Stable probabilistic models improve long-term forecasts for complex weather systems

Stable probabilistic emulation of partially observed dynamical systems

Machine Learning

Summary

Predicting weather or climate over long periods is tough because we can only observe part of the system and many small fast changes are hidden. The authors designed a new kind of model that learns from data how these hidden parts behave, while making sure predictions don’t go off track even after a long time. Their method uses ideas from physics to keep the model stable and reliable. They tested it on a simplified weather system and showed it can predict changes accurately and stay stable under different conditions.

What this means in practice

  • For climate modelers: Use stable stochastic emulators to improve long-term climate predictions under partial observations and variable forcing.
  • For energy grid operators: Incorporate reliable long-term forecasts of coupled atmosphere-ocean dynamics for better management of renewable energy resources exposed to weather variability.

Authors

Mario Massy, Sara Shamekh, Fabrizio Falasca, Matthieu Blanke

Abstract

Predicting the long-term behavior of partially observed dynamical systems such as the coupled atmosphere-ocean system is central to societal decision-making. Motivated by the success of deep learning emulators in weather forecasting, data-driven climate models represent a promising approach. However, climate emulation poses distinct challenges: models must account for unresolved fast variables introduced by unavoidable coarse-graining, reproduce long-term statistics, and remain stable over arbitrarily long rollouts and under external perturbations. These requirements motivate stochastic data-driven emulators, but modern generative models lack stability guarantees. We introduce forced-dissipative stochastic interpolants, a generative framework for learning stochastic reduced dynamics. Its architecture uses structural constraints inspired by turbulent dynamics, which provide stability by design while retaining the flexibility of stochastic interpolants to represent complex probabilistic dynamics. Building on the theory of Markov-chain stability, we establish a Foster--Lyapunov drift condition and prove geometric ergodicity for our emulator, together with stability under steady external forcing. We evaluate the framework on the two-timescale Lorenz-96 system, a prototype of partially observed multiscale turbulence. The resulting emulator remains stable over long integrations and under finite-amplitude forcing, with accurate prediction of forced responses of both the mean and variance.