Published January 1, 2020 | Version v1
Journal article Open

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

  • 1. Univ Oxford, Oxford OX1 3RH, England
  • 2. Fermilab Natl Accelerator Lab, POB 500, Batavia, IL 60510 USA
  • 3. Univ Atlantico, Atlantico, Colombia
  • 4. Georgian Tech Univ, Tbilisi, Georgia
  • 5. Brookhaven Natl Lab, Upton, NY 11973 USA
  • 6. Univ Bristol, Bristol BS8 1TL, Avon, England
  • 7. Ctr Variable Energy Cyclotron, Kolkata 700064, W Bengal, India
  • 8. Univ Warwick, Coventry CV4 7AL, W Midlands, England
  • 9. Univ Sussex, Brighton BN1 9RH, E Sussex, England
  • 10. CERN, European Org Nucl Res, CH-1211 Meyrin, Switzerland
  • 11. Univ Antananarivo, Antananarivo 101, Madagascar
  • 12. SLAC Natl Accelerator Lab, Menlo Pk, CA 94025 USA
  • 13. Inst Fis Corpuscular, Valencia 46980, Spain
  • 14. Univ Basel, CH-4056 Basel, Switzerland
  • 15. Univ Colima, Colima, Mexico

Description

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.

Files

bib-3139d2bb-7b87-43cc-9300-eb028d241dff.txt

Files (398 Bytes)

Name Size Download all
md5:e3ffe4883dd229945be74d300f3d230e
398 Bytes Preview Download