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

Kekic, M ; Adams, C ; Woodruff, K ; Renner, J ; Church, E ; Del Tutto, M ; Morata, JAH ; Gomez-Cadenas, JJ ; Alvarez, V ; Arazi, L ; Arnquist, IJ ; Azevedo, CDR ; Bailey, K ; Ballester, F ; Benlloch-Rodriguez, JM ; Borges, FIGM ; Byrnes, N ; Carcel, S ; Carrion, JV ; Cebrian, S (Universidad de Zaragoza) ; Conde, CAN ; Contreras, T ; Diaz, G ; Diaz, J ; Diesburg, M ; Escada, J ; Esteve, R ; Felkai, R ; Fernandes, AFM ; Fernandes, LMP ; Ferrario, P ; Ferreira, AL ; Freitas, EDC ; Generowicz, J ; Ghosh, S ; Goldschmidt, A ; Gonzalez-Diaz, D ; Guenette, R ; Gutierrez, RM ; Haefner, J ; Hafidi, K ; Hauptman, J ; Henriques, CAO ; Herrero, P ; Herrero, V ; Ifergan, Y ; Jones, BJP ; Labarga, L ; Laing, A ; Lebrun, P ; Lopez-March, N ; Losada, M ; Mano, RDP ; Martin-Albo, J ; Martinez, A ; Martinez-Lema, G ; Martinez-Vara, M ; McDonald, AD ; Meziani, ZE ; Monrabal, F ; Monteiro, CMB ; Mora, FJ ; Vidal, JM ; Novella, P ; Nygren, DR ; Palmeiro, B ; Para, A ; Perez, J ; Querol, M ; Redwine, AB ; Ripoll, L ; Garcia, YR ; Rodriguez, J ; Rogers, L ; Romeo, B ; Romo-Luque, C ; Santos, FP ; dos Santos, JMF ; Simon, A ; Sofka, C ; Sorel, M ; Stiegler, T ; Toledo, JF ; Torrent, J ; Uson, A ; Veloso, JFCA ; Webb, R ; Weiss-Babai, R ; White, JT ; Yahlali, N

Resumen: 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 Xe-136. 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 Th-228 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.

Idioma: Inglés

DOI: 10.1007/JHEP01(2021)189

Año: 2021

Publicado en: Journal of High Energy Physics 1 (2021), 189
ISSN: 1126-6708

Factor impacto JCR: 6.376 (2021)

Categ. JCR: PHYSICS, PARTICLES & FIELDS rank: 6 / 29 = 0.207 (2021) - Q1 - T1

Factor impacto CITESCORE: 10.3 - Physics and Astronomy (Q1)

Factor impacto SCIMAGO: 0.895 - Nuclear and High Energy Physics (Q2)

Tipo y forma: Artículo (PostPrint)

Área (Departamento): Área Física Atóm.Molec.y Nucl. (Dpto. Física Teórica)