期刊
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
卷 505, 期 1, 页码 1268-1279出版社
OXFORD UNIV PRESS
DOI: 10.1093/mnras/stab1349
关键词
methods: data analysis; astronomical data bases: miscellaneous; virtual observatory tools; galaxies: active; BL Lacertae objects: general
资金
- Serrapilheira Institute [Serra -1812.26906]
- Fundacao de Amparo a Pesquisa do Estado do Rio de Janeiro (FAPERJ) Young Scientist Fellowship [E26/202.818/2019]
- Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq) [311997/2019-8]
- Technische Universitat Munchen -Institute for Advanced Studies - German Excellence Initiative (European Union Seventh Framework Programme) [291763]
- Excellence Cluster ORIGINS - Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy [EXEC-2094 -390783311]
Blazars are a highly studied source in high-energy astrophysics and their reliable identification is crucial for multimessenger counterpart associations. This study developed a deep learning architecture to identify Blazars based on non-contemporaneous spectral energy distribution information, achieving satisfying results.
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 approximate to 14000 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据