AGNet: Weighing Black Holes with Machine Learning

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.

5 pages, 3 figures, 1 table. Accepted to the Machine Learning and the Physical Sciences Workshop at NeurIPS 2020

References in corpus (5)

• A Catalog of Quasar Properties from SDSS DR7
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Feature Extraction on Synthetic Black Hole Images

Cited by in corpus (1)

• Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes