A convolutional neural network neutrino event classifier

A. Aurisano, A. Radovic, D. Rocco, A. Himmel, M. D. Messier, E. Niner, G. Pawloski, F. Psihas, A. Sousa, P. Vahle

Research output: Contribution to journalArticle

68 Citations (Scopus)

Abstract

Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

Original languageEnglish (US)
Article numberP09001
JournalJournal of Instrumentation
Volume11
Issue number9
DOIs
StatePublished - Sep 1 2016

Fingerprint

classifiers
Neutrinos
Classifiers
neutrinos
Classifier
Neural Networks
Neural networks
High energy physics
High Energy
Physics
Calorimeter
Image recognition
Image Recognition
Particle interactions
Network Architecture
Calorimeters
Network architecture
Interaction
Image Analysis
physics

Keywords

  • Neutrino detectors
  • Particle identification methods
  • Particle tracking detectors
  • Pattern recognition, cluster finding, calibration and fitting methods

Cite this

Aurisano, A., Radovic, A., Rocco, D., Himmel, A., Messier, M. D., Niner, E., ... Vahle, P. (2016). A convolutional neural network neutrino event classifier. Journal of Instrumentation, 11(9), [P09001]. https://doi.org/10.1088/1748-0221/11/09/P09001

A convolutional neural network neutrino event classifier. / Aurisano, A.; Radovic, A.; Rocco, D.; Himmel, A.; Messier, M. D.; Niner, E.; Pawloski, G.; Psihas, F.; Sousa, A.; Vahle, P.

In: Journal of Instrumentation, Vol. 11, No. 9, P09001, 01.09.2016.

Research output: Contribution to journalArticle

Aurisano, A, Radovic, A, Rocco, D, Himmel, A, Messier, MD, Niner, E, Pawloski, G, Psihas, F, Sousa, A & Vahle, P 2016, 'A convolutional neural network neutrino event classifier', Journal of Instrumentation, vol. 11, no. 9, P09001. https://doi.org/10.1088/1748-0221/11/09/P09001
Aurisano A, Radovic A, Rocco D, Himmel A, Messier MD, Niner E et al. A convolutional neural network neutrino event classifier. Journal of Instrumentation. 2016 Sep 1;11(9). P09001. https://doi.org/10.1088/1748-0221/11/09/P09001
Aurisano, A. ; Radovic, A. ; Rocco, D. ; Himmel, A. ; Messier, M. D. ; Niner, E. ; Pawloski, G. ; Psihas, F. ; Sousa, A. ; Vahle, P. / A convolutional neural network neutrino event classifier. In: Journal of Instrumentation. 2016 ; Vol. 11, No. 9.
@article{67e7b0f94d5a40558c027d87085f18e0,
title = "A convolutional neural network neutrino event classifier",
abstract = "Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.",
keywords = "Neutrino detectors, Particle identification methods, Particle tracking detectors, Pattern recognition, cluster finding, calibration and fitting methods",
author = "A. Aurisano and A. Radovic and D. Rocco and A. Himmel and Messier, {M. D.} and E. Niner and G. Pawloski and F. Psihas and A. Sousa and P. Vahle",
year = "2016",
month = "9",
day = "1",
doi = "10.1088/1748-0221/11/09/P09001",
language = "English (US)",
volume = "11",
journal = "Journal of Instrumentation",
issn = "1748-0221",
publisher = "IOP Publishing Ltd.",
number = "9",

}

TY - JOUR

T1 - A convolutional neural network neutrino event classifier

AU - Aurisano, A.

AU - Radovic, A.

AU - Rocco, D.

AU - Himmel, A.

AU - Messier, M. D.

AU - Niner, E.

AU - Pawloski, G.

AU - Psihas, F.

AU - Sousa, A.

AU - Vahle, P.

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

AB - Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

KW - Neutrino detectors

KW - Particle identification methods

KW - Particle tracking detectors

KW - Pattern recognition, cluster finding, calibration and fitting methods

UR - http://www.scopus.com/inward/record.url?scp=84988354658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988354658&partnerID=8YFLogxK

U2 - 10.1088/1748-0221/11/09/P09001

DO - 10.1088/1748-0221/11/09/P09001

M3 - Article

AN - SCOPUS:84988354658

VL - 11

JO - Journal of Instrumentation

JF - Journal of Instrumentation

SN - 1748-0221

IS - 9

M1 - P09001

ER -