Pulse Shape Discrimination of Fast Neutron Background using Convolutional Neural Network for NEOS II

TL;DR

This paper presents a convolutional neural network approach for pulse shape discrimination in NEOS data, effectively identifying particles across all energy ranges, including low-energy neutrinos, to improve background rejection.

Contribution

The study introduces a CNN-based method for pulse shape discrimination that overcomes low-energy particle sorting limitations of traditional tail analysis techniques.

Findings

CNN accurately classifies pulse shapes across all energy ranges.

Improved signal-to-background ratio in NEOS analysis.

Enhanced detection capability for low-energy neutrinos.

Abstract

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.