The persistent lack of spatially complete Antarctic sea ice thickness (SIT) data at sub-monthly resolution has fundamentally constrained the quantitative understanding of large-scale sea ice mass balance processes and their climat impacts. In the first part this study, a pan-Antarctic SIT dataset at 5-day and 12.5 km resolution was developed based on sparse Ice, Cloud and Land Elevation Satellite (ICESat; 2003–2009) and ICESat-2 (2018–2024) along-track laser altimetry SIT retrievals using a deep learning approach. The reconstructed SIT was quantitatively validated against independent upward-looking sonar (ULS) observations and showed higher accuracy than the other four satellite-derived and reanalyzed Antarctic SIT datasets. The temporal evolution of the reconstructed SIT was further validated by ULS and ICESat-2 observations. Consistent seasonal cycles and intra-seasonal tendencies across these datasets confirm the reconstruction's reliability. Beyond advancing the mechanistic understanding of Antarctic sea ice variability and climate linkages, this reconstruction dataset's near-real-time updating capability offers operational value for monitoring and forecasting the Antarctic sea ice state. In Part II, we developed a new machine learning-based algorithm for deriving SIT from CryoSat-2 radar altimeter track-based measurements. Compared to conventional waveform deriving methods, our results more closely match ASPeCt ship-based observations. In the third part, building upon the aforementioned CryoSat-2 and ICESat-2 track-based data, we have preliminarily developed a daily-resolving, pan-Antarctic coveraged SIT dataset using an AI-based assimilation method.

Antarctic,Sea ice thickness,Satellite retrieval,Artificial Intelligence,Data reconstruction