Omslagsbillede

Domain Generalization with Machine Learning in the NOvA Experiment

This thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which...

Fuld beskrivelse

Saved in:
Bibliografiske detaljer
Hovedforfatter: Sutton, Andrew T.C (Author)
Institution som forfatter: SpringerLink (Online service)
Format: Electronisk eBog
Sprog:engelsk
Udgivet: Cham : Springer Nature Switzerland : Imprint: Springer, 2023.
Udgivelse:1st ed. 2023.
Serier:Springer Theses, Recognizing Outstanding Ph.D. Research,
Fag:
Particles (Nuclear physics).
Particle accelerators.
Measurement.
Measuring instruments.
Machine learning.
Mathematical physics.
Computer simulation.
Particle Physics.
Accelerator Physics.
Measurement Science and Instrumentation.
Machine Learning.
Computational Physics and Simulations.
Online adgang:https://doi.org/10.1007/978-3-031-43583-6
Tags: Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
Beskrivelse
Summary:This thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which studies changes in a beam of neutrinos as it propagates approximately 800 km through the earth. NOvA relies heavily on simulations of the physics processes and the detector response; these simulations work well, but do not match the real experiment perfectly. Thus, neural networks trained on simulated datasets must include systematic uncertainties that account for possible imperfections in the simulation. This thesis presents the first application in HEP of adversarial domain generalization to a regression neural network. Applying domain generalization to problems with large systematic variations will reduce the impact of uncertainties while avoiding the risk of falselyconstraining the phase space. Reducing the impact of systematic uncertainties makes NOvA analysis more robust, and improves the significance of experimental results.
Fysisk beskrivelse:1 online resource (XI, 170 p. 73 illus.). 63 illus. in color.
ISBN:9783031435836
ISSN:2190-5061
DOI:10.1007/978-3-031-43583-6

Lignende værker