Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning

Abstract

The observation of gravitational waves is hindered by the presence of transient noise (glitches). We study data from the third observing run of the Advanced LIGO detectors, and identify new glitch classes. Using training sets assembled by monitoring of the state of the detector, and by citizen-science volunteers, we update the Gravity Spy machine-learning algorithm for glitch classification. We find that a new glitch class linked to ground motion at the detector sites is especially prevalent, and identify two subclasses of this linked to different types of ground motion. Reclassification of data based on the updated model finds that 27 % of all transient noise at LIGO Livingston belongs to the new glitch class, making it the most frequent source of transient noise at that site. Our results demonstrate both how glitch classification can reveal potential improvements to gravitational-wave detectors, and how, given an appropriate framework, citizen-science volunteers may make discoveries in large data sets.

arXiv comment26 pages, 10 figures

References in corpus (37)

• 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
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• Astrophysical Implications of the Binary Black-Hole Merger GW150914
• Observation of gravitational waves from two neutron star-black hole coalescences
• Sensitivity and Performance of the Advanced LIGO Detectors in the Third Observing Run
• A guide to LIGO-Virgo detector noise and extraction of transient gravitational-wave signals
• 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
• Galaxy Zoo : 'Hanny's Voorwerp', a quasar light echo?
• Multiresolution techniques for the detection of gravitational-wave bursts
• LIGO Detector Characterization in the Second and Third Observing Runs
• Planet Hunters: A Transiting Circumbinary Planet in a Quadruple Star System
• Seismic isolation of Advanced LIGO: Review of strategy, instrumentation and performance
• Enhancing Gravitational-Wave Science with Machine Learning
• Prospects for doubling the range of Advanced LIGO
• Effects of Data Quality Vetoes on a Search for Compact Binary Coalescences in Advanced LIGO's First Observing Run
• Blip glitches in Advanced LIGO data
• Distance measures in gravitational-wave astrophysics and cosmology
• Mitigation of the instrumental noise transient in gravitational-wave data surrounding GW170817
• Reducing Scattered Light in LIGO's Third Observing Run
• Omicron: a tool to characterize transient noise in gravitational-wave detectors
• Search for intermediate mass black hole binaries in the first and second observing runs of the Advanced LIGO and Virgo network
• Parameter Estimation and Model Selection of Gravitational Wave Signals Contaminated by Transient Detector Noise Glitches
• Characterising Transient Noise in the LIGO Detectors
• Detection and Parameter Estimation of Gravitational Waves from Binary Neutron-Star Mergers in Real LIGO Data using Deep Learning
• Modeling compact binary signals and instrumental glitches in gravitational wave data
• Classifying the unknown: discovering novel gravitational-wave detector glitches using similarity learning
• Application of dictionary learning to denoise LIGO's blip noise transients
• A 3 Gyr White Dwarf with Warm Dust Discovered via the Backyard Worlds: Planet 9 Citizen Science Project
• Utilizing aLIGO Glitch Classifications to Validate Gravitational-Wave Candidates
• Effect of sine-Gaussian glitches on searches for binary coalescence
• GWSkyNet: a real-time classifier for public gravitational-wave candidates
• Improving the Robustness of the Advanced LIGO Detectors to Earthquakes

Cited by in corpus (44)

• GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run
• GWTC-2.1: Deep Extended Catalog of Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• Tests of General Relativity with GWTC-3
• Search for intermediate mass black hole binaries in the third observing run of Advanced LIGO and Advanced Virgo
• LIGO Detector Characterization in the first half of the fourth Observing run
• Data quality up to the third observing run of Advanced LIGO: Gravity Spy glitch classifications
• Follow-up Analyses to the O3 LIGO-Virgo-KAGRA Lensing Searches
• Accurate modeling and mitigation of overlapping signals and glitches in gravitational-wave data
• Impact of noise transients on low latency gravitational-wave event localisation
• Parameterised population models of transient non-Gaussian noise in the LIGO gravitational-wave detectors
• Gravity Spy: Lessons Learned and a Path Forward
• Transient glitch mitigation in Advanced LIGO data with $\text{glitschen}$
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Gaussian Processes for Glitch-robust Gravitational-wave Astronomy
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Generating transient noise artifacts in gravitational-wave detector data with generative adversarial networks
• Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow
• Unsupervised Learning Architecture for Classifying the Transient Noise of Interferometric Gravitational-wave Detectors
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
• Assessing and Mitigating the Impact of Glitches on Gravitational-Wave Parameter Estimation: a Model Agnostic Approach
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• Establishing significance of gravitational-wave signals from a single observatory in the PyCBC offline search
• Convolutional neural network for gravitational-wave early alert: Going down in frequency
• SiGMa-Net: Deep learning network to distinguish binary black hole signals from short-duration noise transients
• Bayesian modelling of scattered light in the LIGO interferometers
• ArchEnemy: Removing scattered-light glitches from gravitational wave data
• Gwadaptive_scattering: an automated pipeline for scattered light noise characterization
• Localization of gravitational waves using machine learning
• Neural network time-series classifiers for gravitational-wave searches in single-detector periods
• Towards a robust and reliable deep learning approach for detection of compact binary mergers in gravitational wave data
• Noise in the LIGO Livingston Gravitational Wave Observatory due to Trains
• Robust inference of gravitational wave source parameters in the presence of noise transients using normalizing flows
• Training Process of Unsupervised Learning Architecture for Gravity Spy Dataset
• Inferring the Astrophysical Population of Gravitational Wave Sources in the Presence of Noise Transients
• A convolutional neural network to distinguish glitches from minute-long gravitational wave transients
• No Glitch in the Matrix: Robust Reconstruction of Gravitational Wave Signals Under Noise Artifacts
• Machine learning applications in astrophysics: Photometric redshift estimation
• Nonlinear noise regression in gravitational-wave detectors with convolutional neural networks
• Joint inference for gravitational wave signals and glitches using a data-informed glitch model
• Improved binary black hole searches through better discrimination against noise transients
• Learning to detect continuous gravitational waves: an open data-analysis competition
• Improved Binary Black Hole Search Discriminator from the Singular Value Decomposition of Non-Gaussian Noise Transients
• Architectural Optimization and Feature Learning for High-Dimensional Time Series Datasets
• Extract non-Gaussian Features in Gravitational Wave Observation Data Using Self-Supervised Learning