Gradient boosting decision trees classification of blazars of uncertain type in the fourth Fermi-LAT catalog

Abstract

The deepest all-sky survey available in the $\gamma$-ray band - the last release of the Fermi-LAT catalogue (4FGL-DR3) based on the data accumulated in 12 years, contains more than 6600 sources. The largest population among the sources is blazar subclass - 3743, $60.1\%$ of which are classified as BL Lacertae objects (BL Lacs) or Flat Spectrum Radio Quasars (FSRQs), while the rest are listed as blazar candidates of uncertain type (BCU) as their firm optical classification is lacking. The goal of this study is to classify BCUs using different machine learning algorithms which are trained on the spectral and temporal properties of already classified BL Lacs and FSRQs. Artificial Neural Networks, \textit{XGBoost} and LightGBM algorithms are employed to construct predictive models for BCU classification. Using 18 input parameters of 2219 BL Lacs and FSRQs, we train (80\% of the sample) and test (20\%) these algorithms and find that LightGBM model, state-of-the-art classification algorithm based on gradient boosting decision trees, provides the highest performance. Based on our best model, we classify 825 BCUs as BL Lac candidates and 405 as FSRQ candidates, however, 190 remain without a clear prediction but the percentage of BCUs in 4FGL is reduced to 5.1\%. The $\gamma$-ray photon index, synchrotron peak frequency, and high energy peak frequency of a large sample are used to investigate the relationship between FSRQs and BL Lacs (LBLs, IBLs, and HBLs).

Accepted for publication in MNRAS

References in corpus (13)

• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Fourth Catalog of Active Galactic Nuclei Detected by the Fermi Large Area Telescope -- Data Release 3
• Fast cosmological parameter estimation using neural networks
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• Efficient Selection of Quasar Candidates Based on Optical and Infrared Photometric Data Using Machine Learning
• 3FGLzoo. Classifying 3FGL Unassociated Fermi-LAT Gamma-ray Sources by Artificial Neural Networks
• Classification of Fermi-LAT unidentified gamma-ray sources using CatBoost gradient boosting decision trees
• Classifying Stars, Galaxies and AGN in CLAUDS+HSC-SSP Using Gradient Boosted Decision Trees
• Predicting the redshift of gamma-ray loud AGNs using Supervised Machine Learning: Part 2
• Artificial Neural Network Classification of 4FGL Sources
• Machine Learning applied to Multifrequency Data in Astrophysics: Blazar Classification
• A Hybrid method of accurate classification for Blazars Of Uncertain Type in Fermi LAT Catalogs
• Classification of Fermi-LAT blazars with Bayesian neural networks

Cited by in corpus (6)

• Galaxy stellar and total mass estimation using machine learning
• Classification of the \emph{Fermi}-LAT Blazar Candidates of Uncertain type using eXtreme Gradient Boosting
• Fermi LAT AGN classification using supervised machine learning
• Searching for dark matter subhalos in the Fermi-LAT catalog with Bayesian neural networks
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Cluster optical depth and pairwise velocity estimation using machine learning