Göttingen 2025 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

T 18: Methods in Particle Physics I (Calo, Jets, Tagging)

T 18.7: Vortrag

Montag, 31. März 2025, 18:15–18:30, VG 4.101

Flavour Tagging with ParticleNet at ILD — •Ulrich Einhaus¹ and Bryan Bliewert^{2, 3} — ¹Karlsruhe Institut für Technologie KIT — ²Deutsches Elektronen-Synchrotron DESY — ³Universität Hamburg

With the exploitation of the LHC in full swing, the particle physics community is turning its focus on the next flagship collider, an e⁺e⁻ Higgs factory. Many studies are ongoing studying physics prospects and optimising detector designs. In recent years, machine learning approaches to reconstruction algorithms have moved to neural network architectures, showing the performance advantages of their optimised exploitation of detector-level information. One area of application are flavour taggers, where several neural network approaches are actively under development.

This talk presents an implementation of the ParticleNet flavour tagger for the ILD detector concept, with data in full simulation. It covers the structure and performance, in particular the new strange tag, and highlights the dependence on specific observables and their impact on selected physics channels, informing further detector development.

Keywords: Flavour Tagging; ParticleNet; ILD