Generative AI models capture realistic sea-ice evolution from days to decades

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Finn, Tobias Sebastian, Bocquet, Marc, Rampal, Pierre, Durand, Charlotte, Porro, Flavia, Farchi, Alban, Carrassi, Alberto
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911260601221120
author Finn, Tobias Sebastian
Bocquet, Marc
Rampal, Pierre
Durand, Charlotte
Porro, Flavia
Farchi, Alban
Carrassi, Alberto
author_facet Finn, Tobias Sebastian
Bocquet, Marc
Rampal, Pierre
Durand, Charlotte
Porro, Flavia
Farchi, Alban
Carrassi, Alberto
contents Sea ice plays an important role in stabilising the Earth system. Yet, representing its dynamics remains a major challenge for models, as the underlying processes are scale-invariant and highly anisotropic. This poses a dilemma: physics-based models that faithfully reproduce the observed dynamics are computationally costly, while efficient AI models sacrifice realism. Here, to resolve this dilemma, we introduce GenSIM, the first generative AI model to predict the evolution of the full Arctic sea-ice state at 12-hour increments. Trained for sub-daily forecasting on 20 years of sea-ice-ocean simulation data, GenSIM makes realistic predictions for 30 years, while reproducing the dynamical properties of sea ice with its leads and ridges and capturing long-term trends in the sea-ice volume. Notably, although solely driven by atmospheric reanalysis, GenSIM implicitly learns hidden signatures of multi-year ice-ocean interaction. Therefore, generative AI can extrapolate from sub-daily forecasts to decadal simulations, while retaining physical consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14984
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative AI models capture realistic sea-ice evolution from days to decades
Finn, Tobias Sebastian
Bocquet, Marc
Rampal, Pierre
Durand, Charlotte
Porro, Flavia
Farchi, Alban
Carrassi, Alberto
Atmospheric and Oceanic Physics
Machine Learning
86A05
J.2; I.2.10
Sea ice plays an important role in stabilising the Earth system. Yet, representing its dynamics remains a major challenge for models, as the underlying processes are scale-invariant and highly anisotropic. This poses a dilemma: physics-based models that faithfully reproduce the observed dynamics are computationally costly, while efficient AI models sacrifice realism. Here, to resolve this dilemma, we introduce GenSIM, the first generative AI model to predict the evolution of the full Arctic sea-ice state at 12-hour increments. Trained for sub-daily forecasting on 20 years of sea-ice-ocean simulation data, GenSIM makes realistic predictions for 30 years, while reproducing the dynamical properties of sea ice with its leads and ridges and capturing long-term trends in the sea-ice volume. Notably, although solely driven by atmospheric reanalysis, GenSIM implicitly learns hidden signatures of multi-year ice-ocean interaction. Therefore, generative AI can extrapolate from sub-daily forecasts to decadal simulations, while retaining physical consistency.
title Generative AI models capture realistic sea-ice evolution from days to decades
topic Atmospheric and Oceanic Physics
Machine Learning
86A05
J.2; I.2.10
url https://arxiv.org/abs/2508.14984