Detecting rainfall events in CML attenuation time series using convolutional neural networks

26 Jun 2019, 10:50
large seminar room (KIT Campus Alpin)

large seminar room

KIT Campus Alpin

Kreuzeckbahnstraße 19 82467 Garmisch-Partenkirchen
Oral Specific HyMet CML research topics (presentations on Day2, posters on Day1) Specific research topics


julius polz (KIT/IMK-IFU)


CML data might exhibit high signal fluctuations, even during dry periods. At the same time the number of newly available CMLs is rising fast. It is necessary to develop a technique to recognise the pattern of rainfall in CML signal levels, that is (1) generalizing to previously unknown sensors, (2) stable in time and (3) showing better performance than established methods. We therefore introduce convolutional neural networks to the task of wet/dry classification and test them on data from a German-wide CML network.

Primary author

julius polz (KIT/IMK-IFU)


Christian Chwala (KIT (IMK-IFU) / Uni Augsburg) Maximilian Graf Harald Kunstmann

Presentation Materials

There are no materials yet.
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now