4FGLzoo. Classifying Fermi-LAT uncertain gamma-ray sources by machine learning analysis

TL;DR

This paper employs machine learning to classify uncertain gamma-ray sources from Fermi-LAT data, significantly reducing the unknown sources and aiding in understanding the gamma-ray sky.

Contribution

Introduces a machine learning approach to classify gamma-ray sources, decreasing uncertain classifications from 54% to under 12%, and creating a new categorization of Fermi sources.

Findings

Uncertain sources classified with high confidence as blazars.

Reduction of unknown sources from 54% to less than 12%.

Facilitates targeted multi-wavelength follow-up studies.

Abstract

Since 2008 August the Fermi Large Area Telescope (LAT) has provided continuous coverage of the gamma-ray sky yielding more than 5000 gamma-ray sources, but 54% of the detected sources remain with no certain or unknown association with a low energy counterpart. Rigorous determination of class type for a gamma-ray source requires the optical spectrum of the correct counterpart but optical observations are demanding and time-consuming, then machine learning techniques can be a powerful alternative for screening and ranking. We use machine learning techniques to select blazar candidates among uncertain sources characterized by gamma-ray properties very similar to those of Active Galactic Nuclei. Consequently, the percentage of sources of uncertain type drops from 54% to less than 12% predicting a new zoo for the Fermi gamma-ray sources. The result of this study opens up new considerations on the population of the gamma energy sky, and it will facilitate the planning of significant samples for rigorous analysis and multi-wavelength observational campaigns.