Nuclear and High Energy Physics; General Relativity and Quantum Cosmology; astro-ph.IM; Computer Science - Learning
Abstract :
[en] Fast, highly accurate, and reliable inference of the sky origin of gravitational waves would enable real-time multimessenger astronomy. Current Bayesian inference methodologies, although highly accurate and reliable, are slow. Deep learning models have shown themselves to be accurate and extremely fast for inference tasks on gravitational waves, but their output is inherently questionable due to the blackbox nature of neural networks. In this work, we merge Bayesian inference and deep learning by applying importance sampling on an approximate posterior generated by a multiheaded convolutional neural network. The neural network parametrizes Von Mises-Fisher and Gaussian distributions for the sky coordinates and two masses for given simulated gravitational wave injections in the LIGO and Virgo detectors. We generate skymaps for unseen gravitational-wave events that highly resemble predictions generated using Bayesian inference in a few minutes. Furthermore, we can detect poor predictions from the neural network, and quickly flag them.
Disciplines :
Space science, astronomy & astrophysics
Author, co-author :
Kolmus, Alex; Institute for Computing and Information Sciences (ICIS), Radboud University Nijmegen, Nijmegen, Netherlands
Baltus, Grégory ; Université de Liège - ULiège > Faculté des Sciences > CAPAES sciences
Janquart, Justin; Nikhef, Amsterdam, Netherlands ; Institute for Gravitational and Subatomic Physics (GRASP), Utrecht University, Utrecht, Netherlands
Van Laarhoven, Twan ; Institute for Computing and Information Sciences (ICIS), Radboud University Nijmegen, Nijmegen, Netherlands
Caudill, Sarah; Nikhef, Amsterdam, Netherlands ; Institute for Gravitational and Subatomic Physics (GRASP), Utrecht University, Utrecht, Netherlands
Heskes, Tom ; Institute for Computing and Information Sciences (ICIS), Radboud University Nijmegen, Nijmegen, Netherlands
Language :
English
Title :
Fast sky localization of gravitational waves using deep learning seeded importance sampling
NWO - Nederlandse Organisatie voor Wetenschappelijk Onderzoek F.R.S.-FNRS - Fonds de la Recherche Scientifique
Funding text :
This work was (partially) funded by the NWO under the CORTEX project (NWA.1160.18.316). G. B. is supported by aFRIA grant from the Fonds de la Recherche Scientifique-FNRS, Belgium. J. J. is supported by the research program of the Netherlands Organisation for Scientific Research (NWO).
B. P. Abbott, R. Abbott, T. D. Abbott, M. R. Abernathy, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, Tests of General Relativity with GW150914, Phys. Rev. Lett. 116, 221101 (2016). PRLTAO 0031-9007 10.1103/PhysRevLett.116.221101
B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, V. B. Adya, Gw170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence, Phys. Rev. Lett. 119, 141101 (2017). PRLTAO 0031-9007 10.1103/PhysRevLett.119.141101
K. Yamada, T. Narikawa, and T. Tanaka, Testing massive-field modifications of gravity via gravitational waves, Prog. Theor. Exp. Phys. 2019, 103E01 (2019). PTEPCR 2050-3911 10.1093/ptep/ptz103
L. Baiotti, Gravitational waves from neutron star mergers and their relation to the nuclear equation of state, Prog. Part. Nucl. Phys. 109, 103714 (2019). PPNPDB 0146-6410 10.1016/j.ppnp.2019.103714
J. Aasi, B. P. Abbott, R. Abbott, T. Abbott, M. R. Abernathy, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, Advanced LIGO, Classical Quantum Gravity 32, 074001 (2015). CQGRDG 0264-9381 10.1088/0264-9381/32/7/074001
