KIT | KIT-Bibliothek | Impressum | Datenschutz

Rain event detection in commercial microwave link attenuation data using convolutional neural networks

Polz, Julius ORCID iD icon; Chwala, Christian ORCID iD icon; Graf, Maximilian ORCID iD icon; Kunstmann, Harald

Abstract (englisch):

Quantitative precipitation estimation with commercial microwave links (CMLs) is a technique developed to supplement weather radar and rain gauge observations. It is exploiting the relation between the attenuation of CML signal levels and the integrated rain rate along a CML path. The opportunistic nature of this method requires a sophisticated data processing using robust methods. In this study we focus on the processing step of rain event detection in the signal level time series of the CMLs, which we treat as a binary classification problem. This processing step is particularly challenging, because even when there is no rain, the signal level can show large fluctuations similar to that during rainy periods. False classifications can have a high impact on falsely estimated rainfall amounts. We analyze the performance of a convolutional neural network (CNN), which is trained to detect rainfall-specific attenuation patterns in CML signal levels, using data from 3904 CMLs in Germany. The CNN consists of a feature extraction and a classification part with, in total, 20 layers of neurons and 1.4×105 trainable parameters. With a structure inspired by the visual cortex of mammals, CNNs use local connections of neurons to recognize patterns independent of their location in the time series. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000121338
Veröffentlicht am 16.07.2020
DOI: 10.5194/amt-13-3835-2020
Zitationen: 41
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Meteorologie und Klimaforschung – Atmosphärische Umweltforschung (IMK-IFU)
KIT-Zentrum Klima und Umwelt (ZKU)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2020
Sprache Englisch
Identifikator ISSN: 1867-8548
KITopen-ID: 1000121338
HGF-Programm 12.02.03 (POF III, LK 01) Regional Climate-and Water Cycle Variab.
Erschienen in Atmospheric measurement techniques
Verlag Copernicus Publications
Band 13
Heft 7
Seiten 3835–3853
Projektinformation FOR 2589; RealPEP (DFG, DFG KOORD, CH 1785/1-1)
Bemerkung zur Veröffentlichung Gefördert durch den KIT-Publikationsfonds
Vorab online veröffentlicht am 15.07.2020
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page