@Article{NEXTCollaborationKekic_etal2021,
author="NEXT Collaboration (Kekic, M. et al
and Benlloch-Rodriguez, J. M.
and Carcel, S.
and Carrion, J. V.
and Diaz, J.
and Felkai, R.
and Lopez-March, N.
and Martin-Albo, J.
and Martinez, A.
and Martinez-Lema, G.
and Martinez-Vara, M.
and Mu{\~{n}}oz Vidal, J.
and Novella, P.
and Palmeiro, B.
and Querol, M.
and Renner, J.
and Romo-Luque, C.
and Sorel, M.
and Uson, A.
and Yahlali, N.",
title="Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment",
journal="Journal of High Energy Physics",
year="2021",
publisher="Springer",
volume="01",
number="1",
pages="189--22pp",
optkeywords="Dark Matter and Double Beta Decay (experiments)",
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 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.",
optnote="WOS:000616730800001",
optnote="exported from refbase (https://references.ific.uv.es/refbase/show.php?record=4729), last updated on Wed, 18 May 2022 07:42:54 +0000",
issn="1029-8479",
doi="10.1007/JHEP01(2021)189",
opturl="https://arxiv.org/abs/2009.10783",
opturl="https://doi.org/10.1007/JHEP01(2021)189",
language="English"
}