,"method":367,"finding":368,"direction":90,"opportunity":369},"用机器学习与遥感分析埃塞俄比亚甘贝拉镇2005-2025年城市扩张与土地利用变化。","Landsat多时相影像、随机森林分类与GIS空间分析，结合277份问卷。","建成区从93公顷增至1956公顷，灌草地大幅转为建成区和农地。","可将随机森林时序分类与驱动力调查结合，扩展到更多非洲小城镇并耦合城市增长模拟。","2026-10-21T23:30:23.271293Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":9,"content":9,"source_name":376,"source_url":374,"published_at":231,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":84,"score_detail":377,"sources":379,"tags":381,"primary_topic":9,"secondary_topics":383,"classification":384,"search_phrases":395,"slug":398,"view_count":84,"doi":399,"paper":400,"created_at":414},5484,"Spatiotemporal Dynamics and Assess of Ecological Quality in Sylhet Metropolitan Area amid Rapid Urbanization: A Remote Sensing Approach","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11422676\u002Fv1","Spatiotemporal Dynamics and Assess of Ecological Quality in Sylhet Metropolitan Area amid Rapid Urbanization: A Remote Sensing Approach。Research Square","Research Square",{"impact":84,"substance":84,"depth":84,"authority":84,"freshness":84,"relevant":84,"comment":378},"研究孟加拉国锡尔赫特市生态质量，与三农及农业信息化无关，不予精选。",[380],{"name":376,"url":374},[29,30,382],"城市生态",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":385},{"candidates":386,"agricultural_evidence":14,"reason":58},[387,391],{"code":54,"score":106,"supported":42,"title":388,"abstract":389,"tags":390},[187],[187],[29],{"code":48,"score":49,"supported":14,"title":392,"abstract":393,"tags":394},[],[],[30,382],[396,397],"Sylhet 城市扩张 遥感","土地利用 城市生态 遥感监测","Sylhet城市扩张遥感-5484","10.21203\u002Frs.3.rs-11422676\u002Fv1",{"doi":399,"openalex_id":401,"authors":402,"venue":376,"cited_by_count":84,"oa_url":413,"card":9,"direction":90,"ingested_from":92},"W7223013355",[403,405,407,410],{"name":404,"orcid":9},"Md Saikoth Jahan",{"name":406,"orcid":9},"Mst Arjumoni Anu",{"name":408,"orcid":409},"Md. Inzamul Haque","https:\u002F\u002Forcid.org\u002F0000-0003-1756-5561",{"name":411,"orcid":412},"Most. Atia Parvin","https:\u002F\u002Forcid.org\u002F0000-0002-2718-9259","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-11422676\u002Flatest.pdf","2026-10-21T23:30:23.223087Z",{"id":416,"title":417,"url":418,"summary":419,"summary_zh":420,"content":9,"source_name":421,"source_url":418,"published_at":422,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":423,"score_detail":424,"sources":426,"tags":428,"primary_topic":9,"secondary_topics":432,"classification":433,"search_phrases":456,"slug":459,"view_count":84,"doi":460,"paper":461,"created_at":477},5481,"Comparison of Satellite-Based Drought Monitoring Indicators (NDVI, NDMI, and LST): The Case of the Northern Aegean Drainage Basin","https:\u002F\u002Fdoi.org\u002F10.30910\u002Fturkjans.2010067","Thanks to advancements in technology, satellite remote sensing provides a valuable means of monitoring the spatial and temporal responses of vegetation, surface moisture conditions, and land surface temperature to drought. Its capacity to monitor large areas with high temporal continuity significantly eliminates the spatial limitations of ground observations. This allows for the simultaneous and comparable analysis of key variables such as vegetation dynamics, soil moisture, and land surface temperature. Indicators such as the Normalized Difference Vegetation Index (NDVI), Normalized Difference Moisture Index (NDMI), and Land Surface Temperature (LST) provide complementary information on vegetation condition, surface moisture, and thermal stress, thereby supporting drought monitoring. This integrated monitoring framework supports the sustainable management of water resources while strengthening the scientific basis