- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Deep source separation of overlapping gravitational-wave signals and nonstationary noise artifacts

Niklas Houba

  • ETH Zurich, Department of Physics, Institute for Particle and Astrophysics, Wolfgang-Pauli-Str. 27, 8093 Zurich, Switzerland

PDF

Phys. Rev. Research 7, 033115 – Published 1 August, 2025

DOI: https://doi.org/10.1103/6bjw-xjj2

Abstract

The Laser Interferometer Space Antenna (LISA) will observe gravitational waves in the millihertz frequency band, detecting signals from a vast number of astrophysical sources embedded in instrumental noise. Extracting individual signals from overlapping contributions represents a fundamental challenge in LISA data analysis and is traditionally addressed using computationally expensive stochastic Bayesian techniques. In this work, we present a deep learning-based framework for blind source separation in LISA data, employing an encoder-decoder architecture commonly used in digital audio processing to isolate individual signals within complex mixtures. Our approach enables signals from massive black hole binaries, Galactic binaries, and instrumental glitches to be disentangled directly in a single step, circumventing the need for sequential source identification and subtraction. By learning clustered latent-space representations, the framework provides a scalable alternative to conventional methods, with applications in both low-latency event detection and full-scale global-fit analyses. As a proof-of-concept, we assess the model's performance using simulated LISA data in a controlled setting with a limited number of overlapping sources. The results highlight deep source separation as a promising tool for LISA, paving the way for future extensions to more complex datasets.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (85)

