Karlsruhe 2024 – wissenschaftliches Programm

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

T: Fachverband Teilchenphysik

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

T 43.6: Vortrag

Dienstag, 5. März 2024, 17:15–17:30, Geb. 30.33: MTI

Photon Reconstruction with Graph Neural Networks at Beamdump Experiments — •Kylian Schmidt, Torben Ferber, Alexander Heidelbach, Jan Kieseler, and Markus Klute — Institute of Experimental Particle Physics (ETP), Karlsruhe Institute of Technology (KIT)

Axion-Like Particles (ALPs) are hypothetical weakly interacting light particles predicted by theories Beyond the Standard Model which could be mediators between a dark sector and the Standard Model. Some of these theories predict light ALPs which decay into two photons and could be detected at future beamdump experiments such as LUXE-NPOD and SHADOWS.

To investigate the properties of such ALPs, an accurate reconstruction of the decay vertex from the hits measured in the detector can aid the search significantly. For this purpose, the photon shower direction needs to be reconstructed precisely, combining techniques from shower and track reconstruction. This task is a prime candidate for modern methods of photon reconstruction based on Machine Learning such as Graph Neural Networks.

In this talk we present a new application of GravNet, which is able to reconstruct the decay vertex of ALPs from the sparse detector hits of the two photon showers.

Keywords: Graph Neural Networks; Reconstruction; Machine Learning