Jul 16 – 26, 2022
US/Pacific timezone

Graph Neural Network for Large Radius Tracking

Jul 18, 2022, 7:00 PM
2h 20m
211 South Ballroom (HUB)

211 South Ballroom

HUB

Speaker

Chun-Yi Wang (National Tsing Hua University, )

Description

Particle tracking is a challenging pattern recognition task in experimental particle physics. Traditionally, algorithms based on the Kalman filter are used for such tasks and show desirable performance in finding tracks originating from the interaction point. However, many Beyond Standard Model (BSM) theories predict the existence of long-lived particles (LLP). They have a longer lifetime and travel a distance before decaying to Standard Model particles, resulting in large radius tracks. For such displaced tracks, dedicated tunings are often required to reach sensible performance since the quality of seeds for the Kalman filter has a direct impact on its performance.

Recent studies show machine learning-based particle track finding algorithms using graph neural networks (GNN) achieve competitive physics and computing performance for tracks originating from the interaction point. In this work, we developed a GNN-based end-to-end particle track finding algorithm for the High Luminosity LHC and apply such an algorithm to displaced track datasets to study the performance of reconstructing displaced tracks. The algorithm is designed to be agnostic about global track position. The datasets are generated under the ACTS framework and simulated for a generic detector. As the result, we reconstruct prompt and displaced tracks simultaneously with high track efficiency and no significant drop for displaced tracks.

In-person or Virtual? Virtual

Primary authors

Alexandra Ballow (Youngstown State University) Alexis Vallier (Laboratoire des 2 Infinis - Toulouse (L2IT-IN2P3)) Alina Lazar (Youngstown State University) Charline Rougier (Laboratoire des 2 Infinis - Toulouse (L2IT-IN2P3)) Chun-Yi Wang (National Tsing Hua University, ) Daniel Murnane (Lawrence Berkeley National Laboratory) Jad Sardain (Laboratoire des 2 Infinis - Toulouse (L2IT-IN2P3)) Jan Stark (Laboratoire des 2 Infinis - Toulouse (L2IT-IN2P3)) Lindsey Gray (Fermi National Accelerator Laboratory) Mark Neubauer (University of Illinois Urbana-Champaign) Markus Atkinson (University of Illinois Urbana-Champaign) Paolo Calafiura (LBNL) Shih-Chieh Hsu (University of Washington) Steven Farrell (Lawrence Berkeley National Lab) Sylvain Caillou (Laboratoire des 2 Infinis - Toulouse (L2IT-IN2P3)) Thomas Klijnsma (Fermi National Accelerator Laboratory) Xiangyang Ju (Lawrence Berkeley National Lab) Xiaocong Ai ( DESY)

Co-authors

Adam Aurisano (University of Cincinnati) Gage DeZoort (Princeton University) Giuseppe Cerati (Fermi National Accelerator Laboratory) Jean-Roch Vlimant (California Institute of Technology) Jeremy Hewes (Fermi National Accelerator Laboratory) Jim Kowalkowski (Fermi National Accelerator Laboratory) Maria Spiropulu (California Institute of Technology) Savannah Thais (Princeton University)

Presentation materials