LEARNING STOCHASTIC REPRESENTATIONS OF GEOPHYSICAL DYNAMICS

Abstract : In the last years, Neural Networks have enriched the state-of-the-art in probabilistic modeling. This is principally due to the advances in deep learning which allow a better understanding of complex systems. However, the stochastic representation of spatio-temporal fields is still an open challenge that may benefit from the recent advances in probabilistic mode-lization. In this work, we explore neural network to derive a stochastic representation of spatio-temporal dynamical systems based on ensemble forecasting. Trough the implementation of our stochastic model in a classical Kalman filtering scheme, we demonstrate the relevance of the proposed architecture in the reconstruction of geophysical fields with respect to the state-of-the-art approaches.
Type de document :
Pré-publication, Document de travail
Liste complète des métadonnées

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02005403
Contributeur : Said Ouala <>
Soumis le : lundi 4 février 2019 - 09:55:34
Dernière modification le : mercredi 6 mars 2019 - 15:08:26

Fichier

stochastic_dynamics_and_kalman...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02005403, version 1

Citation

Said Ouala, Ronan Fablet, Cedric Herzet, Bertrand Chapron, Ananda Pascual, et al.. LEARNING STOCHASTIC REPRESENTATIONS OF GEOPHYSICAL DYNAMICS. 2019. ⟨hal-02005403⟩

Partager

Métriques

Consultations de la notice

101

Téléchargements de fichiers

75