Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation

Abstract

Inferring the properties of black holes and neutron stars is a key science goal of gravitational-wave (GW) astronomy. To extract as much information as possible from GW observations we must develop methods to reduce the cost of Bayesian inference. In this paper, we use artificial neural networks (ANNs) and the parallelisation power of graphics processing units (GPUs) to improve the surrogate modelling method, which can produce accelerated versions of existing models. As a first application of our method, ANN-Sur, we build a time-domain surrogate model of the spin-aligned binary black hole (BBH) waveform model SEOBNRv4. We achieve median mismatches of 2e-5 and mismatches no worse than 2e-3. For a typical BBH waveform generated from 12 Hz with a total mass of $60M_{\odot }$ the original SEOBNRv4 model takes 1812 ms. Existing bespoke code optimisations (SEOBNRv4opt) reduced this to 91.6 ms and the interpolation based, frequency-domain surrogate SEOBNRv4ROM can generate this waveform in 6.9 ms. Our ANN-Sur model, when run on a CPU takes 2.7 ms and just 0.4 ms when run on a GPU. ANN-Sur can also generate large batches of waveforms simultaneously. We find that batches of up to 10^4 waveforms can be evaluated on a GPU in just 163 ms, corresponding to a time per waveform of 0.016 ms. This method is a promising way to utilise the parallelisation power of GPUs to drastically increase the computational efficiency of Bayesian parameter estimation.

References in corpus (78)

• Multi-messenger Observations of a Binary Neutron Star Merger
• MCMC using Hamiltonian dynamics
• GW190814: Gravitational Waves from the Coalescence of a 23 M${}_{\odot }$ Black Hole with a 2.6 M${}_{\odot }$ Compact Object
• Gravitational Waves from Mergin Compact Binaries: How Accurately Can One Extract the Binary's Parameters from the Inspiral Waveform?
• Frequency-domain gravitational waves from non-precessing black-hole binaries. II. A phenomenological model for the advanced detector era
• Frequency-domain gravitational waves from non-precessing black-hole binaries. I. New numerical waveforms and anatomy of the signal
• GW190412: Observation of a Binary-Black-Hole Coalescence with Asymmetric Masses
• The PyCBC search for gravitational waves from compact binary coalescence
• An improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
• Surrogate models for precessing binary black hole simulations with unequal masses
• Train longer, generalize better: closing the generalization gap in large batch training of neural networks
• Multipolar Effective-One-Body Waveforms for Precessing Binary Black Holes: Construction and Validation
• IMRPhenomXHM: A multi-mode frequency-domain model for the gravitational wave signal from non-precessing black-hole binaries
• Time-domain effective-one-body gravitational waveforms for coalescing compact binaries with nonprecessing spins, tides and self-spin effects
• Setting the cornerstone for the IMRPhenomX family of models for gravitational waves from compact binaries: The dominant harmonic for non-precessing quasi-circular black holes
• Surrogate model of hybridized numerical relativity binary black hole waveforms
• Enriching the Symphony of Gravitational Waves from Binary Black Holes by Tuning Higher Harmonics
• Improving the NRTidal model for binary neutron star systems
• First higher-multipole model of gravitational waves from spinning and coalescing black-hole binaries
• Phenomenological model for the gravitational-wave signal from precessing binary black holes with two-spin effects
• Matter imprints in waveform models for neutron star binaries: tidal and self-spin effects
• Fast prediction and evaluation of gravitational waveforms using surrogate models
• A Numerical Relativity Waveform Surrogate Model for Generically Precessing Binary Black Hole Mergers
• Frequency domain reduced order models for gravitational waves from aligned-spin compact binaries
• Including higher order multipoles in gravitational-wave models for precessing binary black holes
• Fast and Accurate Inference on Gravitational Waves from Precessing Compact Binaries
• An artificial neural network framework for reduced order modeling of transient flows
• A Surrogate Model of Gravitational Waveforms from Numerical Relativity Simulations of Precessing Binary Black Hole Mergers
• Searching for Gravitational Waves from Compact Binaries with Precessing Spins
• A multipolar effective one body waveform model for spin-aligned black hole binaries
• Learning Bayesian posteriors with neural networks for gravitational-wave inference
• A novel scheme for rapid parallel parameter estimation of gravitational waves from compact binary coalescences
• Accelerated gravitational-wave parameter estimation with reduced order modeling
• Frequency domain reduced order model of aligned-spin effective-one-body waveforms with higher-order modes
• Modeling the gravitational wave signature of neutron star black hole coalescences: PhenomNSBH
• Parallelized Inference for Gravitational-Wave Astronomy
• Gravitational-wave detection rates for compact binaries formed in isolation: LIGO/Virgo O3 and beyond
• A Multipolar Effective One Body Model for Non-Spinning Black Hole Binaries
• Reduced-order modeling with artificial neurons for gravitational-wave inference
• An aligned-spin neutron-star--black-hole waveform model based on the effective-one-body approach and numerical-relativity simulations
• A Surrogate Model for Gravitational Wave Signals from Comparable- to Large- Mass-Ratio Black Hole Binaries
• Deep-Learning continuous gravitational waves
• Rush the inspiral: efficient Effective One Body time-domain gravitational waveforms
• Gravitational wave parameter estimation with compressed likelihood evaluations
• Accelerating gravitational wave parameter estimation with multi-band template interpolation
• Non-Intrusive Reduced-Order Modeling Using Uncertainty-Aware Deep Neural Networks and Proper Orthogonal Decomposition: Application to Flood Modeling
• Accelerating parameter inference with graphics processing units
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• GPU-accelerated massive black hole binary parameter estimation with LISA
• Rapid Parameter Estimation of Gravitational Waves from Binary Neutron Star Coalescence using Focused Reduced Order Quadrature
• Effectual gravitational-wave template banks for coalescing compact binaries using a hybrid placement algorithm
• Deep learning for clustering of continuous gravitational wave candidates
• A Precessing Numerical Relativity Waveform Surrogate Model for Binary Black Holes: A Gaussian Process Regression Approach
• Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
• Accelerating the evaluation of inspiral-merger-ringdown waveforms with adapted grids
• Gravitational wave population inference with deep flow-based generative network
• Accurate inspiral-merger-ringdown gravitational waveforms for non-spinning black-hole binaries including the effect of subdominant modes
• Black Hole Hunting with LISA
• Gravitational-wave selection effects using neural-network classifiers
• Towards Rapid Parameter Estimation on Gravitational Waves from Compact Binaries using Interpolated Waveforms
• Regression methods in waveform modeling: a comparative study
• Binary Neutron Stars Gravitational Wave Detection Based on Wavelet Packet Analysis And Convolutional Neural Networks
• Optimizing spinning time-domain gravitational waveforms for Advanced LIGO data analysis
• Interpolating compact binary waveforms using the singular value decomposition
• Including mode mixing in a higher-multipole model for gravitational waveforms from nonspinning black-hole binaries
• Interpolation in waveform space: enhancing the accuracy of gravitational waveform families using numerical relativity
• Faster search for long gravitational-wave transients: GPU implementation of the transient F-statistic
• Predicting the properties of black holes merger remnants with Deep Neural Networks
• A Hamiltonian Monte Carlo method for Bayesian Inference of Supermassive Black Hole Binaries
• The gap between theory and practice in function approximation with deep neural networks
• Rapidly evaluating the compact binary likelihood function via interpolation
• Bayesian inference for binary neutron star inspirals using a Hamiltonian Monte Carlo Algorithm
• Improving performance of SEOBNRv3 by $\sim$300x
• Fast and efficient evaluation of gravitational waveforms via reduced-order spline interpolation
• Deep learning merger masses estimation from gravitational waves signals in the frequency domain
• Enhancing gravitational waveform models through dynamic calibration
• Fast prediction and evaluation of eccentric inspirals using reduced-order models
• Acceleration of low-latency gravitational wave searches using Maxwell-microarchitecture GPUs

