Document Type
Thesis
Date of Award
2023
Degree Name
Master of Science (MS)
Department
Physics
First Advisor
Jing Liu
Abstract
Neutrinos are subatomic particles that weakly interact with matter due to their neutral charge and small cross section. Detectors that search for neutrinos require sensitive instrumentation, which makes them susceptible to various background sources such as gamma rays. Additionally, coherent elastic neutrino-nucleus scattering events, or CEvNS, are the weakest neutrino interactions at 1-25 keV, making them exceptionally difficult to observe. To understand the physics of CEvNS events within the detector material, the recoil signatures of relevant interactions must be determined. Traditional analysis methods are effective, but cannot be applied to energies below 50 keV, due to the overlap of discrimination criteria. In this thesis, we investigate the effectiveness of applied neural networks to distinguish between two recoil signatures present in COHERENT’s CENNS-10 LAr detector. Results indicate that dense neural networks perform well on classifying low energy events that approach the CEvNS energy threshold. We also discuss modifications to the complexity and structure of the neural network, which may improve generality.
Subject Categories
Computer Sciences | Elementary Particles and Fields and String Theory | Physics
Keywords
Detector, Liquid Argon, Machine Learning, Neural Networks, Neutrinos
Number of Pages
54
Publisher
University of South Dakota
Recommended Citation
Siehien, Perry, "Background Discrimination of a Neutrino Detector with Dense Neural Networks" (2023). Dissertations and Theses. 121.
https://red.library.usd.edu/diss-thesis/121