A multi-lead-time self-attention Transformer postprocesses gridded ECMWF ensemble forecasts of 2m temperature and 10/100m wind speed, improving CRPS by 16.5%, 10%, and 9% over raw forecasts.
URL https://confluence.ecmwf.int/display/ CKB/ERA5%3A+data+documentation, known issues with analysed near surface winds and their diurnal cycle, Accessed: 2024-12-05
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts
A multi-lead-time self-attention Transformer postprocesses gridded ECMWF ensemble forecasts of 2m temperature and 10/100m wind speed, improving CRPS by 16.5%, 10%, and 9% over raw forecasts.