Uncertainty quantification when learning dynamical models and solvers with variational methods - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2023

Uncertainty quantification when learning dynamical models and solvers with variational methods

Abstract

In geosciences, data assimilation (DA) addresses the reconstruction of a hidden dynamical process given some observation data. DA is at the core of operational systems such as weather forecasting, operational oceanography and climate studies. Beyond the reconstruction of the mean or most likely state, precise inference of the state posterior distribution remains a key challenge, i.e. quantify uncertainties as well as to inform intrinsical stochastic variabilities. Indeed, DA schemes, such as variational DA and Kalman methods, can have difficulty in dealing with complex non-linear processes. A growing literature investigates the cross-fertilization of DA and machine learning. This study proposes an end-to-end neural network scheme based on a variational Bayes inference formulation. It combines an ELBO (Evidence Lower BOund) variational cost to a trainable gradient-based solver to infer the state posterior probability distribution function given observation data. The inference of the posterior and the trainable solver are learnt jointly. We demonstrate the relevance of the proposed scheme for a Gaussian parameterization of the posterior and different case-study experiments. It includes a benchmark with respect to state-of-the-art schemes.
Fichier principal
Vignette du fichier
preprint_4DVarNetExtr_NLafon.pdf (1.45 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04013195 , version 1 (03-03-2023)

Identifiers

  • HAL Id : hal-04013195 , version 1

Cite

Nicolas Lafon, Ronan Fablet, P Naveau. Uncertainty quantification when learning dynamical models and solvers with variational methods. 2023. ⟨hal-04013195⟩
34 View
22 Download

Share

Gmail Facebook Twitter LinkedIn More