Cosmic Ray Background Removal With Deep Neural Networks in SBND
Metadatos
Mostrar el registro completo del ítemEditorial
Frontiers Research Foundation
Materia
Deep learning Neutrino physics SBN program SBND UNet Liquid Ar detectors
Fecha
2021-08-24Referencia bibliográfica
Acciarri, R... [et al.] (2021). Cosmic Ray Background Removal With Deep Neural Networks in SBND. Frontiers in artificial intelligence, 4. doi: [10.3389/frai.2021.649917]
Patrocinador
U.S. Department of Energy, Office of Science, Office of High Energy Physics; U.S. National Science Foundation; Science and Technology Facilities Council (STFC); The Royal Society of the United Kingdom; Swiss National Science Foundation; Spanish Ministerio de Ciencia e Innovación (PID2019-104676GB-C32); Junta de Andalucía (SOMM17/6104/UGR, P18-FR-4314) FEDER Funds; São Paulo Research Foundation (FAPESP); National Council of Scientific and Technological Development (CNPq) of Brazil; Los Alamos National Laboratory for LDRD; Argonne Leadership Computing Facility; Fermi National Accelerator Laboratory (Fermilab); Fermi Research Alliance, LLC (FRA) DE-AC02-07CH11359Resumen
In liquid argon time projection chambers exposed to neutrino beams and running on
or near surface levels, cosmic muons, and other cosmic particles are incident on the
detectors while a single neutrino-induced event is being recorded. In practice, this means
that data fromsurface liquid argon time projection chambers will be dominated by cosmic particles, both as a source of event triggers and as the majority of the particle count in
true neutrino-triggered events. In this work, we demonstrate a novel application of deep
learning techniques to remove these background particles by applying deep learning
on full detector images from the SBND detector, the near detector in the Fermilab
Short-Baseline Neutrino Program. We use this technique to identify, on a pixel-by-pixel
level, whether recorded activity originated from cosmic particles or neutrino interactions.