Towards diffusion models for large-scale sea-ice modelling ...

• Main Authors: Finn, Tobias Sebastian, Durand, Charlotte, Farchi, Alban, Bocquet, Marc, Brajard, Julien
• Format: Report
• Language: unknown
• Published: arXiv 2024
• Subjects: Machine Learning cs.LG; Atmospheric and Oceanic Physics physics.ao-ph; FOS Computer and information sciences; FOS Physical sciences; Sea ice
• Online Access: https://dx.doi.org/10.48550/arxiv.2406.18417; https://arxiv.org/abs/2406.18417

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. ... : 21 pages, 5 Figures, Camera-ready version for the ICML 2024 Machine Learning for Earth System Modeling workshop ...