Interpreting a Machine Learning Model for Detecting Gravitational Waves

TL;DR

This paper applies interpretability techniques from computer vision to understand machine learning models used for detecting gravitational waves in LIGO data, revealing how different network parts respond to signals and noise.

Contribution

It introduces interpretability analysis of ML models in gravitational wave detection, highlighting neural network specialization and guiding future model design.

Findings

Different network parts specialize in local versus global features.

Network architecture influences feature detection and noise handling.

Interpretability insights can inform future model improvements.

Abstract

We describe a case study of translational research, applying interpretability techniques developed for computer vision to machine learning models used to search for and find gravitational waves. The models we study are trained to detect black hole merger events in non-Gaussian and non-stationary advanced Laser Interferometer Gravitational-wave Observatory (LIGO) data. We produced visualizations of the response of machine learning models when they process advanced LIGO data that contains real gravitational wave signals, noise anomalies, and pure advanced LIGO noise. Our findings shed light on the responses of individual neurons in these machine learning models. Further analysis suggests that different parts of the network appear to specialize in local versus global features, and that this difference appears to be rooted in the branched architecture of the network as well as noise characteristics of the LIGO detectors. We believe efforts to whiten these "black box" models can suggest future avenues for research and help inform the design of interpretable machine learning models for gravitational wave astrophysics.