VIGILant: an automatic classification pipeline for glitches in the Virgo detector

TL;DR

VIGILant is an automated pipeline that classifies and visualizes glitches in the Virgo gravitational-wave detector, improving detection accuracy and operational monitoring using machine learning models.

Contribution

The paper introduces VIGILant, a new machine learning-based pipeline for glitch classification in Virgo data, combining interpretability and high performance.

Findings

ResNet34 achieved an F1 score of 0.9772 and accuracy of 0.9833.

The pipeline operates with inference times of tens of milliseconds per glitch.

VIGILant has been deployed for daily use at the Virgo site since O4c.

Abstract

Glitches frequently contaminate data in gravitational-wave detectors, complicating the observation and analysis of astrophysical signals. This work introduces VIGILant, an automatic pipeline for classification and visualization of glitches in the Virgo detector. Using a curated dataset of Virgo O3b glitches, two machine learning approaches are evaluated: tree-based models (Decision Tree, Random Forest and XGBoost) using structured Omicron parameters, and Convolutional Neural Networks (ResNet) trained on spectrogram images. While tree-based models offer higher interpretability and fast training, the ResNet34 model achieved superior performance, reaching a F1 score of 0.9772 and accuracy of 0.9833 in the testing set, with inference times of tens of milliseconds per glitch. The pipeline has been deployed for daily operation at the Virgo site since observing run O4c, providing the Virgo collaboration with an interactive dashboard to monitor glitch populations and detector behavior. This allows to identify low-confidence predictions, highlighting glitches requiring further attention.