SEP 8, 2026 · PREPRINT
Stochastically Perturbed Weights: Ensembles from Deterministic Machine-Learning Weather Models
arXiv
A methodological proof-of-concept study proposing a novel post-hoc uncertainty quantification scheme for existing deterministic models, tested across multiple architectures with modest performance gaps to trained baselines but requiring model-specific tuning and showing known failure modes.
Reported
CRPSS gap vs trained-probabilisti…0.04 to 0.13 below
Lead time evaluated240 h
Number of initialisation times112