Efficient Generative AI Boosts Probabilistic Forecasting of Sudden Stratospheric Warmings

TL;DR

This paper introduces FM-Cast, a generative AI model that efficiently predicts the 3D evolution of Sudden Stratospheric Warmings, achieving forecast skill comparable to leading weather models in a fraction of the time.

Contribution

The paper presents a novel Flow Matching-based generative AI model for probabilistic forecasting of SSWs, improving efficiency and accuracy over traditional NWP systems.

Findings

FM-Cast forecasts SSW onset, intensity, and 3D morphology up to 15 days ahead.

Achieves forecast skill comparable or superior to ECMWF and CMA models.

Generates 30-day ensemble forecasts in two minutes on a consumer GPU.

Abstract

Sudden Stratospheric Warmings (SSWs) are key sources of subseasonal predictability and major drivers of extreme weather in winter. Accurate and efficient probabilistic forecasting of these events remains a persistent challenge for Numerical Weather Prediction (NWP) systems due to computational bottlenecks and limitations in physical representation. While data-driven forecasting is rapidly evolving, its application to the complex, three-dimensional dynamics of SSWs remains underexplored. Here, we bridge this gap by developing a Flow Matching-based generative AI model (FM-Cast) for efficient and skillful probabilistic forecasting of the spatiotemporal evolution of stratospheric circulation in winter. Evaluated across 18 major SSW events (1998-2024), FM-Cast successfully forecasts the onset, intensity, and 3D morphology of the polar vortex up to 15 days in advance for most cases. Notably, it achieves long-range probabilistic forecast skill comparable to or exceeding leading operational NWP systems (ECMWF and CMA) while generating a 30-day forecast with 50-member ensemble, in just two minutes on a consumer GPU. Furthermore, using idealized "perfect troposphere" experiments, we uncover distinct predictability regimes: events driven by continuous wave forcing versus those governed by an initial trigger and subsequent stratospheric dynamical memory. This work establishes a computationally efficient paradigm for probabilistic stratospheric forecasting that simultaneously deepens our physical understanding of atmosphere-climate dynamics.