Searching for AGN and Pulsar Candidates in 4FGL Unassociated Sources Using Machine Learning

Abstract

In a new release of the fourth Fermi Large Area Telescope source catalog (4FGL) in September a) , 5065 γ-ray sources are reported, including 3207 active galactic nuclei (AGNs), 239 pulsars, 190 other sources and 1429 unassociated sources. We employ two different supervised machine learning classifiers, combined with the direct observation parameters given by the 4FGL fits table b) , to search for sources potentially classified as AGNs and pulsars in the 1429 unassociated sources. In order to reduce the error caused by the large difference in the sizes of samples, we divide the classification process into two separate steps in order to identify the AGNs and the pulsars. First, we select the identified AGNs from all of the samples, and then select the identified pulsars from the remaining. Using the 4FGL sources associated or identified as AGNs, pulsars, and other sources with the features selected through the K-S test, we trained, optimized, and tested our classifier models. Then, the models are applied to classify the 1429 unassociated sources. According to the direct calculation results of the two classifiers, we show the sensitivity, specificity, accuracy in each step, and the class of unassociated sources given by each classifier. The accuracy obtained in the first step is approximately 95%; in the second step, the obtained overall accuracy is approximately 80%. Combining the results of the two classifiers, we predict that there are 674 AGN-type candidates, 86 pulsar-type candidates, 177 other types of γ-ray candidates, and 492 of uncertain type.

On machine learning search for gravitational lenses

“…ML provides computational algorithms that improve the accuracy through experience [17] and is already used in astrophysical problems e.g. for CMB foreground reducing [22], search of AGN and pulsars in Fermi catalog [28] and other cases [5,6,9].…”

An Empirical “High-confidence” Candidate Zone for Fermi BL Lacertae Objects

“…On the other hand, BCUs are those sources without a confirmed classifications due to the missing representative features on optical spectrum (BCU I), synchrotron peak frequencies of SED (BCU II), and/or their broadband emissions (BCU III) (see Ackermann et al 2015;Acero et al 2015 for the details and references therein). Studying such a large sample of BCUs is crucial to understand of the physics of γ-ray emission of blazars (e.g., Singal et al 2012;Singal 2015;Fan et al 2016;Kang et al 2018Kang et al , 2019aZhu et al 2020).…”

Blazar Radio and Optical Survey (BROS): A catalog of blazar candidates showing flat radio spectrum and their optical identification in Pan-STARRS1 Surveys

“…In the 4FGL catalog, however, 657 sources (13.0%) at high galactic latitude |b| > 10 • are still unassociated, despite their location. The nature of these sources has yet to be resolved; however, their locations and multi-wavelength properties suggested that most of them are blazars (e. g., Liodakis & Blinov 2019;Zhu et al 2020). To firmly identify them as blazars, flat spectrum features in the radio band would be required, as one of the most important characteristics of blazars (Urry & Padovani 1995a).…”