A Machine Learning Approach on SMOS Thin Sea Ice Thickness Retrieval

Abstract

This study proposes a machine learning based methodology for estimating Arctic thin sea ice thickness (up to 1 m) from brightness temperature measurements of SMOS. The approach involves employing the so-called Burke model for sea ice emission modeling, integrating a suitable permittivity model and a radiative transfer equation. The training dataset is generated through a model-based simulation, and is then used to train and evaluate two machine learning regression algorithms: Random Forest and Gradient Boosting. Overall, this machine learning methodology results in great agreement with the ESA's official sea ice thickness product. Additionally, a validation performed by using data from mooring measurements shows a subtle improvement by the machine learning algorithms with respect to the ESA's official product. These results indicate their potential to surpass the performance of the current SMOS thin sea ice thickness retrievals.

Keywords

• Gradient Boosting (GB)
• machine learning
• random forest (RF)
• sea ice thickness
• soil moisture and ocean salinity (SMOS) satellite