A posteriori learning of quasi-geostrophic turbulence parametrization: an experiment on integration steps - Ecole Nationale d'Ingénieurs de Brest Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

A posteriori learning of quasi-geostrophic turbulence parametrization: an experiment on integration steps

Résumé

Modeling the subgrid-scale dynamics of reduced models is a long standing open problem that finds application in ocean, atmosphere and climate predictions where direct numerical simulation (DNS) is impossible. While neural networks (NNs) have already been applied to a range of three-dimensional problems with success, the backward energy transfer of two-dimensional flows still remains a stability issue for trained models. We show that learning a model jointly with the dynamical solver and a meaningful $\textit{a posteriori}$-based loss function lead to stable and realistic simulations when applied to quasi-geostrophic turbulence.
Fichier principal
Vignette du fichier
2111.06841.pdf (779.57 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03456259 , version 1 (29-11-2021)
hal-03456259 , version 2 (11-01-2022)

Identifiants

Citer

Hugo Frezat, Julien Le Sommer, Ronan Fablet, Guillaume Balarac, Redouane Lguensat. A posteriori learning of quasi-geostrophic turbulence parametrization: an experiment on integration steps. 2022. ⟨hal-03456259v2⟩
136 Consultations
88 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More