000003391 001__ 3391
000003391 005__ 20230125124311.0
000003391 037__ $$aBELLE2-MTHESIS-2023-001
000003391 041__ $$aeng
000003391 100__ $$aFlorian Jochen Wemmer
000003391 245__ $$aPhoton Reconstruction in the Belle II Calorimeter Using Graph Neural Networks
000003391 260__ $$aKarlsruhe$$bInstitute of Experimental Particle Physics (ETP)$$c2022
000003391 300__ $$a106
000003391 500__ $$aPresented on 11 11 2022
000003391 502__ $$aMSc$$bKarlsruhe, Karlsruhe Institute of Technology (KIT)$$c2022
000003391 520__ $$aThis thesis presents the implementation and performance of the GravNet algorithm for the photon energy reconstruction in the Belle II electromagnetic calorimeter. GravNet is a machine learning algorithm based on the concept of graph neural networks. The Belle II Analysis Software Framework is the currently used reconstruction framework that serves as the baseline for comparison in several studies. GravNet solves many of the conceptual restrictions that limit the performance of the traditional reconstruction approach, especially in the presence of high levels of beam background. The studies in this thesis are considered a first validation and are exclusively based on Monte Carlo generated and simulated data. The GravNet implementation outperforms the baseline energy resolutions over a large range of photon energies from 0.01 GeV to 3.0 GeV by up to 20%. In addition, the studies demonstrate substantial improvements of up to 15% in the reconstruction of neutral pions from the invariant mass of two-photon systems. GravNet proves to be a viable and versatile reconstruction algorithm with a promising outlook for a broad range of present and future applications.  
000003391 700__ $$aProf. Dr. Torben Ferber$$edir.
000003391 700__ $$aProf. Dr. Markus Klute$$edir.
000003391 8560_ $$fflorian.wemmer@student.kit.edu
000003391 8564_ $$uhttps://docs.belle2.org/record/3391/files/BELLE2-MTHESIS-2023-001.pdf
000003391 980__ $$aTHESIS