Abstract
In this paper, we use artificial neural networks (ANNs) techniques to reconstruct the mass composition of high energy cosmic rays. We train artificial neural networks using a high-performance computing cluster with 12 Nvidia Tesla V100 GPUs from the Laboratorio Nacional de Supercomputo del Sureste de Mexico (LNS), and a database of approximately 4.8 million Monte Carlo (MC) simulations of extensive air showers (EAS) using the hadronic interaction model Sibyll 2.3 with two primaries: Protons and Irons, between the energy ranges of 1017 to 1019 eV. The longitudinal development profile of EAS produced by ultra-high energy cosmic rays carries physical information related to the interaction properties of the primary particles with atmospheric nuclei. We extract from the MC values of the longitudinal profile of air showers trough atmospheric depth on different energy ranges, the variable called Xmax (depth of EAS maximum development), which is strongly correlated with the composition of the primary cosmic ray, in order to predict Xmax values for very high-energy cosmic rays by using ANNs. These methods can be used to train a neural network with real EAS events and predict outcomes where statistical limitations with normal means cannot say much.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
