Funder: SERI and SNSF, Switzerland
Funder: Instituto Nazionale di Fisica Nucleare; doi: http://dx.doi.org/10.13039/501100004007
Funder: CAM, Fundacion “La Caixa”, Junta de Andalucia-FEDER, MICINN, and Xunta de Galicia, Spain
Funder: CERN; doi: http://dx.doi.org/10.13039/100012470
Funder: DOE and NSF, United States of America
Funder: CFI, IPP and NSERC, Canada
Funder: CNRS/IN2P3 and CEA, France
Funder: The Royal Society and UKRI/STFC, United Kingdom
Funder: ERDF, H2020-EU and MSCA, European Union
Funder: NRF, South Korea
Funder: FCT, Portugal
Funder: MSMT, Czech Republic
Funder: CNPq, FAPERJ, FAPEG and FAPESP, Brazil
Funder: TUB.ITAK, Turkey
Liquid argon time projection chamber detector technology provides high spatial and calorimetric resolutions on the charged particles traversing liquid argon. As a result, the technology has been used in a number of recent neutrino experiments, and is the technology of choice for the Deep Underground Neutrino Experiment (DUNE). In order to perform high precision measurements of neutrinos in the detector, final state particles need to be effectively identified, and their energy accurately reconstructed. This article proposes an algorithm based on a convolutional neural network to perform the classification of energy deposits and reconstructed particles as track-like or arising from electromagnetic cascades. Results from testing the algorithm on experimental data from ProtoDUNE-SP, a prototype of the DUNE far detector, are presented. The network identifies track- and shower-like particles, as well as Michel electrons, with high efficiency. The performance of the algorithm is consistent between experimental data and simulation.