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

Gourmelon N, Heidler K, Loebel E, Cheng D, Klink J, Dong A, Wu F, Maul N, Koch M, Dreier MN, Pyles DR, Seehaus T, Braun M, Maier A, Christlein V (2026)


Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2026

Journal

Book Volume: 48

Pages Range: 11224-11230

Journal Issue: 9

URI: https://ieeexplore.ieee.org/document/11488532

DOI: 10.1109/TPAMI.2026.3685700

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.

Authors with CRIS profile

Utilized Equipment

Related research project(s)

Involved external institutions

How to cite

APA:

Gourmelon, N., Heidler, K., Loebel, E., Cheng, D., Klink, J., Dong, A.,... Christlein, V. (2026). Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(9), 11224-11230. https://doi.org/10.1109/TPAMI.2026.3685700

MLA:

Gourmelon, Nora, et al. "Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning." IEEE Transactions on Pattern Analysis and Machine Intelligence 48.9 (2026): 11224-11230.

BibTeX: Download