Score: 0

A multi-scale loss formulation for learning a probabilistic model with proper score optimisation

Published: June 12, 2025 | arXiv ID: 2506.10868v1

By: Simon Lang, Martin Leutbecher, Pedro Maciel

Potential Business Impact:

Improves weather forecasts by seeing small details.

Business Areas:
Risk Management Professional Services

We assess the impact of a multi-scale loss formulation for training probabilistic machine-learned weather forecasting models. The multi-scale loss is tested in AIFS-CRPS, a machine-learned weather forecasting model developed at the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS-CRPS is trained by directly optimising the almost fair continuous ranked probability score (afCRPS). The multi-scale loss better constrains small scale variability without negatively impacting forecast skill. This opens up promising directions for future work in scale-aware model training.

Page Count
14 pages

Category
Physics:
Atmospheric and Oceanic Physics