Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches

TL;DR

This paper introduces CTSAE, an unsupervised autoencoder model combining CNN and ViT for effective dimensionality reduction and clustering of gravitational wave glitches, addressing the challenge of unlabeled, evolving glitch patterns.

Contribution

The paper presents the first unsupervised method specifically designed for clustering LIGO gravitational wave glitch data using a novel multi-branch autoencoder with fusion techniques.

Findings

CTSAE outperforms state-of-the-art semi-supervised methods in clustering accuracy.

The multi-branch fusion with CLS token enhances feature extraction across channels.

Demonstrates effectiveness on the GravitySpy O3 dataset.

Abstract

The advancement of The Laser Interferometer Gravitational-Wave Observatory (LIGO) has significantly enhanced the feasibility and reliability of gravitational wave detection. However, LIGO's high sensitivity makes it susceptible to transient noises known as glitches, which necessitate effective differentiation from real gravitational wave signals. Traditional approaches predominantly employ fully supervised or semi-supervised algorithms for the task of glitch classification and clustering. In the future task of identifying and classifying glitches across main and auxiliary channels, it is impractical to build a dataset with manually labeled ground-truth. In addition, the patterns of glitches can vary with time, generating new glitches without manual labels. In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches. CTSAE integrates a novel four-branch autoencoder with a hybrid of Convolutional Neural Networks (CNN) and Vision Transformers (ViT). To further extract features across multi-branches, we introduce a novel multi-branch fusion method using the CLS (Class) token. Our model, trained and evaluated on the GravitySpy O3 dataset on the main channel, demonstrates superior performance in clustering tasks when compared to state-of-the-art semi-supervised learning methods. To the best of our knowledge, CTSAE represents the first unsupervised approach tailored specifically for clustering LIGO data, marking a significant step forward in the field of gravitational wave research. The code of this paper is available at https://github.com/Zod-L/CTSAE