CaltechAUTHORS
  A Caltech Library Service

Noise Reduction in Gravitational-wave Data via Deep Learning

Ormiston, Rich and Nguyen, Tri and Coughlin, Michael and Adhikari, Rana X. and Katsavounidis, Erik (2020) Noise Reduction in Gravitational-wave Data via Deep Learning. Physical Review Research, 2 (3). Art. No. 033066. ISSN 2643-1564. https://resolver.caltech.edu/CaltechAUTHORS:20200615-134234981

[img]
Preview
PDF - Published Version
Creative Commons Attribution.

2140Kb
[img] PDF - Submitted Version
See Usage Policy.

2275Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20200615-134234981

Abstract

With the advent of gravitational wave astronomy, techniques to extend the reach of gravitational wave detectors are desired. In addition to the stellar-mass black hole and neutron star mergers already detected, many more are below the surface of the noise, available for detection if the noise is reduced enough. Our method (DeepClean) applies machine learning algorithms to gravitational wave detector data and data from on-site sensors monitoring the instrument to reduce the noise in the time-series due to instrumental artifacts and environmental contamination. This framework is generic enough to subtract linear, non-linear, and non-stationary coupling mechanisms. It may also provide handles in learning about the mechanisms which are not currently understood to be limiting detector sensitivities. The robustness of the noise reduction technique in its ability to efficiently remove noise with no unintended effects on gravitational-wave signals is also addressed through software signal injection and parameter estimation of the recovered signal. It is shown that the optimal SNR ratio of the injected signal is enhanced by ∼21.6% and the recovered parameters are consistent with the injected set. We present the performance of this algorithm on linear and non-linear noise sources and discuss its impact on astrophysical searches by gravitational wave detectors.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1103/PhysRevResearch.2.033066DOIArticle
https://journals.aps.org/prresearch/abstract/10.1103/PhysRevResearch.2.033066PublisherArticle
https://arxiv.org/abs/2005.06534arXivDiscussion Paper
ORCID:
AuthorORCID
Nguyen, Tri0000-0001-6189-8457
Coughlin, Michael0000-0002-8262-2924
Adhikari, Rana X.0000-0002-5731-5076
Additional Information:© 2020 Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Received 28 May 2020; accepted 19 June 2020; published 14 July 2020. Michael Coughlin was supported by NSF Award No. PHY-0757058 and the David and Ellen Lee Postdoctoral Fellowship at the California Institute of Technology. Rich Ormiston was supported in part by the NSF Award No. PHY-1806630. Tri Nguyen and Erik Katsavounidis work in this was supported by NSF Awards No. OAC-1934700 and No. OAC-1931469. The authors also acknowledge support from the LIGO Laboratory; LIGO was constructed by the California Institute of Technology and Massachusetts Institute of Technology with funding from the National Science Foundation and it operates under Cooperative Agreement No. PHY-1764464.
Group:LIGO, Astronomy Department
Funders:
Funding AgencyGrant Number
NSFPHY-0757058
David and Ellen Lee Postdoctoral ScholarshipUNSPECIFIED
NSFPHY-1806630
NSFOAC-1934700
NSFOAC-1931469
NSFPHY-1764464
Issue or Number:3
Record Number:CaltechAUTHORS:20200615-134234981
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20200615-134234981
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:103926
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:15 Jun 2020 20:57
Last Modified:14 Jul 2020 17:12

Repository Staff Only: item control page