Predicting the black hole mass and correlations in X-ray reverberating AGN using neural networks

Abstract

We develop neural network models to predict the black hole mass using 22 reverberating AGN samples in the XMM-Newton archive. The model features include the fractional excess variance ($F_{\mathrm{var}}$) in 2-10 keV band, Fe-K lag amplitude, 2-10 keV photon counts and redshift. We find that the prediction accuracy of the neural network model is significantly higher than what is obtained from the traditional linear regression method. Our predicted mass can be confined within $\pm (2$-5) per cent of the true value, suggesting that the neural network technique is a promising and independent way to constrain the black hole mass. We also apply the model to 21 non-reverberating AGN to rule out their possibility to exhibit the lags (some have too small mass and $F_{\mathrm{var}}$, while some have too large mass and $F_{\mathrm{var}}$ that contradict the $F_{\mathrm{var}}$-lag-mass relation in reverberating AGN). We also simulate 3200 reverberating AGN samples using the multi-feature parameter space from the neural network model to investigate the global relations if the number of reverberating AGN increases. We find that the $F_{\mathrm{var}}$-mass anti-correlation is likely stronger with increasing number of newly-discovered reverberating AGN. Contrarily, to maintain the lag-mass scaling relation, the tight anti-correlation between the lag and $F_{\mathrm{var}}$ must preserve. In an extreme case, the lag-mass correlation coefficient can significantly decrease and, if observed, may suggest the extended corona framework where their observed lags are more driven by the coronal property rather than geometry.

15 pages, 12 figures, 4 tables, accepted for publication in MNRAS

References in corpus (26)

• Piecing Together the X-ray Background: Bolometric Corrections for Active Galactic Nuclei
• X-ray reverberation around accreting black holes
• Simultaneous X-ray/optical/UV snapshots of active galactic nuclei from XMM-Newton: spectral energy distributions for the reverberation mapped sample
• The AGN Black Hole Mass Database
• Efficient and Accurate Machine-Learning Interpolation of Atomic Energies in Compositions with Many Species
• The corona contracts in a black-hole transient
• The effect of radiation pressure on virial black hole mass estimates and the case of Narrow Line Seyfert 1 galaxies
• A public relativistic transfer function model for X-ray reverberation mapping of accreting black holes
• Discovery of a ~2 hr high frequency X-ray QPO and iron K alpha reverberation in the active galaxy MS 2254.9-3712
• Iron K and Compton hump reverberation in SWIFT J2127.4+5654 and NGC 1365 revealed by NuSTAR and XMM-Newton
• First high energy observations of Narrow Line Seyfert 1s with INTEGRAL/IBIS
• Observations of MCG-5-23-16 with Suzaku, XMM-Newton and NuSTAR: Disk tomography and Compton hump reverberation
• Light bending and X-ray echoes from behind a supermassive black hole
• 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
• AGN Coronae Through A Jet Perspective
• A combined timing/spectral study of IRAS 13224-3809 using XMM-Newton data
• Black hole spin and size of the X-ray emitting region(s) in the Seyfert 1.5 galaxy ESO 362-G18
• The nature of the extreme X-ray variability in the NLS1 1H 0707-495
• Fundamental X-ray Corona Parameters of Swift/BAT AGN
• 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
• X-ray reverberation lags from the 1.5 Seyfert galaxy NGC 5273
• Machine learning application to detect light echoes around black holes
• X-ray reverberation models of the disc wind in ultraluminous X-ray source NGC 5408 X-1

Cited by in corpus (4)

• Extended Corona Models of X-ray Reverberation in the AGN 1H~0707-495 and IRAS 13224-3809
• Revealing the intrinsic X-ray reverberation lags in IRAS 13224-3809 through the Granger causality test
• Uncertainty Quantification of the Virial Black Hole Mass with Conformal Prediction
• Mapping the X-ray corona evolution of IRAS 13224-3809 with the power spectral density