Automated Sentinel-1 sea ice type mapping and in-situ validation during the CIRFA-22 cruise

• Published in: Annals of Glaciology
• Main Authors: Johannes Lohse, Catherine Taelman, Alistair Everett, Nicholas Edward Hughes
• Format: Article in Journal/Newspaper
• Language: English
• Published: Cambridge University Press
• Subjects: remote sensing; sea ice; classification; Meteorology. Climatology; QC851-999; Belgica Bank; Norway; Annals of Glaciology; Sea ice
• Online Access: https://doi.org/10.1017/aog.2024.23; https://doaj.org/article/80668abc684f42ec91131d1181a081ed

We present a fully-automated workflow to map sea ice types from Sentinel-1 data and transfer the results in near real-time to the research vessel Kronprins Haakon (KPH) in order to support tactical navigation and decision-making during a research cruise conducted towards Belgica Bank in April and May 2022. We used overlapping SAR and optical imagery to train a pixel-wise classifier for the required season and region, and implemented a processing chain with the Norwegian Ice Service at MET Norway that automatically classifies all Sentinel-1 images covering the area of interest. During the cruise, classification results were available on KPH within hours after image acquisition, which is significantly faster than manually produced ice charts. We evaluate the results both quantitatively, based on manually selected validation regions, and qualitatively in comparison to in-situ observations and photographs. Our findings show that open water, level ice, and deformed ice are classified with high accuracy, while young ice remains challenging due to its variable small-scale surface roughness. This work presents one of the first attempts to transfer automated ice type classification results into the field in near real-time and contributes to bridging the gap between research and operations in automated sea ice mapping.