Premerger detection of massive black hole binaries using deep learning
arXiv:2402.16282 · doi:10.1103/PhysRevD.109.123031
Abstract
Coalescing massive black hole binaries (MBHBs) are one of primary sources for space-based gravitational wave (GW) observations. The mergers of these binaries are expected to give rise to detectable electromagnetic (EM) emissions with a narrow time window. The premerger detection of GW signals is vital for follow-up EM observations. The conventional approach for searching GW signals involves high computational costs. In this study, we present a deep learning model to search for GW signals from MBHBs. Our model is able to process 4.7 days of simulated data within 0.01 seconds and detect GW signals several hours to days before the final merger. The model provides the possibility of the coincident GW and EM detection of MBHBs.
9 pages, 7 figures
References in corpus (31)
- GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
- GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run
- The NANOGrav 15-year Data Set: Evidence for a Gravitational-Wave Background
- Search for an isotropic gravitational-wave background with the Parkes Pulsar Timing Array
- The NANOGrav 12.5-year Data Set: Search For An Isotropic Stochastic Gravitational-Wave Background
- Intermediate and Extreme Mass-Ratio Inspirals -- Astrophysics, Science Applications and Detection using LISA
- Characterization of the stochastic signal originating from compact binaries populations as measured by LISA
- Electromagnetic Counterparts to Massive Black Hole Mergers
- Forecast for cosmological parameter estimation with gravitational-wave standard sirens from the LISA-Taiji network
- Detection of gravitational-wave signals from binary neutron star mergers using machine learning
- MLGWSC-1: The first Machine Learning Gravitational-Wave Search Mock Data Challenge
- Minidisk dynamics in accreting, spinning black hole binaries: Simulations in full general relativity
- The Taiji-TianQin-LISA network: Precisely measuring the Hubble constant using both bright and dark sirens
- Deep-Learning Continuous Gravitational Waves: Multiple detectors and realistic noise
- Catching Super Massive Black Hole Binaries Without a Net
- Training Strategies for Deep Learning Gravitational-Wave Searches
- Deep Residual Networks for Gravitational Wave Detection
- Improved deep learning techniques in gravitational-wave data analysis
- Space-based gravitational wave signal detection and extraction with deep neural network
- LSTM and CNN application for core-collapse supernova search in gravitational wave real data
- Ensemble of Deep Convolutional Neural Networks for real-time gravitational wave signal recognition
- Search for gravitational-wave bursts in the third Advanced LIGO-Virgo run with coherent WaveBurst enhanced by Machine Learning
- Extreme-mass-ratio burst detection with TianQin
- Rapid search for massive black hole binary coalescences using deep learning
- Exploring gravitational-wave detection and parameter inference using Deep Learning methods
- Use of Excess Power Method and Convolutional Neural Network in All-Sky Search for Continuous Gravitational Waves
- Gravitational-Wave Searches for Cosmic String Cusps in Einstein Telescope Data using Deep Learning
- Dilated convolutional neural network for detecting extreme-mass-ratio inspirals
- SiGMa-Net: Deep learning network to distinguish binary black hole signals from short-duration noise transients
- Deep learning for intermittent gravitational wave signals
- Novel neural-network architecture for continuous gravitational waves
Cited by in corpus (5)
- Gravitational Wave Astronomy With TianQin
- Applications of machine learning in gravitational wave research with current interferometric detectors
- A GPU-accelerated semi-coherent hierarchical search for stellar-mass binary inspiral signals in LISA
- Fast detection and reconstruction of merging Massive Black Hole Binary signals
- Accurate and efficient simulation-based inference for massive black-hole binaries with LISA