Analyzing {\gamma}-rays of the Galactic Center with Deep Learning
High Energy Astrophysical Phenomena
2018-05-29 v2 High Energy Physics - Phenomenology
Abstract
We present a new method to interpret the -ray data of our inner Galaxy as measured by the Fermi Large Area Telescope (Fermi LAT). We train and test convolutional neural networks with simulated Fermi-LAT images based on models tuned to real data. We use this method to investigate the origin of an excess emission of GeV -rays seen in previous studies. Interpretations of this excess include rays created by the annihilation of dark matter particles and rays originating from a collection of unresolved point sources, such as millisecond pulsars. Our new method allows precise measurements of the contribution and properties of an unresolved population of -ray point sources in the interstellar diffuse emission model.
Cite
@article{arxiv.1708.06706,
title = {Analyzing {\gamma}-rays of the Galactic Center with Deep Learning},
author = {Sascha Caron and Germán A. Gómez-Vargas and Luc Hendriks and Roberto Ruiz de Austri},
journal= {arXiv preprint arXiv:1708.06706},
year = {2018}
}
Comments
24 pages, 11 figures