Astrophysical or Terrestrial: Machine learning classification of gravitational-wave candidates using multiple-search information

TL;DR

This paper introduces a machine learning classifier that combines multiple search pipeline data to distinguish astrophysical gravitational-wave signals from terrestrial noise, improving real-time event validation.

Contribution

It presents a novel ML-based classifier utilizing multi-pipeline information, achieving high accuracy and AUC in identifying true gravitational-wave events.

Findings

AUC of 0.96 on training data

Accuracy of 0.90 on training data

AUC of 0.93 on O3 data

Abstract

Low-latency gravitational-wave alerts provide the greater multi-messenger community with information about the candidate events detected by the International Gravitational-Wave Network (IGWN). Prompt release of data products such as the sky localization, false alarm rate (FAR), and $p_\mathrm{astro}$ values allow astronomers to make informed decisions on which candidate gravitational-wave events merit target of opportunity (ToO) follow-up. However, false alarms, often referred to as "glitches", where a gravitational-wave candidate, or trigger, is the result of terrestrial noise, are an inherent part of gravitational-wave searches. In addition, with the presence of multiple gravitational-wave searches, different searches may have varying assessments of the significance of a given trigger. As a complement to quantities such as $p_\mathrm{astro}$, we provide a Machine Learning (ML) based approach to determining whether candidate events are astrophysical or terrestrial in nature, specifically a classifier that utilizes information provided by multiple low-latency search pipelines in its feature space. This classifier has a performance an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.96 and accuracy of 0.90 on the Mock Data Challenge training set and an AUC of 0.93 and accuracy of 0.86 on events from the Advanced LIGO (aLIGO)'s and Advanced Virgo (AdVirgo)'s third observing run (O3).