Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber

(MicroBooNE Collaboration)

doi:10.1103/PhysRevD.99.092001

Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber

(MicroBooNE Collaboration)

Physics and Astronomy (Twin Cities)

Research output: Contribution to journal › Article › peer-review

50 Scopus citations

Abstract

We have developed a convolutional neural network that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a νμ charged-current neutral pion data samples.

Original language	English (US)
Article number	092001
Journal	Physical Review D
Volume	99
Issue number	9
DOIs	https://doi.org/10.1103/PhysRevD.99.092001
State	Published - May 1 2019

Bibliographical note

Publisher Copyright:
© 2019 authors. Published by the American Physical Society. Published by the American Physical Society under the terms of the »https://creativecommons.org/licenses/by/4.0/» Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Access

10.1103/PhysRevD.99.092001

OpenUrl availability

Full text

Cite this

@article{2c4690cb5fa74d409ca971f5fb8c805a,

title = "Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber",

abstract = "We have developed a convolutional neural network that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a νμ charged-current neutral pion data samples.",

author = "{(MicroBooNE Collaboration)} and C. Adams and M. Alrashed and R. An and J. Anthony and J. Asaadi and A. Ashkenazi and M. Auger and S. Balasubramanian and B. Baller and C. Barnes and G. Barr and M. Bass and F. Bay and A. Bhat and K. Bhattacharya and M. Bishai and A. Blake and T. Bolton and L. Camilleri and D. Caratelli and {Caro Terrazas}, I. and R. Carr and {Castillo Fernandez}, R. and F. Cavanna and G. Cerati and Y. Chen and E. Church and D. Cianci and Cohen, {E. O.} and Collin, {G. H.} and Conrad, {J. M.} and M. Convery and L. Cooper-Troendle and Crespo-Anad{\'o}n, {J. I.} and {Del Tutto}, M. and D. Devitt and A. Diaz and K. Duffy and S. Dytman and B. Eberly and A. Ereditato and {Escudero Sanchez}, L. and J. Esquivel and Evans, {J. J.} and Fadeeva, {A. A.} and Fitzpatrick, {R. S.} and Fleming, {B. T.} and D. Franco and Furmanski, {A. P.} and D. Garcia-Gamez",

note = "Publisher Copyright: {\textcopyright} 2019 authors. Published by the American Physical Society. Published by the American Physical Society under the terms of the »https://creativecommons.org/licenses/by/4.0/» Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.",

year = "2019",

month = may,

day = "1",

doi = "10.1103/PhysRevD.99.092001",

language = "English (US)",

volume = "99",

journal = "Physical Review D",

issn = "2470-0010",

publisher = "American Physical Society",

number = "9",

}

TY - JOUR

T1 - Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber

AU - (MicroBooNE Collaboration)

AU - Adams, C.

AU - Alrashed, M.

AU - An, R.

AU - Anthony, J.

AU - Asaadi, J.

AU - Ashkenazi, A.

AU - Auger, M.

AU - Balasubramanian, S.

AU - Baller, B.

AU - Barnes, C.

AU - Barr, G.

AU - Bass, M.

AU - Bay, F.

AU - Bhat, A.

AU - Bhattacharya, K.

AU - Bishai, M.

AU - Blake, A.

AU - Bolton, T.

AU - Camilleri, L.

AU - Caratelli, D.

AU - Caro Terrazas, I.

AU - Carr, R.

AU - Castillo Fernandez, R.

AU - Cavanna, F.

AU - Cerati, G.

AU - Chen, Y.

AU - Church, E.

AU - Cianci, D.

AU - Cohen, E. O.

AU - Collin, G. H.

AU - Conrad, J. M.

AU - Convery, M.

AU - Cooper-Troendle, L.

AU - Crespo-Anadón, J. I.

AU - Del Tutto, M.

AU - Devitt, D.

AU - Diaz, A.

AU - Duffy, K.

AU - Dytman, S.

AU - Eberly, B.

AU - Ereditato, A.

AU - Escudero Sanchez, L.

AU - Esquivel, J.

AU - Evans, J. J.

AU - Fadeeva, A. A.

AU - Fitzpatrick, R. S.

AU - Fleming, B. T.

AU - Franco, D.

AU - Furmanski, A. P.

AU - Garcia-Gamez, D.

N1 - Publisher Copyright: © 2019 authors. Published by the American Physical Society. Published by the American Physical Society under the terms of the »https://creativecommons.org/licenses/by/4.0/» Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

PY - 2019/5/1

Y1 - 2019/5/1

N2 - We have developed a convolutional neural network that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a νμ charged-current neutral pion data samples.

AB - We have developed a convolutional neural network that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training techniques, and software tools developed to train this network. The goal of this work is to develop a complete deep neural network based data reconstruction chain for the MicroBooNE detector. We show the first demonstration of a network's validity on real LArTPC data using MicroBooNE collection plane images. The demonstration is performed for stopping muon and a νμ charged-current neutral pion data samples.

UR - http://www.scopus.com/inward/record.url?scp=85066954822&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066954822&partnerID=8YFLogxK

U2 - 10.1103/PhysRevD.99.092001

DO - 10.1103/PhysRevD.99.092001

M3 - Article

AN - SCOPUS:85066954822

SN - 2470-0010

VL - 99

JO - Physical Review D

JF - Physical Review D

IS - 9

M1 - 092001

ER -

Deep neural network for pixel-level electromagnetic particle identification in the MicroBooNE liquid argon time projection chamber

Abstract

Bibliographical note

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this