Calving fronts and where to find them: a benchmark dataset and methodology for automatic glacier calving front extraction from synthetic aperture radar imagery

Gourmelon, Nora; Seehaus, Thorsten; Braun, Matthias; Maier, Andreas; Christlein, Vincent

doi:https://doi.org/10.5194/essd-14-4287-2022

Articles | Volume 14, issue 9

https://doi.org/10.5194/essd-14-4287-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Benchmark datasets and machine learning algorithms for Earth...

https://doi.org/10.5194/essd-14-4287-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 14, issue 9

Data description paper

|

22 Sep 2022

Data description paper |

| 22 Sep 2022

Calving fronts and where to find them: a benchmark dataset and methodology for automatic glacier calving front extraction from synthetic aperture radar imagery

Nora Gourmelon, Thorsten Seehaus, Matthias Braun, Andreas Maier, and Vincent Christlein

Data sets

CaFFe (CAlving Fronts and where to Find thEm: a benchmark dataset and methodology for automatic glacier calving front extraction from sar imagery) Nora Gourmelon, Thorsten Seehaus, Matthias Holger Braun, Andreas Maier, and Vincent Christlein https://doi.org/10.1594/PANGAEA.940950

Model code and software

Calving Fronts and Where to Find Them Nora Gourmelon https://doi.org/10.5281/zenodo.6469519

Video abstract

Video Abstract - Calving Fronts and Where to Find Them Nora Gourmelon, Thorsten Seehaus, Matthias Holger Braun, Andreas Maier, and Vincent Christlein https://doi.org/10.5446/58416

Short summary

Ice loss of glaciers shows in retreating calving fronts (i.e., the position where icebergs break off the glacier and drift into the ocean). This paper presents a benchmark dataset for calving front delineation in synthetic aperture radar (SAR) images. The dataset can be used to train and test deep learning techniques, which automate the monitoring of the calving front. Provided example models achieve front delineations with an average distance of 887 m to the correct calving front.