Latent Space Data Assimilation by using Deep Learning
Abstract
Performing Data Assimilation (DA) at a low cost is of prime concern in Earth system modeling, particularly at the time of big data where huge quantities of observations are available. Capitalizing on the ability of Neural Networks techniques for approximating the solution of PDE's, we incorporate Deep Learning (DL) methods into a DA framework. More precisely, we exploit the latent structure provided by autoencoders (AEs) to design an Ensemble Transform Kalman Filter with model error (ETKF-Q) in the latent space. Model dynamics are also propagated within the latent space via a surrogate neural network. This novel ETKF-Q-Latent (thereafter referred to as ETKF-Q-L) algorithm is tested on a tailored instructional version of Lorenz 96 equations, named the augmented Lorenz 96 system: it possesses a latent structure that accurately represents the observed dynamics. Numerical experiments based on this particular system evidence that the ETKF-Q-L approach both reduces the computational cost and provides better accuracy than state of the art algorithms, such as the ETKF-Q.
Cite
@article{arxiv.2104.00430,
title = {Latent Space Data Assimilation by using Deep Learning},
author = {Mathis Peyron and Anthony Fillion and Selime Gürol and Victor Marchais and Serge Gratton and Pierre Boudier and Gael Goret},
journal= {arXiv preprint arXiv:2104.00430},
year = {2021}
}
Comments
15 pages, 7 figures and 3 tables