NNETFIX: An artificial neural network-based denoising engine for gravitational-wave signals

• DOI: 10.48550/arxiv.2101.04712
• Publication Date: 2021-01-01
• Authors: K. Mogushi; R. Quitzow-James; M. Cavaglià; Sumeet Kulkarni; F. J. Hayes
• Keywords: Glitch; SIGNAL (programming language)

Instrumental and environmental transient noise bursts in gravitational-wave detectors, or glitches, may impair astrophysical observations by adversely affecting the sky localization parameter estimation of signals. Denoising detector data is especially relevant during low-latency operations because electromagnetic follow-up candidate detections requires accurate, rapid inference sources. NNETFIX a machine learning-based algorithm designed to remove glitches detected coincidence with uses artificial neural networks estimate portion lost due presence glitch, which allows recalculation signal. The denoised be significantly more accurate than obtained from original removing impacted glitch. We test simulated scenarios binary black hole coalescence signals discuss potential for its use future LIGO-Virgo-KAGRA searches. In majority cases high signal-to-noise ratio, we find that overlap maps better glitch removed.