AGNet: Weighing Black Holes with Machine Learning
This work offers a more efficient method for astronomers to measure SMBH masses, which is crucial for understanding galaxy and black hole evolution, especially with upcoming large-scale surveys.
This paper presents an algorithm, AGNet, that estimates supermassive black hole (SMBH) masses using quasar light time series data, bypassing the need for expensive spectral data. The neural network model, trained on 9,038 quasars from SDSS Stripe 82, achieved a 1-sigma scatter of 0.35 dex compared to traditional virial mass measurements.
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$σ$ 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.