2020/12/31 by B. Fraga, Bernardo M. O. Fraga, Ulisses Barres de Almeida +10
Computer Science · Physics and Astronomy · #Artificial intelligence #Astronomy #Astrophysics #Astrophysics and Cosmic Phenomena #Blazar #Computational Physics and Python Applications #Computer science #Dark Matter and Cosmic Phenomena #Galaxy #Gamma ray #Identification (biology) #Physics #Population #Spectral energy distribution #astro-ph.HE
paper · pdf · doi:10.1093/mnras/stab1349
published as MNRAS, Volume 505, Issue 1, July 2021, pages 1268-1279 · 13 pages, 17 figures, updated with accepted version
openalex publication_date 2021/05/10 · arxiv created 2021/06/04 · arxiv updated 2021/06/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
ABSTRACT Blazars are among the most studied sources in high-energy astrophysics as they form the largest fraction of extragalactic gamma-ray sources and are considered prime candidates for being the counterparts of high-energy astrophysical neutrinos. Their reliable identification amid the many faint radio sources is a crucial step for multimessenger counterpart associations. As the astronomical community prepares for the coming of a number of new facilities able to survey the non-thermal sky at unprecedented depths, from radio to gamma-rays, machine-learning techniques for fast and reliable source identification are ever more relevant. The purpose of this work was to develop a deep learning architecture to identify Blazar within a population of active galactic nucleus (AGN) based solely on non-contemporaneous spectral energy distribution information, collected from publicly available multifrequency catalogues. This study uses an unprecedented amount of data, with spectral energy distributions (SEDs) for ≈14 000 sources collected with the Open Universe VOU-Blazars tool. It uses a convolutional long short-term memory neural network purposefully built for the problem of SED classification, which we describe in detail and validate. The network was able to distinguish Blazars from other types of active galactic nuclei (AGNs) to a satisfying degree (achieving a receiver operating characteristic area under curve of 0.98), even when trained on a reduced subset of the whole sample. This initial study does not attempt to classify Blazars among their different sub-classes, or quantify the likelihood of any multifrequency or multimessenger association, but is presented as a step towards these more practically oriented applications.