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

6533b829fe1ef96bd1289940

RESEARCH PRODUCT

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

T. Contreras Z. E. Meziani R. Weiss-babai I. J. Arnquist J.v. Carrión J. Renner J. Renner N. López-march N. López-march L. Rogers F.j. Mora J. Generowicz T.m. Stiegler Vicente Herrero F.p. Santos G. Martínez-lema G. Martínez-lema G. Martínez-lema C.m.b. Monteiro R.d.p. Mano L.m.p. Fernandes J.m. Benlloch-rodríguez J.m. Benlloch-rodríguez P. Herrero C. Adams N. Byrnes B. Palmeiro B. Palmeiro J.a. Hernando Morata N. Yahlali D. González-díaz Y. Rodriguez Garcia J. S. Díaz M. Martínez-vara P. Novella F.i.g.m. Borges Romain Esteve J.f.c.a. Veloso E.d.c. Freitas J. Martin-albo M. Del Tutto A. Usón R. Guenette F. Monrabal F. Monrabal Roberto Gutiérrez A.d. Mcdonald C.d.r. Azevedo J.t. White J.f. Toledo S. Cárcel P. Lebrun A. Martínez A. Martínez M. Diesburg E. Church A. Laing Kevin Bailey J. Rodríguez M. Kekic M. Kekic A.b. Redwine C.a.o. Henriques J. Escada L. Ripoll J. Torrent Lior Arazi B. J. P. Jones Víctor H. Alvarez J. Haefner B. Romeo R. Felkai R. Felkai M. Losada A. Goldschmidt J. Hauptman K. Woodruff L. Labarga Y. Ifergan J.m.f. Dos Santos C. Romo-luque Javier Pérez S. Cebrián Sudip Ghosh R. C. Webb G. Díaz F. Ballester Paola Ferrario Paola Ferrario D.r. Nygren D.r. Nygren A.f.m. Fernandes M. Querol C. Sofka C. Sofka A. Para M. Sorel A.l. Ferreira K. Hafidi C.a.n. Conde A. Simón J.j. Gómez-cadenas J.j. Gómez-cadenas J. Muñoz Vidal J. Muñoz Vidal

subject

Nuclear and High Energy Physics Physics - Instrumentation and Detectors Calibration (statistics)Computer Science::Neural and Evolutionary Computation Nuclear physics FOS: Physical sciences Topology (electrical circuits)01 natural sciences Convolutional neural network Atomic Partícules (Física nuclear)High Energy Physics - Experiment Interaccions electró-positró TECNOLOGIA ELECTRONICA High Energy Physics - Experiment (hep-ex)Particle and Plasma Physics Double beta decay 0103 physical sciences Dark Matter and Double Beta Decay (experiments)Nuclear Nuclear Matrix lcsh:Nuclear and particle physics. Atomic energy. Radioactivity 010306 general physics Electron-positron interactions Mathematical Physics Particles (Nuclear physics)Physics Quantum Physics 010308 nuclear & particles physics business.industry Event (computing)Network on SIGNAL (programming language)Molecular Física Pattern recognition Detector Instrumentation and Detectors (physics.ins-det)Beta Decay Double beta decay Nuclear & Particles Physics Doble desintegració beta Identification (information)lcsh:QC770-798 Física nuclear Artificial intelligence business

description

[EN] 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

year	journal	country	edition	language
2021-01-28	Journal of High Energy Physics

10.1007/jhep01(2021)189 https://doaj.org/article/4a26af73701c4985a3782da446c27452