Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours

TL;DR

This paper develops a deep learning-based anomaly detection method using Variational Recurrent Autoencoders and Isolation Forests to identify changing-state AGNs in large datasets, successfully finding promising candidates.

Contribution

It introduces a novel anomaly detection framework combining VRAE and IF to detect changing-state AGNs in massive datasets, addressing the scarcity of known examples.

Findings

Identified 75 promising changing-state AGN candidates

Successfully applied deep learning to large astronomical datasets

Demonstrated effectiveness of anomaly detection in astrophysical variability

Abstract

The classic classification scheme for Active Galactic Nuclei (AGNs) was recently challenged by the discovery of the so-called changing-state (changing-look) AGNs (CSAGNs). The physical mechanism behind this phenomenon is still a matter of open debate and the samples are too small and of serendipitous nature to provide robust answers. In order to tackle this problem, we need to design methods that are able to detect AGN right in the act of changing-state. Here we present an anomaly detection (AD) technique designed to identify AGN light curves with anomalous behaviors in massive datasets. The main aim of this technique is to identify CSAGN at different stages of the transition, but it can also be used for more general purposes, such as cleaning massive datasets for AGN variability analyses. We used light curves from the Zwicky Transient Facility data release 5 (ZTF DR5), containing a sample of 230,451 AGNs of different classes. The ZTF DR5 light curves were modeled with a Variational Recurrent Autoencoder (VRAE) architecture, that allowed us to obtain a set of attributes from the VRAE latent space that describes the general behaviour of our sample. These attributes were then used as features for an Isolation Forest (IF) algorithm, that is an anomaly detector for a "one class" kind of problem. We used the VRAE reconstruction errors and the IF anomaly score to select a sample of 8,809 anomalies. These anomalies are dominated by bogus candidates, but we were able to identify 75 promising CSAGN candidates.