SMuK 2023 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

T 22: Calorimeter / Detector Systems I

T 22.2: Vortrag

Montag, 20. März 2023, 16:45–17:00, WIL/C133

Artificial Neural Networks for the Energy Reconstruction of ATLAS Liquid-Argon Calorimeter Signals — •Anne-Sophie Berthold, Nick Fritzsche, Christian Gutsche, Alexander Lettau, Arno Straessner, Johann Christoph Voigt, and Philipp Welle — Institut für Kern- und Teilchenphysik, Dresden, Deutschland

From 2029 on, the enhanced performance of the High-Luminosity LHC will increase the number of simultaneous proton-proton collisions at the ATLAS detector considerably. In order to cope with that, the so-called Phase-II upgrade is planned. Up to 200 pile-up events will emerge within one bunch crossing, which is why one important part of this upgrade will be the processing of the Liquid-Argon Calorimeter signals. It has been shown that the conventional, optimal filtering signal processing will loose its performance due to the increase of overlapping signals and a trigger scheme with trigger accept signals in each LHC bunch crossing. That is why more sophisticated algorithms such as neural networks come into focus. This talk deals with the application of convolutional neural networks, which on the one hand need to perform well under varying signal conditions and on the other hand need to satisfy tight resource restrictions. Different network architectures are compared. A scoring, which is visualized in a spider diagram, is introduced to evaluate the network performance with respect to different scenarios.