Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Learning Variational Data Assimilation Models and Solvers

Ronan Fablet 1, 2 Bertrand Chapron 3 Lucas Drumetz 1, 2 Etienne Mémin 4 Olivier Pannekoucke 5 François Rousseau 6, 7
1 Lab-STICC_IMTA_CID_TOMS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
4 FLUMINANCE - Fluid Flow Analysis, Description and Control from Image Sequences
IRMAR - Institut de Recherche Mathématique de Rennes, Inria Rennes – Bretagne Atlantique , INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement
Abstract : This paper addresses variational data assimilation from a learning point of view. Data assimilation aims to reconstruct the time evolution of some state given a series of observations, possibly noisy and irregularly-sampled. Using automatic differentiation tools embedded in deep learning frameworks, we introduce end-to-end neural network architectures for data assimilation. It comprises two key components: a variational model and a gradient-based solver both implemented as neural networks. A key feature of the proposed end-to-end learning architecture is that we may train the NN models using both supervised and unsupervised strategies. Our numerical experiments on Lorenz-63 and Lorenz-96 systems report significant gain w.r.t. a classic gradient-based minimization of the variational cost both in terms of reconstruction performance and optimization complexity. Intriguingly, we also show that the variational models issued from the true Lorenz-63 and Lorenz-96 ODE representations may not lead to the best reconstruction performance. We believe these results may open new research avenues for the specification of assimilation models in geoscience.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal-imt-atlantique.archives-ouvertes.fr/hal-02906798
Contributor : Ronan Fablet <>
Submitted on : Saturday, July 25, 2020 - 6:21:19 PM
Last modification on : Friday, October 23, 2020 - 4:49:53 PM

File

learning4DVar (16).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02906798, version 1

Citation

Ronan Fablet, Bertrand Chapron, Lucas Drumetz, Etienne Mémin, Olivier Pannekoucke, et al.. Learning Variational Data Assimilation Models and Solvers. 2020. ⟨hal-02906798⟩

Share

Metrics

Record views

76

Files downloads

128