Article Dans Une Revue Physica D: Nonlinear Phenomena Année : 2023

Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning

Résumé

The complexity of real-world geophysical systems is often compounded by the fact that the observed measurements depend on hidden variables. These latent variables include unresolved small scales and/or rapidly evolving processes, partially observed couplings, or forcings in coupled systems. This is the case in ocean-atmosphere dynamics, for which unknown interior dynamics can affect surface observations. The identification of computationally-relevant representations of such partiallyobserved and highly nonlinear systems is thus challenging and often limited to short-term forecast applications. Here, we investigate the physics-constrained learning of implicit dynamical embeddings,leveraging neural ordinary differential equation (NODE) representations. A key objective is to constrain their boundedness, which promotes the generalization of the learned dynamics to arbitraryinitial condition. The proposed architecture is implemented within a deep learning framework, and its relevance is demonstrated with respect to state-of-the-art schemes for different case-studies representative of geophysical dynamics.

Fichier principal
Vignette du fichier
S0167278922003347.pdf (9.33 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04171040 , version 1 (31-03-2025)

Licence

Identifiants

Citer

Said Ouala, Steven Brunton, Bertrand Chapron, Ananda Pascual, Fabrice Collard, et al.. Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning. Physica D: Nonlinear Phenomena, 2023, 446, pp.133630. ⟨10.1016/j.physd.2022.133630⟩. ⟨hal-04171040⟩
269 Consultations
454 Téléchargements

Altmetric

Partager

  • More