Multivariate phase-space interpretation of ensemble forecasts: A comparison of physical and AI models
Abstract
Ensemble forecasts from the ECMWF's Integrated Forecasting System (IFS) and the Artificial Intelligence Forecasting System (AIFS-ENS) are compared using a multi-dimensional evaluation framework. Within this framework, the uncertainty is interpreted as the linear subspace spanned by the ensemble members in phase space, from which various geometric properties are extracted. As revealed by the analysis, the error does not entirely lie in this subspace, but is reasonably well calibrated in all directions. Moreover, the framework allows to quantify that this subspace critically depends on the number of ensemble members, suggesting that the current setups only partially represent the uncertainty subspace. This phase-space interpretation furthermore allows a direct comparison of the error-representation patterns of AIFS-ENS and IFS by computing the principal angles between the subspaces: IFS and AIFS ensemble subspaces do not entirely overlap in phase space, even though they were shown to have similar abilities to represent the amplitude and the structure of the error.
Related
- Enhancing Tropical Cyclone Prediction Through AI Weather Model Ensemble Forecasts and Multi‐Source Data Integration
- A recall-optimized LSTM–XGBoost ensemble model for river flood forecasting using multivariate time-series data—case study in Sri Lanka
- Can we create a `race to the top' for weather forecasts to inform smallholder farmer decisions?
- From trends to optimized forecasts: Quantifying the skill and advancing the utility of dynamics-based early warnings for tipping events
- BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables
BibTeX
@misc{bonte2026multivariate,
title = {{Multivariate phase-space interpretation of ensemble forecasts: A comparison of physical and AI models}},
author = {Martin Bonte and Stéphane Vannitsem},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16422},
eprint = {2610.16422},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16422},
}
RIS
TY - UNPB
TI - Multivariate phase-space interpretation of ensemble forecasts: A comparison of physical and AI models
AU - Martin Bonte
AU - Stéphane Vannitsem
PY - 2026
DA - 2026/10/12
PB - arXiv
DO - 10.48550/arxiv.2610.16422
UR - https://arxiv.org/abs/2610.16422
AB - Ensemble forecasts from the ECMWF's Integrated Forecasting System (IFS) and the Artificial Intelligence Forecasting System (AIFS-ENS) are compared using a multi-dimensional evaluation framework. Within this framework, the uncertainty is interpreted as the linear subspace spanned by the ensemble members in phase space, from which various geometric properties are extracted. As revealed by the analysis, the error does not entirely lie in this subspace, but is reasonably well calibrated in all directions. Moreover, the framework allows to quantify that this subspace critically depends on the number of ensemble members, suggesting that the current setups only partially represent the uncertainty subspace. This phase-space interpretation furthermore allows a direct comparison of the error-representation patterns of AIFS-ENS and IFS by computing the principal angles between the subspaces: IFS and AIFS ensemble subspaces do not entirely overlap in phase space, even though they were shown to have similar abilities to represent the amplitude and the structure of the error.
ER -