AGNet: Weighing Black Holes with Deep Learning

TL;DR

This paper introduces AGNet, a deep learning algorithm that estimates supermassive black hole masses from quasar light curves, reducing reliance on expensive spectroscopic data and enabling more efficient future observations.

Contribution

AGNet is the first neural network model to accurately predict SMBH masses directly from optical light curves, bypassing traditional spectroscopic methods.

Findings

Achieved 0.37 dex scatter in SMBH mass predictions, comparable to systematic uncertainties.

Validated the model on nearly 39,000 quasars from SDSS Stripe 82.

Demonstrated potential for application with upcoming Rubin Observatory data.

Abstract

Supermassive black holes (SMBHs) are ubiquitously found at the centers of most massive galaxies. Measuring SMBH mass is important for understanding the origin and evolution of SMBHs. However, traditional methods require spectroscopic data which is expensive to gather. We present an algorithm that weighs SMBHs using quasar light time series, circumventing the need for expensive spectra. We train, validate, and test neural networks that directly learn from the Sloan Digital Sky Survey (SDSS) Stripe 82 light curves for a sample of $38,939$ spectroscopically confirmed quasars to map out the nonlinear encoding between SMBH mass and multi-color optical light curves. We find a 1$\sigma$ scatter of 0.37 dex between the predicted SMBH mass and the fiducial virial mass estimate based on SDSS single-epoch spectra, which is comparable to the systematic uncertainty in the virial mass estimate. Our results have direct implications for more efficient applications with future observations from the Vera C. Rubin Observatory. Our code, \textsf{AGNet}, is publicly available at \url{https://github.com/snehjp2/AGNet}.