Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning

Nora Gourmelon, Konrad Heidler, Erik Loebel, Daniel Cheng, Julian Klink +10 more
1/9/2025
cs.CVcs.LG

No official code found. Best implementation: PCdurham/SEE_ICE (8 stars, MIT, last commit 2022-10-18).

Abstract

Calving front position variation of marine-terminating glaciers is an indicator of ice mass loss and a crucial parameter in numerical glacier models. Deep Learning (DL) systems can automatically extract this position from Synthetic Aperture Radar (SAR) imagery, enabling continuous, weather- and illumination-independent, large-scale monitoring. This study presents the first comparison of DL systems on a common calving front benchmark dataset. A multi-annotator study with ten annotators is performed to contrast the best-performing DL system against human performance. The best DL model's outputs deviate 221 m on average, while the average deviation of the human annotators is 38 m. This significant difference shows that current DL systems do not yet match human performance and that further research is needed to enable fully automated monitoring of glacier calving fronts. The study of Vision Transformers, foundation models, and the inclusion and processing strategy of more information are identified as avenues for future research.

View on arXivView PDF

Code Implementations(1)

PCdurham/SEE_ICECommunity100%
MIT

Glacial Landscape CNN

83PythonMar 17, 20204 years agoMIT

Similar Papers

Few-Shot Domain Adaptation with Temporal References and Static Priors for Glacier Calving Front Delineation

88% match2026

Multi-temporal Calving Front Segmentation

88% match2025

AMD-HookNet++: Evolution of AMD-HookNet with Hybrid CNN-Transformer Feature Enhancement for Glacier Calving Front Segmentation

88% match1 repo2025

Multi-Sensor Deep Learning for Glacier Mapping

86% match2024

Globally Scalable Glacier Mapping by Deep Learning Matches Expert Delineation Accuracy

85% match1 repo372024

MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater

84% match1 repo152025

Cite this paper

@article{gourmelon2025comparison,
  title  = {Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning},
  author = {Nora Gourmelon and Konrad Heidler and Erik Loebel and Daniel Cheng and Julian Klink and Anda Dong and Fei Wu and Noah Maul and Moritz Koch and Marcel Dreier and Dakota Pyles and Thorsten Seehaus and Matthias Braun and Andreas Maier and Vincent Christlein},
  year   = {2025},
  eprint = {2501.05281},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.05281v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.05281.svg)](https://codeofpaper.com/paper/2501.05281)

Discussion