math.DSNov 8, 2026

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

Authors: Benjamin M. Kent, Richard E. Turner

Organizations: University of Cambridge

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.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning

    Jun 3, 2026Kelan Gray, Finlay Brown, Nicolas Boullé +1Koopman Operator LearningLatent Dynamics Modeling

  2. Trustworthy Koopman Operator Learning: Invariance Diagnostics and Error Bounds

    Mar 16, 2026Gustav Conradie, Nicolas Boullé, Jean-Christophe Loiseau +2Koopman Operator LearningUncertainty Quantification

  3. Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting

    Nov 3, 2026Raz Marshanski, Liran Nochumsohn, Mayank Jauhari +2Probabilistic Time Series ForecastingOne-Step Generative Modeling