Galactic center GeV excess and classification of Fermi-LAT sources with machine learning

TL;DR

This paper uses machine learning to classify Fermi-LAT gamma-ray sources and investigates their role in explaining the Galactic center GeV excess, finding MSP-like sources could account for it.

Contribution

It introduces a multi-class machine learning classification of Fermi-LAT sources to analyze the distribution of millisecond pulsar-like sources near the Galactic center.

Findings

MSP-like sources' distribution matches the GC excess hypothesis.

Machine learning effectively classifies gamma-ray sources.

Supports MSPs as a potential explanation for the gamma-ray excess.

Abstract

Excess of gamma rays with a spherical morphology around the Galactic center (GC) observed in the Fermi large area telescope (LAT) data is one of the most intriguing features in the gamma-ray sky. The excess has been interpreted by annihilating dark matter as well as emission from a population of unresolved millisecond pulsars (MSPs). We use a multi-class classification of Fermi-LAT sources with machine learning to study the distribution of MSP-like sources among unassociated Fermi-LAT sources near the GC. We find that the source count distribution of MSP-like sources is comparable with the MSP explanation of the GC excess.