Unsupervised Learning Approach to Anomaly Detection in Gravitational Wave Data

TL;DR

This paper presents an unsupervised anomaly detection method using variational autoencoders to identify gravitational wave signals in noisy detector data, achieving high detection accuracy without labeled training data.

Contribution

It introduces VAEs as a novel, scalable unsupervised framework for gravitational wave anomaly detection, capable of identifying both known and new phenomena.

Findings

Achieved an AUC of 0.89 in detection performance.

Successfully distinguished GW signals from noise.

Demonstrated robustness on real LIGO data.

Abstract

Gravitational waves (GW), predicted by Einstein's General Theory of Relativity, provide a powerful probe of astrophysical phenomena and fundamental physics. In this work, we propose an unsupervised anomaly detection method using variational autoencoders (VAEs) to analyze GW time-series data. By training on noise-only data, the VAE accurately reconstructs noise inputs while failing to reconstruct anomalies, such as GW signals, which results in measurable spikes in the reconstruction error. The method was applied to data from the LIGO H1 and L1 detectors. Evaluation on testing datasets containing both noise and GW events demonstrated reliable detection, achieving an area under the ROC curve (AUC) of 0.89. This study introduces VAEs as a robust, unsupervised approach for identifying anomalies in GW data, which offers a scalable framework for detecting known and potentially new phenomena in physics.