Göttingen 2025 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

T 59: Neutrino Physics V

T 59.3: Vortrag

Mittwoch, 2. April 2025, 16:45–17:00, VG 3.103

Particle identification in JUNO with a Graph Convolutional Network — Thilo Birkenfeld, •Elisabeth Neuerburg, Philipp Soldin, and Achim Stahl — RWTH Aachen

The Jiangmen Underground Neutrino Observatory (JUNO) is a 20 kton liquid scintillator-based neutrino observatory. Identifying the secondary particles gives a handle on the primary neutrino type. In this talk, a method of particle identification using a Graph Convolutional Network (GCN) is presented. A fixed Graph is fed into the network, which uses partition pooling for dimensionality reduction. This method is applied to the discrimination of electrons and positrons. Their discrimination aids in distinguishing atmospheric neutrinos and antineutrinos, as well as backgrounds from the IBD signal of reactor antineutrinos.

Keywords: JUNO; Graph Convolutional Network; Particle identification