287,872 Supermassive Black Holes Masses: Deep Learning Approaching Reverberation Mapping Accuracy

TL;DR

This paper introduces a deep learning method that estimates supermassive black hole masses with high accuracy across a large population, outperforming traditional methods and applicable up to high redshifts.

Contribution

A novel deep encoder-decoder network trained on reverberation-mapping data to accurately estimate black hole masses for over 287,000 quasars.

Findings

Achieves 0.058 dex RMS error in mass estimation.

Maintains high accuracy across a wide mass range.

Surpasses traditional virial estimators in precision.

Abstract

We present a population-scale catalogue of 287,872 supermassive black hole masses with high accuracy. Using a deep encoder-decoder network trained on optical spectra with reverberation-mapping (RM) based labels of 849 quasars and applied to all SDSS quasars up to $z=4$, our method achieves a root-mean-square error of $0.058$\,dex, a relative uncertainty of $\approx 14\%$, and coefficient of determination $R^{2}\approx0.91$ with respect to RM-based masses, far surpassing traditional single-line virial estimators. Notably, the high accuracy is maintained for both low ($<10^{7.5}\,M_\odot$) and high ($>10^{9}\,M_\odot$) mass quasars, where empirical relations are unreliable.