A classifier for gravitational-wave inspiral signals in non-ideal single-detector data

TL;DR

This paper introduces a multivariate classifier using Random Forests to improve detection of gravitational-wave inspiral signals in noisy single-detector data, outperforming traditional methods by leveraging additional features from template banks.

Contribution

The paper presents a novel classifier that combines multiple features from inspiral and sine-Gaussian templates, enhancing detection sensitivity in non-ideal detector data.

Findings

Detects 1.5 to 2 times more signals at low false positive rates

Does not require chi-squared computation for classification

Performs nearly as well as traditional methods when limited to SNR and chi-squared data

Abstract

We describe a multivariate classifier for candidate events in a templated search for gravitational-wave (GW) inspiral signals from neutron-star--black-hole (NS-BH) binaries, in data from ground-based detectors where sensitivity is limited by non-Gaussian noise transients. The standard signal-to-noise ratio (SNR) and chi-squared test for inspiral searches use only properties of a single matched filter at the time of an event; instead, we propose a classifier using features derived from a bank of inspiral templates around the time of each event, and also from a search using approximate sine-Gaussian templates. The classifier thus extracts additional information from strain data to discriminate inspiral signals from noise transients. We evaluate a Random Forest classifier on a set of single-detector events obtained from realistic simulated advanced LIGO data, using simulated NS-BH signals added to the data. The new classifier detects a factor of 1.5 -- 2 more signals at low false positive rates as compared to the standard 're-weighted SNR' statistic, and does not require the chi-squared test to be computed. Conversely, if only the SNR and chi-squared values of single-detector events are available, Random Forest classification performs nearly identically to the re-weighted SNR.