SAR Deep Learning Sea Ice Retrieval Trained with Airborne Laser Scanner Measurements from the MOSAiC Expedition

Abstract

Automated sea ice charting from Synthetic Aperture Radar (SAR) has been researched for more than a decade and still, we are not close to unlocking the full potential of automated solutions in terms of resolution and accuracy. The central complications arise from ground truth data not being readily available in the polar regions. In this paper, we build a dataset from 20 near coincident X-Band SAR acquisitions and as many Airborne Laser Scanner (ALS) measurements from the Multidisciplinary drifting Observatory for the Study of Arctic Climate (MOSAiC), between October and May. This dataset is then used to assess the accuracy and robustness of five machine learning based approaches, by deriving classes from the freeboard, surface roughness (standard deviation at 0.5 m correlation length) and reflectance. It is shown that there is only a weak correllation of the radar backscatter and the sea ice topography. Accuracies between 40 % and 69 % percent and robustnesses between 68 % and 85 % give a realistic insight into modern classifiers' performance across a range of ice conditions over 8 months. It also marks the first time algorithms are trained entirely with labels from coincident measurements, allowing for a probabilistic class retrieval. The results show that segmentation models able to learn from the class distribution significantly perform pixel-wise classification approaches.