Journal of Astronomy and Space Sciences

The Korean Space Science Society (한국우주과학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of Gravitational Waves from Black Hole-Neutron Star Mergers with Machine Learning

  • Nurzhan Ussipov (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Zeinulla Zhanabaev (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Almat, Akhmetali (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Marat Zaidyn (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Dana Turlykozhayeva (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Aigerim Akniyazova (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University) ;
  • Timur Namazbayev (Department of Solid State Physics and Nonlinear Physics, Al-Farabi Kazakh National University)
  • Received : 2024.06.09
  • Accepted : 2024.08.28
  • Published : 2024.09.15
Download PDF
⟨ Previous Next ⟩

Abstract

This study developed a machine learning-based methodology to classify gravitational wave (GW) signals from black hol-eneutron star (BH-NS) mergers by combining convolutional neural network (CNN) with conditional information for feature extraction. The model was trained and validated on a dataset of simulated GW signals injected to Gaussian noise to mimic real world signals. We considered all three types of merger: binary black hole (BBH), binary neutron star (BNS) and neutron starblack hole (NSBH). We achieved up to 96% correct classification of GW signals sources. Incorporating our novel conditional information approach improved classification accuracy by 10% compared to standard time series training. Additionally, to show the effectiveness of our method, we tested the model with real GW data from the Gravitational Wave Transient Catalog (GWTC-3) and successfully classified ~90% of signals. These results are an important step towards low-latency real-time GW detection.

Keywords

Acknowledgement

We would like to express our sincerest gratitude to the Al-Farabi Kazakh National University for supporting this work by providing computing resources (Department of Physics and Technology). This research was funded by the Committee of Science of the Ministry of Education and Science of the Republic of Kazakhstan, grant AP14872061. This work has made use of data, software and/or web tools obtained from the Gravitational Wave Open Science Center (https://www.gw-openscience.org), a service of LIGO Laboratory, the LIGO Scientific Collaboration and the Virgo Collaboration. LIGO is funded by the U.S. National Science Foundation. Virgo is funded by the French Centre National de Recherche Scientifique (CNRS), the Italian Istituto Nazionale della Fisica Nucleare (INFN) and the Dutch Nikhef, with contributions by Polish and Hungarian institutes.

