FuXi-En4DVar: An Assimilation System Based on Machine Learning Weather Forecasting Model Ensuring Physical Constraints

Abstract

Recent machine learning (ML)-based weather forecasting models have improved the accuracy and efficiency of forecasts while minimizing computational resources, yet still depend on traditional data assimilation (DA) systems to generate analysis fields. Four dimensional variational data assimilation (4DVar) enhances model states, relying on the prediction model to propagate observation to the initial field. Consequently, the initial fields from traditional DA are not optimal for ML-based models, necessitating a customized DA system. This paper introduces an ensemble 4DVar system integrated with the FuXi model (FuXi-En4DVar), which can independently generate accurate analysis fields. It utilizes automatic differentiation to compute gradients, and demonstrates the equivalence of these gradients with those derived from adjoint models. Experimental results indicate that this system preserves the physical balance of the analysis field and exhibits flow-dependent characteristics. These features enhance the propagation and assimilation of observation into the initial analysis field, thereby improving the accuracy of the analysis fields.