  1. M. Colpi, K. Danzmann, M. Hewitson, K. Holley-Bockelmann, P. Jetzer, G. Nelemans, A. Petiteau, D. Shoemaker, C. Sopuerta, R. Stebbins et al., LISA definition study report, arXiv:2402.07571
  2. W. Martens and E. Joffre, Trajectory design for the ESA LISA mission, J. Astronaut. Sci. 68, 402 (2021).
  3. B. P. Abbott, R. Abbott, T. D. Abbott, M. R. Abernathy, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari et al., Observation of gravitational waves from a binary black hole merger, Phys. Rev. Lett. 116, 061102 (2016).
  4. B. P. Abbott, R. Abbott, T. D. Abbott, M. R. Abernathy, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari et al., GW151226: Observation of gravitational waves from a 22-solar-mass binary black hole coalescence, Phys. Rev. Lett. 116, 241103 (2016).
  5. B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, V. B. Adya et al., GW170104: Observation of a 50-solar-mass binary black hole coalescence at redshift 0.2, Phys. Rev. Lett. 118, 221101 (2017).
  6. B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, and V. B. Adya, GW170608: Observation of a 19 solar-mass binary black hole coalescence, Astrophys. J. Lett. 851, L35 (2017).
  7. B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, V. B. Adya et al. (LIGO Scientific Collaboration and Virgo Collaboration), GW170814: A three-detector observation of gravitational waves from a binary black hole coalescence, Phys. Rev. Lett. 119, 141101 (2017).
  8. B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, V. B. Adya et al., GW170817: Observation of gravitational waves from a binary neutron star inspiral, Phys. Rev. Lett. 119, 161101 (2017).
  9. B. P. Abbott, R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt 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 (2019).
  10. B. P. Abbott, R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt et al., GW190425: Observation of a compact binary coalescence with total mass ∼ 3.4 M⊙, Astrophys. J. Lett. 892, L3 (2020).
  11. R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt, M. Agathos et al., GW190412: Observation of a binary-black-hole coalescence with asymmetric masses, Phys. Rev. D 102, 043015 (2020).
  12. R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt, M. Agathos et al., GW190814: Gravitational Waves from the Coalescence of a 23 solar mass black hole with a 2.6 solar mass compact object, Astrophys. J. Lett. 896, L44 (2020).
  13. R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt, M. Agathos et al. (LIGO Scientific Collaboration and Virgo Collaboration), GW190521: A binary black hole merger with a total mass of 150M⨀, Phys. Rev. Lett. 125, 101102 (2020).
  14. LISA Science Study Team, LISA Science Requirements document, Technical Report, European Space Agency (2018), Technical Report ESA-L3-EST-SCI-RS-001.
  15. P. Amaro-Seoane, S. Aoudia, S. Babak, P. Binétruy, E. Berti, A. Bohé, C. Caprini, M. Colpi, N. J. Cornish, K. Danzmann et al., Low-frequency gravitational-wave science with eLISA/NGO, Class. Quantum Gravity 29, 124016 (2012).
  16. J. Crowder and N. J. Cornish, Solution to the galactic foreground problem for LISA, Phys. Rev. D 75, 043008 (2007).
  17. A. W. Criswell, S. Rieck, and V. Mandic, Templated anisotropic analyses of the LISA Galactic foreground, Phys. Rev. D 111, 023025 (2025).
  18. J.-B. Bayle, M. Lilley, A. Petiteau, and H. Halloin, Effect of filters on the time-delay interferometry residual laser noise for LISA, Phys. Rev. D 99, 084023 (2019).
  19. S. Paczkowski, R. Giusteri, M. Hewitson, N. Karnesis, E. D. Fitzsimons, G. Wanner, and G. Heinzel, Postprocessing subtraction of tilt-to-length noise in LISA, Phys. Rev. D 106, 042005 (2022).
  20. N. Houba, Tilt-to-Length Noise Estimation and Reduction Algorithms for Spaceborne Gravitational-Wave Observatories, Fortschrittsberichte des Instituts für Flugmechanik und Flugregelung (Shaker Verlag, Düren, 2023), Vol. 15.
