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

TL;DR

This study applies machine learning algorithms to classify uncertain gamma-ray sources in the 4FGL catalog, achieving over 91% accuracy in distinguishing blazar types using minimal parameters.

Contribution

It demonstrates the effectiveness of supervised machine learning models in classifying Fermi blazars and identifies optimal parameter combinations for high accuracy.

Findings

Random forests, SVMs, and ANNs achieve over 91% accuracy.

Optimal models use 8 to 12 parameters for best performance.

Predicted 724 BL Lac and 332 FSRQ candidates with high confidence.

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.