Shallow and deep learning of extreme rainfall events from convective atmospheres

Bürger, Gerd; Heistermann, Maik

doi:https://doi.org/10.5194/nhess-23-3065-2023

Articles | Volume 23, issue 9

https://doi.org/10.5194/nhess-23-3065-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Past and future European atmospheric extreme events under...

https://doi.org/10.5194/nhess-23-3065-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 23, issue 9

Research article

|

18 Sep 2023

Research article |

| 18 Sep 2023

Shallow and deep learning of extreme rainfall events from convective atmospheres

Gerd Bürger and Maik Heistermann

Supplement

https://doi.org/10.5194/nhess-23-3065-2023-supplement

Data sets

ERA5 hourly data on single levels from 1940 to present H. Hersbach, B. Bell, P. Berrisford, G. Biavati, A. Horányi, J. Muñoz Sabater, J. Nicolas, C. Peubey, R. Radu, I. Rozum, D. Schepers, A. Simmons, C. Soci, D. Dee, and J.-N. Thépaut https://doi.org/10.24381/cds.adbb2d47

Starkregenereignisse Version 2022.01 mit Überschreitung der DWD-Warnstufe 3 für Unwetter basierend auf RADKLIM-RW Version 2017.002, Parameter und Polygone der Starkregenereignisse in Deutschland K. Lengfeld, E. Walawender, T. Winterrath, E. Weigl, and A. Becker https://doi.org/10.5676/DWD/CatRaRE_W3_Eta_v2022.01

Model code and software

Convective Atmospheres: Linking Radar-based Event Descriptors and Losses From Flash Floods (CARLOFFF) Gerd Bürger https://doi.org/10.5281/zenodo.8146270

Caffe BVLC (Berkeley Vision and Learning Center) https://github.com/BVLC/caffe

Download

Article (4023 KB)
Full-text XML

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 reanalyzed daily atmospheric 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 projected for CatRaRE-type probabilities, from reanalyzed as well as from simulated atmospheric fields.