| Name: | Anilkumar Tolamatti |
| Affiliation: | BARC, Mumbai |
| Conference ID : | ASI2023_550 |
| Title : | Machine Learning Approach for Classification of Uncertain Type Blazar Candidates in the Fourth Fermi-LAT Catalogue |
| Authors : | A Tolamatti* , K K Singh*, K K Yadav* ,
*Astrophysical Sciences Division, Bhabha Atomic Research Centre, Mumbai 400085, India
*Homi Bhabha National Institute, Anushakti Nagar, Mumbai 400094, India |
| Mode of Presentation: | Poster |
| Abstract Category : | Extragalactic Astronomy |
| Abstract : | The Large Area Telescope on board Fermi satellite (Fermi-LAT) has revolutionized the field of high energy astrophysics with a many fold increase in the number of known gamma-ray sources over a decade. Recent third release (DR3) of the fourth Fermi-LAT catalogue (4FGL) features a total of 6658 sources with approximately 2157 unassociated sources. Despite continuous ongoing efforts to associate unidentified sources with possible counterparts using information from intensive multi-wavelength observation campaigns, the catalogue still shows a substantial fraction of sources without a plausible association. Majority of the associated sources in the 4FGL catalogue belong to the blazar class. In this contribution, we report results from the classification of 112 blazar candidates of uncertain type using informations from the X-ray, UV, Optical and IR observations. We adopt the Extreme Gradient Boosting (XGB) algorithm to segregate these sources into blazar subclasses namely BL Lacertae objects (BL Lacs) and Flat Spectrum Radio Quasars (FSRQs). Out 112 candidates, 66 are identified as BL Lacs and 5 as FSRQs whereas nature of remaining sources remains ambiguous. |
