Göttingen 2025 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
T: Fachverband Teilchenphysik
T 103: Methods in Particle Physics V (Event Reconstruction, PID)
T 103.5: Vortrag
Freitag, 4. April 2025, 10:00–10:15, VG 4.101
Particle Identification at Belle II using Neural Networks — •Erik Gräter1,2, Stefan Wallner1, Hans-Günther Moser1, and Martin Bartl1 — 1Max-Planck-Institut für Physik, München — 2Technische Universität München
We will present advancements in the charged-particle identification at the Belle II experiment located at KEK, Japan. At Belle II we employ a neural network to combine the information from six subdetectors to identify the particle species. Improvements in the reconstruction of the subdetector information that enters the neural network were made. In the context of this we will deliver a new neural-network trained on the latest data including those improvements. With a detailed study of the performance on particle-identification Additionally, we will provide an in-depth analysis of the importance of individual neural-network input features on its classification decisions.
Keywords: Belle II; Particle Identification; Neural Networks