[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2174":3},{"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,"view_count":32,"doi":33,"paper":34,"created_at":50},2174,"Optical Remote Sensing and Machine Learning Enable Scalable Carbon Mapping in Himalayan Forests Despite Spectral Saturation Challenges","https:\u002F\u002Fdoi.org\u002F10.32942\u002Fx29d5f","Accurate aboveground biomass (AGB) estimation is critical for climate change mitigation and carbon accounting in mountain regions, yet spatially explicit mapping remains limited by reliance on conventional field methods and underexplored machine learning approaches in the Himalaya. Bhutan, a carbon-negative nation maintaining 70% forest cover, faces urgent demand to develop robust monitoring, reporting, and verification (MRV) systems for carbon market participation under the Paris Agreement Article 6. This study developed a random forest (RF) model that integrates Sentinel-2A multispectral imagery, nine vegetation indices, topographic variables, and field-measured AGB from 99 plots across 244.6 hectares in the Kyentshen Community Forest. Using recursive feature elimination, 10 key predictors were identified from 27 candidate variables: Band 11, SLAVI, Band 12, WDRVI, NDVI, elevation, NDWI, GNDVI, band ratio (r3), and Band 9. The optimized RF model achieved R² = 0.34 and RMSE = 67.98 ± 19.79 t\u002Fha on training data (Ntree = 500, Mtry = 3). However, test-set performance declined substantially (R² = 0.42, RMSE = 86.14 t\u002Fha), indicating overfitting and reflecting limitations of spectral saturation in high-biomass stands (>300 t\u002Fha). A Wilcoxon signed-rank test revealed systematic overestimation (predicted median: 118.36 t\u002Fha vs. observed: 105.15 t\u002Fha; p = 0.03). Despite moderate accuracy, this study demonstrates that freely available Sentinel-2 data combined with machine learning offers a cost-effective, scalable alternative to traditional field mapping for rapid AGB assessment across Bhutan's temperate forests. Vegetation indices, particularly SLAVI and WDRVI, proved superior to raw spectral bands, offering improved sensitivity to dense canopies. The spatial-transect methodology and 10-predictor framework provide a replicable foundation for advancing Bhutan's forest carbon accounting systems. We recommend integrating synthetic aperture radar (SAR) or LiDAR to overcome optical saturation, enabling higher accuracy for robust MRV compliance and carbon credit monetization. This work directly supports the maintenance of Bhutan's carbon-neutral status and establishes the technical baseline for scaling AGB monitoring across mountain regions where engineered infrastructure capacity is limited, but climate action urgency is paramount.","准确估算地上生物量（AGB）对于山区减缓气候变化和碳核算至关重要，但空间显式制图仍受限于对传统野外方法的依赖以及喜马拉雅地区机器学习方法研究不足。不丹是一个维持70%森林覆盖率的负碳国家，迫切需要建立稳健的监测、报告与核查（MRV）体系，以参与《巴黎协定》第六条下的碳市场。本研究开发了一个随机森林（RF）模型，整合了Sentinel-2A多光谱影像、9个植被指数、地形变量以及Kyentshen社区森林244.6公顷范围内99个样地的实测AGB数据。通过递归特征消除法，从27个候选变量中筛选出10个关键预测因子：Band 11、SLAVI、Band 12、WDRVI、NDVI、海拔、NDWI、GNDVI、波段比值（r3）和Band 9。优化后的RF模型在训练数据上达到R² = 0.34，RMSE = 67.98 ± 19.79 t\u002Fha（Ntree = 500，Mtry = 3）。然而，测试集性能显著下降（R² = 0.42，RMSE = 86.14 t\u002Fha），表明存在过拟合，并反映了高生物量林分（>300 t\u002Fha）中光谱饱和的局限性。Wilcoxon符号秩检验揭示了系统性高估（预测中位数：118.36 t\u002Fha vs. 观测值：105.15 t\u002Fha；p = 0.03）。尽管精度中等，本研究表明，免费可获取的Sentinel-2数据结合机器学习为不丹温带森林的快速AGB评估提供了一种成本效益高、可扩展的传统野外制图替代方案。植被指数，特别是SLAVI和WDRVI，被证明优于原始光谱波段，对密集冠层具有更高的敏感性。空间样带方法和10预测因子框架为推进不丹森林碳核算体系提供了可复制的基础。我们建议整合合成孔径雷达（SAR）或激光雷达（LiDAR）以克服光学饱和，从而实现更高精度，满足稳健的MRV合规和碳信用货币化需求。本研究直接支持不丹维持碳中和地位，并为在工程基础设施能力有限但气候行动紧迫性极高的山区推广AGB监测建立了技术基线。",null,"OpenAlex","2026-09-09T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,8,1,"研究用Sentinel-2与随机森林实现山地森林生物量制图，方法可复现但精度中等，对农业遥感与碳汇监测有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","遥感监测","碳核算","森林碳汇","生物量估算",0,"10.32942\u002Fx29d5f",{"doi":33,"openalex_id":35,"authors":36,"venue":9,"cited_by_count":32,"oa_url":42,"card":43,"direction":47,"ingested_from":49},"W7212083800",[37,39],{"name":38,"orcid":9},"Namgay Wangchuk",{"name":40,"orcid":41},"Yonten Dorji","https:\u002F\u002Forcid.org\u002F0000-0002-6508-9582","https:\u002F\u002Fecoevorxiv.org\u002Frepository\u002Fobject\u002F14866\u002Fdownload\u002F25843\u002F",{"tldr":44,"method":45,"finding":46,"direction":47,"opportunity":48},"用Sentinel-2与随机森林估算不丹喜马拉雅森林生物量，实现可扩展碳制图。","Sentinel-2多光谱、9个植被指数、地形因子与99个样地实测AGB，随机森","模型精度中等且高生物量区存在光谱饱和，SLAVI与WDRVI优于原始波段。","农业遥感与作物表型","融合SAR或LiDAR克服光学饱和，提升山地森林碳储量估算与MRV精度。","openalex","2026-09-11T23:30:32.934604Z"]