References

  1. Aasi J, Abbott BP, Abbott R, Abbott T, Abernathy MR, et al., Advanced LIGO, Class. Quantum Grav. 32, 074001 (2015). https://doi.org/10.1088/0264-9381/32/7/074001 
  2. Abbott BP, Abbott R, Abbott TD, Abernathy M, Acernese F, et al., Observation of gravitational waves from a binary black hole merger, Phys. Rev. Lett. 116, 061102 (2016). https://doi.org/10.1103/PhysRevLett.116.061102 
  3. Abbott BP, Abbott R, Abbott TD, Abernathy MR, Ackley K, et al., Exploring the sensitivity of next generation gravitational wave detectors, Class. Quantum Grav. 34, 044001 (2017a). https://doi.org/10.1088/1361-6382/aa51f4 
  4. Abbott BP, Abbott R, Abbott TD, Abraham S, Acernese F, et al., GWTC-1: a gravitational-wave transient catalog of compact binary mergers observed by LIGO and Virgo during the first and second observing runs, Phys. Rev. X. 9, 031040 (2019a). https://doi.org/10.1103/PhysRevX.9.031040 
  5. Abbott BP, Abbott R, Abbott TD, Abraham S, Acernese F, et al., GW190425: observation of a compact binary coalescence with total mass ~3.4M⊙, Astrophys. J. Lett. 892, L3 (2020). https://doi.org/10.3847/2041-8213/ab75f5 
  6. Abbott BP, Abbott R, Abbott TD, Abraham S, Acernese F, et al., Prospects for observing and localizing gravitationalwave transients with advanced LIGO, advanced Virgo and KAGRA, Living Rev. Relativ. 21, 3 (2018). https://doi.org/10.1007/s41114-020-00026-9 
  7. Abbott BP, Abbott R, Abbott TD, Acernese F, Ackley K, et al., GW170817: observation of gravitational waves from a binary neutron star inspiral, Phys. Rev. Lett. 119, 161101 (2017b). https://doi.org/10.1103/PhysRevLett.119.161101 
  8. Abbott BP, Abbott R, Abbott TD, Acernese F, Ackley K, et al., Multi-messenger observations of a binary neutron star merger, Astrophys. J. Lett. 848, L12 (2017c). https://doi.org/10.3847/2041-8213/aa91c9 
  9. Abbott BP, Abbott R, Abbott TD, Acernese F, Ackley K, et al., Properties of the binary neutron star merger GW170817. Phys. Rev. X. 9, 011001 (2019b). https://doi.org/10.1103/PhysRevX.9.011001 
  10. Abbott BP, Abbott R, Adhikari R, Ajith P, Allen B, et al., LIGO: the laser interferometer gravitational-wave observatory, Rep. Prog. Phys. 72, 076901 (2009). https://doi.org/10.1088/0034-4885/72/7/076901 
  11. Abbott R, Abbott TD, Abraham S, Acernese F, Ackley K, et al., Observation of gravitational waves from two neutron starblack hole coalescences, Astrophys. J. Lett. 915, L5 (2021). https://doi.org/10.3847/2041-8213/ac082e 
  12. Abbott R, Abbott TD, Acernese F, Ackley K, Adams C, et al., GWTC-3: compact binary coalescences observed by LIGO and Virgo during the second part of the third observing run, Phys. Rev. X. 13, 041039 (2023a). https://doi.org/10.1103/PhysRevX.13.041039 
  13. Abbott R, Abbott TD, Acernese F, Ackley K, Adams C, et al., Population of merging compact binaries inferred using gravitational waves through GWTC-3, Phys. Rev. X. 13, 011048 (2023b). https://doi.org/10.1103/PhysRevX.13.011048 
  14. Acernese F, Agathos M, Agatsuma K, Aisa D, Allemandou N, et al., Advanced Virgo: a second-generation interferometric gravitational wave detector, Class. Quantum Grav. 32, 024001 (2015). https://doi.org/10.1088/0264-9381/32/2/024001 
  15. Antelis J, Moreno C, An independent search of gravitational waves in the first observation run of advanced LIGO using cross-correlation, Gen. Relativ. Gravit. 51, 61 (2019). https://doi.org/10.1007/s10714-019-2546-x 
  16. Biwer CM, Capano C, De S, Cabero M, Brown D, et al., PyCBC inference: a python-based parameter estimation toolkit for compact binary coalescence signals, Publ. Astron. Soc. Pac. 131, 024503 (2019). https://doi.org/10.1088/1538-3873/aaef0b 
  17. Bohe A, Shao L, Taracchini A, Buonanno A, Babak S, et al., Improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational wave astrophysics with advanced detectors, Phys. Rev. D. 95, 044028 (2017). https://doi.org/10.1103/PhysRevD.95.044028 
  18. Cahillane C, Mansell G, Review of the advanced LIGO gravitational wave observatories leading to observing run four, Galaxies, 10, 36 (2022). https://doi.org/10.3390/galaxies10010036 
  19. Canton TD, Nitz AH, Lundgren A, Nielsen AP, Brown DA, et al., Implementing a search for aligned-spin neutron star-black hole systems with advanced ground based gravitational wave detectors, Phys. Rev. D. 90, 082004 (2014). https://doi.org/10.1103/PhysRevD.90.082004 
  20. Chapman-Bird CEA, Berry CPL, Woan G, Rapid determination of LISA sensitivity to extreme mass ratio inspirals with machine learning, Mon. Not. R. Astron. Soc. 522, 6043-6054 (2023). https://doi.org/10.1093/mnras/stad1397 
