Home > Research > Publications & Outputs > Neutrino interaction classification with a conv...

Research

Associated organisational unit

Electronic data

  • 2006.15052v1

    Submitted manuscript, 2.65 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

Keywords

View graph of relations

Neutrino interaction classification with a convolutional neural network in the DUNE far detector

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Neutrino interaction classification with a convolutional neural network in the DUNE far detector. / DUNE Collaboration ; Blake, A.; Brailsford, D. et al.
In: Physical Review D, Vol. 102, 092003, 09.11.2020.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

DUNE Collaboration, Blake, A, Brailsford, D, Cross, R, Nowak, JA & Ratoff, P 2020, 'Neutrino interaction classification with a convolutional neural network in the DUNE far detector', Physical Review D, vol. 102, 092003. https://doi.org/10.1103/PhysRevD.102.092003

APA

DUNE Collaboration, Blake, A., Brailsford, D., Cross, R., Nowak, J. A., & Ratoff, P. (2020). Neutrino interaction classification with a convolutional neural network in the DUNE far detector. Physical Review D, 102, Article 092003. https://doi.org/10.1103/PhysRevD.102.092003

Vancouver

DUNE Collaboration, Blake A, Brailsford D, Cross R, Nowak JA, Ratoff P. Neutrino interaction classification with a convolutional neural network in the DUNE far detector. Physical Review D. 2020 Nov 9;102:092003. doi: 10.1103/PhysRevD.102.092003

Author

DUNE Collaboration ; Blake, A. ; Brailsford, D. et al. / Neutrino interaction classification with a convolutional neural network in the DUNE far detector. In: Physical Review D. 2020 ; Vol. 102.

Bibtex

@article{819bb4beab5b4e35a0767180e4580cde,
title = "Neutrino interaction classification with a convolutional neural network in the DUNE far detector",
abstract = " The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects. ",
keywords = "physics.ins-det, hep-ex",
author = "{DUNE Collaboration} and DUNE Collaboration and Arnold, {L. O.} and Arroyave, {M. A.} and J. Asaadi and A. Aurisano and V. Aushev and D. Autiero and F. Azfar and H. Back and Back, {J. J.} and C. Backhouse and P. Baesso and L. Bagby and R. Bajou and S. Balasubramanian and P. Baldi and B. Bambah and F. Barao and G. Barenboim and Barker, {G. J.} and W. Barkhouse and C. Barnes and G. Barr and Monarca, {J. Barranco} and N. Barros and A. Blake and D. Brailsford and R. Cross and Nowak, {J. A.} and P. Ratoff",
year = "2020",
month = nov,
day = "9",
doi = "10.1103/PhysRevD.102.092003",
language = "English",
volume = "102",
journal = "Physical Review D",
issn = "1550-7998",
publisher = "American Physical Society",

}

RIS

TY - JOUR

T1 - Neutrino interaction classification with a convolutional neural network in the DUNE far detector

AU - DUNE Collaboration

AU - Collaboration, DUNE

AU - Arnold, L. O.

AU - Arroyave, M. A.

AU - Asaadi, J.

AU - Aurisano, A.

AU - Aushev, V.

AU - Autiero, D.

AU - Azfar, F.

AU - Back, H.

AU - Back, J. J.

AU - Backhouse, C.

AU - Baesso, P.

AU - Bagby, L.

AU - Bajou, R.

AU - Balasubramanian, S.

AU - Baldi, P.

AU - Bambah, B.

AU - Barao, F.

AU - Barenboim, G.

AU - Barker, G. J.

AU - Barkhouse, W.

AU - Barnes, C.

AU - Barr, G.

AU - Monarca, J. Barranco

AU - Barros, N.

AU - Blake, A.

AU - Brailsford, D.

AU - Cross, R.

AU - Nowak, J. A.

AU - Ratoff, P.

PY - 2020/11/9

Y1 - 2020/11/9

N2 - The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects.

AB - The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure $CP$-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on a convolutional neural network has been developed to provide highly efficient and pure selections of electron neutrino and muon neutrino charged-current interactions. The electron neutrino (antineutrino) selection efficiency peaks at 90% (94%) and exceeds 85% (90%) for reconstructed neutrino energies between 2-5 GeV. The muon neutrino (antineutrino) event selection is found to have a maximum efficiency of 96% (97%) and exceeds 90% (95%) efficiency for reconstructed neutrino energies above 2 GeV. When considering all electron neutrino and antineutrino interactions as signal, a selection purity of 90% is achieved. These event selections are critical to maximize the sensitivity of the experiment to $CP$-violating effects.

KW - physics.ins-det

KW - hep-ex

U2 - 10.1103/PhysRevD.102.092003

DO - 10.1103/PhysRevD.102.092003

M3 - Journal article

VL - 102

JO - Physical Review D

JF - Physical Review D

SN - 1550-7998

M1 - 092003

ER -