Binary Black Hole Parameter Estimation with Hybrid CNN-Transformer Neural Networks

2026-06-11

AI Summary

This work proposes a hybrid deep learning architecture combining convolutional neural networks (CNNs) and Transformer encoders for end-to-end parameter estimation of non-precessing binary black hole systems, addressing the high computational cost and poor scalability of traditional template-based and multi-detector time-delay analyses. The model leverages CNNs to extract local time–frequency features and employs the Transformer to capture long-range dependencies, achieving a balance between accuracy and efficiency. Experimental results demonstrate that the approach delivers robust and precise predictions for both intrinsic and extrinsic parameters on simulated signals in Gaussian noise as well as real gravitational-wave events, significantly enhancing generalization capability and inference speed.

Abstract

The detection of gravitational waves has revolutionized our ability to explore fundamental aspects of the Universe. Traditionally, modeled gravitational-wave signals have been identified using template-based matched filtering, followed by coincidence analysis across multiple detectors in the signal-to-noise ratio time series. Recent advances in Machine Learning and Deep Learning have sparked growing interest in their application to both signal detection and parameter estimation. In this study, a hybrid Deep Learning strategy is proposed that leverages the effectiveness of Transformer encoders alongside well-established Convolutional Neural Network architectures in an attempt to estimate the intrinsic and extrinsic parameters of non-precessing binary black hole systems. The primary focus of this work is point estimation, producing single best-fit values for each parameter rather than full posterior distributions. This method is evaluated on both simulated signals embedded in Gaussian noise and real gravitational-wave events, and it demonstrates strong predictive performance and robustness across key astrophysical parameters.

Problem

• Binary Black Hole
• Parameter Estimation
• Gravitational Waves
• Point Estimation
• Deep Learning

Innovation

• hybrid CNN-Transformer
• binary black hole
• parameter estimation
• gravitational waves
• point estimation