F. Acernese, M. Agathos, K. Agatsuma, D. Aisa, N. Allemandou, A. Allocca, J. Amarni, P. Astone, G. Balestri, G. Ballardin, Advanced Virgo: A second-generation interferometric gravitational wave detector, Classical Quantum Gravity 32, 024001 (2015). CQGRDG 0264-9381 10.1088/0264-9381/32/2/024001
Z. Doctor, R. Kessler, K. Herner, A. Palmese, M. Soares-Santos, J. Annis, D. Brout, D. E. Holz, M. Sako, A. Rest, A search for optical emission from binary black hole merger GW170814 with the dark energy camera, Astrophys. J. Lett. 873, L24 (2019). AJLEEY 2041-8213 10.3847/2041-8213/ab08a3
R. Perna, D. Lazzati, and W. Farr, Limits on electromagnetic counterparts of gravitational-wave-detected binary black hole mergers, Astrophys. J. 875, 49 (2019). ASJOAB 0004-637X 10.3847/1538-4357/ab107b
B. P. Abbott, R. Abbott, T. D. Abbott, F. Acernese, K. Ackley, C. Adams, T. Adams, P. Addesso, R. X. Adhikari, V. B. Adya, GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral, Phys. Rev. Lett. 119, 161101 (2017). PRLTAO 0031-9007 10.1103/PhysRevLett.119.161101
P. S. Cowperthwaite, E. Berger, V. A. Villar, B. D. Metzger, M. Nicholl, R. Chornock, P. K. Blanchard, W. Fong, R. Margutti, M. Soares-Santos, The electromagnetic counterpart of the binary neutron star merger LIGO/Virgo GW170817. II. UV, optical, and near-infrared light curves and comparison to kilonova models, Astrophys. J. Lett. 848, L17 (2017). AJLEEY 2041-8213 10.3847/2041-8213/aa8fc7
E. Berti, K. Yagi, and N. Yunes, Extreme gravity tests with gravitational waves from compact binary coalescences: (I) inspiral-merger, Gen. Relativ. Gravit. 50, 46 (2018). GRGVA8 0001-7701 10.1007/s10714-018-2372-6
L. Barack, V. Cardoso, S. Nissanke, T. P. Sotiriou, A. Askar, C. Belczynski, G. Bertone, E. Bon, D. Blas, R. Brito, Black holes, gravitational waves and fundamental physics: A roadmap, Classical Quantum Gravity 36, 143001 (2019). CQGRDG 0264-9381 10.1088/1361-6382/ab0587
M. Fishbach, R. Gray, I. Hernandez Magaña, H. Qi, A. Sur, F. Acernese, L. Aiello, A. Allocca, M. A. Aloy, A. Amato, A standard siren measurement of the Hubble constant from GW170817 without the electromagnetic counterpart, Astrophys. J. Lett. 871, L13 (2019). AJLEEY 2041-8213 10.3847/2041-8213/aaf96e
J. Veitch, V. Raymond, B. Farr, W. Farr, P. Graff, S. Vitale, B. Aylott, K. Blackburn, N. Christensen, M. Coughlin, Parameter estimation for compact binaries with ground-based gravitational-wave observations using the lali nference software library, Phys. Rev. D 91, 042003 (2015). PRVDAQ 1550-7998 10.1103/PhysRevD.91.042003
C. M. Biwer, C. D. Capano, S. De, M. Cabero, D. A. Brown, A. H. Nitz, and V. Raymond, p y cbc inference: A python-based parameter estimation toolkit for compact binary coalescence signals, Publ. Astron. Soc. Pac. 131, 024503 (2019). PASPAU 0004-6280 10.1088/1538-3873/aaef0b
J. Skilling, Nested sampling for general Bayesian computation, Bayesian Anal. 1, 833 (2006). 10.1214/06-BA127
K. P. Murphy, Machine Learning: A Probabilistic Perspective (MIT Press, Cambridge, MA, 2012).
G. Ashton, M. Hübner, P. D. Lasky, C. Talbot, K. Ackley, S. Biscoveanu, Q. Chu, A. Divakarla, P. J. Easter, B. Goncharov, bilby: A user-friendly Bayesian inference library for gravitational-wave astronomy, Astrophys. J. Suppl. Ser. 241, 27 (2019). APJSA2 1538-4365 10.3847/1538-4365/ab06fc
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). NPAHAX 1745-2473 10.1038/s41567-021-01425-7
L. P. Singer and L. R. Price, Rapid Bayesian position reconstruction for gravitational-wave transients, Phys. Rev. D 93, 024013 (2016). PRVDAQ 2470-0010 10.1103/PhysRevD.93.024013
The GWTC-2 catalog [22] data release provides skymaps made using Bayesian inference methods for recent events. Comparison with the skymaps made by BAYESTAR can be made by looking at skymaps on https://gracedb.ligo.org/latest/.
