Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 37: Cosmic Rays II

T 37.5: Vortrag

Dienstag, 1. April 2025, 17:15–17:30, VG 3.102

Identifying Ultra-High-Energy Photons with a Convolutional Neural Network on the Basis of Surface Detector Measurements at the Pierre Auger Observatory — •Tim Fehler, Eleonora Guido, Marcus Niechciol, Markus Risse, and Daniel Steiniger for the Pierre-Auger collaboration — Experimentelle Astroteilchenphysik, Center for Particle Physics Siegen, Universität Siegen

Towards ultra-high energies (UHE, E 10¹⁷ eV), the expected flux of cosmic photons becomes so small that only the indirect detection via extensive air showers remains feasible. The quest to identify ultra-high-energy photons then fundamentally boils down to a classification problem, in which photon-induced air showers must be distinguished from the vast background of hadron-induced showers, utilizing only the limited data provided by detector sampling on an individual event basis. This work explores the application of a convolutional neural network (CNN) to this task, considering the full temporal evolution of the signal in surface-detector stations of the Pierre Auger Observatory as input. We show that with this approach, high levels of accuracy in classifying simulated shower events can be reached, providing a promising tool for future searches for UHE photons.

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 945422. It is also partially supported by BMBF Verbundforschung Astroteilchenphysik under project No. 05A23PS1.

Keywords: Ultra-High-Energy Photons; CNN; Surface Detector; Pierre Auger Observatory