Dortmund 2021 – scientific programme

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

T: Fachverband Teilchenphysik

T 46: Cosmic Rays II

T 46.2: Talk

Tuesday, March 16, 2021, 16:15–16:30, Tu

Towards the Determination of the UHECR Composition using Deep Learning and the Surface Detector of the Pierre Auger Observatory — Martin Erdmann, •Jonas Glombitza, Berenika Idaszek, and Niklas Langner — III. Physikalisches Institut A, RWTH Aachen University

Ultra-high energy cosmic rays (UHECRs) are the most energetic particles found in nature. When propagating within the Earth's atmosphere, they induce extensive air showers which can be measured by cosmic-ray observatories. The Pierre Auger Observatory features a surface detector (SD) which is overlooked by 27 fluorescence telescopes. The reconstruction of event-by-event information sensitive to the cosmic-ray mass is a challenging task and so far, mainly based on fluorescence observations with a duty cycle of about 15%.

Recently, deep learning-based algorithms have shown to be extraordinary successful across many domains. Applying these algorithms to surface-detector data allows for an event-by-event estimation of the cosmic-ray mass, exploiting the 100% duty cycle of the SD [1].

In this contribution we present a deep neural network, designed to exploit the symmetries of the SD and suited to the real operation-conditions at the Pierre Auger Observatory. We evaluate the performance of the method and introduce a calibration of the algorithm using Auger hybrid data. Finally, we estimate the expected accuracy of the method to determine the UHECR composition at the highest energies with unprecedented statistics.

[1] arXiv:2101/02946