SuperIce

SuperIce aims to develop a simulator of high-resolution sea ice thickness in the Arctic to address critical questions related to sea ice predictability at seasonal timescales and its role in the Earth’s climate system.

Current satellite-based observations of sea ice thickness provide valuable data but are limited by their spatial resolution. High-resolution information is crucial for accurate predictions and understanding small-scale features such as ice leads and thin ice, which significantly impact seasonal forecasting and heat flux calculations.

To overcome these limitations, this project proposes a multi-step approach. First, a physically based sea ice model, neXtSIM, is employed to generate high-resolution synthetic sea ice thickness datasets. These synthetic datasets are then filtered to mimic the resolution of satellite products. An AI-based diffusion model is trained to super-resolve the low-resolution SIT data. Finally, the AI-based model is applied to real Earth observation (EO) data, and its results are validated against high-resolution satellite data.

The project aims to achieve several objectives:

1. Exploiting the potential of high-resolution sea ice modeling and AI-based super-resolution techniques to create synthetic datasets for improved seasonal forecasting and climate impact assessment. 
2. Quantifying the impact of using synthetic datasets in enhancing EO data.
3. Fostering collaboration between the AI, sea-ice modeling, and remote sensing communities through conferences, seminars, and workshops, promoting diversity and inclusivity in the scientific community.