Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers

Journal Article · · EPJ Web Conf.
 [1];  [1];  [2];  [2];  [3];  [3];  [3];  [3];  [4];  [4];  [2];  [2];  [5];  [5];  [5];  [5];  [5]
  1. Cincinnati U.
  2. Fermilab
  3. Northwestern U.
  4. Caltech, Pasadena (main)
  5. LBNL, Berkeley
+ Show Author Affiliations
This paper presents a graph neural network (GNN) technique for low-level reconstruction of neutrino interactions in a Liquid Argon Time Projection Chamber (LArTPC). GNNs are still a relatively novel technique, and have shown great promise for similar reconstruction tasks in the LHC. In this paper, a multihead attention message passing network is used to classify the relationship between detector hits by labelling graph edges, determining whether hits were produced by the same underlying particle, and if so, the particle type. The trained model is 84% accurate overall, and performs best on the EM shower and muon track classes. The model’s strengths and weaknesses are discussed, and plans for developing this technique further are summarised.
Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
DOE Contract Number:
AC02-07CH11359
OSTI ID:
1831483
Report Number(s):
FERMILAB-PUB-21-103-SCD; arXiv:2103.06233; oai:inspirehep.net:1850945
Journal Information:
EPJ Web Conf., Journal Name: EPJ Web Conf. Vol. 251
Country of Publication:
United States
Language:
English

References (5)

Operation of the ATLAS trigger system in Run 2 journal October 2020
The GENIE neutrino Monte Carlo generator
  • Andreopoulos, C.; Bell, A.; Bhattacharya, D.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 614, Issue 1 https://doi.org/10.1016/j.nima.2009.12.009
journal February 2010
Scalable deep convolutional neural networks for sparse, locally dense liquid argon time projection chamber data journal July 2020
Liquid argon TPC signal formation, signal processing and reconstruction techniques journal July 2017
Geant4—a simulation toolkit
  • Agostinelli, S.; Allison, J.; Amako, K.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 506, Issue 3 https://doi.org/10.1016/S0168-9002(03)01368-8
journal July 2003

Cited By (1)

Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking text January 2021

Similar Records

Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers
Journal Article · Sun Aug 22 20:00:00 EDT 2021 · EPJ Web of Conferences (Online) · OSTI ID:1826698
Graph Neural Network for Object Reconstruction in Liquid Argon Time Projection Chambers
Conference · Sat Dec 31 23:00:00 EST 2022 · J.Phys.Conf.Ser. · OSTI ID:1958460
Graph neural network for neutrino physics event reconstruction
Journal Article · Mon Aug 05 20:00:00 EDT 2024 · Physical Review. D. · OSTI ID:2333005

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS