Neural variational Data Assimilation with Uncertainty Quantification using SPDE priors - IMT - Institut Mines-Télécom Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Neural variational Data Assimilation with Uncertainty Quantification using SPDE priors

Résumé

The spatio-temporal interpolation of large geophysical datasets has historically been addressed by Optimal Interpolation (OI) and more sophisticated equation-based or data-driven Data Assimilation (DA) techniques. Recent advances in the deep learning community enables to address the interpolation problem through a neural architecture incorporating a variational data assimilation framework. The reconstruction task is seen as a joint learning problem of the prior involved in the variational inner cost, seen here as a projection operator of the state, and the gradient-based minimization of the latter. Both prior models and solvers are stated as neural networks with automatic differentiation which can be trained by minimizing a loss function, typically the mean squared error between some ground truth and the reconstruction.

Such a strategy turns out to be very efficient to improve the mean state estimation, but still needs complementary developments to quantify its related uncertainty. In this work, we use the theory of Stochastic Partial Differential Equations (SPDE) and Gaussian Processes (GP) to estimate both space-and time-varying covariance of the state. Our neural variational scheme is modified to embed an augmented state formulation with both state and SPDE parametrization to estimate. We demonstrate the potential of the proposed framework on a spatio-temporal GP driven by diffusionbased anisotropies and on realistic Sea Surface Height (SSH) datasets. We show how our solution reaches the OI baseline in the Gaussian case. For nonlinear dynamics, as almost always stated in DA, our solution outperforms OI, while allowing for fast and interpretable online parameter estimation

Fichier principal
Vignette du fichier
Neural_DA_SPDE_prior.pdf (4.85 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04675468 , version 1 (22-08-2024)

Licence

Identifiants

  • HAL Id : hal-04675468 , version 1

Citer

Maxime Beauchamp, Ronan Fablet, Simon Benaichouche, Pierre Tandeo, Nicolas Desassis, et al.. Neural variational Data Assimilation with Uncertainty Quantification using SPDE priors. 2024. ⟨hal-04675468⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More