Visualizing convolutional neural network for classifying gravitational waves from core-collapse supernovae

TL;DR

This paper demonstrates how convolutional neural networks can classify gravitational wave signals from supernovae using spectrograms, with visualization techniques revealing key features influencing the model's decisions.

Contribution

The study introduces a CNN-based approach for gravitational wave classification from supernovae and employs class activation mapping for interpretability.

Findings

CNN accurately classifies supernova gravitational wave signals.

Visualization highlights importance of specific spectral features like g-modes.

Model interpretability aids in improving detection strategies.

Abstract

In this study, we employ a convolutional neural network to classify gravitational waves originating from core-collapse supernovae. Training is conducted using spectrograms derived from three-dimensional numerical simulations of waveforms, which are injected onto real noise data from the third observing run of both Advanced LIGO and Advanced Virgo. To gain insights into the decision-making process of the model, we apply class activation mapping techniques to visualize the regions in the input image that are significant for the model's prediction. The class activation maps reveal that the model's predictions predominantly rely on specific features within the input spectrograms, namely, the $g$-mode and low-frequency modes. The visualization of convolutional neural network models provides interpretability to enhance their reliability and offers guidance for improving detection efficiency.