Search for gamma-ray-emitting active galactic nuclei in the Fermi-LAT unassociated sample using machine learning

Abstract

The second Fermi-LAT source catalog (2FGL) is the deepest all-sky survey available in the gamma-ray band. It contains 1873 sources, of which 576 remain unassociated. Machine-learning algorithms can be trained on the gamma-ray properties of known active galactic nuclei (AGN) to find objects with AGN-like properties in the unassociated sample. This analysis finds 231 high-confidence AGN candidates, with increased robustness provided by intersecting two complementary algorithms. A method to estimate the performance of the classification algorithm is also presented, that takes into account the differences between associated and unassociated gamma-ray sources. Follow-up observations targeting AGN candidates, or studies of multiwavelength archival data, will reduce the number of unassociated gamma-ray sources and contribute to a more complete characterization of the population of gamma-ray emitting AGN.

7 pages, 6 figures, 3 tables; accepted for publication in ApJ. A full version of Table 3 in ASCII format is available as ancillary file

References in corpus (6)

• CRATES: An All-Sky Survey of Flat-Spectrum Radio Sources
• Roma-BZCAT: A multifrequency catalogue of Blazars
• CGRaBS: An All-Sky Survey of Gamma-Ray Blazar Candidates
• A Survey of 56 Mid-latitude EGRET Error Boxes for Radio Pulsars
• Unveiling the nature of the unidentified gamma-ray sources IV: the $\text{Swift}$ catalog of potential X-ray counterparts
• 0FGL J1830.3+0617: A Fermi Blazar Near the Galactic Plane

Cited by in corpus (37)

• Fermi Large Area Telescope Fourth Source Catalog
• Optical spectroscopic observations of $\gamma$-ray blazar candidates VI. Further observations from TNG, WHT, OAN, SOAR and Magellan telescopes
• The Extragalactic Gamma-ray Sky in the Fermi era
• Optical Spectroscopic Observations of Gamma-ray Blazar Candidates. V. TNG, KPNO, and OAN Observations of Blazar Candidates of Uncertain Type in the Northern Hemisphere
• Optical spectroscopic observations of gamma-ray blazar candidates II. The 2013 KPNO campaign in the Northern Hemisphere
• Blazar Flaring Patterns (B-FlaP): Classifying Blazar Candidates of Uncertain type in the third Fermi-LAT catalog by Artificial Neural Networks
• Refining the associations of the Fermi Large Area Telescope Source Catalogs
• Optical spectroscopic survey of a sample of Unidentified Fermi objects
• Research and characterisation of blazar candidates among the Fermi/LAT 3FGL catalogue using multivariate classifications
• Evaluating the optical classification of Fermi BCUs using machine learning
• Optical spectroscopic survey of a sample of Unidentified Fermi objects: II
• Upper limits from five years of blazar observations with the VERITAS Cherenkov telescopes
• Optical spectroscopic observations of gamma-ray blazar candidates VIII: the 2016-2017 follow up campaign carried out at SPM, NOT, KPNO and SOAR telescopes
• An optical overview of blazars with LAMOST I: Hunting changing-look blazars and new redshift estimates
• Using an Artificial Neural Network to Classify Multi-component Emission Line Fits
• A new method to unveil blazars among multi-wavelength counterparts of Unassociated Fermi gamma-ray Sources
• Optical spectroscopic observations of gamma-ray blazar candidates. IX. Optical archival spectra and further observations from SOAR and OAGH
• Classification of Blazar Candidates of Uncertain Type from the Fermi LAT 8-Year Source Catalog with an Artificial Neural Network
• Optical spectroscopic observations of low-energy counterparts of Fermi-LAT gamma-ray sources
• Classification of Fermi-LAT sources with deep learning using energy and time spectra
• Evaluating the classification of Fermi BCUs from the 4FGL Catalog Using Machine Learning
• Searching for AGN and Pulsar Candidates in 4FGL Unassociated Sources Using Machine Learning
• Predicting the redshift of gamma-ray loud AGNs using Supervised Machine Learning: Part 2
• Optimizing neural network techniques in classifying Fermi-LAT gamma-ray sources
• Machine learning methods for constructing probabilistic Fermi-LAT catalogs
• Artificial Neural Network Classification of 4FGL Sources
• Classifications of Fermi-LAT unassociated sources in multiple machine learning methods
• Using Neural Networks to Differentiate Newly Discovered BL Lacs and FSRQs among the 4FGL Unassociated Sources Employing Gamma-ray, X-ray, UV/Optical and IR Data
• The $\gamma$-ray sky seen at X-ray energies II: the Swift hunt of Fermi BL Lac objects among unidentified gamma-ray sources
• Classification of blazar candidates of unknown type in Fermi 4LAC by unanimous voting from multiple Machine Learning Algorithms
• On the physical association of Fermi-LAT blazars with their low-energy counterparts
• Search for AGN counterparts of unidentified Fermi-LAT sources with optical polarimetry: Demonstration of the technique
• Optical spectroscopic characterization of Fermi blazar candidates of uncertain type with TNG and DOT: First Results
• Search for the multiwavelength counterparts to extragalactic unassociated Fermi γ-ray sources
• Assessing the capability of random forest to predict the evolution of enhanced gamma-ray states of active galactic nuclei
• Classification of Fermi-LAT blazars with Bayesian neural networks
• Identifying AGN host galaxies by Machine Learning with HSC+WISE