Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces VIGILant, an automated pipeline for classifying glitches in the Virgo gravitational wave detector using machine learning. The pipeline compares tree-based models using Omicron parameters with Convolutional Neural Networks (ResNet) trained on spectrograms. Results show that a ResNet34 model achieves a F1 score of 0.9772 and accuracy of 0.9833, outperforming tree-based methods, and has been deployed for daily operation at the Virgo site.
A ResNet34 model can classify gravitational wave detector glitches with 98% accuracy, enabling real-time monitoring and identification of anomalies.
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.