Template-free search for gravitational wave events using coincident anomaly detection

TL;DR

This paper introduces a novel, template-free neural network approach called CoAD for detecting gravitational wave events by exploiting coincident signals across detectors, without requiring labeled training data.

Contribution

The paper presents a new unsupervised neural network method for gravitational wave detection that does not rely on waveform templates or labeled training data.

Findings

CoAD achieves up to 0.91 recall at one event per year false-alarm rate.

It can detect signals with SNR below 10, demonstrating high sensitivity.

Integrated gradient analysis helps localize signals and improve detection precision.

Abstract

Gravitational-wave (GW) observatories have used template-based search to detect hundreds of compact binary coalescences (CBCs). However, template-based search cannot detect astrophysical sources that lack accurate waveform models, including core-collapse supernovae, neutron star glitches, and cosmic strings. Here, we present a novel approach for template-free search using coincident anomaly detection (CoAD). CoAD requires neither labeled training examples nor background-only training sets, instead exploiting the coincidence of events across spatially separated detectors as the training loss itself: two neural networks independently analyze data from each detector and are trained to maximize coincident predictions. Additionally, we show that integrated gradient analysis can localize GW signals from the neural-network weights, providing a path toward data-driven template construction of unmodeled sources, and further improving precision by frequency matching. Using the CodaBench dataset of real LIGO backgrounds with injected simulated CBCs and sine-Gaussian low-frequency bursts, CoAD achieves recall up to 0.91 and 0.85 respectively at a false-alarm rate of one event per year, and achieves recall above 0.5 at signal-to-noise ratios below 10. The fully-unsupervised nature of CoAD makes it especially well-suited for next-generation detectors with greater sensitivity and associated increases in GW event rates.