Metadata only
Author
Show all
Date
2021-04-05Type
- Journal Article
Citations
Cited 33 times in
Web of Science
Cited 36 times in
Scopus
ETH Bibliography
yes
Altmetrics
Abstract
Quantifying uncertainty in weather forecasts is critical, especially for predicting extreme weather events. This is typically accomplished with ensemble prediction systems, which consist of many perturbed numerical weather simulations, or trajectories, run in parallel. These systems are associated with a high computational cost and often involve statistical post-processing steps to inexpensively improve their raw prediction qualities. We propose a mixed model that uses only a subset of the original weather trajectories combined with a post-processing step using deep neural networks. These enable the model to account for non-linear relationships that are not captured by current numerical models or post-processing methods. Applied to the global data, our mixed models achieve a relative improvement in ensemble forecast skill (CRPS) of over 14%. Furthermore, we demonstrate that the improvement is larger for extreme weather events on select case studies. We also show that our post-processing can use fewer trajectories to achieve comparable results to the full ensemble. By using fewer trajectories, the computational costs of an ensemble prediction system can be reduced, allowing it to run at higher resolution and produce more accurate forecasts.
This article is part of the theme issue ‘Machine learning for weather and climate modelling’. Show more
Publication status
publishedExternal links
Journal / series
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering SciencesVolume
Pages / Article No.
Publisher
Royal SocietySubject
deep learning; weather uncertainty quantification; ensemble post-processing; extreme weather eventsOrganisational unit
03950 - Hoefler, Torsten / Hoefler, Torsten
More
Show all metadata
Citations
Cited 33 times in
Web of Science
Cited 36 times in
Scopus
ETH Bibliography
yes
Altmetrics