Cargando…

Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors

Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector syst...

Descripción completa

Detalles Bibliográficos
Autores principales: Ju, Xiangyang, Farrell, Steven, Calafiura, Paolo, Murnane, Daniel, Prabhat, Gray, Lindsey, Klijnsma, Thomas, Pedro, Kevin, Cerati, Giuseppe, Kowalkowski, Jim, Perdue, Gabriel, Spentzouris, Panagiotis, Tran, Nhan, Vlimant, Jean-Roch, Zlokapa, Alexander, Pata, Joosep, Spiropulu, Maria, An, Sitong, Aurisano, Adam, Hewes, V., Hewes, Jeremy, Tsaris, Aristeidis, Terao, Kazuhiro, Usher, Tracy
Lenguaje:eng
Publicado: 2020
Materias:
Acceso en línea:http://cds.cern.ch/record/2715452
_version_ 1780965435286487040
author Ju, Xiangyang
Farrell, Steven
Calafiura, Paolo
Murnane, Daniel
Prabhat
Gray, Lindsey
Klijnsma, Thomas
Pedro, Kevin
Cerati, Giuseppe
Kowalkowski, Jim
Perdue, Gabriel
Spentzouris, Panagiotis
Tran, Nhan
Vlimant, Jean-Roch
Zlokapa, Alexander
Pata, Joosep
Spiropulu, Maria
An, Sitong
Aurisano, Adam
Hewes, V.
Hewes, Jeremy
Tsaris, Aristeidis
Terao, Kazuhiro
Usher, Tracy
author_facet Ju, Xiangyang
Farrell, Steven
Calafiura, Paolo
Murnane, Daniel
Prabhat
Gray, Lindsey
Klijnsma, Thomas
Pedro, Kevin
Cerati, Giuseppe
Kowalkowski, Jim
Perdue, Gabriel
Spentzouris, Panagiotis
Tran, Nhan
Vlimant, Jean-Roch
Zlokapa, Alexander
Pata, Joosep
Spiropulu, Maria
An, Sitong
Aurisano, Adam
Hewes, V.
Hewes, Jeremy
Tsaris, Aristeidis
Terao, Kazuhiro
Usher, Tracy
author_sort Ju, Xiangyang
collection CERN
description Pattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.
id cern-2715452
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2020
record_format invenio
spelling cern-27154522023-10-04T06:45:42Zhttp://cds.cern.ch/record/2715452engJu, XiangyangFarrell, StevenCalafiura, PaoloMurnane, DanielPrabhatGray, LindseyKlijnsma, ThomasPedro, KevinCerati, GiuseppeKowalkowski, JimPerdue, GabrielSpentzouris, PanagiotisTran, NhanVlimant, Jean-RochZlokapa, AlexanderPata, JoosepSpiropulu, MariaAn, SitongAurisano, AdamHewes, V.Hewes, JeremyTsaris, AristeidisTerao, KazuhiroUsher, TracyGraph Neural Networks for Particle Reconstruction in High Energy Physics detectorsphysics.data-anOther Fields of Physicshep-exParticle Physics - Experimentphysics.ins-detDetectors and Experimental TechniquesPattern recognition problems in high energy physics are notably different from traditional machine learning applications in computer vision. Reconstruction algorithms identify and measure the kinematic properties of particles produced in high energy collisions and recorded with complex detector systems. Two critical applications are the reconstruction of charged particle trajectories in tracking detectors and the reconstruction of particle showers in calorimeters. These two problems have unique challenges and characteristics, but both have high dimensionality, high degree of sparsity, and complex geometric layouts. Graph Neural Networks (GNNs) are a relatively new class of deep learning architectures which can deal with such data effectively, allowing scientists to incorporate domain knowledge in a graph structure and learn powerful representations leveraging that structure to identify patterns of interest. In this work we demonstrate the applicability of GNNs to these two diverse particle reconstruction problems.arXiv:2003.11603FERMILAB-CONF-20-163-PPD-QIS-SCDoai:cds.cern.ch:27154522020-03-25
spellingShingle physics.data-an
Other Fields of Physics
hep-ex
Particle Physics - Experiment
physics.ins-det
Detectors and Experimental Techniques
Ju, Xiangyang
Farrell, Steven
Calafiura, Paolo
Murnane, Daniel
Prabhat
Gray, Lindsey
Klijnsma, Thomas
Pedro, Kevin
Cerati, Giuseppe
Kowalkowski, Jim
Perdue, Gabriel
Spentzouris, Panagiotis
Tran, Nhan
Vlimant, Jean-Roch
Zlokapa, Alexander
Pata, Joosep
Spiropulu, Maria
An, Sitong
Aurisano, Adam
Hewes, V.
Hewes, Jeremy
Tsaris, Aristeidis
Terao, Kazuhiro
Usher, Tracy
Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title_full Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title_fullStr Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title_full_unstemmed Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title_short Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
title_sort graph neural networks for particle reconstruction in high energy physics detectors
topic physics.data-an
Other Fields of Physics
hep-ex
Particle Physics - Experiment
physics.ins-det
Detectors and Experimental Techniques
url http://cds.cern.ch/record/2715452
work_keys_str_mv AT juxiangyang graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT farrellsteven graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT calafiurapaolo graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT murnanedaniel graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT prabhat graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT graylindsey graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT klijnsmathomas graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT pedrokevin graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT ceratigiuseppe graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT kowalkowskijim graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT perduegabriel graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT spentzourispanagiotis graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT trannhan graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT vlimantjeanroch graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT zlokapaalexander graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT patajoosep graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT spiropulumaria graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT ansitong graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT aurisanoadam graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT hewesv graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT hewesjeremy graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT tsarisaristeidis graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT teraokazuhiro graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors
AT ushertracy graphneuralnetworksforparticlereconstructioninhighenergyphysicsdetectors