Leveraging Data-Driven Weather Models for Improving Numerical Weather Prediction Skill through Large-Scale Spectral Nudging

Abstract Operational meteorological forecasting has long relied on physics-based numerical weather prediction (NWP) models. Recently, this landscape has faced disruption by the advent of data-driven artificial intelligence (AI)-based weather models, which offer tremendous computational performance and competitive forecasting accuracy. However, data-driven models for medium-range forecasting generally suffer from major limitations, including low effective resolution and a narrow range of predicted variables. This study illustrates the relative strengths and weaknesses of these competing paradigms using the physics-based Global Environmental Multiscale (GEM) and the AI-based GraphCast models. Analyses of their respective global predictions in physical and spectral space reveal that GraphCast-predicted large scales outperform GEM, particularly for longer lead times, even though fine scales predicted by GraphCast suffer from excessive smoothing. Building on this insight, a hybrid NWP–AI system is proposed, wherein temperature and horizontal wind components predicted by GEM are spectrally nudged toward GraphCast predictions at large scales, while GEM itself freely generates the fine-scale details critical for local predictability and weather extremes. This hybrid approach is capable of leveraging the strengths of GraphCast to enhance the prediction skill of the GEM model while generating a full suite of physically consistent forecast fields with a full power spectrum. Additionally, trajectories of tropical cyclones are predicted with enhanced accuracy without significant changes in intensity. Work is in progress for operationalization of this hybrid system at the Canadian Meteorological Centre. Significance Statement Recent developments in the field of artificial intelligence–based weather prediction have yielded models that are capable of generating forecasts that outperform those of traditional physics-based models. A comparison of two such systems reveals that although the data-driven model produces superior estimates of global atmospheric conditions at longer lead times, it lacks fine details and predicts only a limited set of meteorologically important variables. This paper proposes a hybrid system to leverage the advantages of the two component models where large-scale wind and temperature predicted by the physics-based model are nudged toward those from the data-driven model’s forecasts. This system promises to improve the operational guidance generated by the Canadian Meteorological Centre in the near future.