Arctic Sea Ice Lead Detection from Chinese HY-2B Radar Altimeter Data

Sea ice thickness is one of the essential characteristics sea ice. lead detection key to estimation from radar altimetry data. This research studies ten different surface type classification methods, including supervised learning, unsupervised and threshold being applied HY-2B altimeter data collected in October 2019 Arctic Ocean. The Sentinel-1 Synthetic Aperture Radar (SAR) images were used for training validation classifiers. Compared with other classifiers, Bagging ensemble learning classifier showed excellent robust performance overall accuracy up 95.69%. In order assess practical applications, fractions January March 2021 based on mapped using trained compared CryoSat-2 L2I product. results fraction monthly variability lead, had a reasonable spatial distribution was consistent products. According these results, can provide an reference future level