Confirming new changing--look AGNs discovered through optical variability using a random-forest based light curve classifier

TL;DR

This study develops an automated method using a random-forest classifier on light curves to identify changing-look AGNs, successfully confirming several candidates through spectroscopic follow-up, thus advancing understanding of AGN evolution.

Contribution

The paper introduces a novel automated approach combining optical variability data and machine learning to efficiently identify changing-look AGNs from a spectroscopic sample.

Findings

Successfully identified 30 CL candidates from initial 60

Spectroscopic follow-up confirmed 4 clear CL AGNs

Achieved a success rate of at least 66% in candidate selection

Abstract

Determining the frequency and duration of changing--look (CL) active galactic nuclei (AGNs) phenomena, where the optical broad emission lines appear or disappear, is crucial to understand the evolution of the accretion flow around supermassive black holes. We present a strategy to select new CL candidates starting from a spectroscopic type 2 AGNs sample and searching for current type 1 photometric variability. We use the publicly available Zwicky Transient Facility (ZTF) alert stream and the Automatic Learning for the Rapid Classification of Events (ALeRCE) light curve classifier to produce a list of CL candidates with a highly automated algorithm, resulting in 60 candidates. Visual inspection reduced the sample to 30. We performed new spectroscopic observations of six candidates of our clean sample, without further refinement, finding the appearance of clear broad Balmer lines in four of them and tentative evidence of type changes in the remaining two, which suggests a promising success rate of $\geq66$ per cent for this CL selection method.