Speaker
Description
This talk addresses the challenge of particle identification (PID) in the SuperFGD detector, a highly granular scintillator target that is a central component of the upgraded ND280 near detector in the T2K neutrino experiment. Precise PID is essential for reconstructing neutrino interactions and reducing systematic uncertainties in T2K's oscillation measurements. The SuperFGD comprises approximately two million 1-cm³ scintillator cubes, providing exceptional topological detail of particle tracks and showers. This fine granularity, while a powerful asset, presents a significant pattern recognition challenge due to the high dimensionality of the data. We discuss the application of advanced neural network techniques to leverage this rich topological information for robust particle classification, with a primary focus on separation of electrons from photons. This discrimination is essential for identifying electron neutrino interactions, where photons constitute the dominant background.
