Towards diffusion models for large-scale sea-ice modelling
This work addresses computational efficiency and physical accuracy in sea-ice modeling for climate research, though it remains incremental due to unresolved smoothing issues.
The authors tackled the problem of generating realistic sea-ice states for large-scale Earth system modeling using diffusion models, achieving similar performance scores to data-space diffusion models while enforcing physical bounds through a censored Gaussian distribution.
We make the first steps towards diffusion models for unconditional generation of multivariate and Arctic-wide sea-ice states. While targeting to reduce the computational costs by diffusion in latent space, latent diffusion models also offer the possibility to integrate physical knowledge into the generation process. We tailor latent diffusion models to sea-ice physics with a censored Gaussian distribution in data space to generate data that follows the physical bounds of the modelled variables. Our latent diffusion models reach similar scores as the diffusion model trained in data space, but they smooth the generated fields as caused by the latent mapping. While enforcing physical bounds cannot reduce the smoothing, it improves the representation of the marginal ice zone. Therefore, for large-scale Earth system modelling, latent diffusion models can have many advantages compared to diffusion in data space if the significant barrier of smoothing can be resolved.