Improving Physics Based Electron Neutrino Appearance Identification with a Long Short-Term Memory Network

Abstract

The NOνA experiment is a long baseline neutrino oscillation experiment with the objective to measure the oscillation probability of muon type neutrinos (νμ) into electron type neutrinos (νe). NOνA measures the interactions of neutrinos from the NuMI beam in two functionally identical liquid scintillator detectors. The far detector detects the appearance of electron neutrinos, leading to measurement of the oscillation parameters under study. Using an off axis beam with an 810 km baseline length, NOνA is sensitive to measuring the neutrino mass hierarchy, the CP violating parameter, and the octant of the mixing angle, θ23. The data presented in this thesis has been collected from October 2013, until May 2018. The first NOνA νe charged current identifier utilized an artificial neural network with the physical features of the highest energy reconstructed shower as inputs. The νe charged current identifier in this thesis utilizes a Long Short-Term Memory network with the physical features of every reconstructed shower in a particular interaction. In addition to the Long Short-Term Memory network, there are two Boosted Decision Trees to assist in event level selection. In the analysis of the data, 54 νe candidate events were detected with an expected background of 15 events. The results of this analysis prefer the normal mass hierarchy with maximal mixing and δCP = 1.92+0.08. Results π −1.19 from this analysis differ from the published NOνA analysis, due to the differences of electron identification techniques.