Reformulates ML weather model rollout training as 4DVar in autoencoder latent space to approximate cross-variable error covariances and improve physical realism in long-term forecasts.
FuXi: A cascade machine learning forecasting system for 15-day global weather forecast.npj Climate and Atmospheric Science, 6(1):190, November 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning more physically realistic dynamics in machine-learning based weather forecasting with latent-space constraints
Reformulates ML weather model rollout training as 4DVar in autoencoder latent space to approximate cross-variable error covariances and improve physical realism in long-term forecasts.