Abstract This study introduces a cost‐effective hybrid ensemble‐variational (EnVar) radar data assimilation (DA) approach through a new machine‐learning (ML) ‐aided static covariance (MLBEC). Previous studies employed convective‐scale static BECs to compensate the deficient ensemble covariances in hybrid EnVar. The used static BECs (ZBEC) often mix the error statistics of the rotating updraft (RU) and flank features for analyzing supercells. In contrast, MLBEC distinguishes the RU and flank features properly. A random forest model is developed and trained with an accuracy classification score of 0. 98 to guide the application of MLBEC in proper locations. The cost‐effective hybrid EnVar with MLBEC is demonstrated through the analyses and forecasts of two tornadic supercell cases in Oklahoma. Results show that hybrid EnVar using MLBEC improves storm analyses and forecasts by more properly analyzing RUs during the DA cycling compared to using ZBEC. When comparing with pure EnVar using 36‐member ensembles, ZBEC‐based hybrid EnVar with 12‐member ensembles enhances reflectivity analyses and forecasts; however, it does not improve mesocyclone forecasts. In contrast, MLBEC‐based hybrid EnVar with 12‐member ensembles achieves further improvements in reflectivity forecasts and produces strong mesocyclone tracks that align with observations. Furthermore, hybrid EnVar using MLBEC with six‐member ensembles still yields superior performance in reflectivity and mesocyclone forecasts than costly pure EnVar with 36‐member ensembles and ZBEC‐based hybrid EnVar with 12‐member ensembles, demonstrating a reduction in costs by 71% and 35%, respectively.
Wang et al. (Sun,) studied this question.