AI Emulation of Stochastic Sudden Stratospheric Warming with Interpretable Latent Structure

2026-10-01

AI Summary

This study addresses the challenge of data-driven modeling under severe class imbalance during rare weather regime transitions by proposing a probabilistic deep learning emulator. Methodologically, we design a ResNet-inspired conditional variational autoencoder (CVAE) that incorporates explicit current-state conditioning. This approach reveals physically interpretable metastable structures within the latent space, enabling the unsupervised separation of strong and weak vortex regimes. Results demonstrate that the proposed model faithfully reproduces stratospheric variability dynamics and rare transition processes, accurately capturing short-term dynamics, stationary distributions, and transition rates. By effectively resolving these complex meteorological phenomena, this work establishes a novel paradigm for the early warning of extreme weather events.

Abstract

Rare weather regime transitions pose a challenge for data-driven modeling due to class imbalance. In this study, we develop a probabilistic deep learning emulator for a prototypical system with regime transitions, the stochastic Holton--Mass model of stratospheric variability, and analyze the structure of its learned latent space. The Holton--Mass model exhibits two metastable regimes, a strong and a weak polar vortex, maintained by nonlinear wave--mean flow interactions, with weak stochastic forcing intermittently triggering rare transitions between these regimes that qualitatively represent SSW events. We employ a ResNet-inspired Conditional Variational Autoencoder with six-layer encoder and decoder layers and explicit current-state conditioning to model the distribution of the system's state at the next time step (one day). The emulator accurately reproduces short-term dynamics, steady-state probability distributions, regime persistence statistics, rare transition rates, the transition committor function, and the transition expected lead time of the physical model. Beyond emulation fidelity, we interrogate the learned latent representation to understand how the model internalizes the underlying metastable structure of the dynamics. Principal Component Analysis of the 32-dimensional latent space reveals a clear and unsupervised separation into four physically interpretable clusters corresponding to strong versus weak vortex regimes and stable versus transition-prone configurations. Such emergent regime separation in latent space is hard to identify for deep generative models applied to high-dimensional stochastic systems. Our results show that carefully designed probabilistic emulators can uncover physically meaningful manifolds governing extreme-event dynamics, potentially aiding the development of improved operational advanced warning systems.

Problem

• Sudden Stratospheric Warming
• rare regime transitions
• class imbalance
• data-driven modeling
• interpretable latent structure

Innovation

• Conditional Variational Autoencoder
• Stochastic Sudden Stratospheric Warming
• Interpretable Latent Space
• Rare Regime Transitions
• Probabilistic Emulator