Scholarlink

<p>Above-ground biomass (AGB) is a&#xa0;critical indicator of various ecological parameters, such as forest degradation or carbon storage. However, obtaining ground-truth AGB measurements is costly and time-intensive, requires expert knowledge, and is limited to small areas. Current methods estimate AGB using observable parameters like canopy height, often relying on spaceborne platforms. Despite advances in satellite sensor technology, the spatial resolution of AGB maps remains limited (e.g., <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(100 \times 100\)</EquationSource> </InlineEquation> meters in ESA CCI), compared to the resolution of some openly available satellite imagery, such as ESA Sentinel data. To increase the spatial resolution of AGB maps, Karaman et&#xa0;al. (<CitationRef CitationID="CR16">2025</CitationRef>) proposed a&#xa0;guided super-resolution approach in which a&#xa0;low-resolution biomass map is upsampled to a&#xa0;resolution of <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(10 \times 10\)</EquationSource> </InlineEquation> meters using a&#xa0;Sentinel-1/2 image as a&#xa0;guide. Here, we show that incorporating multi-temporal satellite data, rather than a&#xa0;single time step, further enhances the accuracy of high-resolution AGB maps by 185 Mg/ha MAE and 266 Mg/ha RMSE on the BioMassters dataset. In addition, we analyze the impact of different input features and design modifications on model performance and provide a&#xa0;rationale for their effectiveness.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

MT-GSR4B: Multi-Temporally Guided Super-Resolution for Above-Ground Biomass Estimation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月4日

查看全文
  • Kaan Karaman,
  • Vivien Sainte Fare Garnot,
  • Damien Robert,
  • Maria João Santos,
  • Jan Dirk Wegner

摘要

Above-ground biomass (AGB) is a critical indicator of various ecological parameters, such as forest degradation or carbon storage. However, obtaining ground-truth AGB measurements is costly and time-intensive, requires expert knowledge, and is limited to small areas. Current methods estimate AGB using observable parameters like canopy height, often relying on spaceborne platforms. Despite advances in satellite sensor technology, the spatial resolution of AGB maps remains limited (e.g., \(100 \times 100\) meters in ESA CCI), compared to the resolution of some openly available satellite imagery, such as ESA Sentinel data. To increase the spatial resolution of AGB maps, Karaman et al. (2025) proposed a guided super-resolution approach in which a low-resolution biomass map is upsampled to a resolution of \(10 \times 10\) meters using a Sentinel-1/2 image as a guide. Here, we show that incorporating multi-temporal satellite data, rather than a single time step, further enhances the accuracy of high-resolution AGB maps by 185 Mg/ha MAE and 266 Mg/ha RMSE on the BioMassters dataset. In addition, we analyze the impact of different input features and design modifications on model performance and provide a rationale for their effectiveness.