of decision-making processes, significantly contributing to disaster risk reduction. This study comparatively evaluates NDVI, NDMI, and LST values derived from Landsat 8 data obtained in March, April, and May between 2019 and 2022, and examines the relationships between these variables across the Northern Aegean Drainage Basin (NADB). The results show increasingly strong negative relationships between LST and the spectral indices from March to May, with the strongest correlations observed in May for NDMI–LST (r = −0.78) and NDVI–LST (r = −0.74). The NDMI-LST relationship can be said to be slightly better than the NDVI-LST relationship. The correlation coefficient between NDMI and NDVI was calculated to be lowest in March at r=0.54 and highest in May at r=0.90. It was determined that areas with high LST values had lower NDVI and NDMI values. Drought monitoring using remote sensing methods is important in terms of time and accuracy, but it is not sufficient on its own. In addition to problems arising from satellite imagery, land surfaces are affected by short-term climatic factors. Therefore, the indices obtained from satellite images must be evaluated together with meteorological and terrestrial data. However, it is thought that satellite-based drought monitoring will produce more reliable results under current technological and methodological conditions.","得益于技术进步，卫星遥感为监测植被、地表水分状况和地表温度对干旱的时空响应提供了重要手段。其大范围、高时间连续性的监测能力显著消除了地面观测的空间局限性，使得植被动态、土壤水分和地表温度等关键变量能够被同步、可比地分析。归一化差异植被指数（NDVI）、归一化差异水分指数（NDMI）和地表温度（LST）等指标提供了关于植被状况、地表水分和热胁迫的互补信息，从而支持干旱监测。这一综合监测框架既支持水资源的可持续管理，又增强了决策过程的科学基础，对减少灾害风险具有重要贡献。本研究对2019年至2022年3月、4月和5月获取的Landsat 8数据所衍生的NDVI、NDMI和LST值进行了比较评估，并考察了北爱琴海流域（NADB）内这些变量之间的关系。结果表明，从3月到5月，LST与光谱指数之间的负相关关系日益增强，5月观测到最强相关性，NDMI–LST（r = −0.78）和NDVI–LST（r = −0.74）。可以认为NDMI-LST关系略优于NDVI-LST关系。NDMI与NDVI之间的相关系数在3月最低（r=0.54），5月最高（r=0.90）。研究确定，LST值较高的区域其NDVI和NDMI值较低。利用遥感方法进行干旱监测在时间和精度方面具有重要意义，但仅靠其自身并不充分。除卫星影像带来的问题外，地表还受到短期气候因素的影响。因此，从卫星影像获得的指数必须与气象和地面数据结合评估。然而，可以认为在当前技术和方法条件下，基于卫星的干旱监测将产生更可靠的结果。","Türk Tarım ve Doğa Bilimleri Dergisi","2026-10-19T00:00:00Z",61,{"impact":21,"substance":19,"depth":107,"authority":106,"freshness":21,"relevant":22,"comment":425},"方法对比扎实、结论明确，但属区域案例研究，公共影响有限，适合作为遥感干旱监测主题的补充素材而非头条精选。",[427],{"name":421,"url":418},[27,29,429,430,431],"干旱监测","NDMI","LST",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":434},{"candidates":435,"agricultural_evidence":14,"reason":58},[436,441,445,450],{"code":40,"score":107,"supported":42,"title":437,"abstract":439,"tags":440},[438],"drought",[45,438],[429],{"code":54,"score":21,"supported":42,"title":442,"abstract":443,"tags":444},[],[186,187],[27,29],{"code":263,"score":95,"supported":42,"title":446,"abstract":447,"tags":449},[],[448,266],"土壤",[],{"code":451,"score":41,"supported":42,"title":452,"abstract":453,"tags":455},"H3",[],[454],"水资源",[],[457,458],"北爱琴海流域 干旱监测","干旱监测 遥感监测 NDMI NDVI","北爱琴海流域干旱监测-5481","10.30910\u002Fturkjans.2010067",{"doi":460,"openalex_id":462,"authors":463,"venue":421,"cited_by_count":84,"oa_url":470,"card":471,"direction":476,"ingested_from":92},"W7222954725",[464,467],{"name":465,"orcid":466},"Arman Monshizadeh Karimi","https:\u002F\u002Forcid.org\u002F0000-0002-2945-5346",{"name":468,"orcid":469},"İ̇smail Taş","https:\u002F\u002Forcid.org\u002F0000-0003-0872-2529","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F6296754",{"tldr":472,"method":473,"finding":474,"direction":90,"opportunity":475},"比较Landsat 8的NDVI、NDMI与LST三种遥感干旱指标在北爱琴海流域的相关性。","用2019-2022年3-5月Landsat 8数据计算NDVI、NDMI、LS","LST与NDMI、NDVI负相关随春季增强，5月最强（r=-0.78、-0.74），NDMI略优。","可融合气象与地面数据构建多源干旱指数，并验证NDMI-LST关系在其他气候区的普适性。","智慧农业 \u002F 农业物联网","2026-10-21T23:30:10.758669Z"]