Residual neural networks to classify the high frequency emission in core-collapse supernova gravitational waves

TL;DR

This paper introduces a ResNet50-based method to classify high frequency gravitational wave features from core-collapse supernovae, demonstrating high accuracy at galactic distances using real interferometric noise.

Contribution

The study develops and validates a novel deep learning approach for classifying high frequency GW features, enhancing early-stage supernova analysis.

Findings

High classification accuracy at 1-5 kpc distances.

Method shows potential for real interferometric data analysis.

Accuracy declines at larger distances due to dataset limitations.

Abstract

We present a new methodology to explore the morphology of the High Frequency Feature (HFF), i.e., the dominant, rising-frequency GW emission from a proto-neutron star in core-collapse supernovae (CCSNe). We used a residual neural network (ResNet50) to perform multi-class classification of image samples constructed from time-frequency Morlet wavelet scalograms. We defined a three-class problem by categorizing the HFF slope as Steep, Moderate, or Low, according to physically informed ranges. The ResNet50 model was optimized with phenomenological waveforms injected into real noise from the LIGO-Virgo O3b observing run and then tested with numerically simulated CCSN waveforms embedded in the same real noise. At galactic distances of 1 kpc and 5 kpc with H1 and L1 data and 1 kpc with V1 data, we obtained highly accurate results (test accuracies from 0.8933 to 0.9867), which show the feasibility of our methodology. For further distances, we observed declines in test accuracy until 0.8000 with H1 and L1 data at 10 kpc and until 0.5933 with V1 data at 10 kpc, which we attribute to limitations in the input datasets. Our methodology is sufficiently general to enable early-stage characterization of the HFF in real interferometric data.