Latent Space Data Assimilation by using Deep Learning
This work addresses the need for efficient Data Assimilation in Earth system modeling, particularly with big data, but it is incremental as it builds on existing ETKF-Q methods by incorporating deep learning techniques.
The authors tackled the problem of high computational cost in Data Assimilation for Earth system modeling by developing a novel algorithm, ETKF-Q-L, which uses autoencoders and a surrogate neural network in latent space. Their method reduced computational cost and improved accuracy over state-of-the-art algorithms like ETKF-Q, as evidenced by numerical experiments on an augmented Lorenz 96 system.
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.