Learning Dynamical Systems from Partial Observations - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Learning Dynamical Systems from Partial Observations

Résumé

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled by an unknown time-varying differential equation, and the evolution term is estimated from the data, using a neural network. Any future state can then be computed by placing the associated differential equation in an ODE solver. We first evaluate our approach on shallow water and Euler simulations. We find that our method not only demonstrates high quality long-term forecasts, but also learns to produce hidden states closely resembling the true states of the system, without direct supervision on the latter. Additional experiments conducted on challenging, state of the art ocean simulations further validate our findings, while exhibiting notable improvements over classical baselines.

Dates et versions

hal-02418376 , version 1 (18-12-2019)

Identifiants

Citer

Ibrahim Ayed, Emmanuel de Bézenac, Arthur Pajot, Julien Brajard, Patrick Gallinari. Learning Dynamical Systems from Partial Observations. 2019. ⟨hal-02418376⟩
298 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More