English

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

Machine Learning 2023-02-01 v2 Machine Learning Dynamical Systems

Abstract

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 partially-observed 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 arbitrary initial 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.

Keywords

Cite

@article{arxiv.2202.05750,
  title  = {Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning},
  author = {Said Ouala and Steven L. Brunton and Ananda Pascual and Bertrand Chapron and Fabrice Collard and Lucile Gaultier and Ronan Fablet},
  journal= {arXiv preprint arXiv:2202.05750},
  year   = {2023}
}
R2 v1 2026-06-24T09:32:26.535Z