QuantWeather is an end-to-end dual-head neural network that produces calibrated quantile-based probabilistic forecasts for subseasonal precipitation, achieving higher skill and lower inference cost than ensemble methods requiring post-hoc calibration.
A foundation model for the earth system.Nature, 641:1180–1187
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.CE 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
QuantWeather: Quantile-Aware Probabilistic Forecasting for Subseasonal Precipitation
QuantWeather is an end-to-end dual-head neural network that produces calibrated quantile-based probabilistic forecasts for subseasonal precipitation, achieving higher skill and lower inference cost than ensemble methods requiring post-hoc calibration.