Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors

TL;DR

This paper introduces a novel CNN-based method for event reconstruction and classification in water Cherenkov neutrino detectors, significantly improving performance over traditional techniques using simulated CHIPS detector data.

Contribution

It presents a new CNN approach tailored for water Cherenkov detector event analysis, enhancing cosmic muon rejection, event classification, and energy estimation.

Findings

Significant performance improvement over likelihood-based methods

Effective cosmic muon rejection and event classification

Accurate neutrino energy estimation

Abstract

This work presents a novel approach to water Cherenkov neutrino detector event reconstruction and classification. Three forms of a Convolutional Neural Network have been trained to reject cosmic muon events, classify beam events, and estimate neutrino energies, using only a slightly modified version of the raw detector event as input. When evaluated on a realistic selection of simulated CHIPS-5kton prototype detector events, this new approach significantly increases performance over the standard likelihood-based reconstruction and simple neural network classification.