| Abstract : | The Fermi Large Area Telescope (LAT) has detected more than 7000 gamma-ray sources in the first 14 years of its operation. The major fraction of LAT point sources are Active Galactic Nuclei (AGN) and pulsars. Blazars constitute the largest portion of Fermi AGN and are divided into BL Lacertae objects (BL Lac), Flat Spectrum Radio Quasars (FSRQs), and blazars of unidentified type (BCUs). For a robust classification, one needs to consider not only the gamma-ray data but also the multi-wavelength information. In past, Swift, Gaia, SDSS, and WISE counterpart data are used for Fermi AGN classification. After the release of the VLA Sky Survey (VLASS) data, it is possible to supply information of radio counterparts also into the classification algorithms. We use machine learning techniques to classify AGN in the 4th data release of the Fermi-LAT point catalogue (4FGL-DR4), supported by potential multi-wavelength counterparts from Swift BAT/XRT, Gaia, SDSS, WISE, and VLASS. |
