Predicting the redshift of gamma-ray loud AGNs using supervised machine learning

TL;DR

This paper demonstrates that machine learning, specifically the Superlearner ensemble, can reliably predict the redshifts of gamma-ray loud AGNs from their gamma-ray and photometric data, aiding astrophysical research.

Contribution

It introduces a novel application of Superlearner ensemble machine learning to estimate AGN redshifts from gamma-ray data, achieving high correlation with observed values.

Findings

Pearson correlation coefficient of 71.3% between predicted and observed redshifts

Average normalized redshift prediction error of 11.6 x 10^-4

Reliable predictive model despite small sample size

Abstract

AGNs are very powerful galaxies characterized by extremely bright emissions coming out from their central massive black holes. Knowing the redshifts of AGNs provides us with an opportunity to determine their distance to investigate important astrophysical problems such as the evolution of the early stars, their formation along with the structure of early galaxies. The redshift determination is challenging because it requires detailed follow-up of multi-wavelength observations, often involving various astronomical facilities. Here, we employ machine learning algorithms to estimate redshifts from the observed gamma-ray properties and photometric data of gamma-ray loud AGN from the Fourth Fermi-LAT Catalog. The prediction is obtained with the Superlearner algorithm, using LASSO selected set of predictors. We obtain a tight correlation, with a Pearson Correlation Coefficient of 71.3% between the inferred and the observed redshifts, an average {\Delta}z_norm = 11.6 x 10^-4. We stress that notwithstanding the small sample of gamma-ray loud AGNs, we obtain a reliable predictive model using Superlearner, which is an ensemble of several machine learning models.