Spatio-temporal distribution of sea-ice thickness using a machine learning approach with Google Earth Engine and Sentinel-1 GRD data

Abstract

Knowledge of ice thickness and its distribution is of great interest to plan ship and offshore operations in ice areas. It is also a major direct factor in climate change. However, it is currently the most inaccurate sea-ice parameter according to a large majority of the scientific community. Satellite-borne synthetic aperture radar (SAR) data are highly valuable for monitoring daily ice-covered oceans. In this study, we develop a new technique based on a machine learning Random Forest (RF) regression approach using the combination of the in-situ thickness measurements and the backscattering information from Sentinel-1 to retrieve the level first-year ice (FYI) thickness. By applying the technique over the Sentinel-1 ground range detected (GRD) data set available in Google Earth Engine (GEE) over the Beaufort Sea spanning a time period from Apr 2015 to Sep 2018, a thickness of up to 1.5 m with a root mean square error (RMSE) of 22 cm is retrieved.