Exploring the Use of Machine Learning Weather Models in Data Assimilation

TL;DR

This paper evaluates the tangent linear and adjoint models of ML-based weather models GraphCast and NeuralGCM for data assimilation, highlighting issues with unphysical noise that affect their operational viability.

Contribution

It provides the first assessment of the physical consistency of ML weather models' tangent linear and adjoint models for data assimilation applications.

Findings

Adjoint models show some similarity to traditional models but exhibit unphysical noise.

Unphysical noise in ML models could impair data assimilation accuracy.

Addressing noise issues is essential for operational integration of ML weather models.

Abstract

The use of machine learning (ML) models in meteorology has attracted significant attention for their potential to improve weather forecasting efficiency and accuracy. GraphCast and NeuralGCM, two promising ML-based weather models, are at the forefront of this innovation. However, their suitability for data assimilation (DA) systems, particularly for four-dimensional variational (4DVar) DA, remains under-explored. This study evaluates the tangent linear (TL) and adjoint (AD) models of both GraphCast and NeuralGCM to assess their viability for integration into a DA framework. We compare the TL/AD results of GraphCast and NeuralGCM with those of the Model for Prediction Across Scales - Atmosphere (MPAS-A), a well-established numerical weather prediction (NWP) model. The comparison focuses on the physical consistency and reliability of TL/AD responses to perturbations. While the adjoint results of both GraphCast and NeuralGCM show some similarity to those of MPAS-A, they also exhibit unphysical noise at various vertical levels, raising concerns about their robustness for operational DA systems. The implications of this study extend beyond 4DVar applications. Unphysical behavior and noise in ML-derived TL/AD models could lead to inaccurate error covariances and unreliable ensemble forecasts, potentially degrading the overall performance of ensemble-based DA systems, as well. Addressing these challenges is critical to ensuring that ML models, such as GraphCast and NeuralGCM, can be effectively integrated into operational DA systems, paving the way for more accurate and efficient weather predictions.