Learning Constrained Dynamical Embeddings for Geophysical Dynamics - IMT Atlantique Access content directly
Conference Papers Year :

Learning Constrained Dynamical Embeddings for Geophysical Dynamics

Said Ouala
Steven L Brunton
  • Function : Author
Duong Nguyen
Lucas Drumetz
Ronan Fablet

Abstract

In this work, we investigate the implementation of physical constraints for the regularization of linear quadratic dynamical representations of partially observed systems. We focus on energy preserving quadratic terms and propose to enforce this constraint within the learning criterion of the models. We further demonstrate on the Lorenz 63 system that the generalization performance is significantly improved to states beyond the attractor spanned by the observation data when this constraint is satisfied.
Fichier principal
Vignette du fichier
CI2019_paper_46.pdf (1.04 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02285700 , version 1 (18-11-2020)

Identifiers

  • HAL Id : hal-02285700 , version 1

Cite

Said Ouala, Steven L Brunton, Duong Nguyen, Lucas Drumetz, Ronan Fablet. Learning Constrained Dynamical Embeddings for Geophysical Dynamics. CI 2019 : 9th International Workshop on Climate Informatics, 2019, Paris, France. ⟨hal-02285700⟩
96 View
47 Download

Share

Gmail Facebook Twitter LinkedIn More