Pulse shape discrimination plays a key role in improving the signal-to-background ratio in NEOS analysis by removing fast neutrons. Identifying particles by looking at the tail of the waveform has been an effective and plausible approach for pulse shape discrimination, but has the limitation in sorting low energy particles. As a good alternative, the convolutional neural network can scan the entire waveform as they are to recognize the characteristics of the pulse and perform shape classification of NEOS data. This network provides a powerful identification tool for all energy ranges and helps to search unprecedented phenomena of low-energy, a few MeV or less, neutrinos.
@article{arxiv.2009.13355,
title = {Pulse Shape Discrimination of Fast Neutron Background using Convolutional Neural Network for NEOS II},
author = {NEOS II Collaboration and Y. Jeong and B. Y. Han and E. J. Jeon and H. S. Jo and D. K. Kim and J. Y. Kim and J. G. Kim and Y. D. Kim and Y. J. Ko and H. M. Lee and M. H. Lee and J. Lee and C. S. Moon and Y. M. Oh and H. K. Park and K. S. Park and S. H. Seo and K. Siyeon and G. M. Sun and Y. S. Yoon and I. Yu},
journal= {arXiv preprint arXiv:2009.13355},
year = {2020}
}