Waves in a Forest: A Random Forest Classifier to Distinguish between Gravitational Waves and Detector Glitches

TL;DR

This paper presents a new machine learning approach using a random forest classifier to effectively distinguish between gravitational wave signals and detector glitches based on their posterior distributions, improving detection confidence.

Contribution

The study introduces a novel statistical method leveraging posterior distributions and random forests to differentiate signals from glitches in gravitational wave data, achieving over 93% accuracy.

Findings

Random forests can distinguish signals from glitches with high accuracy.

Posterior distributions contain discriminative features for classification.

The method identifies regions where misclassification is more likely.

Abstract

The LIGO-Virgo-KAGRA (LVK) network of gravitational-wave (GW) detectors have observed many tens of compact binary mergers to date. Transient, non-Gaussian noise excursions, known as "glitches", can impact signal detection in various ways. They can imitate true signals as well as reduce the confidence of real signals. In this work, we introduce a novel statistical tool to distinguish astrophysical signals from glitches, using their inferred source parameter posterior distributions as a feature set. By modelling both simulated GW signals and real detector glitches with a gravitational waveform model, we obtain a diverse set of posteriors which are used to train a random forest classifier. We show that random forests can identify differences in the posterior distributions for signals and glitches, aggregating these differences to tell apart signals from common glitch types with high accuracy of over 93%. We conclude with a discussion on the regions of parameter space where the classifier is prone to making misclassifications, and the different ways of implementing this tool into LVK analysis pipelines.