A Generative Model for Quasar Spectra

TL;DR

This paper introduces a Gaussian process-based generative model for quasar spectra that predicts both spectral features and black hole properties from single-epoch data, outperforming traditional methods in accuracy.

Contribution

The paper presents a novel multi-output generative model for quasars that jointly models spectra and physical properties using Gaussian processes, enabling accurate predictions from limited data.

Findings

Accurately predicts black hole masses from single-epoch spectra.

Successfully predicts unobserved spectral regions.

Achieves near-optimal accuracy in black hole mass estimation.

Abstract

We build a multi-output generative model for quasar spectra and the properties of their black hole engines, based on a Gaussian process latent-variable model. This model treats every quasar as a vector of latent properties such that the spectrum and all physical properties of the quasar are associated with non-linear functions of those latent parameters; the Gaussian process kernel functions define priors on the function space. Our generative model is trained with a justifiable likelihood function that allows us to treat heteroscedastic noise and missing data correctly, which is crucial for all astrophysical applications. It can predict simultaneously unobserved spectral regions, as well as the physical properties of quasars in held-out test data. We apply the model to rest-frame ultraviolet and optical quasar spectra for which precise black hole masses (based on reverberation mapping measurements) are available. Unlike reverberation-mapping studies, which require multi-epoch data, our model predicts black hole masses from single-epoch spectra, even with limited spectral coverage. We demonstrate the capabilities of the model by predicting black hole masses and unobserved spectral regions. We find that we predict black hole masses at close to the best possible accuracy.