Physics-inspired deep learning to characterize the signal manifold of quasi-circular, spinning, non-precessing binary black hole mergers
arXiv:2004.09524 · doi:10.1016/j.physletb.2020.135628
Abstract
The spin distribution of binary black hole mergers contains key information concerning the formation channels of these objects, and the astrophysical environments where they form, evolve and coalesce. To quantify the suitability of deep learning to characterize the signal manifold of quasi-circular, spinning, non-precessing binary black hole mergers, we introduce a modified version of WaveNet trained with a novel optimization scheme that incorporates general relativistic constraints of the spin properties of astrophysical black holes. The neural network model is trained, validated and tested with 1.5 million waveforms generated within the regime of validity of NRHybSur3dq8, i.e., mass-ratios and individual black hole spins . Using this neural network model, we quantify how accurately we can infer the astrophysical parameters of black hole mergers in the absence of noise. We do this by computing the overlap between waveforms in the testing data set and the corresponding signals whose mass-ratio and individual spins are predicted by our neural network. We find that the convergence of high performance computing and physics-inspired optimization algorithms enable an accurate reconstruction of the mass-ratio and individual spins of binary black hole mergers across the parameter space under consideration. This is a significant step towards an informed utilization of physics-inspired deep learning models to reconstruct the spin distribution of binary black hole mergers in realistic detection scenarios.
arXiv comment25 pages, 12 figures, 1 appendix, 1 Interactive visualization at https://khanx169.github.io/smr_bbm_v2/interactive_results.html
References in corpus (64)
- WaveNet: A Generative Model for Raw Audio
- GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
- GW190425: Observation of a Compact Binary Coalescence with Total Mass
- Properties of the Binary Black Hole Merger GW150914
- GW190412: Observation of a Binary-Black-Hole Coalescence with Asymmetric Masses
- Coalescence of Two Spinning Black Holes: An Effective One-Body Approach
- Merging black hole binaries in galactic nuclei: implications for advanced-LIGO detections
- Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
- The Formation of Eccentric Compact Binary Inspirals and the Role of Gravitational Wave Emission in Binary-Single Stellar Encounters
- Eccentric Black Hole Mergers Forming in Globular Clusters
- Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
- Surrogate model of hybridized numerical relativity binary black hole waveforms
- Black Hole Mergers in Galactic Nuclei Induced by the Eccentric Kozai-Lidov Effect
- Post-Newtonian Dynamics in Dense Star Clusters: Formation, Masses, and Merger Rates of Highly-Eccentric Black Hole Binaries
- Post-Newtonian Dynamics in Dense Star Clusters: Highly-Eccentric, Highly-Spinning, and Repeated Binary Black Hole Mergers
- Eccentric Black Hole Mergers in Dense Star Clusters: The Role of Binary-Binary Encounters
- Matching matched filtering with deep networks in gravitational-wave astronomy
- Two stellar-mass black holes in the globular cluster M22
- Black hole growth through hierarchical black hole mergers in dense star clusters: implications for gravitational wave detections
- Black hole mergers and blue stragglers from hierarchical triples formed in globular clusters
- Black hole triple dynamics: breakdown of the orbit average approximation and implications for gravitational wave detections
- Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
- A Data Ecosystem to Support Machine Learning in Materials Science
- Black Hole Mergers From Globular Clusters Observable by LISA I: Eccentric Sources Originating From Relativistic -body Dynamics
- A waveform model for eccentric binary black hole based on effective-one-body-numerical-relativity (EOBNR) formalism
- On the rate of black hole binary mergers in galactic nuclei due to dynamical hardening
- Gravitational-wave parameter estimation with autoregressive neural network flows
- Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
- Eccentric, nonspinning, inspiral, Gaussian-process merger approximant for the detection and characterization of eccentric binary black hole mergers
- Convolutional neural networks: a magic bullet for gravitational-wave detection?
- Accurate and efficient waveforms for compact binaries on eccentric orbits
- Using spin to understand the formation of LIGO's black holes
- An eccentric binary black hole inspiral-merger-ringdown gravitational waveform model from numerical relativity and post-Newtonian theory
- Complete waveform model for compact binaries on eccentric orbits
- On the Assembly Rate of Highly Eccentric Binary Black Hole Mergers
- MOCCA-SURVEY Database I: Eccentric Black Hole Mergers During Binary-Single Interactions In Globular Clusters
- Foundations of an effective-one-body model for coalescing binaries on eccentric orbits
- Gravitational Wave Denoising of Binary Black Hole Mergers with Deep Learning
- Post-Newtonian Dynamics in Dense Star Clusters: Binary Black Holes in the LISA Band
- Can we measure individual black-hole spins from gravitational-wave observations?
- Black Hole Mergers From Globular Clusters Observable by LISA II: Resolved Eccentric Sources and the Gravitational Wave Background
- Multiple stellar-mass black holes in globular clusters: theoretical confirmation
- Enabling real-time multi-messenger astrophysics discoveries with deep learning
- An Analytical Portrait of Binary Mergers in Hierarchical Triple Systems
- Effect of eccentricity on binary neutron star searches in Advanced LIGO
- Detection of eccentric supermassive black hole binaries with pulsar timing arrays: Signal-to-noise ratio calculations
- Induced Ellipticity for Inspiraling Binary Systems
- Measurement Accuracy of Inspiraling Eccentric Neutron Star and Black Hole Binaries Using Gravitational Waves
- Accuracy of Estimating Highly Eccentric Binary Black Hole Parameters with Gravitational-Wave Detections
- Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors
- Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
- Influence of conservative corrections on parameter estimation for extreme-mass-ratio inspirals
- Parameter estimation for inspiraling eccentric compact binaries including pericenter precession
- Topology of Black Hole Binary-Single Interactions
- Physics of eccentric binary black hole mergers: A numerical relativity perspective
- Application of dictionary learning to denoise LIGO's blip noise transients
- Fusing numerical relativity and deep learning to detect higher-order multipole waveforms from eccentric binary black hole mergers
- Double Gravitational Wave Mergers
- How Post-Newtonian Dynamics Shape the Distribution of Stationary Binary Black Hole LISA Sources in nearby Globular Clusters
- Characterization of numerical relativity waveforms of eccentric binary black hole mergers
- Implementing Tidal and Gravitational Wave Energy Losses in Few-body Codes: A Fast and Easy Drag Force Model
- Black Hole Mergers from Globular Clusters Observable by LISA and LIGO: Results from post-Newtonian Binary-Single Scatterings
- Python Open Source Waveform Extractor (POWER): An open source, Python package to monitor and post-process numerical relativity simulations
- Use of conditional variational auto encoder to analyze ringdown gravitational waves
Cited by in corpus (12)
- Quantum Machine Learning for Chemistry and Physics
- FAIR for AI: An interdisciplinary and international community building perspective
- Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
- Convergence of Artificial Intelligence and High Performance Computing on NSF-supported Cyberinfrastructure
- Machine Learning Gravitational Waves from Binary Black Hole Mergers
- Deep Learning Ensemble for Real-time Gravitational Wave Detection of Spinning Binary Black Hole Mergers
- Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
- Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
- 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
- Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers
- Genetic-algorithm-optimized neural networks for gravitational wave classification
- Statistically-informed deep learning for gravitational wave parameter estimation