  21. Chawale MSA, Mohod SB, Chandak MDS, WCQMV: design of a wavelet compression based quadratic model for EEG classification using multivariate analysis, Int. J. Sci. Res. Sci. Technol. 9, 1-10 (2022). https://doi.org//10.32628/IJSRST229174 
  22. Dreissigacker C, Sharma R, Messenger C, Zhao R, Prix R, Deeplearning continuous gravitational waves, Phys. Rev. D. 100, 044009 (2019). https://doi.org/10.1103/PhysRevD.100.044009 
  23. Gabbard H, Williams M, Hayes F, Messenger C, Matching matched filtering with deep networks for gravitational-wave astronomy, Phys. Rev. Lett. 120, 141103 (2018). https://doi.org/10.1103/PhysRevLett.120.141103 
  24. Gebhard TD, Kilbertus N, Harry I, Scholkop B, Convolutional neural networks: a magic bullet for gravitational-wave detection? Phys. Rev. D, 2019, 100, 063015. https://doi.org/10.1103/PhysRevD.100.063015 
  25. George D, Huerta E, Deep Learning for real-time gravitational wave detection and parameter estimation: results with advanced LIGO data, Phys. Lett. B. 778, 64-70 (2018). https://doi.org/10.1016/j.physletb.2017.12.053 
  26. Kang Y, Liu C, Shao L, Electromagnetic follow-up observations of binary neutron star mergers with early warnings from decihertz gravitational-wave observatories, Mon. Not. R. Astron. Soc. 515, 739-748 (2022). https://doi.org/10.1093/mnras/stac1738 
  27. LIGO Scientific Collaboration, LALSuite: LIGO Scientific Collaboration Algorithm Library Suite, Astrophys. Source Code Libr. record ascl:2012.021 (2018). https://doi.org/10.7935/GT1W-FZ16 
  28. Matas A, Dietrich T, Buonanno A, Hinderer T, Purrer M, et al., Aligned-spin neutron-star-black-hole waveform model based on the effective-one-body approach and numerical-relativity simulations, Phys. Rev. D. 102, 043023 (2020). https://doi.org/10.1103/PhysRevD.102.043023 
  29. Messina F, Dudi R, Nagar A, Bernuzzi S, Quasi-5.5PN TaylorF2 approximant for compact binaries: point-mass phasing and impact on the tidal polarizability inference, Phys. Rev. D. 99, 124051 (2019). https://doi.org/10.1103/PhysRevD.99.124051 
  30. Mitra A, Shukirgaliyev B, Abylkairov YS, Abdikamalov E, Exploring supernova gravitational waves with machine learning, Mon. Not. R. Astron. Soc. 520, 2473-2483 (2023). https://doi.org/10.1093/mnras/stad169 
  31. Nalband S, Prince A, Agrawal A, Entropy-based feature extraction and classification of vibroartho-graphic signal using complete ensemble empirical mode decomposition with adaptive noise, IET Sci. Meas. Technol. 12, 350-359 (2018). https://doi.org/10.1049/iet-smt.2017.0284 
  32. Ormiston R, Nguyen T, Coughlin M, Adhikari RX, Katsavounidis E, Noise reduction in gravitational-wave data via deep learning. Phys. Rev. Res. 2, 033066 (2020). https://doi.org/10.1103/PhysRevResearch.2.033066 
  33. Qiu R, Krastev PG, Gill K, Berger E, Deep learning detection and classification of gravitational waves from neutron star-black hole mergers, Phys. Lett. B. 840, 137850 (2023). https://doi.org/10.1016/j.physletb.2023.137850 
  34. Shannon CE, Weaver W, The Mathematical Theory of Communication (University of Illinois Press, Urbana, 1949). 
  35. Usman SA, Nitz AH, Harry IW, Biwer CM, Brown DA, et al., The PyCBC search for gravitational waves from compact binary coalescence, Class. Quantum Grav. 33, 215004 (2016). https://doi.org/10.1088/0264-9381/33/21/215004 
  36. Vartanyan D, Burrows A, Gravitational waves from neutrino emission asymmetries in core-collapse supernovae, Astrophys. J. 901, 108. (2020). https://doi.org/10.3847/1538-4357/abafac 
  37. Wang H, Wu S, Cao Z, Liu X, Zhu JY, Gravitational-wave signal recognition of LIGO data by deep learning, Phys. Rev. D. 101, 104003 (2020). https://doi.org/10.1103/PhysRevD.101.104003 
  38. Welch P, The use of fast Fourier transform for the estimation of power spectra: a method based on time averaging over short, modified periodograms, IEEE Trans. Audio Electroacoust. 15, 70-73 (1967). https://doi.org/10.1109/TAU.1967.1161901 
  39. Yuan C, Murase K, Kimura SS, Meszaros P, High-energy neutrino emission subsequent to gravitational wave radiation from supermassive black hole mergers, Phys. Rev. D. 102, 083013(2020). https://doi.org/10.1103/PhysRevD.102.083013 
  40. Yun Q, Han WB, Guo YY, Wang H, Du M, Detecting extrememass-ratio inspirals for space-borne detectors with deep learning, arXiv prepr. (2023). https://doi.org/10.48550/arXiv.2309.06694 
  41. Zhanabaev Z, Ussipov NM, Information-entropy method for detecting gravitational wave signals, Eurasian Phys. Tech. J. 20, 79-86 (2023). https://doi.org/10.31489/2023NO2/79-86 
  42. Zhang Z, Li Y, Jin S, Zhang Z, Wang H, et al., Modulation signal recognition based on information entropy and ensemble learning, Entropy, 20, 198 (2018). https://doi.org/10.3390/e20030198