Met2Net trains multivariable weather forecasters with per-variable encoders and a two-stage latent-space objective, beating TAU on WeatherBench and ERA5.
Mixed autoencoder for self- supervised visual representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems
Met2Net trains multivariable weather forecasters with per-variable encoders and a two-stage latent-space objective, beating TAU on WeatherBench and ERA5.