Multivariate Classification with Random Forests for Gravitational Wave Searches of Black Hole Binary Coalescence

TL;DR

This paper demonstrates that using a random forest machine learning approach significantly enhances the sensitivity of gravitational wave searches for black hole binaries, outperforming traditional ranking methods across various mass ranges.

Contribution

Introduces a multivariate candidate ranking statistic based on random forests, improving detection sensitivity in gravitational wave searches for black hole mergers.

Findings

Sensitive volume improvements up to 109% for high-mass searches

Sensitive volume improvements up to 241% for ringdown-only searches

Sensitivity varies with mass regime, ratio, and data quality

Abstract

Searches for gravitational waves produced by coalescing black hole binaries with total masses $\gtrsim25\,$M$_\odot$ use matched filtering with templates of short duration. Non-Gaussian noise bursts in gravitational wave detector data can mimic short signals and limit the sensitivity of these searches. Previous searches have relied on empirically designed statistics incorporating signal-to-noise ratio and signal-based vetoes to separate gravitational wave candidates from noise candidates. We report on sensitivity improvements achieved using a multivariate candidate ranking statistic derived from a supervised machine learning algorithm. We apply the random forest of bagged decision trees technique to two separate searches in the high mass $\left( \gtrsim25\,\mathrm{M}_\odot \right)$ parameter space. For a search which is sensitive to gravitational waves from the inspiral, merger, and ringdown (IMR) of binary black holes with total mass between $25\,$M$_\odot$ and $100\,$M$_\odot$, we find sensitive volume improvements as high as $70_{\pm 13}-109_{\pm 11}$\% when compared to the previously used ranking statistic. For a ringdown-only search which is sensitive to gravitational waves from the resultant perturbed intermediate mass black hole with mass roughly between $10\,$M$_\odot$ and $600\,$M$_\odot$, we find sensitive volume improvements as high as $61_{\pm 4}-241_{\pm 12}$\% when compared to the previously used ranking statistic. We also report how sensitivity improvements can differ depending on mass regime, mass ratio, and available data quality information. Finally, we describe the techniques used to tune and train the random forest classifier that can be generalized to its use in other searches for gravitational waves.