Deep-learning continuous gravitational waves

Download statistics - Document (COUNTER):

Dreissigacker, C.; Sharma, R.; Messenger, C.; Zhao, R.; Prix, R.: Deep-learning continuous gravitational waves. In: Physical Review D 100 (2019), Nr. 4, 44009. DOI:

Repository version

To cite the version in the repository, please use this identifier:

Selected time period:


Sum total of downloads: 65

We present a first proof-of-principle study for using deep neural networks (DNNs) as a novel search method for continuous gravitational waves (CWs) from unknown spinning neutron stars. The sensitivity of current wide-parameter-space CW searches is limited by the available computing power, which makes neural networks an interesting alternative to investigate, as they are extremely fast once trained and have recently been shown to rival the sensitivity of matched filtering for black-hole merger signals [D. George and E. A. Huerta, Phys. Rev. D 97, 044039 (2018)10.1103/PhysRevD.97.044039; H. Gabbard, M. Williams, F. Hayes, and C. Messenger, Phys. Rev. Lett. 120, 141103 (2018)10.1103/PhysRevLett.120.141103]. We train a convolutional neural network with residual (shortcut) connections and compare its detection power to that of a fully coherent matched-filtering search using the Weave pipeline [K. Wette, S. Walsh, R. Prix, and M. A. Papa, Phys. Rev. D 97, 123016 (2018)10.1103/PhysRevD.97.123016]. As test benchmarks we consider two types of all-sky searches over the frequency range from 20 to 1000 Hz: an "easy" search using T=105 s of data, and a "harder" search using T=106 s. The detection probability pdet is measured on a signal population for which matched filtering achieves pdet=90% in Gaussian noise. In the easiest test case (T=105 s at 20 Hz) the DNN achieves pdet∼88%, corresponding to a loss in sensitivity depth of ∼5% versus coherent matched filtering. However, at higher frequencies and for longer observation times the DNN detection power decreases, until pdet∼13% and a loss of ∼66% in sensitivity depth in the hardest case (T=106 s at 1000 Hz). We study the DNN generalization ability by testing on signals of different frequencies, spindowns and signal strengths than they were trained on. We observe excellent generalization: only five networks, each trained at a different frequency, would be able to cover the whole frequency range of the search. © 2019 authors. Published by the American Physical Society.
License of this version: CC BY 4.0 Unported
Document Type: Article
Publishing status: publishedVersion
Issue Date: 2019
Appears in Collections:Fakultät für Mathematik und Physik

distribution of downloads over the selected time period:

downloads by country:

pos. country downloads
total perc.
1 image of flag of Germany Germany 40 61.54%
2 image of flag of United States United States 13 20.00%
3 image of flag of China China 8 12.31%
4 image of flag of No geo information available No geo information available 1 1.54%
5 image of flag of Taiwan Taiwan 1 1.54%
6 image of flag of Saudi Arabia Saudi Arabia 1 1.54%
7 image of flag of Netherlands Netherlands 1 1.54%

Further download figures and rankings:


Zur Erhebung der Downloadstatistiken kommen entsprechend dem „COUNTER Code of Practice for e-Resources“ international anerkannte Regeln und Normen zur Anwendung. COUNTER ist eine internationale Non-Profit-Organisation, in der Bibliotheksverbände, Datenbankanbieter und Verlage gemeinsam an Standards zur Erhebung, Speicherung und Verarbeitung von Nutzungsdaten elektronischer Ressourcen arbeiten, welche so Objektivität und Vergleichbarkeit gewährleisten sollen. Es werden hierbei ausschließlich Zugriffe auf die entsprechenden Volltexte ausgewertet, keine Aufrufe der Website an sich.

Search the repository