Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning
This work addresses the need for automated monitoring of glacier mass loss for climate research, but it is incremental as it highlights current limitations rather than achieving new performance levels.
This study compared deep learning systems for delineating glacier calving fronts in SAR images on a common benchmark dataset, finding that the best model had an average deviation of 221 m, significantly worse than human annotators at 38 m.
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.