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

• DOI: 10.1007/jhep01(2021)189
• Publication Date: 2021-01-29T09:43:35Z
• Authors: M. Kekic; C. Adams; K. Woodruff; J. Renner; E. Church; M. Del Tutto; J. A. Hernando Mo...; J. J. Gómez-Cadenas; V. Álvarez; L. Arazi; I. J. Arnquist; C. D. R. Azevedo; K. Bailey; F. Ballester; J. M. Benlloch-Ro...; F. I. G. M. Borges; N. Byrnes; S. Cárcel; J. V. Carrión; S. Cebrián; C. A. N. Conde; T. Contreras; G. Díaz; J. Díaz; M. Diesburg; J. Escada; R. Esteve; R. Felkai; A. F. M. Fernandes; L. M. P. Fernandes; P. Ferrario; A. L. Ferreira; E. D. C. Freitas; J. Generowicz; S. Ghosh; A. Goldschmidt; D. González-Díaz; R. Guenette; R. M. Gutiérrez; J. Haefner; K. Hafidi; J. Hauptman; C. A. O. Henriques; P. Herrero; V. Herrero; Y. Ifergan; B. J. P. Jones; L. Labarga; A. Laing; P. Lebrun; N. López-March; M. Losada; R. D. P. Mano; J. Martín-Albo; A. Martínez; G. Martínez-Lema; M. Martínez-Vara; A. D. McDonald; Z.-E. Meziani; F. Monrabal; C. M. B. Monteiro; F. J. Mora; J. Muñoz Vidal; P. Novella; D. R. Nygren; B. Palmeiro; A. Para; J. Pérez; M. Querol; A. B. Redwine; L. Ripoll; Y. Rodríguez García; J. Rodríguez; L. Rogers; B. Romeo; C. Romo-Luque; F. P. Santos; J. M. F. dos Santos; A. Simón; C. Sofka; M. Sorel; T. Stiegler; J. F. Toledo; J. Torrent; A. Usón; J. F. C. A. Veloso; R. Webb; R. Weiss-Babai; J. T. White; N. Yahlali
• Keywords: Artificial intelligence; Physics - Instrumentation and Detectors; Xenon; Nuclear physics; QC770-798; Pattern recognition (psychology); Astrophysics; Atomic; 01 natural sciences; 7. Clean energy; High Energy Physics - Experiment; Identification (biology); High Energy Physics - Experiment (hep-ex); Particle and Plasma Physics; 0302 clinical medicine; Dark Matter and Double Beta Decay (experiments); Mathematical Physics; Quantum Physics; Radiation; Network topology; Physics; Statistics; Instrumentation and Detectors (physics.ins-det); Nuclear & Particles Physics; Scintillation Detector Technology; Monte Carlo method; Detector Performance; Physical Sciences; Calibration; Física nuclear; Artificial neural network; Nuclear and High Energy Physics; Advancements in Particle Detector Technology; Neutron Detection; FOS: Physical sciences; Convolutional neural network; Quantum mechanics; Partícules (Física nuclear); Interaccions electró-positró; TECNOLOGIA ELECTRONICA; 03 medical and health sciences; Nuclear and particle physics. Atomic energy. Radioactivity; Machine learning; Neutrino; 0103 physical sciences; FOS: Mathematics; Nuclear; Nuclear Matrix; Particle Physics and High-Energy Collider Experiments; Electron-positron interactions; Event (particle physics); Biology; Particles (Nuclear physics); Radiation Detection; Botany; Molecular; Física; Detector; Deep learning; Beta Decay; Computer science; Double beta decay; Doble desintegració beta; Operating system; Physics and Astronomy; Mathematics

Abstract 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.