Learning ocean dynamical priors from noisy data using assimilation-derived neural nets - Archive ouverte HAL Access content directly
Conference Papers Year :

Learning ocean dynamical priors from noisy data using assimilation-derived neural nets

(1, 2) , (3, 2) , (4, 5) , (1, 2) , (6) , (7) , (8) , (8) , (1, 2)
1
2
3
4
5
6
7
8

Abstract

Recent studies have investigated the identification of governing equations of geophysical systems from data. Here, we investigate such identification issues for ocean surface dynamcis from ocean remote sensing data. From a methodological point of view, we address the learning of data-driven dynamical models when only provided with a noisy training dataset. We propose a novel architecture that relies on data assimilation schemes to learn the underlying dynamical model through the minimization of a reconstruction cost. We demonstrate the relevance of the proposed architecture with respect to the state-of-the-art approaches in the identification and forecasting of synthetic and real case-studies.
Fichier principal
Vignette du fichier
Learning_Ocean_Dynamical_Priors_from_Noisy_Data_Using_Assimilation-Derived_Neural_Nets.pdf (386.73 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02285693 , version 1 (21-06-2022)

Identifiers

Cite

Said Ouala, Duong Nguyen, Cédric Herzet, Lucas Drumetz, Bertrand Chapron, et al.. Learning ocean dynamical priors from noisy data using assimilation-derived neural nets. IGARSS 2019 - International Geoscience and remote Sensing Symposium, Jul 2019, Yokohama, Japan. pp.1-3, ⟨10.1109/IGARSS.2019.8900345⟩. ⟨hal-02285693⟩
105 View
17 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More