A Search for Binary Black Hole Mergers in LIGO O1-O3 Data with Convolutional Neural Networks

TL;DR

This paper introduces a neural network-based pipeline for detecting binary black hole mergers in LIGO data, achieving high detection rates and enabling faster, low-latency gravitational wave searches for multi-messenger astronomy.

Contribution

The work develops a machine learning pipeline trained on real LIGO data that detects BBH mergers with high accuracy across multiple observing runs, improving detection speed and reliability.

Findings

Detected 57 out of 75 cataloged BBH events in LIGO data

Achieved a low false alarm rate through extensive testing

Enabled low-latency gravitational wave detection

Abstract

Since the first detection of gravitational waves in 2015 by LIGO from the binary black hole merger GW150914, gravitational-wave astronomy has developed significantly, with over 200 compact binary merger events cataloged. The use of neural networks has the potential to significantly speed up the detection, classification, and especially parameter estimation for gravitational wave events, compared to current techniques, quite important for electromagnetic follow-up of events. In this work, we present a machine learning pipeline using neural networks to detect gravitational wave events. We generate training data using real LIGO data to train and refine neural networks that can detect binary black hole (BBH) mergers, and apply these models to search through LIGO's first three observing runs. We detect 57 out of the 75 total cataloged BBH events with two detectors of data in O1, O2, and O3, with 57 false positives that can mostly be ruled out with parameter inference and human inspection. Finally, we extensively test this pipeline on time-shifted data to characterize its False Alarm Rate (FAR). These results are an important step in developing machine learning-based GW searches, enabling low-latency detection and multi-messenger astronomy.