Dortmund 2021 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
T: Fachverband Teilchenphysik
T 46: Cosmic Rays II
T 46.1: Talk
Tuesday, March 16, 2021, 16:00–16:15, Tu
Composition Measurements with AugerPrime using Deep Learning* — Sonja Schröder and •Julian Rautenberg for the Pierre Auger collaboration — Bergische Universität Wuppertal, Gaußstr. 20, 42119 Wuppertal, Germany
The AugerPrime upgrade of the Pierre Auger Observatory in Argentina will enhance the precision of primary particle composition measurements made by the Surface Detector. This will be achieved using the different response of the Water Cherenkov Detector (WCD) and the Surface Scintillator Detector (SSD) to the electromagnetic and muonic component of the extensive air shower.
With the deployment of AugerPrime ongoing, the cosmic ray composition sensitivity of the upgrade can already be probed using simulations and modern machine learning techniques.
In this presentation, a Deep Learning approach is shown to be able to reconstruct the depth of shower maximum, Xmax, a mass sensitive observable, on an event-by-event basis. For this, a combination of deep convolutional neural networks is used to process information simultaneously from both WCD and SSD signals, obtained from full AugerPrime detector simulations using a mixed composition of protons, helium, oxygen, and iron. The increase in sensitivity gained through the
addition of the SSD, as well as the end estimated
mass bias and resolution will be presented.
*Supported by the BMBF Verbundforschung Astroteilchenphysik (Vorhaben 05A17PX1).