Machine learning applied to multifrequency data in astrophysics: blazar classification

Autor(es)

Arsioli, B. ^{[1, 2]} ; Dedin, P. ^[2]

Afiliação do(s) autor(es)

^[1] ICRANet, Pzza Repubbl 10, I-65122 Pescara - Italy

^[2] Univ Estadual Campinas, Gleb Wataghin Phys Inst, Rua S Buarque de Holanda 777, BR-13083859 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Monthly Notices of the Royal Astronomical Society; v. 498, n. 2, p. 1750-1764, OCT 2020.
• Citações Web of Science: 0

Resumo

The study of machine learning (ML) techniques for the autonomous classification of astrophysical sources is of great interest, and we explore its applications in the context of a multifrequency data-frame. We test the use of supervised ML to classify blazars according to its synchrotron peak frequency, either lower or higher than 10(15) Hz. We select a sample with 4178 blazars labelled as 1279 high synchrotron peak (HSP: nu-peak > 10(15) Hz) and 2899 low synchrotron peak (LSP: nu-peak < 10(15) Hz). A set of multifrequency features were defined to represent each source that includes spectral slopes (alpha(nu 1,nu 2)) between the radio, infra-red, optical, and X-ray bands, also considering IR colours. We describe the optimization of five ML classification algorithms that classify blazars into LSP or HSP: Random forests (RFs), support vector machine (SVM), K-nearest neighbours (KNN), Gaussian Naive Bayes (GNB), and the Ludwig auto-ML framework. In our particular case, the SVM algorithm had the best performance, reaching 93 per cent of balanced accuracy. A joint-feature permutation test revealed that the spectral slopes alpha-radio-infrared (IR) and alpha-radio-optical are the most relevant for the ML modelling, followed by the IR colours. This work shows that ML algorithms can distinguish multifrequency spectral characteristics and handle the classification of blazars into LSPs and HSPs. It is a hint for the potential use of ML for the autonomous determination of broadband spectral parameters (as the synchrotron nu-peak), or even to search for new blazars in all-sky data bases. (AU)

• Processo FAPESP: 19/08956-2 - Fenomenologia de oscilações de neutrinos
• Beneficiário: Pedro Dedin Neto
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto