Work

Swift: an autoregressive consistency model for efficient weather forecasting

Year: 2026

Type: article

Abstract: 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.

Source: Machine Learning Earth

DOI: 10.1088/3049-4753/ae802a

Authors: Jason Stock, Troy Arcomano, Rao Kotamarthi

Institutions: Argonne National Laboratory, Allen Institute for Artificial Intelligence

Language: English

Topic: Meteorological Phenomena and Simulations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: gold

Estimated APC paid: $3,125