Karlsruhe 2024 – scientific programme

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

T: Fachverband Teilchenphysik

T 43: Data, AI, Computing 3 (pointclouds & graphs)

T 43.4: Talk

Tuesday, March 5, 2024, 16:45–17:00, Geb. 30.33: MTI

Graph Neural Network based Tracking at Belle II — •Lea Reuter, Giacomo De Pietro, Torben Ferber, and Slavomira Stefkova — Institute of Experimental Particle Physics (ETP), Karlsruhe Institute of Technology (KIT)

Displaced vertices are an important signature in Standard Model analyses involving K_S and many searches for New Physics. However, the current Belle II tracking algorithm falls short when dealing with particles that decay after a large distance, resulting in a decrease in tracking efficiency with increasing displacement.

In this work, we show a novel track finding algorithm that combines the Object Condensation algorithm with Graph Neural Networks. This approach simultaneously identifies all tracks in an event and determines their respective parameters. Additionally, we integrated the new track finding algorithm into the Belle II analysis software framework, improving the resolution through additional track fitting.

Our results show significant improvements compared to the existing Belle II track finding algorithm for displaced tracks, while keeping a similar efficiency and fake rate for prompt tracks originating from the interaction point.

Keywords: Tracking; Graph Neural Networks; Machine Learning; Reconstruction; Drift Chamber