Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment

Journal Article · Thu Jan 28 00:00:00 EST 2021 · Journal of High Energy Physics (Online)

DOI:https://doi.org/10.1007/jhep01(2021)189· OSTI ID:1767024

Kekic, M.; Adams, C.; Woodruff, K.; Renner, J.; Church, E.; Del Tutto, M.; Hernando Morata, J. A.; Gómez-Cadenas, J. J.; Álvarez, V.; Arazi, L.; Arnquist, I. J.; Azevedo, C. R.; Bailey, K.; Ballester, F.; Benlloch-Rodríguez, J. M.; Borges, F. M.; Byrnes, N.; Cárcel, S.; Carrión, J. V.; Cebrián, S. ; Conde, C. N.; Contreras, T.; Díaz, G.; Díaz, J.; Diesburg, M.; Escada, J.; Esteve, R.; Felkai, R.; Fernandes, A. M.; Fernandes, L. P.; Ferrario, P.; Ferreira, A. L.; Freitas, E. C.; Generowicz, J.; Ghosh, S.; Goldschmidt, A.; González-Díaz, D.; Guenette, R.; Gutiérrez, R. M.; Haefner, J.; Hafidi, K.; Hauptman, J.; Henriques, C. O.; Herrero, P.; Herrero, V.; Ifergan, Y.; Jones, B. P.; Labarga, L.; Laing, A.; Lebrun, P.; López-March, N.; Losada, M.; Mano, R. P.; Martín-Albo, J.; Martínez, A.; Martínez-Lema, G.; Martínez-Vara, M.; McDonald, A. D.; Meziani, Z. -E.; Monrabal, F.; Monteiro, C. B.; Mora, F. J.; Muñoz Vidal, J.; Novella, P.; Nygren, D. R.; Palmeiro, B.; Para, A.; Pérez, J.; Querol, M.; Redwine, A. B.; Ripoll, L.; Rodríguez García, Y.; Rodríguez, J.; Rogers, L.; Romeo, B.; Romo-Luque, C.; Santos, F. P.; dos Santos, J. F.; Simón, A.; Sofka, C.; Sorel, M.; Stiegler, T.; Toledo, J. F.; Torrent, J.; Usón, A.; Veloso, J. A.; Webb, R.; Weiss-Babai, R.; White, J. T.; Yahlali, N.

Convolutional neural networks (CNNs) are widely used state-of-the-art computer vision tools that are becoming increasingly popular in high-energy physics. In this paper, we attempt to understand the potential of CNNs for event classification in the NEXT experiment, which will search for neutrinoless double-beta decay in ¹³⁶Xe. To do so, we demonstrate the usage of CNNs for the identification of electron-positron pair production events, which exhibit a topology similar to that of a neutrinoless double-beta decay event. These events were produced in the NEXT-White high-pressure xenon TPC using 2.6 MeV gamma rays from a ²²⁸Th calibration source. We train a network on Monte Carlo-simulated events and show that, by applying on-the-fly data augmentation, the network can be made robust against differences between simulation and data. The use of CNNs offers significant improvement in signal efficiency and background rejection when compared to previous non-CNN-based analyses.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Argonne National Laboratory (ANL), Argonne, IL (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Univ. of Texas at Arlington, TX (United States)
• Sponsoring Organization: USDOE Office of Science (SC), High Energy Physics (HEP); NEXT Collaboration; USDOE Office of Science (SC), Nuclear Physics (NP)
• Contributing Organization: NEXT Collaboration
• Grant/Contract Number: AC02-07CH11359; FG02-13ER42020; SC0019223; SC0019054; AC05-76RL01830; AC02-05CH11231; AC02-06CH11357
• OSTI ID: 1767024
• Alternate ID(s): OSTI ID: 1781652; OSTI ID: 1798755; OSTI ID: 1840928; OSTI ID: 1908620
• Report Number(s): FERMILAB-PUB-20-648-ND-SCD; arXiv:2009.10783; PNNL-SA-159903; oai:inspirehep.net:1818727; TRN: US2206336
• Journal Information: Journal of High Energy Physics (Online), Vol. 2021, Issue 1; ISSN 1029-8479
• Publisher: Springer Berlin
• Country of Publication: United States
• Language: English

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY
Dark Matter and Double Beta Decay (experiments)
NEXT experiment
CNN
Neutrinoless double beta decay
event classification
high-pressure xenon chambers
73 NUCLEAR PHYSICS AND RADIATION PHYSICS