HourGlass probabilistically reconstructs hourly weather evolution between 6-hourly forecast states using CRPS training on NWP trajectories, preserving skill and small-scale variability better than deterministic downscalers.
Title resolution pending
1 Pith paper cite this work, alongside 416 external citations. Polarity classification is still indexing.
1
Pith paper citing it
416
external citations · OpenAlex
fields
physics.ao-ph 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
HourGlass: A probabilistic data-driven temporal downscaler for global and regional weather forecasting
HourGlass probabilistically reconstructs hourly weather evolution between 6-hourly forecast states using CRPS training on NWP trajectories, preserving skill and small-scale variability better than deterministic downscalers.