Classifying the unknown: discovering novel gravitational-wave detector glitches using similarity learning

Abstract

The observation of gravitational waves from compact binary coalescences by LIGO and Virgo has begun a new era in astronomy. A critical challenge in making detections is determining whether loud transient features in the data are caused by gravitational waves or by instrumental or environmental sources. The citizen-science project Gravity Spy has been demonstrated as an efficient infrastructure for classifying known types of noise transients (glitches) through a combination of data analysis performed by both citizen volunteers and machine learning. We present the next iteration of this project, using similarity indices to empower citizen scientists to create large data sets of unknown transients, which can then be used to facilitate supervised machine-learning characterization. This new evolution aims to alleviate a persistent challenge that plagues both citizen-science and instrumental detector work: the ability to build large samples of relatively rare events. Using two families of transient noise that appeared unexpectedly during LIGO's second observing run (O2), we demonstrate the impact that the similarity indices could have had on finding these new glitch types in the Gravity Spy program.

8 pages, 3 figures, 1 table. Updated to match the published version

References in corpus (27)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• Advanced LIGO
• GW151226: Observation of Gravitational Waves from a 22-Solar-Mass Binary Black Hole Coalescence
• GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2
• GW170814: A Three-Detector Observation of Gravitational Waves from a Binary Black Hole Coalescence
• GW170608: Observation of a 19-solar-mass Binary Black Hole Coalescence
• Improving galaxy morphologies for SDSS with Deep Learning
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Machine Learning for the Zwicky Transient Facility
• Mitigation of the instrumental noise transient in gravitational-wave data surrounding GW170817
• Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Transfer learning for galaxy morphology from one survey to another
• A hierarchical method for vetoing noise transients in gravitational-wave detectors
• Classification methods for noise transients in advanced gravitational-wave detectors
• Transient Classification in LIGO data using Difference Boosting Neural Network
• Classification methods for noise transients in advanced gravitational-wave detectors II: performance tests on Advanced LIGO data
• Finding the origin of noise transients in LIGO data with machine learning
• Characterising Transient Noise in the LIGO Detectors
• Parameter Estimation and Model Selection of Gravitational Wave Signals Contaminated by Transient Detector Noise Glitches

Cited by in corpus (24)

• Convolutional neural networks: a magic bullet for gravitational-wave detection?
• Omicron: a tool to characterize transient noise in gravitational-wave detectors
• Discovering features in gravitational-wave data through detector characterization, citizen science and machine learning
• 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
• Application of dictionary learning to denoise LIGO's blip noise transients
• Detection of Gravitational Waves Using Bayesian Neural Networks
• Utilizing aLIGO Glitch Classifications to Validate Gravitational-Wave Candidates
• The Importance of Priors on LIGO-Virgo Parameter Estimation: the Case of Primordial Black Holes
• Generalized Approach to Matched Filtering using Neural Networks
• Improving significance of binary black hole mergers in Advanced LIGO data using deep learning : Confirmation of GW151216
• Gravity Spy: Lessons Learned and a Path Forward
• GWSkyNet: a real-time classifier for public gravitational-wave candidates
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Exploring gravitational-wave detection and parameter inference using Deep Learning methods
• Real-Time Detection of Unmodelled Gravitational-Wave Transients Using Convolutional Neural Networks
• Advances in Machine and Deep Learning for Modeling and Real-time Detection of Multi-Messenger Sources
• SiGMa-Net: Deep learning network to distinguish binary black hole signals from short-duration noise transients
• Application of the independent component analysis to the iKAGRA data
• New methods to assess and improve LIGO detector duty cycle
• Computational Techniques for Parameter Estimation of Gravitational Wave Signals
• Improved binary black hole searches through better discrimination against noise transients
• Boosting the Efficiency of Parametric Detection with Hierarchical Neural Networks
• Extract non-Gaussian Features in Gravitational Wave Observation Data Using Self-Supervised Learning