Detecting Gravitational-waves from Extreme Mass Ratio Inspirals using Convolutional Neural Networks

Abstract

Extreme mass ratio inspirals (EMRIs) are among the most interesting gravitational wave (GW) sources for space-borne GW detectors. However, successful GW data analysis remains challenging due to many issues, ranging from the difficulty of modeling accurate waveforms, to the impractically large template bank required by the traditional matched filtering search method. In this work, we introduce a proof-of-principle approach for EMRI detection based on convolutional neural networks (CNNs). We demonstrate the performance with simulated EMRI signals buried in Gaussian noise. We show that over a wide range of physical parameters, the network is effective for EMRI systems with a signal-to-noise ratio larger than 50, and the performance is most strongly related to the signal-to-noise ratio. The method also shows good generalization ability towards different waveform models. Our study reveals the potential applicability of machine learning technology like CNNs towards more realistic EMRI data analysis.

12 pages, 4 figures

References in corpus (22)

• The NumPy array: a structure for efficient numerical computation
• Intermediate and Extreme Mass-Ratio Inspirals -- Astrophysics, Science Applications and Detection using LISA
• The TianQin project: current progress on science and technology
• Using LISA EMRI sources to test off-Kerr deviations in the geometry of massive black holes
• Science with the TianQin Observatory: Preliminary results on Galactic double white dwarf binaries
• Gravitational radiation reaction and inspiral waveforms in the adiabatic limit
• Science with the TianQin observatory: Preliminary results on stellar-mass binary black holes
• Science with the TianQin observatory: Preliminary result on extreme-mass-ratio inspirals
• Testing Chern-Simons Modified Gravity with Gravitational-Wave Detections of Extreme-Mass-Ratio Binaries
• Enabling real-time multi-messenger astrophysics discoveries with deep learning
• Detection of gravitational-wave signals from binary neutron star mergers using machine learning
• An algorithm for detection of extreme mass ratio inspirals in LISA data
• Denoising Gravitational Waves with Enhanced Deep Recurrent Denoising Auto-Encoders
• A Constrained Metropolis-Hastings Search for EMRIs in the Mock LISA Data Challenge 1B
• Improved deep learning techniques in gravitational-wave data analysis
• Improved time-frequency analysis of extreme-mass-ratio inspiral signals in mock LISA data
• SOAP: A generalised application of the Viterbi algorithm to searches for continuous gravitational-wave signals
• Gravitational waves from extreme mass ratio inspirals around bumpy black holes
• 2 Fast 2 Fiducial: Gaussian processes for the interpolation and marginalization of waveform error in extreme-mass-ratio-inspiral parameter estimation
• Detecting extreme mass ratio inspiral events in LISA data using the Hierarchical Algorithm for Clusters and Ridges (HACR)
• Bayesian inference on EMRI signals using low frequency approximations
• Highly eccentric EMRI waveforms via fast self-forced inspirals

Cited by in corpus (23)

• Gravitational Wave Astronomy With TianQin
• Space-based gravitational wave signal detection and extraction with deep neural network
• Extreme-mass-ratio burst detection with TianQin
• Identification of Gravitational-waves from Extreme Mass Ratio Inspirals
• LISA stellar-mass black hole searches with semicoherent and particle-swarm methods
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Detecting Strong Gravitational Lensing of Gravitational Waves with TianQin
• Measuring the Hubble Constant Using Strongly Lensed Gravitational Wave Signals
• Dilated convolutional neural network for detecting extreme-mass-ratio inspirals
• Testing gravity with Extreme-Mass-Ratio Inspirals
• A GPU-accelerated semi-coherent hierarchical search for stellar-mass binary inspiral signals in LISA
• Observing white dwarf tidal stripping with TianQin gravitational wave observatory
• Matched filtering for gravitational wave detection without template bank driven by deep learning template prediction model bank
• GWSpace: a multi-mission science data simulator for space-based gravitational wave detection
• Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
• SgrA${}^{\ast }$ spin and mass estimates through the detection of an extremely large mass-ratio inspiral
• Searching for gravitational waves from stellar-mass binary black holes early inspiral
• Constraining the Deviation of Kerr Metric via Bumpy Parameterization and Particle Swarm Optimization in Extreme Mass-Ratio Inspirals
• Extracting overlapping gravitational-wave signals of galactic compact binaries: a mini review
• Sensitivity toward dark matter annihilation imprints on 21-cm signal with SKA-Low: A convolutional neural network approach
• Searching for stellar-origin binary black holes in LISA Data Challenge 1b: Yorsh
• Constructing a gravitational wave analysis pipeline for extremely large mass ratio inspirals
• Global time-frequency search for stellar-mass binary black holes in LISA