Published January 1, 2019 | Version v1
Journal article Open

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

Creators

  • 1. Harvard Univ, Cambridge, MA 02138 USA
  • 2. Kansas State Univ, Manhattan, KS 66506 USA
  • 3. IIT, Chicago, IL 60616 USA
  • 4. Univ Cambridge, Cambridge CB3 0HE, England
  • 5. Univ Texas Arlington, Arlington, TX 76019 USA
  • 6. MIT, 77 Massachusetts Ave, Cambridge, MA 02139 USA
  • 7. Univ Bern, CH-3012 Bern, Switzerland
  • 8. Yale Univ, New Haven, CT 06520 USA
  • 9. Fermilab Natl Accelerator Lab, Batavia, IL 60510 USA
  • 10. Univ Michigan, Ann Arbor, MI 48109 USA
  • 11. Univ Oxford, Oxford OX1 3RH, England
  • 12. Brookhaven Natl Lab, Upton, NY 11973 USA
  • 13. TUBITAK Space Technol Res Inst, METU Campus, TR-06800 Ankara, Turkey
  • 14. Syracuse Univ, Syracuse, NY 13244 USA
  • 15. PNNL, Richland, WA 99352 USA
  • 16. Univ Lancaster, Lancaster LA1 4YW, England
  • 17. Columbia Univ, New York, NY 10027 USA

Description

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 nu(mu) charged-current neutral pion data samples.

Files

bib-f0d10fe2-33e4-4207-97da-3621b872703e.txt

Files (417 Bytes)

Name Size Download all
md5:83f0f942c9c7452141d563dc2708633f
417 Bytes Preview Download