Scholarlink

<p>Accurate global glacier mapping is critical for understanding climate change impacts. Despite its importance, automated glacier mapping at a global scale remains largely unexplored. Here we address this gap and propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. Assessing the spatial, temporal and cross-sensor generalisation shows that our best strategy achieves intersection over union &#xa0;&gt;0.85 on previously unobserved images in most cases, which drops to &#xa0;&gt;0.75 for debris-rich areas such as High-Mountain Asia and increases to &#xa0;&gt;0.90 for regions dominated by clean ice. A comparative validation against human expert uncertainties in terms of area and distance deviations underscores GlaViTU performance, approaching or matching expert-level delineation. Adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available. The calibrated confidence for glacier extents is reported making the predictions more reliable and interpretable. We also release a benchmark dataset that covers 9% of glaciers worldwide. Our results support efforts towards automated multitemporal and global glacier mapping.</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

Globally scalable glacier mapping by deep learning matches expert delineation accuracy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年1月2日

查看全文
  • Konstantin A. Maslov,
  • Claudio Persello,
  • Thomas Schellenberger,
  • Alfred Stein

摘要

Accurate global glacier mapping is critical for understanding climate change impacts. Despite its importance, automated glacier mapping at a global scale remains largely unexplored. Here we address this gap and propose Glacier-VisionTransformer-U-Net (GlaViTU), a convolutional-transformer deep learning model, and five strategies for multitemporal global-scale glacier mapping using open satellite imagery. Assessing the spatial, temporal and cross-sensor generalisation shows that our best strategy achieves intersection over union  >0.85 on previously unobserved images in most cases, which drops to  >0.75 for debris-rich areas such as High-Mountain Asia and increases to  >0.90 for regions dominated by clean ice. A comparative validation against human expert uncertainties in terms of area and distance deviations underscores GlaViTU performance, approaching or matching expert-level delineation. Adding synthetic aperture radar data, namely, backscatter and interferometric coherence, increases the accuracy in all regions where available. The calibrated confidence for glacier extents is reported making the predictions more reliable and interpretable. We also release a benchmark dataset that covers 9% of glaciers worldwide. Our results support efforts towards automated multitemporal and global glacier mapping.