Karlsruhe 2024 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

T: Fachverband Teilchenphysik

T 16: Data, AI, Computing 1 (anomaly detection)

T 16.3: Talk

Monday, March 4, 2024, 16:30–16:45, Geb. 30.33: MTI

Deep neural network reconstruction of muon densities from measurements of the underground muon detector of the Pierre Auger Observatory — •Anton Poctarev for the Pierre-Auger collaboration — Karlsruhe Institut für Technologie Campus Nord, Geb. 425, Eggenstein-Leopoldshafen

Ultra-High Energy Cosmic Rays (UHECRs) are the most energetic particles discovered by mankind. They are of high interest and their sources and the means by which they are accelerated remain undetermined. To get a clearer picture of UHECRs, it is integral to determine the mass of each incoming particle. Furthermore, the deficit of muons produced by simulations using current hadronic interaction models compared to extensive air showers (EAS) leaves a lot of questions open regarding our understanding of hadronic interactions. Since the number of muons in an EAS is directly linked to the number of nucleons in the primary particle, we can study and refine our theories of hadronic interactions and improve our handle on mass composition by measuring muon multiplicities. The Pierre Auger Observatory employs underground muon counters for this task.
Simulations of the underground muon detector of the Pierre Auger Observatory are used to train a deep learning neural network to reconstruct muon densities. In this contribution we present the method and compare the bias and resolution to traditional reconstruction methods.

Keywords: Cosmic Rays; Neural Networks