Towards diffusion models for large-scale sea-ice modelling

TL;DR

This paper explores the application of latent diffusion models for large-scale sea-ice state generation, aiming to reduce computational costs and incorporate physical constraints, with promising results in physical accuracy and efficiency.

Contribution

It introduces tailored latent diffusion models for sea-ice physics, integrating physical bounds and demonstrating comparable performance to data-space models with potential advantages.

Findings

Latent diffusion models achieve similar scores as data-space models.

Physical bounds improve marginal ice zone representation.

Latent models offer computational advantages for Earth system modeling.

Abstract

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.