Cited by in corpus (33)

• SEOBNRv5PHM: Next generation of accurate and efficient multipolar precessing-spin effective-one-body waveforms for binary black holes
• Laying the foundation of the effective-one-body waveform models SEOBNRv5: improved accuracy and efficiency for spinning non-precessing binary black holes
• Eccentric binary black hole surrogate models for the gravitational waveform and remnant properties: comparable mass, nonspinning case
• Parameter estimation with gravitational waves
• The Science of the Einstein Telescope
• Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
• MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
• Machine Learning Gravitational Waves from Binary Black Hole Mergers
• Accelerating multimodal gravitational waveforms from precessing compact binaries with artificial neural networks
• Inference-optimized AI and high performance computing for gravitational wave detection at scale
• Quasinormal modes of dS and AdS Black Holes: Feedforward neural network method
• Combining effective-one-body accuracy and reduced-order-quadrature speed for binary neutron star merger parameter estimation with machine learning
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Using machine learning to parametrize postmerger signals from binary neutron stars
• Density estimation with Gaussian processes for gravitational-wave posteriors
• Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• Probabilistic Model for the Gravitational Wave Signal from Merging Black Holes
• Autoencoder-driven Spiral Representation Learning for Gravitational Wave Surrogate Modelling
• Rapid inference and comparison of gravitational-wave population models with neural variational posteriors
• Inferring Binary Properties from Gravitational Wave Signals
• A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms
• Fast and faithful interpolation of numerical relativity surrogate waveforms using meshfree approximation
• Optimizing Neural Network Surrogate Models: Application to Black Hole Merger Remnants
• AI and extreme scale computing to learn and infer the physics of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers
• Accelerating the time-domain LISA response model with central finite differences and hybridization techniques
• Surrogate modeling of gravitational waves microlensed by spherically symmetric potentials
• Chase Orbits, not Time: A Scalable Paradigm for Long-Duration Eccentric Gravitational-Wave Surrogates
• Deep Residual Error and Bag-of-Tricks Learning for Gravitational Wave Surrogate Modeling
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• Sequence modeling of higher-order wave modes of binary black hole mergers