Forecast nonlinear systems with calibrated probabilistic Koopman models

Learning calibrated probabilistic forecasts using Koopman mode decomposition and the continuous ranked probability score

Machine Learning

Summary

Predicting how complex systems change over time, like weather or fluids, is tricky because they behave nonlinearly and unpredictably. The authors combine a method called Koopman mode decomposition with machine learning to create probabilistic forecasts that not only predict future states but also express uncertainty accurately. Their approach learns to produce trustworthy probability distributions of possible outcomes, improving reliability especially when data is noisy or limited. They tested this on several simulated systems, including fluid flows, showing it can capture different future possibilities and remain accurate for extended periods.

What this means in practice

  • For weather prediction teams: Generate well-calibrated probabilistic weather forecasts that better capture uncertainty using structured dynamical system models combined with machine learning.
  • For computational fluid dynamics engineers: Produce accurate and uncertainty-aware predictions for fluid flow behaviors such as vortex shedding based on limited or noisy simulation data.

Authors

Benjamin M. Kent, Richard E. Turner

Abstract

Well-calibrated forecasting for non-linear dynamical systems is essential in science and engineering applications such as fluid dynamics and weather prediction. We present a forecasting method combining probabilistic machine learning with the structured linear dynamics of Koopman mode decomposition. Within this framework, the observation, linear dynamics, and state reconstruction operators are constructed using standard machine learning architectures, producing predictive distributions via the pushforward of injected noise samples. The model is trained using a proper scoring rule, the continuous ranked probability score, to directly target calibrated, accurate forecasts. The approach is validated on two non-linear ordinary differential equation examples and two partial differential equation examples, vortex shedding and cavity flow, using both large and small, noisy datasets. Results demonstrate that known Koopman eigenfunctions and spectra can be identified and used for accurate forecasting. The model can also produce multi-modal predictive distributions, demonstrated for a trajectory initialised on the boundary between two basins of attraction. Uncertainty is captured by the sample ensemble spread, with spread--skill ratios close to one over the training horizon in several experiments, although for extended rollouts and noisy datasets, the ensemble may become under- or over-dispersed. In low-noise experiments, temporal rollout is generally accurate for at least twice the training horizon, and up to twenty times in some cases. Approximation quality is comparable to a deep ensemble approximation over the training horizon, but at a reduced computational cost and with better robustness in identifying Koopman eigenvalues.