Proof of Concept for Sea Ice Stage of Development Classification Using Deep Learning

• Published in: Remote Sensing
• Main Authors: Ryan Kruk, M. Christopher Fuller, Alexander S. Komarov, Dustin Isleifson, Ian Jeffrey
• Format: Article in Journal/Newspaper
• Language: English
• Published: MDPI AG 2020
• Subjects: sea ice; Arctic; Canadian sea ice chart; deep learning; SAR; RADARSAT-2; Science; Q; Sea ice
• Online Access: https://doi.org/10.3390/rs12152486; https://doaj.org/article/8c71ed265391457b85d84fdf2bebd945

Accurate maps of ice concentration and ice type are needed to address increased interest in commercial marine transportation through the Arctic. RADARSAT-2 SAR imagery is the primary source of data used by expert ice analysts at the Canadian Ice Service (CIS) to produce sea ice maps over the Canadian territory. This study serves as a proof of concept that neural networks can be used to accurately predict ice type from SAR data. Datasets of SAR images served as inputs, and CIS ice charts served as labelled outputs to train a neural network to classify sea ice type. Our results show that DenseNet achieves the highest overall classification accuracy of 94.0% including water and the highest ice classification accuracy of 91.8% on a three class dataset using a fusion of HH and HV SAR polarizations for the input samples. The 91.8% ice classification accuracy validates the premise that a neural network can be used to effectively categorize different ice types based on SAR data.