Multi-temporal calving front segmentation

The calving fronts of marine-terminating glaciers undergo constant changes. These changes significantly affect the glacier’s mass and dynamics, demanding continuous monitoring. To address this need, deep learning models were developed that can automatically delineate the calving front in Synthetic Aperture Radar imagery. However, these models often struggle to correctly classify areas affected by seasonal conditions such as ice mélange or snow-covered surfaces. To address this issue, we propose to process multiple frames from a satellite image time series of the same glacier in parallel and exchange temporal information between the corresponding feature maps to stabilize each prediction. We integrate our approach into the current state-of-the-art architecture Tyrion and accomplish a new state-of-the-art performance on the CaFFe benchmark dataset. In particular, we achieve a Mean Distance Error of 184.4 m and a mean Intersection over Union of 83.6 . Furthermore, we empirically demonstrate that our modifications are highly robust to seasonal conditions, achieving a Mean Distance Error of 213.0 m under adverse conditions and outperforming prior state-of-the-art methods, such as Tyrion, by more than 100 m. The CaFFe benchmark dataset is publicly available at https://doi.pangaea.de/10.1594/PANGAEA.940950 and the code at https://github.com/ki7077/Multi-Temporal-Tyrion .