IACT event analysis with the MAGIC telescopes using deep convolutional neural networks with CTLearn

Abstract: The Major Atmospheric Gamma Imaging Cherenkov (MAGIC) telescope system consists of two imaging atmospheric Cherenkov telescopes (IACTs) and is located on the Canary island of La Palma. IACTs are excellent tools to inspect the very-high-energy (few tens of GeV and above) gamma-ray sky by capturing images of the air showers, originated by the absorption of gamma rays and cosmic rays by the atmosphere, through the detection of Cherenkov photons emitted in the shower. One of the main factors determining the sensitivity of IACTs to gamma-ray sources, in general, is how well reconstructed the properties (type, energy, and incoming direction) of the primary particle triggering the air shower are. We present how deep convolutional neural networks (CNNs) are being explored as a promising method for IACT full-event reconstruction. The performance of the method is evaluated on observational data using the standard MAGIC Analysis and Reconstruction Software, MARS, and CTLearn, a package for IACT event reconstruction through deep learning.