Noise Reduction in Gravitational-wave Data via Deep Learning

Abstract

With the advent of gravitational wave astronomy, techniques to extend the reach of gravitational wave detectors are desired. In addition to the stellar-mass black hole and neutron star mergers already detected, many more are below the surface of the noise, available for detection if the noise is reduced enough. Our method (DeepClean) applies machine learning algorithms to gravitational wave detector data and data from on-site sensors monitoring the instrument to reduce the noise in the time-series due to instrumental artifacts and environmental contamination. This framework is generic enough to subtract linear, non-linear, and non-stationary coupling mechanisms. It may also provide handles in learning about the mechanisms which are not currently understood to be limiting detector sensitivities. The robustness of the noise reduction technique in its ability to efficiently remove noise with no unintended effects on gravitational-wave signals is also addressed through software signal injection and parameter estimation of the recovered signal. It is shown that the optimal SNR ratio of the injected signal is enhanced by $\sim 21.6\%$ and the recovered parameters are consistent with the injected set. We present the performance of this algorithm on linear and non-linear noise sources and discuss its impact on astrophysical searches by gravitational wave detectors.

12 pages, 7 figures

References in corpus (32)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Observation of Gravitational Waves from a Binary Black Hole Merger
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• Advanced LIGO
• dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
• A guide to convolution arithmetic for deep learning
• Bilby: A user-friendly Bayesian inference library for gravitational-wave astronomy
• Frequency-domain gravitational waves from non-precessing black-hole binaries. II. A phenomenological model for the advanced detector era
• Interferometer design of the KAGRA gravitational wave detector
• Frequency-domain gravitational waves from non-precessing black-hole binaries. I. New numerical waveforms and anatomy of the signal
• A simple model of complete precessing black-hole-binary gravitational waveforms
• A guide to LIGO-Virgo detector noise and extraction of transient gravitational-wave signals
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Characterization of transient noise in Advanced LIGO relevant to gravitational wave signal GW150914
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• IndIGO and LIGO-India: Scope and Plans for Gravitational Wave Research and Precision Metrology in India
• Machine-learning non-stationary noise out of gravitational wave detectors
• Improving the Sensitivity of Advanced LIGO Using Noise Subtraction
• Gravitational Waves: Sources, Detectors and Searches
• Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data
• Improving astrophysical parameter estimation via offline noise subtraction for Advanced LIGO
• The upgrade of GEO600
• Transient Classification in LIGO data using Difference Boosting Neural Network
• Regression of Environmental Noise in LIGO Data
• Implications of dedicated seismometer measurements on Newtonian-noise cancellation for Advanced LIGO
• Towards a first design of a Newtonian-noise cancellation system for Advanced LIGO
• Increasing LIGO sensitivity by feedforward subtraction of auxiliary length control noise
• Global Feed-Forward Vibration Isolation in a km scale Interferometer
• Tackling excess noise from bilinear and nonlinear couplings in gravitational-wave interferometers
• Bilinear noise subtraction at the GEO 600 observatory

Cited by in corpus (36)

• Applications and Techniques for Fast Machine Learning in Science
• Subtracting glitches from gravitational-wave detector data during the third observing run
• Modeling compact binary signals and instrumental glitches in gravitational wave data
• Data quality up to the third observing run of Advanced LIGO: Gravity Spy glitch classifications
• Uncertainty limits on neutron star radius measurements with gravitational waves
• Site-selection criteria for the Einstein Telescope
• Accurate modeling and mitigation of overlapping signals and glitches in gravitational-wave data
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Early warning of coalescing neutron-star and neutron-star-black-hole binaries from nonstationary noise background using neural networks
• Space-based gravitational wave signal detection and extraction with deep neural network
• Inference-optimized AI and high performance computing for gravitational wave detection at scale
• Ensemble of Deep Convolutional Neural Networks for real-time gravitational wave signal recognition
• An autoencoder neural network integrated into gravitational-wave burst searches to improve the rejection of noise transients
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
• 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
• Exploring Supernova Gravitational Waves with Machine Learning
• Bayesian approach to radio frequency interference mitigation
• Matched filtering for gravitational wave detection without template bank driven by deep learning template prediction model bank
• Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
• 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
• Predicting the motion of a high-Q pendulum subject to seismic perturbations using machine learning
• 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
• Machine Learning for Quantum-Enhanced Gravitational-Wave Observatories
• All-sky search for long-duration gravitational-wave bursts in the third Advanced LIGO and Advanced Virgo run
• Application of a new transient-noise analysis tool for an unmodeled gravitational-wave search pipeline
• Impact of noise transients on gravitational-wave burst detection efficiency of the BayesWave pipeline with multi-detector networks
• Architectural Optimization and Feature Learning for High-Dimensional Time Series Datasets
• Application of Non-Linear Noise Regression in the Virgo Detector
• Extract non-Gaussian Features in Gravitational Wave Observation Data Using Self-Supervised Learning
• Auto-encoder model for faster generation of effective one-body gravitational waveform approximations
• Nonlinear Independent Component Analysis Scheme and its application to gravitational wave data analysis
• Graph-based Summary Statistics for Revealing the Stochastic Gravitational Wave Background in Pulsar Timing Arrays