Evaluating the classification of Fermi BCUs from the 4FGL Catalog Using Machine Learning

Abstract

The recently published fourth Fermi Large Area Telescope source catalog (4FGL) reports 5065 gamma-ray sources in terms of direct observational gamma-ray properties. Among the sources, the largest population is the Active Galactic Nuclei (AGN), which consists of 3137 blazars, 42 radio galaxies, and 28 other AGNs. The blazar sample comprises 694 flat-spectrum radio quasars (FSRQs), 1131 BL Lac-type objects (BL Lacs), and 1312 blazar candidates of an unknown type (BCUs). The classification of blazars is difficult using optical spectroscopy given the limited knowledge with respect to their intrinsic properties, and the limited availability of astronomical observations. To overcome these challenges, machine learning algorithms are being investigated as alternative approaches. Using the 4FGL catalog, a sample of 3137 Fermi blazars with 23 parameters is systematically selected. Three established supervised machine learning algorithms (random forests (RFs), support vector machines (SVMs), artificial neural networks (ANNs)) are employed to general predictive models to classify the BCUs. We analyze the results for all of the different combinations of parameters. Interestingly, a previously reported trend the use of more parameters leading to higher accuracy is not found. Considering the least number of parameters used, combinations of eight, 12 or 10 parameters in the SVM, ANN, or RF generated models achieve the highest accuracy (Accuracy $\simeq$ 91.8\%, or $\simeq$ 92.9\%). Using the combined classification results from the optimal combinations of parameters, 724 BL Lac type candidates and 332 FSRQ type candidates are predicted; however, 256 remain without a clear prediction.

Accepted for publication in ApJ. 14 pages, 2 figures, 6 tables

References in corpus (19)

• Bright AGN Source List from the First Three Months of the Fermi Large Area Telescope All-Sky Survey
• The Spectral Energy Distributions of Fermi Blazars
• Machine Learning in Astronomy: a practical overview
• The jet-disc connection in AGN
• Intrinsic $\gamma$-ray luminosity, black hole mass, jet and accretion in Fermi blazars
• Constraints on minimum electron Lorentz factor and matter content of jets for a sample of bright Fermi blazars
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• On the BL Lacertae objects/radio quasars and the FRI/II dichotomy
• Gamma-Ray Active Galactic Nucleus Type through Machine-Learning Algorithms
• 3FGLzoo. Classifying 3FGL Unassociated Fermi-LAT Gamma-ray Sources by Artificial Neural Networks
• Discerning the $\gamma$-ray emitting region in the flat spectrum radio quasars
• Evaluating the optical classification of Fermi BCUs using machine learning
• Evidence for the Secondary Emission as the Origin of Hard Spectra in TeV Blazars
• Basic properties of Fermi blazars and the "blazar sequence"
• Bethe-Heitler cascades as a plausible origin of hard spectra in distant TeV blazars
• What Powers the Most Relativistic Jets? II: Flat Spectrum Radio Quasars
• Constraints on the location of the gamma-ray emission region for the gamma-ray-loud radio source GB 1310+487
• What determines the observational differences of blazars?
• FSRQ/BL Lac dichotomy as the magnetized advective accretion process around black holes: a unified classification of blazars