Boosting weather forecast via generative superensemble

Abstract

Accurate weather forecasting is essential for a broad range of socioeconomic activities. While data-driven approaches match numerical weather prediction accuracy with reduced computational cost, their deterministic nature overlooks uncertainties in initial state estimate, model systematic biases, and stochasticity arising from unresolved subgrid physical processes. This obliviousness results in over-confident deterministic predictions that limit operational utility and allow prediction errors to compound over time, rendering uncertainty quantification and error correction intractable. To address these challenges, we present the Generative Ensemble Prediction System (GenEPS), a framework that systematically explores uncertainties in initial states, model formulations, and model stochasticity. GenEPS provides a plug-and-play solution for ensemble forecasting with arbitrary data-driven deterministic weather prediction models. Initial conditions and stochastic uncertainty sampling mitigate random errors, while cross-model integration accounts for inherent model formulation differences to reduce systematic biases. By explicitly representing all three sources of uncertainty, GenEPS outperforms state-of-the-art numerical ensemble predictions and data-driven predictions when evaluated against ERA5 reanalysis data using both deterministic and probabilistic metrics. GenEPS also enhances extreme event predictions, offering physically consistent forecast fields. These advances establish a new paradigm in ensemble forecasting through multi-model generative integration, combining a surging number of data-driven weather forecasting models and potentially numerical models, to achieve more reliable predictions.