  21. M. L. Katz, N. Karnesis, N. Korsakova, J. R. Gair, and N. Stergioulas, Efficient GPU-accelerated multisource global fit pipeline for LISA data analysis, Phys. Rev. D 111, 024060 (2025).
  22. T. B. Littenberg and N. J. Cornish, Prototype global analysis of LISA data with multiple source types, Phys. Rev. D 107, 063004 (2023).
  23. S. H. Strub, L. Ferraioli, C. Schmelzbach, S. C. Stähler, and D. Giardini, Global analysis of LISA data with Galactic binaries and massive black hole binaries, Phys. Rev. D 110, 024005 (2024).
  24. P. J. Green, Reversible jump Markov chain Monte Carlo computation and Bayesian model determination, Biometrika 82, 711 (1995).
  25. C. Ritter and M. A. Tanner, Facilitating the Gibbs sampler: The Gibbs stopper and the Griddy-Gibbs sampler, J. Am. Stat. Assoc. 87, 861 (1992).
  26. P. Müller, A Generic Approach to Posterior Integration and Gibbs Sampling, Technical Report TR91-09 (Department of Statistics, Purdue University, 1991).
  27. S. H. Strub, L. Ferraioli, C. Schmelzbach, S. C. Stähler, and D. Giardini, Bayesian parameter estimation of Galactic binaries in LISA data with Gaussian process regression, Phys. Rev. D 106, 062003 (2022).
  28. T. Dooney, H. Narola, S. Bromuri, R. L. Curier, C. V. D. Broeck, S. Caudill, and D. S. Tan, DeepExtractor: Time-domain reconstruction of signals and glitches in gravitational wave data with deep learning, arXiv:2501.18423.
  29. T. Zhao, Y. Zhou, R. Shi, P. Xu, Z. Cao, and Z. Ren, Compact binary coalescence gravitational wave signal counting and separation, Phys. Rev. D 111, 104028 (2025).
  30. I. M. Vílchez and C. F. Sopuerta, Efficient massive black hole binary parameter estimation for LISA using sequential neural likelihood, arXiv:2406.00565.
  31. D. Michelsanti, Z.-H. Tan, S.-X. Zhang, Y. Xu, M. Yu, D. Yu, and J. Jensen, An overview of deep-learning-based audio-visual speech enhancement and separation, IEEE/ACM Trans. Audio Speech Lang. Process. 29, 1368 (2021).
  32. E. Vincent, T. Virtanen, and S. Gannot, eds., Audio Source Separation and Speech Enhancement (John Wiley and Sons, Nashville, TN, 2018).
  33. P. Ochieng, Deep neural network techniques for monaural speech enhancement and separation: state of the art analysis, Artif. Intell. Rev. 56, 3651 (2023).
  34. A. Tharwat, Independent component analysis: An introduction, Appl. Comput. Inf. 17, 222 (2020).
  35. J. Thiemann and E. Vincent, An experimental comparison of source separation and beamforming techniques for microphone array signal enhancement, in 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) (IEEE, Southampton, UK, 2013), pp. 1–5.
  36. A. Wang, An industrial strength audio search algorithm, in International Society for Music Information Retrieval (ISMR) Conference (Baltimore, Maryland, USA, 2003).
  37. H. Lee, M. Gwak, K. Lee, M. Kim, J. Konan, and O. Bhargave, Speech enhancement for virtual meetings on cellular networks, arXiv:2302.00868.
  38. S. Ansari, A. S. Alatrany, K. A. Alnajjar, T. Khater, S. Mahmoud, D. Al-Jumeily, and A. J. Hussain, A survey of artificial intelligence approaches in blind source separation, Neurocomputing 561, 126895 (2023).
  39. J.-T. Chien, Source Separation and Machine Learning (Academic Press, San Diego, CA, 2018).
  40. A. Défossez, N. Usunier, L. Bottou, and F. Bach, Music source separation in the waveform domain (2019) (unpublished).
  41. A. Mangiagli, C. Caprini, M. Volonteri, S. Marsat, S. Vergani, N. Tamanini, and L. Speri, Cosmology with massive black hole binary mergers in the LISA era, in Proceedings of 41st International Conference on High Energy physics – PoS(ICHEP2022), ICHEP2022 (Sissa Medialab, Bologna, Italy, 2022).
  42. A. Mangiagli, C. Caprini, S. Marsat, L. Speri, R. R. Caldwell, and N. Tamanini, Massive black hole binaries in LISA: constraining cosmological parameters at high redshifts, arXiv:2312.04632.
  43. E. Leroy, J. Bobin, and H. Moutarde, Low-dimensional signal representations for massive black hole binary signals analysis from LISA data, Astron. Astrophys. 689, A107 (2024).
