Artificial Neural Network classification of 4FGL sources

ABSTRACT The Fermi-LAT DR1 and DR2 4FGL catalogues feature more than 5000 gamma-ray sources of which about one fourth are not associated with already known objects, approximately third blazars uncertain nature. We perform a three-category classification the independently, using an ensemble Artificial Neural Networks (ANNs) to characterize them based on likelihood being Pulsar (PSR), BL Lac type blazar (BLL) or Flat Spectrum Radio Quasar (FSRQ). identify candidate PSR, BLL, FSRQ among unassociated approximate equipartition three categories select 10 outliers as potentially interesting for follow-up studies.