Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State

Gravitational waves (GWs) from binary neutron stars (BNSs) offer a valuable understanding of the nature of compact objects and hadronic matter, and the science potential will be greatly enhanced by the third-generation (3G) GW detectors, which are expected to detect BNS signals with order-of-magnitu...

Full description

Saved in:
Bibliographic Details
Main Authors: Qian Hu, Jessica Irwin, Qi Sun, Christopher Messenger, Lami Suleiman, Ik Siong Heng, John Veitch
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:The Astrophysical Journal Letters
Subjects:
Online Access:https://doi.org/10.3847/2041-8213/ade42f
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849430338549317632
author Qian Hu
Jessica Irwin
Qi Sun
Christopher Messenger
Lami Suleiman
Ik Siong Heng
John Veitch
author_facet Qian Hu
Jessica Irwin
Qi Sun
Christopher Messenger
Lami Suleiman
Ik Siong Heng
John Veitch
author_sort Qian Hu
collection DOAJ
description Gravitational waves (GWs) from binary neutron stars (BNSs) offer a valuable understanding of the nature of compact objects and hadronic matter, and the science potential will be greatly enhanced by the third-generation (3G) GW detectors, which are expected to detect BNS signals with order-of-magnitude improvements in duration, detection rates, and signal strength. However, the resulting computational demands for analyzing such prolonged signals pose a critical challenge that existing Bayesian methods cannot feasibly address in the 3G era. To bridge this critical gap, we demonstrate a machine learning–based workflow capable of producing source parameter estimation and constraints on equations of state (EOSs) for hours-long BNS signals in seconds with minimal hardware costs. We employ efficient compression of the GW data and EOS using neural networks, based on which we build normalizing flows for inference that can deliver results in seconds. The optimized computational cost of BNS signal analysis with our framework shows that machine learning has the potential to be an indispensable tool for future catalog-level BNS analyses, paving the way for large-scale investigations of BNS-related physics across the 3G observational landscape.
format Article
id doaj-art-ab34db5e08554fa0a54a032a4cbe2d74
institution Kabale University
issn 2041-8205
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series The Astrophysical Journal Letters
spelling doaj-art-ab34db5e08554fa0a54a032a4cbe2d742025-08-20T03:28:01ZengIOP PublishingThe Astrophysical Journal Letters2041-82052025-01-019871L1710.3847/2041-8213/ade42fDecoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of StateQian Hu0https://orcid.org/0000-0002-3033-6491Jessica Irwin1https://orcid.org/0000-0002-2364-2191Qi Sun2https://orcid.org/0009-0004-5204-765XChristopher Messenger3https://orcid.org/0000-0001-7488-5022Lami Suleiman4https://orcid.org/0000-0003-3783-7448Ik Siong Heng5https://orcid.org/0000-0002-1977-0019John Veitch6https://orcid.org/0000-0002-6508-0713Institute for Gravitational Research, School of Physics and Astronomy, University of Glasgow , Glasgow, G12 8QQ, UK ; Qian.Hu@glasgow.ac.uk, John.Veitch@glasgow.ac.ukInstitute for Gravitational Research, School of Physics and Astronomy, University of Glasgow , Glasgow, G12 8QQ, UK ; Qian.Hu@glasgow.ac.uk, John.Veitch@glasgow.ac.ukDepartment of Computer Science, City University of Hong Kong , Tat Chee Avenue, Kowloon, Hong Kong SAR, Hong KongInstitute for Gravitational Research, School of Physics and Astronomy, University of Glasgow , Glasgow, G12 8QQ, UK ; Qian.Hu@glasgow.ac.uk, John.Veitch@glasgow.ac.ukNicholas and Lee Begovich Center for Gravitational Wave Physics and Astronomy, California State University Fullerton , Fullerton, CA 92831, USAInstitute for Gravitational Research, School of Physics and Astronomy, University of Glasgow , Glasgow, G12 8QQ, UK ; Qian.Hu@glasgow.ac.uk, John.Veitch@glasgow.ac.ukInstitute for Gravitational Research, School of Physics and Astronomy, University of Glasgow , Glasgow, G12 8QQ, UK ; Qian.Hu@glasgow.ac.uk, John.Veitch@glasgow.ac.ukGravitational waves (GWs) from binary neutron stars (BNSs) offer a valuable understanding of the nature of compact objects and hadronic matter, and the science potential will be greatly enhanced by the third-generation (3G) GW detectors, which are expected to detect BNS signals with order-of-magnitude improvements in duration, detection rates, and signal strength. However, the resulting computational demands for analyzing such prolonged signals pose a critical challenge that existing Bayesian methods cannot feasibly address in the 3G era. To bridge this critical gap, we demonstrate a machine learning–based workflow capable of producing source parameter estimation and constraints on equations of state (EOSs) for hours-long BNS signals in seconds with minimal hardware costs. We employ efficient compression of the GW data and EOS using neural networks, based on which we build normalizing flows for inference that can deliver results in seconds. The optimized computational cost of BNS signal analysis with our framework shows that machine learning has the potential to be an indispensable tool for future catalog-level BNS analyses, paving the way for large-scale investigations of BNS-related physics across the 3G observational landscape.https://doi.org/10.3847/2041-8213/ade42fGravitational wavesGravitational wave astronomyNeutron starsNuclear astrophysicsAstronomy data analysis
spellingShingle Qian Hu
Jessica Irwin
Qi Sun
Christopher Messenger
Lami Suleiman
Ik Siong Heng
John Veitch
Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
The Astrophysical Journal Letters
Gravitational waves
Gravitational wave astronomy
Neutron stars
Nuclear astrophysics
Astronomy data analysis
title Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
title_full Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
title_fullStr Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
title_full_unstemmed Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
title_short Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
title_sort decoding long duration gravitational waves from binary neutron stars with machine learning parameter estimation and equations of state
topic Gravitational waves
Gravitational wave astronomy
Neutron stars
Nuclear astrophysics
Astronomy data analysis
url https://doi.org/10.3847/2041-8213/ade42f
work_keys_str_mv AT qianhu decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT jessicairwin decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT qisun decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT christophermessenger decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT lamisuleiman decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT iksiongheng decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate
AT johnveitch decodinglongdurationgravitationalwavesfrombinaryneutronstarswithmachinelearningparameterestimationandequationsofstate