Learning 4DVAR inversion directly from observations

TL;DR

This paper introduces a hybrid deep learning architecture that learns 4DVAR data assimilation directly from observations, combining mechanistic constraints with data-driven approaches for improved inversion and regularization.

Contribution

It proposes a novel hybrid model that integrates 4DVAR principles into deep learning to perform data assimilation directly from noisy observations.

Findings

Successfully learned inversion with regularizing properties

Demonstrated computational efficiency

Validated on a relevant experiment

Abstract

Variational data assimilation and deep learning share many algorithmic aspects in common. While the former focuses on system state estimation, the latter provides great inductive biases to learn complex relationships. We here design a hybrid architecture learning the assimilation task directly from partial and noisy observations, using the mechanistic constraint of the 4DVAR algorithm. Finally, we show in an experiment that the proposed method was able to learn the desired inversion with interesting regularizing properties and that it also has computational interests.