GenEPS uses a diffusion prior and SDEdit to generate ensembles from deterministic AI weather models and reports a day-10 Z500 ACC of 0.679, above ECMWF ENS's 0.646.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.ao-ph 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Boosting weather forecast via generative superensemble
GenEPS uses a diffusion prior and SDEdit to generate ensembles from deterministic AI weather models and reports a day-10 Z500 ACC of 0.679, above ECMWF ENS's 0.646.