ML4WX

Probabilistic & ensemble forecasting★ Highlight

Enriching Operational High-Resolution Ensemble Forecasts with StyleGAN-2

Clément Brochet, Gabriel Ionut Moldovan, Julien Rabault, Cyril Regan, Laure Raynaud

Artificial Intelligence for the Earth Systems · · ECMWF, Météo-France (incl. CNRM)

Paper

Why it matters. StyleGAN-2 augments the operational kilometre-scale AROME-EPS ensemble, matching tail sampling of a much larger ensemble; practical for operational ensembles.

In one sentence. StyleGAN-2 generates extra members for the operational kilometre-scale AROME-EPS, so a few hundred GAN members match tail sampling of a much larger ensemble.

Labels

Topic
Probabilistic & ensemble forecasting, Regional & km-scale models
Type
New model or method
Method
GAN or VAE
Time scale
6 h–3 days
Domain
Regional
Data
NWP analysis or forecasts (IFS, GFS, ...), km-scale or high-res simulation
Status
Pre-operational / experimental
Identifiers
DOI:10.1175/aies-d-24-0058.1 OpenAlex:W4408797031
Added
2026-10-22

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.