A permutation-invariant variational autoencoder with energy and Sinkhorn loss terms is shown to preserve ensemble spread better than PCA or autoencoder baselines on ECMWF temperature and wind forecasts.
Title resolution pending
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 low-dimensional representations of ensemble forecast fields using autoencoder-based methods
A permutation-invariant variational autoencoder with energy and Sinkhorn loss terms is shown to preserve ensemble spread better than PCA or autoencoder baselines on ECMWF temperature and wind forecasts.