GWitchHunters: Machine Learning and citizen science to improve the performance of Gravitational Wave detector

Abstract

The Gravitational waves have opened a new window on the Universe and paved the way to a new era of multimessenger observations of cosmic sources. Second-generation ground-based detectors such as Advanced LIGO and Advanced Virgo have been extremely successful in detecting gravitational wave signals from coalescence of black holes and/or neutron stars. However, in order to reach the required sensitivities, the background noise must be investigated and removed. In particular, transient noise events called "glitches" can affect data quality and mimic real astrophysical signals, and it is therefore of paramount importance to characterize them and find their origin, a task that will support the activities of detector characterization of Virgo and other interferometers. Machine learning is one of the most promising approaches to characterize and remove noise glitches in real time, thus improving the sensitivity of interferometers. A key input to the preparation of a training dataset for these machine learning algorithms can originate from citizen science initiatives, where volunteers contribute to classify and analyze signals collected by detectors. We will present GWitchHunters, a new citizen science project focused on the study of gravitational wave noise, that has been developed within the REINFORCE project (a "Science With And For Society" project funded under the EU's H2020 program). We will present the project, its development and the key tasks that citizens are participating in, as well as its impact on the study of noise in the Advanced Virgo detector.

arXiv comment5 pages, 1 figures, Contribution to Proceedings of the 15 Pisa Meeting on Advanced Detectors

References in corpus (8)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Advanced LIGO
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• Characterization of the LIGO detectors during their sixth science run
• Gravity Spy: Integrating Advanced LIGO Detector Characterization, Machine Learning, and Citizen Science
• Image-based deep learning for classification of noise transients in gravitational wave detectors
• Classification methods for noise transients in advanced gravitational-wave detectors

Cited by in corpus (9)

• The Science of the Einstein Telescope
• Possible Causes of False General Relativity Violations in Gravitational Wave Observations
• Gravity Spy: Lessons Learned and a Path Forward
• 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
• Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
• Classification uncertainty for transient gravitational-wave noise artefacts with optimised conformal prediction
• Joint inference for gravitational wave signals and glitches using a data-informed glitch model
• Learning to detect continuous gravitational waves: an open data-analysis competition