2020/09/30 by NEXT Collaboration, M. Kekic, C. Adams +122 · 24 citations
Physics and Astronomy · #Artificial intelligence #Astrophysics #Calibration #Computer science #Convolutional neural network #Deep learning #Double beta decay #Event (particle physics) #Monte Carlo method #Nuclear physics #Particle Detector Development and Performance #Particle physics #Particle physics theoretical and experimental studies #Pattern recognition (psychology) #Physics #Radiation Detection and Scintillator Technologies #Statistics #Xenon #hep-ex #physics.ins-det
paper · pdf · doi:10.1007/jhep01(2021)189
published in Journal of High Energy Physics 2021(1) (Springer Nature) · 19 pages, 10 figures; version matches published JHEP version
openalex publication_date 2021/01/01 · arxiv created 2021/01/30 · arxiv updated 2021/02/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
A bstract 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 136 Xe. 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 228 Th 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.