Machine Learning Gravitational Waves from Binary Black Hole Mergers

Abstract

We apply machine learning methods to build a time-domain model for gravitational waveforms from binary black hole mergers, called mlgw. The dimensionality of the problem is handled by representing the waveform's amplitude and phase using a principal component analysis. We train mlgw on about $\mathcal{O}(10^3)$ TEOBResumS and SEOBNRv4 effective-one-body waveforms with mass ratios $q\in [1,20]$ and aligned dimensionless spins $s\in [-0.80,0.95]$. The resulting models are faithful to the training sets at the $\sim 10^{-3}$ level (averaged on the parameter space). The speed up for a single waveform generation is a factor 10 to 50 (depending on the binary mass and initial frequency) for TEOBResumS and approximately an order of magnitude more for SEOBNRv4. Furthermore, mlgw provides a closed form expression for the waveform and its gradient with respect to the orbital parameters; such an information might be useful for future improvements in GW data analysis. As demonstration of the capabilities of mlgw to perform a full parameter estimation, we re-analyze the public data from the first GW transient catalog (GWTC-1). We find broadly consistent results with previous analyses at a fraction of the cost, although the analysis with spin aligned waveforms gives systematic larger values of the effective spins with respect to previous analyses with precessing waveforms. Since the generation time does not depend on the length of the signal, our model is particularly suitable for the analysis of the long signals that are expected to be detected by third-generation detectors. Future applications include the analysis of waveform systematics and model selection in parameter estimation.

15 pages, 11 figures, submitted to Phys. Rev. D

References in corpus (47)

• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• Frequency-domain gravitational waves from non-precessing black-hole binaries. II. A phenomenological model for the advanced detector era
• Robust parameter estimation for compact binaries with ground-based gravitational-wave observations using the LALInference software library
• Transition from inspiral to plunge in binary black hole coalescences
• An improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
• A Conceptual Introduction to Hamiltonian Monte Carlo
• Effective-one-body model for black-hole binaries with generic mass ratios and spins
• The SXS Collaboration catalog of binary black hole simulations
• A catalog of 174 binary black-hole simulations for gravitational-wave astronomy
• Surrogate models for precessing binary black hole simulations with unequal masses
• Towards models of gravitational waveforms from generic binaries II: Modelling precession effects with a single effective precession parameter
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Multipolar Effective-One-Body Waveforms for Precessing Binary Black Holes: Construction and Validation
• Time-domain effective-one-body gravitational waveforms for coalescing compact binaries with nonprecessing spins, tides and self-spin effects
• Effective One Body description of tidal effects in inspiralling compact binaries
• Surrogate model of hybridized numerical relativity binary black hole waveforms
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Faithful Effective-One-Body waveforms of small-mass-ratio coalescing black-hole binaries
• An improved analytical description of inspiralling and coalescing black-hole binaries
• Validating the effective-one-body model of spinning, precessing binary black holes against numerical relativity
• Fast prediction and evaluation of gravitational waveforms using surrogate models
• Frequency domain reduced order model of aligned-spin effective-one-body waveforms with generic mass-ratios and spins
• A faithful analytical effective one body waveform model for spin-aligned, moderately eccentric, coalescing black hole binaries
• Parameter estimation for compact binary coalescence signals with the first generation gravitational-wave detector network
• A multipolar effective one body waveform model for spin-aligned black hole binaries
• Frequency domain reduced order model of aligned-spin effective-one-body waveforms with higher-order modes
• The RIT binary black hole simulations catalog
• Surrogate model for an aligned-spin effective one body waveform model of binary neutron star inspirals using Gaussian process regression
• A Multipolar Effective One Body Model for Non-Spinning Black Hole Binaries
• Reduced-order modeling with artificial neurons for gravitational-wave inference
• A Surrogate Model for Gravitational Wave Signals from Comparable- to Large- Mass-Ratio Black Hole Binaries
• IMRPhenomTP: A phenomenological time domain model for dominant quadrupole gravitational wave signal of coalescing binary black holes
• A new analytic representation of the ringdown waveform of coalescing spinning black hole binaries
• The second RIT binary black hole simulations catalog and its application to gravitational waves parameter estimation
• Rush the inspiral: efficient Effective One Body time-domain gravitational waveforms
• The Third RIT binary black hole simulations catalog
• Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation
• Statistical and systematic errors for gravitational-wave inspiral signals: A principal component analysis
• A Precessing Numerical Relativity Waveform Surrogate Model for Binary Black Holes: A Gaussian Process Regression Approach
• Comparing Effective One Body Hamiltonians for spin-aligned coalescing binaries
• Using Deep Learning to Localize Gravitational Wave Sources
• Fusing numerical relativity and deep learning to detect higher-order multipole waveforms from eccentric binary black hole mergers
• Regression methods in waveform modeling: a comparative study
• Optimizing spinning time-domain gravitational waveforms for Advanced LIGO data analysis
• Physics-inspired deep learning to characterize the signal manifold of quasi-circular, spinning, non-precessing binary black hole mergers
• Data formats for numerical relativity waves
• A Hamiltonian Monte Carlo method for Bayesian Inference of Supermassive Black Hole Binaries

