Searching for Changing-state AGNs in Massive Data Sets. I. Applying Deep Learning and Anomaly-detection Techniques to Find AGNs with Anomalous Variability Behaviors

Vista sencilla de ítem
dc.contributor.authorSánchez-Sáez, P.
dc.contributor.authorLira, H.
dc.contributor.authorMartí, L.
dc.contributor.authorSánchez-Pi, N.
dc.contributor.authorArredondo, J.
dc.contributor.authorBauer, F. E.
dc.contributor.authorBayo, Amelia
dc.contributor.authorCabrera-Vives, G.
dc.contributor.authorDonoso-Oliva, C.
dc.contributor.authorEstévez, P. A.
dc.contributor.authorEyheramendy, S.
dc.contributor.authorFörster, F.
dc.contributor.authorHernández-García, L.
dc.contributor.authorMuñoz Arancibia, A. M.
dc.contributor.authorPérez-Carrasco, M.
dc.contributor.authorSepúlveda, M.
dc.contributor.authorVergara, J. R.
dc.date.accessioned2022-11-30T02:46:55Z
dc.date.available2022-11-30T02:46:55Z
dc.date.issued2021
dc.description.abstractThe 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.en_ES
dc.facultadFacultad de Cienciasen_ES
dc.file.nameSanchez_Sea2021.pdf
dc.identifier.citationP. Sánchez-Sáez et al 2021 AJ 162 206en_ES
dc.identifier.doihttps://doi.org/10.3847/1538-3881/ac1426
dc.identifier.urihttp://repositoriobibliotecas.uv.cl/handle/uvscl/7531
dc.languageen
dc.publisherAmerican Astronomical Society (Aas)
dc.rights© 2021. The American Astronomical Society. All rights reserved
dc.sourceThe Astronomical Journal
dc.subjectACTIVE GALACTIC NUCLEIen_ES
dc.subjectASTRONOMY DATA ANALYSISen_ES
dc.subjectSURVEYSen_ES
dc.subjectINTERDISCIPLINARY ASTRONOMYen_ES
dc.titleSearching for Changing-state AGNs in Massive Data Sets. I. Applying Deep Learning and Anomaly-detection Techniques to Find AGNs with Anomalous Variability Behaviors
dc.typeArticulo
uv.departamentoInstituto de Fisica y Astronomia

Archivos

Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
Sanchez_Sea2021.pdf
Tamaño:
2.31 MB
Formato:
Adobe Portable Document Format
Descargar

Colecciones

Artículos investigadores UV