Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting
This addresses the need for efficient and reliable ensemble forecasting from medium-range to seasonal scales, particularly for subseasonal-to-seasonal applications, representing an incremental improvement over existing methods.
The authors tackled the inefficiency of diffusion models for weather forecasting by introducing Swift, a single-step consistency model that enables autoregressive fine-tuning with a CRPS objective, resulting in forecasts stable for up to 75 days, running 39 times faster than state-of-the-art diffusion baselines while achieving competitive skill with operational systems.
Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for subseasonal-to-seasonal (S2S) applications where long lead-times and domain-driven calibration are essential. To address this, we introduce Swift, a single-step consistency model that, for the first time, enables autoregressive finetuning of a probability flow model with a continuous ranked probability score (CRPS) objective. This eliminates the need for multi-model ensembling or parameter perturbations. Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running $39\times$ faster than state-of-the-art diffusion baselines while achieving forecast skill competitive with the numerical-based, operational IFS ENS. This marks a step toward efficient and reliable ensemble forecasting from medium-range to seasonal-scales.