loading page

Generative diffusion for regional surrogate models from sea-ice simulations
  • +3
  • Tobias Sebastian Finn,
  • Charlotte Durand,
  • Alban Farchi,
  • Marc Bocquet,
  • Pierre Rampal,
  • Alberto Carrassi
Tobias Sebastian Finn
CEREA, École des Ponts and EDF R&D

Corresponding Author:[email protected]

Author Profile
Charlotte Durand
CEREA, École des Ponts and EDF R&D, Île-de-France, France
Author Profile
Alban Farchi
Author Profile
Marc Bocquet
Author Profile
Pierre Rampal
Author Profile
Alberto Carrassi
Dept. of Physics and Astronomy "Augusto Righi", University of Bologna
Author Profile


We introduce deep generative diffusion for multivariate and regional surrogate modeling learned from sea-ice simulations. Given initial conditions and atmospheric forcings, the model is trained to generate forecasts for a 12-hour lead time from simulations by the state-of-the-art sea-ice model neXtSIM. For our regional model setup, the diffusion model outperforms as ensemble forecast all other tested models, including a free-drift model and a stochastic extension of a deterministic data-driven surrogate model. The diffusion model additionally retains information at all scales, resolving smoothing issues of deterministic models. Furthermore, by generating physical consistent forecasts, previously unseen for such kind of completely data-driven surrogates, the model can almost match the scaling properties of neXtSIM, which are also observed for real sea ice. With these results, we provide a strong indication that diffusion models can achieve similar results as traditional geophysical models with the significant advantage of being orders of magnitude faster and solely learned from data.