Learning calibrated probabilistic forecasts using Koopman mode decomposition and the continuous ranked probability score
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.
Related
- Towards Calibrated Probabilistic Forecasts for Events of Interest via Outcome-Conditional Recalibration
- Learning joint probabilistic weather forecasts from station observations alone
- Probabilistic Streamflow Forecasts for Mississippi River Navigation Risk and Parametric Insurance
- Privacy-Preserving Distributed Online Dispatch of Low-Carbon Microgrids with TCN–BiLSTM Probabilistic Photovoltaic Forecasts
- Tail reliability in probabilistic electricity price forecasts: comparing model combination and conformal prediction in the GB day-ahead market
BibTeX
@misc{kent2026learning,
title = {{Learning calibrated probabilistic forecasts using Koopman mode decomposition and the continuous ranked probability score}},
author = {Benjamin M. Kent and Richard E. Turner},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.11257},
eprint = {2611.11257},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.11257},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning calibrated probabilistic forecasts using Koopman mode decomposition and the continuous ranked probability score
AU - Benjamin M. Kent
AU - Richard E. Turner
PY - 2026
DA - 2026/11/08
PB - arXiv
DO - 10.48550/arxiv.2611.11257
UR - https://arxiv.org/abs/2611.11257
AB - 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.
ER -