A Caltech Library Service

Early warning of coalescing neutron-star and neutron-star-black-hole binaries from the nonstationary noise background using neural networks

Yu, Hang and Adhikari, Rana X. and Magee, Ryan and Sachdev, Surabhi and Chen, Yanbei (2021) Early warning of coalescing neutron-star and neutron-star-black-hole binaries from the nonstationary noise background using neural networks. Physical Review D, 104 (6). Art. No. 062004. ISSN 2470-0010. doi:10.1103/PhysRevD.104.062004.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
Creative Commons Attribution.


Use this Persistent URL to link to this item:


The success of the multimessenger astronomy relies on gravitational-wave observatories like LIGO and Virgo to provide prompt warning of merger events involving neutron stars (including both binary neutron stars and neutron-star-black-hole binaries), which further depends critically on the low-frequency sensitivity of LIGO as a typical binary neutron star stays in this band for minutes. However, the current sub-60 Hz sensitivity of LIGO has not yet reached its design target and the excess noise can be more than an order of magnitude below 20 Hz. It is limited by nonlinearly coupled noises from auxiliary control loops which are also nonstationary, posing challenges to realistic early warning pipelines. Nevertheless, machine-learning-based neural networks provide ways to simultaneously improve the low-frequency sensitivity and mitigate its nonstationarity, and detect the real-time gravitational-wave signal with a very short computational time. We propose to achieve this by inputting both the main gravitational-wave readout and key auxiliary witnesses to a compound neural network. Using simulated data with characteristic representing the real LIGO detectors, our machine-learning-based neural networks can reduce nonlinearly coupled noise by about a factor of 5 and allows a typical binary neutron star (neutron-star black hole) to be detected 100 s (10 s) before the merger at a distance of 40 Mpc (160 Mpc). If one can further reduce the noise to the fundamental limit, our neural networks can achieve detection out to a distance of 80 and 240 Mpc for binary neutron stars and neutron-star-black-hole binaries, respectively. It thus demonstrates that utilizing machine-learning-based neural networks is a promising direction for the timely detection of the coalescence of electromagnetically bright LIGO/Virgo sources.

Item Type:Article
Related URLs:
URLURL TypeDescription Paper
Yu, Hang0000-0002-6011-6190
Adhikari, Rana X.0000-0002-5731-5076
Magee, Ryan0000-0001-9769-531X
Sachdev, Surabhi0000-0002-0525-2317
Chen, Yanbei0000-0002-9730-9463
Alternate Title:Early warning of coalescing neutron-star and neutron-star-black-hole binaries from nonstationary noise background using neural networks
Additional Information:© 2021 American Physical Society. Received 20 April 2021; accepted 4 August 2021; published 7 September 2021. We thank Zachary Mark, Katerina Chatziioannou, Erik Katsavounidis, and Deep Chatterjee for useful comments and discussions. H. Y. is supported by the Sherman Fairchild Foundation. R. X. A. is supported by NSF PHY-1764464. S. S. is supported by the Eberly Research Funds of Penn State, The Pennsylvania State University, University Park, Pennsylvania. The authors gratefully acknowledge the computational resources provided by the LIGO Laboratory and supported by NSF Grants No. PHY-0757058 and No. PHY-0823459. LIGO was constructed by the California Institute of Technology and Massachusetts Institute of Technology with funding from the NSF and operates under cooperative agreement PHY-1764464. This paper carries LIGO Document Number LIGO-P2100093.
Group:Astronomy Department, LIGO, TAPIR, Walter Burke Institute for Theoretical Physics
Funding AgencyGrant Number
Sherman Fairchild FoundationUNSPECIFIED
Eberly College of ScienceUNSPECIFIED
Pennsylvania State UniversityUNSPECIFIED
Other Numbering System:
Other Numbering System NameOther Numbering System ID
LIGO DocumentP2100093
Issue or Number:6
Record Number:CaltechAUTHORS:20210809-205945884
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:110180
Deposited By: George Porter
Deposited On:09 Aug 2021 22:55
Last Modified:13 Sep 2021 18:11

Repository Staff Only: item control page