AGNet: Weighing Black Holes with Machine Learning

TL;DR

This paper introduces a machine learning algorithm that estimates supermassive black hole masses from quasar light curves, eliminating the need for costly spectral data and enabling efficient analysis of large astronomical datasets.

Contribution

The novel approach uses neural networks trained on SDSS data to predict black hole masses directly from optical light curves, bypassing traditional spectral measurements.

Findings

Achieved a 0.35 dex scatter in mass predictions

Demonstrated effectiveness on SDSS Stripe 82 quasars

Implications for future large-scale surveys like Vera Rubin Observatory

Abstract

Supermassive black holes (SMBHs) are ubiquitously found at the centers of most galaxies. Measuring SMBH mass is important for understanding the origin and evolution of SMBHs. However, traditional methods require spectral data which is expensive to gather. To solve this problem, 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 data for a sample of $9,038$ spectroscopically confirmed quasars to map out the nonlinear encoding between black hole mass and multi-color optical light curves. We find a 1$\sigma$ scatter of 0.35 dex between the predicted mass and the fiducial virial mass based on SDSS single-epoch spectra. Our results have direct implications for efficient applications with future observations from the Vera Rubin Observatory.