Using machine learning to correct model error in data assimilation and forecast applications

TL;DR

This paper introduces a hybrid data assimilation approach combining machine learning and traditional models to correct model errors, improving forecast accuracy in geophysical applications.

Contribution

It proposes a novel iterative method that integrates ML with data assimilation to correct existing model errors, demonstrated on a quasi-geostrophic model.

Findings

ML models learn significant parts of model error

Hybrid models improve short- to mid-range forecast accuracy

Hybrid models enhance data assimilation analysis quality

Abstract

The idea of using machine learning (ML) methods to reconstruct the dynamics of a system is the topic of recent studies in the geosciences, in which the key output is a surrogate model meant to emulate the dynamical model. In order to treat sparse and noisy observations in a rigorous way, ML can be combined to data assimilation (DA). This yields a class of iterative methods in which, at each iteration a DA step assimilates the observations, and alternates with a ML step to learn the underlying dynamics of the DA analysis. In this article, we propose to use this method to correct the error of an existent, knowledge-based model. In practice, the resulting surrogate model is an hybrid model between the original (knowledge-based) model and the ML model. We demonstrate numerically the feasibility of the method using a two-layer, two-dimensional quasi-geostrophic channel model. Model error is introduced by the means of perturbed parameters. The DA step is performed using the strong-constraint 4D-Var algorithm, while the ML step is performed using deep learning tools. The ML models are able to learn a substantial part of the model error and the resulting hybrid surrogate models produce better short- to mid-range forecasts. Furthermore, using the hybrid surrogate models for DA yields a significantly better analysis than using the original model.