Training Process of Unsupervised Learning Architecture for Gravity Spy Dataset

TL;DR

This paper examines the training process of an unsupervised deep learning architecture designed for classifying transient noise in gravitational-wave detector data, aiming to improve noise understanding and detector performance.

Contribution

It provides an in-depth analysis of the training process of a novel unsupervised learning architecture applied to the Gravity Spy dataset, highlighting its potential for noise classification.

Findings

Effective training process identified for the unsupervised architecture.

Potential for online and offline noise analysis demonstrated.

Improved understanding of transient noise characteristics.

Abstract

Transient noise appearing in the data from gravitational-wave detectors frequently causes problems, such as instability of the detectors and overlapping or mimicking gravitational-wave signals. Because transient noise is considered to be associated with the environment and instrument, its classification would help to understand its origin and improve the detector's performance. In a previous study, an architecture for classifying transient noise using a time-frequency 2D image (spectrogram) is proposed, which uses unsupervised deep learning combined with variational autoencoder and invariant information clustering. The proposed unsupervised-learning architecture is applied to the Gravity Spy dataset, which consists of Advanced Laser Interferometer Gravitational-Wave Observatory (Advanced LIGO) transient noises with their associated metadata to discuss the potential for online or offline data analysis. In this study, focused on the Gravity Spy dataset, the training process of unsupervised-learning architecture of the previous study is examined and reported.