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.
@article{arxiv.2206.14904,
title = {Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors},
author = {Josh Tingey and Simeon Bash and John Cesar and Thomas Dodwell and Stefano Germani and Paul Kooijman and Petr Mánek and Mustafa Ozkaynak and Andy Perch and Jennifer Thomas and Leigh Whitehead},
journal= {arXiv preprint arXiv:2206.14904},
year = {2023}
}
Comments
45 pages, 22 figures, 5 tables, to be submitted to Nuclear Instruments and Methods in Physics Research - section A