Out-of-the-box calving front detection method using deep-learning

Abstract. Glaciers across the globe react to the changing climate. Monitoring the transformation of glaciers is essential for projecting their contribution to global mean sea level (GMSL) rise. The delineation of glacier-calving fronts is an important part of the satellite-based monitoring process. This work presents a calving front extraction method based on the deep learning framework nnU-Net, which stands for no new U-Net. The framework automates the training of a popular neural network, called U-Net, designed for segmentation tasks. Our presented method marks the calving front in Synthetic Aperture Radar images of glaciers. The images are taken by six different sensor systems. A benchmark dataset for calving front extraction is used for training and evaluation. The dataset contains two labels for each image. One label denotes a classic image segmentation into different zones (glacier, ocean, rock, and no information available). The other label marks the edge between the glacier and the ocean, i. e., the calving front. In this work, the nnU-Net is modified to predict both labels simultaneously. In the field of machine learning, the prediction of multiple labels is referred to as Multi-Task-Learning (MTL). The resulting predictions of both labels benefit from simultaneous optimization. For further testing of the capabilities of MTL, two different network architectures are compared, and an additional task, the segmentation of the glacier outline, is added to the training. In the end, we show that fusing the label of the calving front and the zone label is the most efficient way to optimize both tasks with no significant accuracy reduction compared to the MTL neural network architectures. The automatic detection of the calving front with a nnU-Net trained on fused labels improves from the baseline mean distance error of 753 ± 76 m to 541 ± 84 m. The scripts for our experiments are published on Gitlab (https://gitlab.cs.fau.de/ho11laqe/nnunet\_glacer.git).