Space-based gravitational wave signal detection and extraction with deep neural network
arXiv:2207.07414 · doi:10.1038/s42005-023-01334-6
Abstract
Space-based gravitational wave (GW) detectors will be able to observe signals from sources that are otherwise nearly impossible from current ground-based detection. Consequently, the well established signal detection method, matched filtering, will require a complex template bank, leading to a computational cost that is too expensive in practice. Here, we develop a high-accuracy GW signal detection and extraction method for all space-based GW sources. As a proof of concept, we show that a science-driven and uniform multi-stage self-attention-based deep neural network can identify synthetic signals that are submerged in Gaussian noise. Our method exhibits a detection rate exceeding 99% in identifying signals from various sources, with the signal-to-noise ratio at 50, at a false alarm rate of 1%. while obtaining at least 95% similarity compared with target signals. We further demonstrate the interpretability and strong generalization behavior for several extended scenarios.
arXiv comment19 pages, 7 figures
References in corpus (47)
- Observation of Gravitational Waves from a Binary Black Hole Merger
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- TianQin: a space-borne gravitational wave detector
- Tests of general relativity with GW150914
- The construction and use of LISA sensitivity curves
- Detection, Measurement and Gravitational Radiation
- 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
- Science with the space-based interferometer eLISA. I: Supermassive black hole binaries
- Upper Limits on the Isotropic Gravitational-Wave Background from Advanced LIGO's and Advanced Virgo's Third Observing Run
- BayesWave: Bayesian Inference for Gravitational Wave Bursts and Instrument Glitches
- Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
- New Horizons for Fundamental Physics with LISA
- Coherent method for detection of gravitational wave bursts
- Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
- Real-time gravitational-wave science with neural posterior estimation
- Matching matched filtering with deep networks in gravitational-wave astronomy
- Reconstructing the spectral shape of a stochastic gravitational wave background with LISA
- Seismic isolation of Advanced LIGO: Review of strategy, instrumentation and performance
- FastEMRIWaveforms: New tools for millihertz gravitational-wave data analysis
- Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
- LISA verification binaries with updated distances from Gaia Data Release 2
- Improved reconstruction of a stochastic gravitational wave background with LISA
- The Fast and the Fiducial: Augmented kludge waveforms for detecting extreme-mass-ratio inspirals
- Formation Rate of Extreme Mass Ratio Inspirals in Active Galactic Nuclei
- Real-Time Detection of Gravitational Waves from Binary Neutron Stars using Artificial Neural Networks
- Gravitational Wave Denoising of Binary Black Hole Mergers with Deep Learning
- Image-based deep learning for classification of noise transients in gravitational wave detectors
- Gravitational wave signal recognition of O1 data by deep learning
- Noise Reduction in Gravitational-wave Data via Deep Learning
- A higher-multipole gravitational waveform model for an eccentric binary black holes based on the effective-one-body-numerical-relativity formalism
- Accreting Double white dwarf binaries: Implications for LISA
- Finding the origin of noise transients in LIGO data with machine learning
- Improved analytic extreme-mass-ratio inspiral model for scoping out eLISA data analysis
- Deep learning for multimessenger core-collapse supernova detection
- Efficient Gravitational-wave Glitch Identification from Environmental Data Through Machine Learning
- Denoising of gravitational wave signals via dictionary learning algorithms
- Detecting Gravitational-waves from Extreme Mass Ratio Inspirals using Convolutional Neural Networks
- Extraction of Binary Black Hole Gravitational Wave Signals from Detector Data Using Deep Learning
- Resolving Galactic binaries in LISA data using particle swarm optimization and cross-validation
- Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders
- Denoising Gravitational Waves using Deep Learning with Recurrent Denoising Autoencoders
- Black Hole Hunting with LISA
- Total-variation-based methods for gravitational wave denoising
- Rapid search for massive black hole binary coalescences using deep learning
- Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
- Space-based Gravitational Wave Observatories
Cited by in corpus (13)
- Applications of machine learning in gravitational wave research with current interferometric detectors
- Dilated convolutional neural network for detecting extreme-mass-ratio inspirals
- Premerger detection of massive black hole binaries using deep learning
- Robust inference of gravitational wave source parameters in the presence of noise transients using normalizing flows
- Gravitational Wave Signal Extraction Against Non-Stationary Instrumental Noises with Deep Neural Network
- A novel stacked hybrid autoencoder for imputing LISA data gaps
- Searching for gravitational waves from stellar-mass binary black holes early inspiral
- Compact Binary Coalescence Gravitational Wave Signals Counting and Separation
- Search for exotic gravitational wave signals beyond general relativity using deep learning
- GWAI: Artificial Intelligence Platform for Enhanced Gravitational Wave Data Analysis
- Denoising gravitational wave with deep learning in the time-frequency domain
- Parameter inference of millilensed gravitational waves using neural spline flows
- Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra