Suppression of Neutron Background using Deep Neural Network and Fourier Frequency Analysis at the KOTO Experiment

2023/09/21 by Tung, Y. -C., Li, J., Hsiung, Y. B. +9
#FOS: Physical sciences #High Energy Physics - Experiment (hep-ex) #Instrumentation and Detectors (physics.ins-det)

paper · doi:10.48550/arxiv.2309.12063

Abstract

We present two analysis techniques for distinguishing background events induced by neutrons from photon signal events in the search for the rare K⁰_L→π⁰νν decay at the J-PARC KOTO experiment. These techniques employed a deep convolutional neural network and Fourier frequency analysis to discriminate neutrons from photons, based on their variations in cluster shape and pulse shape, in the electromagnetic calorimeter made of undoped CsI. The results effectively suppressed the neutron background by a factor of 5.6×10⁵, while maintaining the efficiency of K⁰_L→π⁰νν at 70%.

Related

• Pulse Shape Discrimination of Fast Neutron Background using Convolutional Neural Network for NEOS II
• Convolutional Neural Network-Based Neutron and Gamma Discrimination in EJ-276 for Low-Energy Detection
• Enhancing Photon Identification with Neural Network Methods
• Discrimination of neutron-γ in the low energy regime using machine learning for an EJ-276D plastic scintillator
• Kaon-Scatter Introduced Backgrounds in the KOTO Experiment