R. Abbott, T. D. Abbott, S. Abraham, F. Acernese, K. Ackley, A. Adams, C. Adams, R. X. Adhikari, V. B. Adya, C. Affeldt, GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo during the First Half of the Third Observing Run, Phys. Rev. X 11, 021053 (2021). PRXHAE 2160-3308 10.1103/PhysRevX.11.021053
Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature (London) 521, 436 (2015). NATUAS 0028-0836 10.1038/nature14539
J. Schmidhuber, Deep learning in neural networks: An overview, Neural Netw. 61, 85 (2015). NNETEB 0893-6080 10.1016/j.neunet.2014.09.003
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, arXiv:2010.12931.
S. R. Green and J. Gair, Complete parameter inference for GW150914 using deep learning, Mach. Learn. 2, 03LT01 (2021). MALEEZ 0885-6125 10.1088/2632-2153/abfaed
G. Papamakarios, E. Nalisnick, D. J. Rezende, S. Mohamed, and B. Lakshminarayanan, Normalizing flows for probabilistic modeling and inference, J. Mach. Learn. Res. 22, 1 (2021). 1532-4435
Throughout this paper, reference posterior is used to imply a posterior that is generated using Bayesian inference.
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). PRLTAO 0031-9007 10.1103/PhysRevLett.127.241103
M. J. Williams, J. Veitch, and C. Messenger, Nested sampling with normalizing flows for gravitational-wave inference, Phys. Rev. D 103, 103006 (2021). PRVDAQ 2470-0010 10.1103/PhysRevD.103.103006
C. M. Bishop, Pattern Recognition and Machine Learning (Springer, New York, 2006).
P. Canizares, S. E. Field, J. R. Gair, and M. Tiglio, Gravitational wave parameter estimation with compressed likelihood evaluations, Phys. Rev. D 87, 124005 (2013). PRVDAQ 1550-7998 10.1103/PhysRevD.87.124005
D. George and E. A. Huerta, Deep neural networks to enable real-time multimessenger astrophysics, Phys. Rev. D 97, 044039 (2018). PRVDAQ 2470-0010 10.1103/PhysRevD.97.044039
X. Fan, J. Li, X. Li, Y. Zhong, and J. Cao, Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors, Sci. China Phys. Mech. Astron. 62, 969512 (2019). SCPMCL 1674-7348 10.1007/s11433-018-9321-7
N. I. Fisher, T. Lewis, and B. J. J. Embleton, Statistical Analysis of Spherical Data (Cambridge University Press, Cambridge, England, 1993).
R. L. Russell and C. Reale, Multivariate uncertainty in deep learning, IEEE Trans. Neural Netw. Learn. Syst. (2021). 10.1109/TNNLS.2021.3086757
M. Hannam, P. Schmidt, A. Bohé, L. Haegel, S. Husa, F. Ohme, G. Pratten, and M. Pürrer, Simple Model of Complete Precessing Black-Hole-Binary Gravitational Waveforms, Phys. Rev. Lett. 113, 151101 (2014). PRLTAO 0031-9007 10.1103/PhysRevLett.113.151101
D. P. Kingma and J. L. Ba, Adam: A method for stochastic gradient descent, in Proceedings of the ICLR: International Conference on Learning Representations (2015).
I. Loshchilov and F. Hutter, SGDR: Stochastic gradient descent with warm restarts, in Proceedings of the ICLR: International Conference on Learning Representations (2017).
The gaussian_kde from the s ci p y python package.
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). PRVDAQ 2470-0010 10.1103/PhysRevD.100.063015
C. Chatterjee, L. Wen, K. Vinsen, M. Kovalam, and A. Datta, Using deep learning to localize gravitational wave sources, Phys. Rev. D 100, 103025 (2019). PRVDAQ 2470-0010 10.1103/PhysRevD.100.103025
A. J. K. Chua and M. Vallisneri, Learning Bayesian Posteriors with Neural Networks for Gravitational-Wave Inference, Phys. Rev. Lett. 124, 041102 (2020). PRLTAO 0031-9007 10.1103/PhysRevLett.124.041102
