The detection, extraction and parameter estimation of extreme-mass-ratio inspirals with deep learning

One of the primary goals of space-borne gravitational wave detectors is to detect and analyze extreme-mass-ratio inspirals (EMRIs). This task is particularly challenging because EMRI signals are complex, lengthy, and faint. In this work, we introduce a 2-layer convolutional neural network (CNN) approach to detect EMRI signals for space-borne detectors, achieving a true positive rate (TPR) of 96.9% at a 1% false positive rate (FPR) for signal-to-noise ratio (SNR) from 50 to 100. Especially, the key intrinsic parameters of EMRIs such as the mass, spin of the supermassive black hole (SMBH) and the initial eccentricity of the orbit can also be inferred directly by employing a neural network. The mass and spin of the SMBH can be determined at 99% and 92% respectively. This will greatly reduce the parameter spaces and computing cost for the following Bayesian parameter estimation. Our model also has a low dependency on the accuracy of the waveform model. This study underscores the potential of deep learning methods in EMRI data analysis, enabling the rapid detection of EMRI signals and efficient parameter estimation.