Speakers
Katharina sophia Schaeuble
Ulrich Einhaus
(KIT - Karlsruhe Institute of Technology (DE))
Description
We present a versatile GNN-based end-to-end reconstruction algorithm for highly granular calorimeters that can include track and timing information to aid the reconstruction of particles. The algorithm starts directly from calorimeter hits and possibly reconstructed tracks, and outputs a coordinate transformation in which all shower objects are well separated from each other and assigned properties such as particle momenta and ID in one go.
We showcase the versatility of this approach by presenting its application to a detector that matches the complexity of the CMS high-granularity calorimeter, an ATLAS-like setting as well as future collider detectors.
Authors
Alessandro Brusamolino
(KIT - Karlsruhe Institute of Technology (DE))
Dolores Garcia
(CERN)
Fabian Riemer
(KIT)
Jan Kieseler
(KIT - Karlsruhe Institute of Technology (DE))
Katharina sophia Schaeuble
Kenneth Long
(Massachusetts Inst. of Technology (US))
Mr
Philipp Zehetner
(Ludwig Maximilians Universitat (DE))
Shah Rukh Qasim
(University of Zurich (CH))
Ulrich Einhaus
(KIT - Karlsruhe Institute of Technology (DE))