A stochastic transformer weather model trained with the almost fair CRPS loss produces ensemble forecasts that beat ECMWF's physics-based IFS ensemble on most medium-range variables and match it at subseasonal timescales.
Enter the ensembles
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
-
AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score
A stochastic transformer weather model trained with the almost fair CRPS loss produces ensemble forecasts that beat ECMWF's physics-based IFS ensemble on most medium-range variables and match it at subseasonal timescales.