Machine learning application to detect light echoes around black holes

Abstract

X-ray reverberation has become a powerful tool to probe the disc-corona geometry near black holes. Here, we develop Machine Learning (ML) models to extract the X-ray reverberation features imprinted in the Power Spectral Density (PSD) of AGN. The machine is trained using simulated PSDs in the form of a simple power-law encoded with the relativistic echo features. Dictionary Learning and sparse coding algorithms are used for the PSD reconstruction, by transforming the noisy PSD to a representative sparse version. Then, the Support Vector Machine is employed to extract the interpretable reverberation features from the reconstructed PSD that holds the information of the source height. The results show that the accuracy of predicting the source height, $h$, is genuinely high and the misclassification is only found when $h$ > 15$r_g$. When the test PSD has a bending power-law shape, which is completely new to the machine, the accuracy is still high. Therefore, the ML model does not require the intrinsic shape of the PSD to be determined in advance. By focusing on the PSD parameter space observed in real AGN data, classification for $h\le$ 10$r_g$ can be determined with 100% accuracy, even using a PSD in an energy band that contains a reflection flux as low as 10% of the total flux. For $h$ > 10$r_g$, the data, if misclassified, will have small uncertainties of $\Delta h$ ~ 2-4$r_g$. This work shows, as a proof of concept, that the ML technique could shape new methodological directions in the X-ray reverberation analysis.

12 pages, 13 figures, accepted for publication in MNRAS

References in corpus (12)

• X-ray reverberation around accreting black holes
• A public relativistic transfer function model for X-ray reverberation mapping of accreting black holes
• Investigating the X-ray time-lags in PG 1244+026 using an extended corona model
• Theoretical modelling of the AGN iron-line vs continuum time-lags in the lamp-post geometry
• Simultaneous spectral and reverberation modelling of relativistic reflection in Mrk 335
• A combined timing/spectral study of IRAS 13224-3809 using XMM-Newton data
• Multi-timescale reverberation mapping of Mrk 335
• Returning radiation in strong gravity around black holes: Reverberation from the accretion disc
• Interference as an origin of the peaked noise in accreting X-ray binaries
• Evolution of the truncated disc and inner hot-flow of GX 339-4
• Modelling the X-ray power spectra of AGN by using reprocessing echoes from an extended corona
• An Algorithm for the Visualization of Relevant Patterns in Astronomical Light Curves

Cited by in corpus (2)

• Predicting the black hole mass and correlations in X-ray reverberating AGN using neural networks
• X-ray reverberation models of the disc wind in ultraluminous X-ray source NGC 5408 X-1