Enhancing gravitational-wave detection: a machine learning pipeline combination approach with robust uncertainty quantification

2025/04/24 by G. Ashton, Ann-Kristin Malz, Ashton, Gregory +3 · 1 citation
Physics and Astronomy · #FOS: Physical sciences #General Relativity and Quantum Cosmology (gr-qc) #High Energy Astrophysical Phenomena (astro-ph.HE) #Pulsars and Gravitational Waves Research

paper · pdf · doi:10.48550/arxiv.2504.17587

openalex publication_date 2025/04/24 · openalex created_date 2025/10/19 · openalex updated_date 2026/08/01

Abstract

Gravitational-wave data from advanced-era interferometric detectors consists of background Gaussian noise, frequent transient artefacts, and rare astrophysical signals. Multiple search algorithms exist to detect the signals from compact binary coalescences, but their varying performance complicates interpretation. We present a machine learning-driven approach that combines results from individual pipelines and utilises conformal prediction to provide robust, calibrated uncertainty quantification. Using simulations, we demonstrate improved detection efficiency and apply our model to GWTC-3, enhancing confidence in multi-pipeline detections, such as the sub-threshold binary neutron star candidate GW200311₁03121.

Cited by

• CLAWDIA: A dictionary learning framework for gravitational-wave data analysis

Related

• Combining gravitational wave search pipelines to find subthreshold signals in GWTC-5.0
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Applications of machine learning in gravitational-wave research with current interferometric detectors
• Calibrating gravitational-wave search algorithms with conformal prediction
• A machine-learning pipeline for real-time detection of gravitational waves from compact binary coalescences