Skip to Main content Skip to Navigation
Journal articles

Learning Latent Dynamics for Partially-Observed Chaotic Systems

Abstract : This paper addresses the data-driven identification of latent dynamical representations of partially-observed systems, i.e., dynamical systems for which some components are never observed, with an emphasis on forecasting applications, including long-term asymptotic patterns. Whereas state-of-the-art data-driven approaches rely on delay embeddings and linear decompositions of the underlying operators, we introduce a framework based on the data-driven identification of an augmented state-space model using a neural-network-based representation. For a given training dataset, it amounts to jointly learn an ODE (Ordinary Differential Equation) representation in the latent space and reconstructing latent states. Through numerical experiments, we demonstrate the relevance of the proposed framework w.r.t. state-of-the-art approaches in terms of short-term forecasting performance and long-term behaviour. We further discuss how the proposed framework relates to Koopman operator theory and Takens' embedding theorem.
Complete list of metadata
Contributor : Said Ouala <>
Submitted on : Friday, August 30, 2019 - 10:39:12 AM
Last modification on : Friday, April 9, 2021 - 5:06:32 PM

Links full text



Said Ouala, Duong Nguyen, Lucas Drumetz, Bertrand Chapron, Ananda Pascual, et al.. Learning Latent Dynamics for Partially-Observed Chaotic Systems. Chaos: An Interdisciplinary Journal of Nonlinear Science, American Institute of Physics, 2020, 30 (10), ⟨10.1063/5.0019309⟩. ⟨hal-02274705⟩



Record views