  44. T. Kupfer, V. Korol, T. B. Littenberg, S. Shah, E. Savalle, P. J. Groot, T. R. Marsh, M. Le Jeune, G. Nelemans, A. F. Pala, A. Petiteau, G. Ramsay, D. Steeghs, and S. Babak, LISA galactic binaries with astrometry from Gaia DR3 (2024).
  45. N. Cornish and T. Robson, Galactic binary science with the new LISA design, J. Phys.: Conf. Ser. 840, 012024 (2017).
  46. K. Lackeos, T. B. Littenberg, N. J. Cornish, and J. I. Thorpe, The LISA data challenge radler analysis and time-dependent ultra-compact binary catalogues, Astron. Astrophys. 678, A123 (2023).
  47. T. B. Littenberg and A. K. Lali, Have any LISA verification binaries been found? arXiv:2404.03046.
  48. J. R. Gair, C. Tang, and M. Volonteri, Lisa extreme-mass-ratio inspiral events as probes of the black hole mass function, Phys. Rev. D 81, 104014 (2010).
  49. I. Qunbar and N. C. Stone, Enhanced extreme mass ratio inspiral rates and intermediate mass black holes, Phys. Rev. Lett. 133, 141401 (2024).
  50. C. P. L. Berry, S. A. Hughes, C. F. Sopuerta, A. J. K. Chua, A. Heffernan, K. Holley-Bockelmann, D. P. Mihaylov, M. C. Miller, and A. Sesana, The unique potential of extreme mass-ratio inspirals for gravitational-wave astronomy, arXiv:1903.03686.
  51. A. Rüdiger, G. Heinzel, and M. Tröbs, LISA, the Laser Interferometer Space Antenna, requires the ultimate in lasers, clocks, and drag-free control, in Lasers, Clocks and Drag-Free Control (Springer, Berlin, 2008), pp. 427–455.
  52. G. Wanner, S. Shah, M. Staab, H. Wegener, and S. Paczkowski, In-depth modeling of tilt-to-length coupling in LISA's interferometers and TDI Michelson observables, Phys. Rev. D 110, 022003 (2024).
  53. P. L. Bender, A. Brillet, I. Ciufolini, A. M. Cruise, C. Cutler, K. Danzmann et al., LISA. Laser Interferometer Space Antenna for the detection and observation of gravitational waves. An international project in the field of Fundamental Physics in Space, Max-Planck-Institut für Quantenoptik, München, Germany (1998), Pre-Phase A Report.
  54. Q. Baghi, N. Korsakova, J. Slutsky, E. Castelli, N. Karnesis, and J.-B. Bayle, Detection and characterization of instrumental transients in LISA Pathfinder and their projection to LISA, Phys. Rev. D 105, 042002 (2022).
  55. E. Castelli, Q. Baghi, J. G. Baker, J. Slutsky, J. Bobin, N. Karnesis, A. Petiteau, O. Sauter, P. Wass, and W. J. Weber, Extraction of gravitational wave signals from LISA data in the presence of artifacts, arXiv:2411.13402.
  56. N. Houba, L. Ferraioli, and D. Giardini, Detection and mitigation of glitches in LISA data: A machine learning approach, Phys. Rev. D 109, 083027 (2024).
  57. M. Tinto, F. B. Estabrook, and J. W. Armstrong, Time-delay interferometry for LISA, Phys. Rev. D 65, 082003 (2002).
  58. M. Tinto and S. V. Dhurandhar, Time-delay interferometry, Living Rev. Relativity 8, 4 (2005).
  59. M. Vallisneri, J.-B. Bayle, S. Babak, and A. Petiteau, Time-delay interferometry without delays, Phys. Rev. D 103, 082001 (2021).
  60. K. Li, X. Hu, and Y. Luo, On the use of deep mask estimation module for neural source separation systems, arXiv:2206.07347.
  61. A. J. R. Simpson, Probabilistic binary-mask cocktail-party source separation in a convolutional deep neural network, arXiv:1503.06962.
  62. M. Niu and Y. Zhang, Binaural blind source separation based on deep clustering, in Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery, edited by H. Meng, T. Lei, M. Li, K. Li, N. Xiong, and L. Wang (Springer International Publishing, Cham, 2021), pp. 1077–1086.
  63. M. Li, C. Cao, C. Li, and S. Yang, Deep embedding clustering based on residual autoencoder, Neural Process. Lett. 56, 127 (2024).
  64. J. Xie, R. Girshick, and A. Farhadi, Unsupervised deep embedding for clustering analysis, in Proceedings of the 33rd International Conference on International Conference on Machine Learning, ICML'16 (JMLR.org, New York NY USA, 2016), Vol. 48, pp. 478–487.
  65. M. Moradi Fard, T. Thonet, and E. Gaussier, Deep k-means: Jointly clustering with k-means and learning representations, Pattern Recognit. Lett. 138, 185 (2020).
