Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈Ev〉 ∼ 6GeV

A. Ghosh, B. Yaeggy, R. Galindo, Z. Ahmad Dar, F. Akbar, M. V. Ascencio, A. Bashyal, A. Bercellie, J. L. Bonilla, G. Caceres, T. Cai, M. F. Carneiro, H. da Motta, G. A. Díaz, J. Felix, A. Filkins, R. Fine, A. M. Gago, T. Golan, R. GranD. A. Harris, S. Henry, S. Jena, D. Jena, J. Kleykamp, M. Kordosky, D. Last, T. Le, A. Lozano, X. G. Lu, E. Maher, S. Manly, W. A. Mann, C. Mauger, K. S. McFarland, B. Messerly, J. Miller, L. M. Montano, D. Naples, J. K. Nelson, C. Nguyen, A. Olivier, V. Paolone, G. N. Perdue, M. A. Ramírez, H. Ray, D. Ruterbories, C. J.Solano Salinas, H. Su, M. Sultana, V. S. Syrotenko, E. Valencia, M. Wospakrik, C. Wret, K. Yang, L. Zazueta

Research output: Contribution to journalArticlepeer-review

Abstract

This paper presents a novel neutral-pion reconstruction that takes advantage of the machine learning technique of semantic segmentation using MINERvA data collected between 2013-2017, with an average neutrino energy of 6 GeV. Semantic segmentation improves the purity of neutral pion reconstruction from two γs from 70.7 ± 0.9% to 89.3 ± 0.7% and improves the efficiency of the reconstruction by approximately 40%. We demonstrate our method in a charged current neutral pion production analysis where a single neutral pion is reconstructed. This technique is applicable to modern tracking calorimeters, such as the new generation of liquid-argon time projection chambers, exposed to neutrino beams with 〈Ev〉 between 1-10 GeV. In such experiments it can facilitate the identification of ionization hits which are associated with electromagnetic showers, thereby enabling improved reconstruction of charged-current ve events arising from vμ → ve appearance.

Original languageEnglish (US)
Article numberP07060
JournalJournal of Instrumentation
Volume16
Issue number7
DOIs
StatePublished - Jul 2021
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2021 IOP Publishing Ltd and Sissa Medialab

Keywords

  • Analysis and statistical methods
  • Calibration
  • Cluster finding
  • Fitting methods
  • Neutrino detectors
  • Pattern recognition

Fingerprint

Dive into the research topics of 'Neutral pion reconstruction using machine learning in the MINERvA experiment at 〈E<sub>v</sub>〉 ∼ 6GeV'. Together they form a unique fingerprint.

Cite this