Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations

Résumé

The data-driven recovery of the unknown governing equations of dynamical systems has recently received an increasing interest. However, the identification of governing equations remains challenging when dealing with noisy and partial observations. Here, we address this challenge and investigate variational deep learning schemes. Within the proposed framework, we jointly learn an inference model to reconstruct the true states of the system and the governing laws of these states from series of noisy and partial data. In doing so, this framework bridges classical data assimilation and state-of-the-art machine learning techniques. We also demonstrate that it generalises state-of-the-art methods. Importantly, both the inference model and the governing model embed stochastic components to account for stochastic variabilities, model errors, and reconstruction uncertainties. Various experiments on chaotic and stochastic dynamical systems support the relevance of our scheme w.r.t. state-of-the-art approaches.
Fichier principal
Vignette du fichier
TSP_DAODEN.pdf (3.65 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-02931101 , version 1 (04-09-2020)
hal-02931101 , version 2 (15-09-2020)
hal-02931101 , version 3 (26-09-2020)
hal-02931101 , version 4 (29-09-2020)
hal-02931101 , version 5 (30-09-2020)
hal-02931101 , version 6 (14-01-2021)
hal-02931101 , version 7 (16-02-2021)

Identifiants

  • HAL Id : hal-02931101 , version 7

Citer

Duong Nguyen, Said Ouala, Lucas Drumetz, Ronan Fablet. Variational Deep Learning for the Identification and Reconstruction of Chaotic and Stochastic Dynamical Systems from Noisy and Partial Observations. 2021. ⟨hal-02931101v7⟩
244 Consultations
232 Téléchargements

Partager

Gmail Facebook X LinkedIn More