  66. Y. Luo, Z. Chen, J. R. Hershey, J. L. Roux, and N. Mesgarani, Deep clustering and conventional networks for music separation: Stronger together, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2016).
  67. T. Chang, B. P. Rasmussen, B. G. Dickson, and L. J. Zachmann, Chimera: A multi-task recurrent convolutional neural network for forest classification and structural estimation, Remote Sensing 11, 768 (2019).
  68. E. Manilow, P. Seetharaman, and B. Pardo, Simultaneous separation and transcription of mixtures with multiple polyphonic and percussive instruments, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Virtual Barcelona, Spain, 2020), pp. 771–775.
  69. T. Nakamura, S. Kozuka, and H. Saruwatari, Time-domain audio source separation with neural networks based on multiresolution analysis, IEEE/ACM Trans. Audio Speech Lang. Process. 29, 1687 (2021).
  70. T. Nakamura and H. Saruwatari, Time-domain audio source separation based on wave-u-net combined with discrete wavelet transform, in ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Virtual Barcelona, Spain, 2020), pp. 386–390.
  71. Y. Luo and N. Mesgarani, Conv-tasnet: Surpassing ideal time–frequency magnitude masking for speech separation, IEEE/ACM Trans. Audio, Speech Lang. Process. 27, 1256 (2019).
  72. O. Ronneberger, P. Fischer, and T. Brox, U-net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, edited by N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi (Springer International Publishing, Cham, 2015), pp. 234–241.
  73. N. Tishby, F. C. Pereira, and W. Bialek, The information bottleneck method, arXiv:physics/0004057.
  74. O. Ronneberger, P. Fischer, and T. Brox, U-net: Convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, edited by N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi (Springer International Publishing, Cham, 2015), pp. 234–241.
  75. T. A. Prince, M. Tinto, S. L. Larson, and J. W. Armstrong, LISA optimal sensitivity, Phys. Rev. D 66, 122002 (2002).
  76. T. T. Cai and R. Ma, Theoretical foundations of t-SNE for visualizing high-dimensional clustered data, J. Mach. Learn. Res. 23, 1 (2022).
  77. F. Locatello, D. Weissenborn, T. Unterthiner, A. Mahendran, G. Heigold, J. Uszkoreit, A. Dosovitskiy, and T. Kipf, Object-centric learning with slot attention, in Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS '20 (Curran Associates Inc., Red Hook, NY, 2020).
  78. H. W. Kuhn, The Hungarian method for the assignment problem, Nav. Res. Logist. Q. 2, 83 (1955).
  79. M. L. Katz, S. Marsat, A. J. K. Chua, S. Babak, and S. L. Larson, GPU-accelerated massive black hole binary parameter estimation with LISA, Phys. Rev. D 102, 023033 (2020).
  80. M. L. Katz, Fully automated end-to-end pipeline for massive black hole binary signal extraction from LISA data, arXiv:2111.01064.
  81. M. L. Katz, mikekatz04/BBHx: First official public release (v1.0.0), available at https://doi.org/10.5281/zenodo.5730688.
  82. N. J. Cornish and T. B. Littenberg, Tests of Bayesian model selection techniques for gravitational wave astronomy, Phys. Rev. D 76, 083006 (2007).
  83. K. Pearson, On lines and planes of closest fit to systems of points in space, Lond. Edinb. Dubl. Phil. Mag. J. Sci. 2, 559 (1901).
  84. L. McInnes, J. Healy, N. Saul, and L. Großberger, UMAP: Uniform manifold approximation and projection, J.Open Source Softw. 3, 861 (2018).
  85. J. Boelts, M. Deistler, M. Gloeckler, Á Tejero-Cantero, J.-M. Lueckmann, G. Moss, P. Steinbach, T. Moreau, F. Muratore, J. Linhart et al., sbi reloaded: A toolkit for simulation-based inference workflows, J. Open Source Softw. 10, 7754 (2025).

Outline

Information

Phys. Rev. Research 7, 033115– Published 1 August, 2025
  • Received 14 March 2025
  • Accepted 1 July 2025
Crossmark - Check for updates button
Creative Commons Logo

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.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation