A semi-supervised Machine Learning search for never-seen Gravitational-Wave sources

TL;DR

This paper introduces a semi-supervised machine learning approach to detect unmodeled gravitational-wave sources by identifying anomalous spectrogram patterns in LIGO data, addressing the challenge of discovering rare or unexpected signals.

Contribution

The study develops and applies a semi-supervised deep learning method for detecting unmodeled GW signals, expanding the search beyond known binary coalescence models.

Findings

No unmodeled GW candidates were found in the analyzed data.

The method can detect unusual GW patterns with a 50% detection rate at specific amplitudes.

The approach demonstrates potential for discovering rare or unforeseen GW sources.

Abstract

By now, tens of gravitational-wave (GW) events have been detected by the LIGO and Virgo detectors. These GWs have all been emitted by compact binary coalescence, for which we have excellent predictive models. However, there might be other sources for which we do not have reliable models. Some are expected to exist but to be very rare (e.g., supernovae), while others may be totally unanticipated. So far, no unmodeled sources have been discovered, but the lack of models makes the search for such sources much more difficult and less sensitive. We present here a search for unmodeled GW signals using semi-supervised machine learning. We apply deep learning and outlier detection algorithms to labeled spectrograms of GW strain data, and then search for spectrograms with anomalous patterns in public LIGO data. We searched $\sim 13\%$ of the coincident data from the first two observing runs. No candidates of GW signals were detected in the data analyzed. We evaluate the sensitivity of the search using simulated signals, we show that this search can detect spectrograms containing unusual or unexpected GW patterns, and we report the waveforms and amplitudes for which a $50\%$ detection rate is achieved.