Transformers for Charged Particle Track Reconstruction in High Energy Physics

Abstract

Reconstructing charged particle tracks is a fundamental task in modern collider experiments. The unprecedented particle multiplicities expected at the High-Luminosity Large Hadron Collider (HL-LHC) pose significant challenges for track reconstruction, where traditional algorithms become computationally infeasible. To address this challenge, we present a novel learned approach to track reconstruction that adapts recent advances in computer vision and object detection. Our architecture combines a Transformer hit filtering network with a MaskFormer reconstruction model that jointly optimises hit assignments and the estimation of the charged particles' properties. Evaluated on the TrackML dataset, our best performing model achieves state-of-the-art tracking performance with 97% efficiency for a fake rate of 0.6%, and inference times of 100ms. Our tunable approach enables specialisation for specific applications like triggering systems, while its underlying principles can be extended to other reconstruction challenges in high energy physics. This work demonstrates the potential of modern deep learning architectures to address emerging computational challenges in particle physics while maintaining the precision required for groundbreaking physics analysis.

References in corpus (22)

• Particle-flow reconstruction and global event description with the CMS detector
• Description and performance of track and primary-vertex reconstruction with the CMS tracker
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• Performance of the CMS muon detector and muon reconstruction with proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Jet reconstruction and performance using particle flow with the ATLAS Detector
• Muon reconstruction and identification efficiency in ATLAS using the full Run 2 $pp$ collision data set at $\sqrt{s}=13$ TeV
• Electron and photon reconstruction and identification with the CMS experiment at the CERN LHC
• Performance of reconstruction and identification of $\tau$ leptons decaying to hadrons and ${\nu }_{\tau }$ in pp collisions at $\sqrt{s}=$ 13 TeV
• Performance of the ATLAS Track Reconstruction Algorithms in Dense Environments in LHC Run 2
• ATLAS flavour-tagging algorithms for the LHC Run 2 $pp$ collision dataset
• Combination of searches for Higgs boson pairs in $pp$ collisions at $\sqrt{s}=$13 TeV with the ATLAS detector
• Design and performance of the LHCb trigger and full real-time reconstruction in Run 2 of the LHC
• Allen: A high level trigger on GPUs for LHCb
• A Common Tracking Software Project
• Electron and photon efficiencies in LHC Run 2 with the ATLAS experiment
• The Tracking Machine Learning challenge : Throughput phase
• Software Performance of the ATLAS Track Reconstruction for LHC Run 3
• Towards a realistic track reconstruction algorithm based on graph neural networks for the HL-LHC
• Constraints on the Higgs boson self-coupling from the combination of single and double Higgs boson production in proton-proton collisions at $\sqrt{s}$ = 13 TeV
• Beyond 4D Tracking: Using Cluster Shapes for Track Seeding
• GPU-accelerated track reconstruction in the ALICE High Level Trigger
• Secondary Vertex Reconstruction with MaskFormers