CERN Accelerating science

ATLAS Note
Report number	ATL-ITK-PROC-2022-006
Title	ATLAS ITk Track Reconstruction with a GNN-based pipeline
Author(s)	Caillou, Sylvain (Centre National de la Recherche Scientifique (FR)) ; Calafiura, Paolo (Lawrence Berkeley National Lab. (US)) ; Farrell, Steven Andrew ; Ju, Xiangyang (Lawrence Berkeley National Lab. (US)) ; Murnane, Daniel Thomas (Lawrence Berkeley National Lab. (US)) ; Rougier, Charline (Centre National de la Recherche Scientifique (FR)) ; Stark, Jan (Centre National de la Recherche Scientifique (FR)) ; Vallier, Alexis (Centre National de la Recherche Scientifique (FR))
Corporate Author(s)	The ATLAS collaboration
Collaboration	ATLAS Collaboration
Publication	2022
Imprint	12 Jul 2022
Number of pages	11
Subject category	Particle Physics - Experiment
Accelerator/Facility, Experiment	CERN LHC ; ATLAS
Free keywords	TRACKING
Abstract	In preparation for the upcoming HL-LHC era, ATLAS is pursuing several methods to reduce the resources consumption needed to reconstruct the trajectory of charged particles (tracks) in the new all-silicon Inner Tracker (ITk). This includes the development of new algorithms suitable for massively parallel computing architecture like GPUs. Algorithms for track pattern recognition based on graph neural networks (GNNs) have emerged as a particularly promising approach. Previous work using simulated data from the TrackML challenge show high track reconstruction efficiency. In the present document we describe a first functional implementation of a GNN-based track pattern reconstruction for ITk, achieving a high GNN track reconstruction efficiency and promising fake track rate.

Corresponding record in: Inspire