Classification of Fermi-LAT blazars with Bayesian neural networks

• Main Authors: Butter, A. (Author), Finke, T. (Author), Keil, F. (Author), Kramer, M. (Author), Manconi, S. (Author)
• Format: Article
• Language: English
• Published: IOP Publishing Ltd 2022
• Subjects: active galactic nuclei; gamma ray experiments; gamma ray theory; Machine learning
• Online Access: View Fulltext in Publisher
• ISBN: 14757516 (ISSN)
• DOI: 10.1088/1475-7516/2022/04/023

The use of Bayesian neural networks is a novel approach for the classification of 3-ray sources. We focus on the classification of Fermi-LAT blazar candidates, which can be divided into BL Lacertae objects and Flat Spectrum Radio Quasars. In contrast to conventional dense networks, Bayesian neural networks provide a reliable estimate of the uncertainty of the network predictions. We explore the correspondence between conventional and Bayesian neural networks and the effect of data augmentation. We find that Bayesian neural networks provide a robust classifier with reliable uncertainty estimates and are particularly well suited for classification problems that are based on comparatively small and imbalanced data sets. The results of our blazar candidate classification are valuable input for population studies aimed at constraining the blazar luminosity function and to guide future observational campaigns. © 2022 IOP Publishing Ltd and Sissa Medialab.