Alert Classification for the ALeRCE Broker System: The Anomaly Detector

Vista sencilla de ítem
dc.contributor.authorPerez-Carrasco, Manuel
dc.contributor.authorCabrera-Vives, Guillermo
dc.contributor.authorHernandez-García, Lorena
dc.contributor.authorFörster, F.
dc.contributor.authorSanchez-Saez, Paula
dc.contributor.authorMuñoz Arancibia, Alejandra M.
dc.contributor.authorArredondo, Javier
dc.contributor.authorAstorga, Nicolás
dc.contributor.authorBauer, Franz E.
dc.contributor.authorBayo, Amelia
dc.contributor.authorCatelan, M.
dc.contributor.authorDastidar, Raya
dc.contributor.authorEstévez, P.A.
dc.contributor.authorLira, Paulina
dc.contributor.authorPignata, Giuliano
dc.date.accessioned2023-12-06T19:48:39Z
dc.date.available2023-12-06T19:48:39Z
dc.date.issued2023-10-01
dc.descriptionINDEXACIÓN: SCOPUS.es
dc.description.abstractAstronomical broker systems, such as Automatic Learning for the Rapid Classification of Events (ALeRCE), are currently analyzing hundreds of thousands of alerts per night, opening up an opportunity to automatically detect anomalous unknown sources. In this work, we present the ALeRCE anomaly detector, composed of three outlier detection algorithms that aim to find transient, periodic, and stochastic anomalous sources within the Zwicky Transient Facility data stream. Our experimental framework consists of cross-validating six anomaly detection algorithms for each of these three classes using the ALeRCE light-curve features. Following the ALeRCE taxonomy, we consider four transient subclasses, five stochastic subclasses, and six periodic subclasses. We evaluate each algorithm by considering each subclass as the anomaly class. For transient and periodic sources the best performance is obtained by a modified version of the deep support vector data description neural network, while for stochastic sources the best results are obtained by calculating the reconstruction error of an autoencoder neural network. Including a visual inspection step for the 10 most promising candidates for each of the 15 ALeRCE subclasses, we detect 31 bogus candidates (i.e., those with photometry or processing issues) and seven potential astrophysical outliers that require follow-up observations for further analysis. © 2023. The Author(s). Published by the American Astronomical Society.es
dc.identifier.citationAstronomical Journal, Volume 166, Issue 4, 1 October 2023, Article number 151es
dc.identifier.doi10.3847/1538-3881/ace0c1
dc.identifier.issn00046256
dc.identifier.urihttps://repositorio.unab.cl/xmlui/handle/ria/54470
dc.language.isoenes
dc.publisherAmerican Astronomical Societyes
dc.rights.licenseCC BY 4.0 DEED Attribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleAlert Classification for the ALeRCE Broker System: The Anomaly Detectores
dc.typeArtículoes
Archivos
Bloque original
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
Perez-Carrasco_2023_AJ_166_151.pdf
Tamaño:
49.7 MB
Formato:
Adobe Portable Document Format
Descripción:
TEXTO COMPLETO EN INGLÉS
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
FCE - Artículos de Revista