Cited by in corpus (32)

• Parameter estimation with gravitational waves
• The Science of the Einstein Telescope
• Effective one-body model for extreme-mass-ratio spinning binaries on eccentric equatorial orbits: testing radiation reaction and waveform
• Constraints on the maximum densities of neutron stars from postmerger gravitational waves with third-generation observations
• Training Strategies for Deep Learning Gravitational-Wave Searches
• $\mathtt{bajes}$: Bayesian inference of multimessenger astrophysical data, methods and application to gravitational-waves
• Fast, faithful, frequency-domain effective-one-body waveforms for compact binary coalescences
• Searching for ringdown higher modes with a numerical relativity-informed post-merger model
• Accelerating multimodal gravitational waveforms from precessing compact binaries with artificial neural networks
• Effective-one-body waveforms for extreme-mass-ratio binaries: Consistency with second-order gravitational self-force quasicircular results and extension to nonprecessing spins and eccentricity
• Optimization of model independent gravitational wave search using machine learning
• Combining effective-one-body accuracy and reduced-order-quadrature speed for binary neutron star merger parameter estimation with machine learning
• Numerical-relativity validation of effective-one-body waveforms in the intermediate-mass-ratio regime
• Accurate and Efficient Waveform Model for Precessing Binary Black Holes
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Effective one body Hamiltonian in scalar-tensor gravity at third post-Newtonian order
• Localization of gravitational waves using machine learning
• Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
• A fully precessing higher-mode surrogate model of effective-one-body waveforms
• Assessing the impact of non-Gaussian noise on convolutional neural networks that search for continuous gravitational waves
• Convolutional Neural Networks for signal detection in real LIGO data
• Parameter inference for coalescing massive black hole binaries using deep learning
• Deep-Learning Classification and Parameter Inference of Rotational Core-Collapse Supernovae
• A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms
• Optimizing Neural Network Surrogate Models: Application to Black Hole Merger Remnants
• Comparison of neural network architectures for feature extraction from binary black hole merger waveforms
• Enhancing gravitational-wave host localization with SKYFAST: rapid volume and inclination angle reconstruction
• QPOML: A Machine Learning Approach to Detect and Characterize Quasi-Periodic Oscillations in X-ray Binaries
• Conditional Autoencoder for Generating Binary Neutron Star Waveforms with Tidal and Precession Effects
• Graph-based Summary Statistics for Revealing the Stochastic Gravitational Wave Background in Pulsar Timing Arrays
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• Waveforms and fluxes: Towards a self-consistent effective one body waveform model for nonprecessing, coalescing black-hole binaries for third generation detectors