Arctic sea ice cover data from spaceborne synthetic aperture radar by deep learning

摘要

Widely used sea ice concentration and sea ice cover in polar regions are derived mainly from spaceborne microwave radiometer and scatterometer data, and the typical spatial resolution of these products ranges from several to dozens of kilometers. Due to dramatic changes in polar sea ice, high-resolution sea ice cover data are drawing increasing attention for polar navigation, environmental research, and offshore operations. In this paper, we focused on developing an approach for deriving a high-resolution sea ice cover product for the Arctic using Sentinel-1 (S1) dual-polarization (horizontal-horizontal, HH, and horizontal-vertical, HV) data in extra wide swath (EW) mode. The approach for discriminating sea ice from open water by synthetic aperture radar (SAR) data is based on a modified U-Net architecture, a deep learning network. By employing an integrated stacking model to combine multiple U-Net classifiers with diverse specializations, sea ice segmentation is achieved with superior accuracy over any individual classifier. We applied the proposed approach to over 28?000 S1 EW images acquired in 2019 to obtain sea ice cover products in a high spatial resolution of 400?m. The validation by 96 cases of visual interpretation results shows an overall accuracy of 96.10?%. The S1-derived sea ice cover was converted to concentration and then compared with Advanced Microwave Scanning Radiometer 2 (AMSR2) sea ice concentration data, showing an average absolute difference of 5.55?% with seasonal fluctuations. A direct comparison with Interactive Multisensor Snow and Ice Mapping System (IMS) daily sea ice cover data achieves an average accuracy of 93.98?%. These results show that the developed S1-derived sea ice cover results are comparable to the AMSR and IMS data in terms of overall accuracy but superior to these data in presenting detailed sea ice cover information, particularly in the marginal ice zone (MIZ). Data are available at https://doi.org/10.11922/sciencedb.00273 (Wang and Li, 2020).