A Neural Network-Based Search for Unmodeled Transients in LIGO-Virgo-KAGRA's Third Observing Run

2024-12-27

AI Summary

This study conducts a model-agnostic search for gravitational-wave transients in the 30–1500 Hz band, with durations from milliseconds to several seconds, using data from the LIGO-Virgo-KAGRA third observing run—without assuming prior knowledge of source sky location, polarization, or waveform morphology. Method: We propose GWAK, a novel framework that constructs a physics-informed, low-dimensional embedding space via joint feature learning. It integrates deep neural networks, unsupervised and semi-supervised representation learning, data denoising, and anomaly detection. Contribution/Results: GWAK achieves unified characterization and joint classification of compact binary coalescences (CBCs), detector glitches (“glitches”), and unmodeled transients. It successfully recovers three confirmed CBC events, precisely discriminates multiple glitch classes, and demonstrates high sensitivity to unmodeled transients—outperforming conventional pipelines significantly in both robustness and detection capability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This paper presents the results of a Neural Network (NN)-based search for short-duration gravitational-wave transients in data from the third observing run of LIGO, Virgo, and KAGRA. The search targets unmodeled transients with durations of milliseconds to a few seconds in the 30-1500 Hz frequency band, without assumptions about the incoming signal direction, polarization, or morphology. Using the Gravitational Wave Anomalous Knowledge (GWAK) method, three compact binary coalescences (CBCs) identified by existing pipelines are successfully detected, along with a range of detector glitches. The algorithm constructs a low-dimensional embedded space to capture the physical features of signals, enabling the detection of CBCs, detector glitches, and unmodeled transients. This study demonstrates GWAK's ability to enhance gravitational-wave searches beyond the limits of existing pipelines, laying the groundwork for future detection strategies.

Problem

• Gravitational Wave Detection
• Unknown Transient Signals
• LIGO Virgo KAGRA Observations

Innovation

• GWAK algorithm
• unbiased search
• gravitational wave detection