skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events

Abstract

Particle detectors record the interactions of subatomic particles and their passage through matter. The identification of these particles is necessary for in-depth physics analysis. While particles can be identified by their individual behavior as they travel through matter, the full context of the interaction in which they are produced can aid the classification task substantially. We have developed the first convolutional neural network for particle identification which uses context information. This is also the first implementation of a four-tower siamese-type architecture both for separation of independent inputs and inclusion of context information. The network classifies clusters of energy deposits from the NOvA neutrino detectors as electrons, muons, photons, pions, and protons with an overall efficiency and purity of 83.3% and 83.5%, respectively. We show that providing the network with context information improves performance by comparing our results with a network trained without context information.

Authors:
 [1];  [2];  [3];  [3];  [4];  [2];  [1];  [3];  [5];  [4]
  1. Texas U.
  2. Fermilab
  3. Indiana U.
  4. Cincinnati U.
  5. William-Mary Coll.
Publication Date:
Research Org.:
Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), High Energy Physics (HEP) (SC-25)
OSTI Identifier:
1573833
Report Number(s):
arXiv:1906.00713; FERMILAB-PUB-19-258-PPD
oai:inspirehep.net:1737736
DOE Contract Number:  
AC02-07CH11359
Resource Type:
Journal Article
Journal Name:
Phys.Rev.
Additional Journal Information:
Journal Volume: D100; Journal Issue: 7
Country of Publication:
United States
Language:
English
Subject:
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS

Citation Formats

Psihas, F., Niner, E., Groh, M., Murphy, R., Aurisano, A., Himmel, A., Lang, K., Messier, M. D., Radovic, A., and Sousa, A. Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events. United States: N. p., 2019. Web. doi:10.1103/PhysRevD.100.073005.
Psihas, F., Niner, E., Groh, M., Murphy, R., Aurisano, A., Himmel, A., Lang, K., Messier, M. D., Radovic, A., & Sousa, A. Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events. United States. doi:10.1103/PhysRevD.100.073005.
Psihas, F., Niner, E., Groh, M., Murphy, R., Aurisano, A., Himmel, A., Lang, K., Messier, M. D., Radovic, A., and Sousa, A. Tue . "Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events". United States. doi:10.1103/PhysRevD.100.073005. https://www.osti.gov/servlets/purl/1573833.
@article{osti_1573833,
title = {Context-Enriched Identification of Particles with a Convolutional Network for Neutrino Events},
author = {Psihas, F. and Niner, E. and Groh, M. and Murphy, R. and Aurisano, A. and Himmel, A. and Lang, K. and Messier, M. D. and Radovic, A. and Sousa, A.},
abstractNote = {Particle detectors record the interactions of subatomic particles and their passage through matter. The identification of these particles is necessary for in-depth physics analysis. While particles can be identified by their individual behavior as they travel through matter, the full context of the interaction in which they are produced can aid the classification task substantially. We have developed the first convolutional neural network for particle identification which uses context information. This is also the first implementation of a four-tower siamese-type architecture both for separation of independent inputs and inclusion of context information. The network classifies clusters of energy deposits from the NOvA neutrino detectors as electrons, muons, photons, pions, and protons with an overall efficiency and purity of 83.3% and 83.5%, respectively. We show that providing the network with context information improves performance by comparing our results with a network trained without context information.},
doi = {10.1103/PhysRevD.100.073005},
journal = {Phys.Rev.},
number = 7,
volume = D100,
place = {United States},
year = {2019},
month = {10}
}

Works referenced in this record:

Characteristics of Bubble Chambers
journal, January 1955


Machine learning at the energy and intensity frontiers of particle physics
journal, August 2018


Jet-images — deep learning edition
journal, July 2016

  • de Oliveira, Luke; Kagan, Michael; Mackey, Lester
  • Journal of High Energy Physics, Vol. 2016, Issue 7
  • DOI: 10.1007/JHEP07(2016)069

A convolutional neural network neutrino event classifier
journal, September 2016


CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks
journal, January 2018


Improved energy reconstruction in NOvA with regression convolutional neural networks
journal, January 2019


Convolutional neural networks applied to neutrino events in a liquid argon time projection chamber
journal, March 2017


Background rejection in NEXT using deep neural networks
journal, January 2017


Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINER v A experiment
journal, November 2018


New constraints on oscillation parameters from ν e appearance and ν μ disappearance in the NOvA experiment
journal, August 2018


Neutrino–nucleus cross sections for oscillation experiments
journal, December 2017

  • Katori, Teppei; Martini, Marco
  • Journal of Physics G: Nuclear and Particle Physics, Vol. 45, Issue 1
  • DOI: 10.1088/1361-6471/aa8bf7

The NuMI neutrino beam
journal, January 2016

  • Adamson, P.; Anderson, K.; Andrews, M.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 806
  • DOI: 10.1016/j.nima.2015.08.063

Event Reconstruction Techniques in NOvA
journal, December 2015


The GENIE neutrino Monte Carlo generator
journal, February 2010

  • 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
  • DOI: 10.1016/j.nima.2009.12.009

Geant4—a simulation toolkit
journal, July 2003

  • 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
  • DOI: 10.1016/S0168-9002(03)01368-8

The NO v A simulation chain
journal, December 2015


A Fuzzy Relative of the ISODATA Process and Its Use in Detecting Compact Well-Separated Clusters
journal, January 1973


ROOT — An object oriented data analysis framework
journal, April 1997

  • Brun, Rene; Rademakers, Fons
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 389, Issue 1-2
  • DOI: 10.1016/S0168-9002(97)00048-X

The art framework
journal, December 2012