Latent Space Data Assimilation by using Deep Learning

TL;DR

This paper introduces a novel latent space data assimilation method using deep learning, which leverages autoencoders and neural networks to improve efficiency and accuracy in Earth system modeling.

Contribution

It develops the ETKF-Q-L algorithm that integrates autoencoders and neural networks for low-cost, accurate data assimilation in latent space, a novel approach in the field.

Findings

Reduces computational cost compared to traditional methods

Achieves better accuracy in data assimilation tasks

Successfully tested on augmented Lorenz 96 system

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.