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

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.

Accepted for publication in the Astronomical Journal (AJ)

References in corpus (21)

• The NumPy array: a structure for efficient numerical computation
• X-ray Properties of Black-Hole Binaries
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• Modelling the behaviour of accretion flows in X-ray binaries
• The Zwicky Transient Facility: Data Processing, Products, and Archive
• Modeling the Time Variability of SDSS Stripe 82 Quasars as a Damped Random Walk
• Active Galactic Nuclei: what's in a name?
• The Discovery of the First "Changing Look" Quasar: New Insights into the Physics & Phenomenology of AGN
• The 5th edition of the Roma-BZCAT. A short presentation
• The Half Million Quasars (HMQ) Catalogue
• The destruction and recreation of the X-ray corona in a changing-look Active Galactic Nucleus
• A recurrent neural network for classification of unevenly sampled variable stars
• Understanding extreme quasar optical variability with CRTS: I. Major AGN flares
• A New Catalogue of Type 1 AGN and its Implication on the AGN Unified Model
• Optical variability of AGN in the PTF/iPTF survey
• A new class of flares from accreting supermassive black holes
• A Morphological Classification Model to Identify Unresolved PanSTARRS1 Sources: Application in the ZTF Real-Time Pipeline
• Improving Damped Random Walk parameters for SDSS Stripe 82 Quasars with Pan-STARRS1
• Anomaly detection in the Zwicky Transient Facility DR3
• Near Infrared Variability of obscured and unobscured X-ray selected AGN in the COSMOS field
• Characterization of Optical Light Curves of Extreme Variability Quasars Over a ~16-yr Baseline

Cited by in corpus (1)

• Convolutional Deep Denoising Autoencoders for Radio Astronomical Images