Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue The Astronomical Journal Année : 2021

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

P. Sánchez-Sáez
  • Fonction : Auteur
Hernan Lira
  • Fonction : Auteur
  • PersonId : 1102200
Luis Martí
Nayat Sanchez-Pi
  • Fonction : Auteur
  • PersonId : 1102034
J. Arredondo
  • Fonction : Auteur
A. Bayo
G. Cabrera-Vives
  • Fonction : Auteur
C. Donoso-Oliva
  • Fonction : Auteur
P. A. Estévez
  • Fonction : Auteur
S. Eyheramendy
  • Fonction : Auteur
F. Förster
  • Fonction : Auteur
L. Hernández-García
  • Fonction : Auteur
A. M. Muñoz Arancibia
  • Fonction : Auteur
M. Pérez-Carrasco
  • Fonction : Auteur
M. Sepúlveda
  • Fonction : Auteur
J. R. Vergara
  • Fonction : Auteur

Résumé

The classic classification scheme for active galactic nuclei (AGNs) was recently challenged by the discovery of the so-called changing-state (changing-look) AGNs. 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 AGNs right in the act of changing state. Here we present an anomaly-detection technique designed to identify AGN light curves with anomalous behaviors in massive data sets. 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 data sets 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 behavior 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 8809 anomalies. These anomalies are dominated by bogus candidates, but we were able to identify 75 promising CSAGN candidates.
Fichier principal
Vignette du fichier
aj_162_5_206.pdf (2.31 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03294849 , version 1 (20-10-2021)

Licence

Paternité

Identifiants

Citer

P. Sánchez-Sáez, Hernan Lira, Luis Martí, Nayat Sanchez-Pi, J. Arredondo, et al.. Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours. The Astronomical Journal, 2021, 162 (5), ⟨10.3847/1538-3881/ac1426⟩. ⟨hal-03294849⟩

Collections

INRIA INRIA-CHILE
104 Consultations
72 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More