Detecting extreme-mass-ratio inspirals for space-borne detectors with deep learning

TL;DR

This paper presents a deep learning approach using CNNs and Q-transform preprocessing to detect faint EMRI signals in space-borne gravitational wave data, achieving high accuracy at realistic SNR levels.

Contribution

Introduces a CNN-based method with Q-transform preprocessing for efficient EMRI detection, incorporating TDI for practical application, and demonstrates high detection performance on simulated data.

Findings

Achieves 94.2% TPR at 1% FPR for SNR 50-100

Demonstrates effective EMRI detection with deep learning in simulated datasets

Validates the method's potential for rapid EMRI signal detection in space-based detectors

Abstract

One of the primary objectives for space-borne gravitational wave detectors is the detection of extreme-mass-ratio inspirals (EMRIs). This undertaking poses a substantial challenge because of the complex and long EMRI signals, further complicated by their inherently faint signal. In this research, we introduce a 2-layer Convolutional Neural Network (CNN) approach to detect EMRI signals for space-borne detectors. Our method employs the Q-transform for data preprocessing, effectively preserving EMRI signal characteristics while minimizing data size. By harnessing the robust capabilities of CNNs, we can reliably distinguish EMRI signals from noise, particularly when the signal-to-noise~(SNR) ratio reaches 50, a benchmark considered a ``golden'' EMRI. At the meantime, we incorporate time-delay interferometry (TDI) to ensure practical utility. We assess our model's performance using a 0.5-year dataset, achieving a true positive rate~(TPR) of 94.2\% at a 1\% false positive rate~(FPR) across various signal-to-noise ratio form 50-100, with 91\% TPR and 1\% FPR at an SNR of 50. This study underscores the promise of incorporating deep learning methods to advance EMRI data analysis, potentially leading to rapid EMRI signal detection.