2026-10-10T16:02:27Z https://www.scidb.cn/oai

10.57760/sciencedb.33311 2026-03-20T11:11:31Z

2026-03-20 CryoSat-2-based Antarctic sea ice thickness dataset for 2010–2024 doi:10.57760/sciencedb.33311 en Sea ice is crucial for modulating Antarctic air–sea fluxes, and its thickness (SIT) is the primary factor controlling the exchange of heat, moisture, and momentum. Although CryoSat-2 is commonly used for SIT retrieval, conventional algorithms rely on empirical parameters and auxiliary data that introduce substantial uncertainties. In this study, we developed a novel SIT dataset for 2010–2024, derived directly from radar parameters using a machine learning (ML) method. Intercomparisons show that the ML-derived SIT shows better consistency with the ICESat-2 product than conventional algorithm results. Validation against shipborne observations indicates that ML-based SIT achieves a mean absolute error of 0.558 m, lower than conventional methods (0.823 m). Temporal comparisons reveal that the ML-derived sea ice volume (SIV) exhibits a more realistic seasonal cycle, with the maximum value occurring in September, compared to the conventional method, which shows a peak in August. This new SIT dataset provides a robust basis for estimating SIV with reduced uncertainty, investigating sea ice variability mechanisms, and assessing the impact of sea ice changes. Antarctic; sea ice thickness; machine learning Ziqi Ma Qinghua Yang Yafei Nie PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset Science Data Bank