Data-driven surrogate modeling of high-resolution sea-ice thickness in the Arctic by Charlotte Durand, Tobias Sebastian Finn, Alban Farchi, Marc Bocquet, Guillaume Boutin, and Einar Ólason published in the Cryosphere.

In this article, Charlotte Durand et al. focus on predicting Arctic-wide sea-ice thickness using surrogate modeling with deep learning. The model has a predictive power of 12 h up to 6 months. For this forecast horizon, persistence and daily climatology are systematically outperformed, a result of learned thermodynamics and advection. Consequently, surrogate modeling with deep learning proves to be effective at capturing the complex behavior of sea ice.

https://doi.org/10.5194/tc-18-1791-2024

_Fig.1 (from Charlotte Durand et al.): SIT simulated by neXtSIM at 15:00 UTC on 3 March 2009. The shaded area represents the cropped grid cells that are further removed in order to keep a 512×512 grid cell SIT field without loss of information.