Abstract
Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front delineation in Synthetic Aperture Radar imagery. While Deep Learning systems exhibit errors up to 221 m, human annotators deviate by only 38 m, underscoring the need for further research.
Funding Information
  • DFG project (CH 2080/5-1)
  • Bayerisches Staatsministerium für Wissenschaft und Kunst through ENB (M5613.5.2020)
  • JPL, California Institute of Technology
  • National Aeronautics and Space Administration
  • NHR@FAU for HPC resources (DFG 440719683)