[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"topic-CBERS-4":3},{"name":4,"kind":5,"tokens":6,"total":7,"page":7,"page_size":8,"items":9},"CBERS-4","tag",[4],1,100,[10],{"id":11,"title":12,"url":13,"summary":14,"summary_zh":15,"content":16,"source_name":17,"source_url":13,"published_at":18,"category":19,"cover_url":16,"hotness":20,"is_selected":21,"score":22,"score_detail":23,"sources":30,"tags":32,"primary_topic":16,"secondary_topics":37,"classification":38,"search_phrases":82,"slug":85,"view_count":86,"doi":87,"paper":88,"created_at":114},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。",null,"Journal of Hyperspectral Remote Sensing","2026-10-20T00:00:00Z","论文",10,false,78,{"impact":24,"substance":25,"depth":26,"authority":27,"freshness":28,"relevant":7,"comment":29},18,22,17,12,9,"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。",[31],{"name":17,"url":13},[33,34,35,36,4],"遥感监测","土地利用","森林保护","亚马逊",[],{"status":39,"locked":21,"version":40,"method":41,"evidence":42},"needs_review","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":47,"reason":81},[44,53,60,68,75],{"code":45,"score":46,"supported":47,"title":48,"abstract":49,"tags":52},"H6",7,true,[],[50,51],"生物多样性","biodiversity",[34],{"code":54,"score":46,"supported":47,"title":55,"abstract":56,"tags":59},"I3",[],[57,58],"遥感","remote sensing",[33],{"code":61,"score":62,"supported":47,"title":63,"abstract":64,"tags":67},"H7",6,[],[65,66],"气候变化","climate change",[],{"code":69,"score":70,"supported":47,"title":71,"abstract":72,"tags":74},"H2",3,[],[73],"soil",[],{"code":76,"score":70,"supported":47,"title":77,"abstract":78,"tags":80},"I7",[],[79],"研究方法",[],"多个产业证据相当，需要确认主归属",[83,84],"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",0,"10.29150\u002Fjhrs.v16i4.269068",{"doi":87,"openalex_id":89,"authors":90,"venue":17,"cited_by_count":86,"oa_url":13,"card":107,"direction":111,"ingested_from":113},"W7223141286",[91,94,96,99,102,105],{"name":92,"orcid":93},"Ubiratan Joaquim da Silva","https:\u002F\u002Forcid.org\u002F0000-0001-7995-6416",{"name":95,"orcid":16},"Gabriel Henrique Santos Silva",{"name":97,"orcid":98},"Juarez Antonio da Silva","https:\u002F\u002Forcid.org\u002F0000-0002-2898-0309",{"name":100,"orcid":101},"Anderson Luiz Ribeiro de Paiva","https:\u002F\u002Forcid.org\u002F0000-0003-3475-1454",{"name":103,"orcid":104},"Leidjane Maria Maciel de Oliveira","https:\u002F\u002Forcid.org\u002F0000-0003-1251-6998",{"name":106,"orcid":16},"Sylvana Melo dos Santos",{"tldr":108,"method":109,"finding":110,"direction":111,"opportunity":112},"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%。","农业遥感与作物表型","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。","openalex","2026-10-22T11:20:42.901761Z"]