BEXCO - Room F(201/202/203/204)
[GA119] The texture of the Galactic Center Excess (GCE) from machine learning methods
An excess of gamma rays from the Inner Galaxy in the Fermi LAT data has been identified, the GCE. This emission has been interpreted as a possible signature of the annihilation of dark matter particles, or as originating from a collection of unresolved point sources, such as gamma-ray millisecond pulsars. We explore the clustering properties of the diffuse emission arising from a population of gamma-ray point sources and from the annihilation of dark matter particles in the halo of the Galaxy using machine learning methods. We analyze the morphology of the GeV excess within a +/- 15 degree box around the Galactic Center using a convolutional neural network to unveiling the diffuse vs granular nature of the GCE. For both dark matter and point sources we adopt the spatial distribution and spectrum to fit the claimed GeV excess, we create realistic simulations of the Fermi LAT data to generate training and test samples to validate our novel method.