Preprints
https://doi.org/10.5194/egusphere-2022-1159
https://doi.org/10.5194/egusphere-2022-1159
 
07 Nov 2022
07 Nov 2022
Status: this preprint is open for discussion.

Deep learning of extreme rainfall events from convective atmospheres

Gerd Bürger and Maik Heistermann Gerd Bürger and Maik Heistermann
  • Institute of Earth and Environmental Science, University of Potsdam, Potsdam, 14476, Germany

Abstract. Our subject is a new Catalogue of radar-based heavy Rainfall Events (CatRaRE) over Germany, and how it relates to the concurrent atmospheric circulation. We classify daily atmospheric ERA5 fields of convective indices according to CatRaRE, using an array of conventional statistical and more recent machine learning (ML) algorithms, and apply them to corresponding fields of simulated present and future atmospheres from the CORDEX project. Due to the stochastic nature of ML optimization there is some spread in the results. The ALL-CNN network performs best on average, with several learning runs exceeding an Equitable Threat Score (ETS) of 0.52; the single best result was from ResNet with ETS = 0.54. The best performing classical scheme was a Random Forest with ETS = 0.51. Regardless of the method, increasing trends are predicted for the probability of CatRaRE-type events, from ERA5 as well as from the CORDEX fields.

Gerd Bürger and Maik Heistermann

Status: open (until 04 Jan 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-1159', Anonymous Referee #1, 28 Nov 2022 reply

Gerd Bürger and Maik Heistermann

Gerd Bürger and Maik Heistermann

Viewed

Total article views: 229 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
165 57 7 229 18 1 2
  • HTML: 165
  • PDF: 57
  • XML: 7
  • Total: 229
  • Supplement: 18
  • BibTeX: 1
  • EndNote: 2
Views and downloads (calculated since 07 Nov 2022)
Cumulative views and downloads (calculated since 07 Nov 2022)

Viewed (geographical distribution)

Total article views: 218 (including HTML, PDF, and XML) Thereof 218 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2022
Download
Short summary
Our subject is a new Catalogue of radar-based heavy Rainfall Events (CatRaRE) over Germany, and how it relates to the concurrent atmospheric circulation. We classify daily atmospheric ERA5 fields of convective indices according to CatRaRE, using conventional statistical and more recent machine learning algorithms, and apply them to present and future atmospheres. Increasing trends are predicted for the probability of CatRaRE-type events, from ERA5 as well as from the CORDEX fields.