Automated algorithms to build Active Galactic Nuclei classifiers

TL;DR

This paper develops machine learning models using X-ray and optical data to classify Active Galactic Nuclei and determine their types, achieving high accuracy and demonstrating robustness with different redshift data.

Contribution

Introduces tree-based machine learning classifiers for AGN and their types, trained on XMM-Newton and SDSS data, with detailed performance evaluation.

Findings

High precision (94%) and recall (93%) for AGN classification.

Type 1/2 classifier achieves 74% precision and 80% recall for type 2 AGN.

Performance remains robust with photometric redshifts, but declines without redshift information.

Abstract

We present a machine learning model to classify Active Galactic Nuclei (AGN) and galaxies (AGN-galaxy classifier) and a model to identify type 1 (optically unabsorbed) and type 2 (optically absorbed) AGN (type 1/2 classifier). We test tree-based algorithms, using training samples built from the X-ray Multi-Mirror Mission -Newton (XMM-Newton) catalogue and the Sloan Digital Sky Survey (SDSS), with labels derived from the SDSS survey. The performance was tested making use of simulations and of cross-validation techniques. With a set of features including spectroscopic redshifts and X-ray parameters connected to source properties (e.g. fluxes and extension), as well as features related to X-ray instrumental conditions, the precision and recall for AGN identification are 94 and 93 per cent, while the type 1/2 classifier has a precision of 74 per cent and a recall of 80 per cent for type 2 AGN. The performance obtained with photometric redshifts is very similar to that achieved with spectroscopic redshifts in both test cases, while there is a decrease in performance when excluding redshifts. Our machine learning model trained on X-ray features can accurately identify AGN in extragalactic surveys. The type 1/2 classifier has a valuable performance for type 2 AGN, but its ability to generalise without redshifts is hampered by the limited census of absorbed AGN at high redshift.