SIFM: A Foundation Model for Multi-granularity Arctic Sea Ice Forecasting
This work addresses forecasting challenges for climate science and polar ecosystems, but it is incremental as it builds on prior deep learning methods by incorporating multi-granularity correlations.
The paper tackles the problem of forecasting Arctic sea ice concentration at multiple temporal granularities by proposing SIFM, a foundation model that leverages both intra-granularity and inter-granularity information, resulting in outperforming existing deep learning models for specific granularities.
Arctic sea ice performs a vital role in global climate and has paramount impacts on both polar ecosystems and coastal communities. In the last few years, multiple deep learning based pan-Arctic sea ice concentration (SIC) forecasting methods have emerged and showcased superior performance over physics-based dynamical models. However, previous methods forecast SIC at a fixed temporal granularity, e.g. sub-seasonal or seasonal, thus only leveraging inter-granularity information and overlooking the plentiful inter-granularity correlations. SIC at various temporal granularities exhibits cumulative effects and are naturally consistent, with short-term fluctuations potentially impacting long-term trends and long-term trends provides effective hints for facilitating short-term forecasts in Arctic sea ice. Therefore, in this study, we propose to cultivate temporal multi-granularity that naturally derived from Arctic sea ice reanalysis data and provide a unified perspective for modeling SIC via our Sea Ice Foundation Model. SIFM is delicately designed to leverage both intra-granularity and inter-granularity information for capturing granularity-consistent representations that promote forecasting skills. Our extensive experiments show that SIFM outperforms off-the-shelf deep learning models for their specific temporal granularity.