A New Mid-Infrared and X-ray Machine Learning Algorithm to Discover Compton-thick AGN

TL;DR

This paper introduces a machine learning algorithm that combines mid-infrared and X-ray data to accurately predict the obscuration levels of active galactic nuclei, aiding in the discovery of Compton-thick AGN.

Contribution

A novel multi-wavelength machine learning method for predicting AGN column densities, especially effective for highly obscured sources, improving identification of Compton-thick AGN.

Findings

Achieved 75% classification accuracy in predicting NH values.

Correlation coefficient of 0.86 indicates strong predictive performance.

Effective for AGN with Log(NH) < 22.5, expanding detection capabilities.

Abstract

We present a new method to predict the line-of-sight column density (NH) values of active galactic nuclei (AGN) based on mid-infrared (MIR), soft, and hard X-ray data. We developed a multiple linear regression machine learning algorithm trained with WISE colors, Swift-BAT count rates, soft X-ray hardness ratios, and an MIR-soft X-ray flux ratio. Our algorithm was trained off 451 AGN from the Swift-BAT sample with known NH and has the ability to accurately predict NH values for AGN of all levels of obscuration, as evidenced by its Spearman correlation coefficient value of 0.86 and its 75% classification accuracy. This is significant as few other methods can be reliably applied to AGN with Log(NH <) 22.5. It was determined that the two soft X-ray hardness ratios and the MIR-soft X-ray flux ratio were the largest contributors towards accurate NH determination. This algorithm will contribute significantly to finding Compton-thick (CT-) AGN (NH >= 10^24 cm^-2), thus enabling us to determine the true intrinsic fraction of CT-AGN in the local universe and their contribution to the Cosmic X-ray Background.