Towards an anomaly detection pipeline for gravitational waves at the Einstein Telescope

TL;DR

This paper introduces a deep autoencoder-based anomaly detection pipeline for short-duration gravitational wave signals, demonstrating high sensitivity and low false alarms in simulated data, advancing automated GW search methods.

Contribution

The paper presents a novel deep convolutional autoencoder approach for GW anomaly detection, achieving high detection efficiency and generalization in a benchmark dataset, without requiring prior signal models.

Findings

Successfully detects IMBH-forming mergers with 23% initial efficiency

Recovers all injected IMBH mergers after weak supervision

Maintains approximately 4.5 false alarms per year for single detectors

Abstract

We present the implementation of an anomaly-detection algorithm based on a deep convolutional autoencoder for the search for gravitational waves (GWs) in time-frequency spectrograms. Our method targets short-duration ($\lesssim 2\,\text{s}$) GW signals, exemplified by mergers of compact objects forming or involving an intermediate-mass black hole (IMBH). Such short signals are difficult to distinguish from background noise; yet their brevity makes them well-suited to machine-learning analyses with modest computational requirements. Using the data from the Einstein Telescope Mock Data Challenge as a benchmark, we demonstrate that the approach can successfully flag GW-like transients as anomalies in interferometer data of a single detector, achieving an initial detection efficiency of 23% for injected signals corresponding to IMBH-forming mergers. After introducing weak supervision, the model exhibits excellent generalisation and recovers all injected IMBH-forming mergers, independent of their total mass or signal-to-noise ratio, with a false-alarm rate due to statistical noise fluctuations of approximately 4.5 events per year for a single interferometer operating with a 100% duty cycle. The method also successfully identifies lower-mass mergers leading to the formation of black holes with mass larger than $\simeq 20\,M_\odot$. Our pipeline does not yet classify anomalies, distinguishing between actual GW signals and noise artefacts; however, it highlights any deviation from the learned background noise distribution for further scrutiny. These results demonstrate that anomaly detection offers a powerful, model-independent framework for future GW searches, paving the way toward fully automated and adaptive analysis pipelines.