Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators. (October 2018)

• Record Type: Journal Article
• Authors: Fu, C.; Di Fulvio, A.; Clarke, S.D.; Wentzloff, D.; Pozzi, S.A.; Kim, H.S.
• Is Part Of: Annals of nuclear energy. Volume 120(2018)
• Page Start: 410
• Page End: 421
• Publication Date: 2018-10
• Subjects: Neural networks -- Organic scintillators -- Piled-up identification -- Pulse shape discrimination; Nuclear energy -- Periodicals; Nuclear engineering -- Periodicals; 621.4805
• DOI: 10.1016/j.anucene.2018.05.054
• Languages: English
• ISSNs: 0306-4549

Abstract

Highlights: Neural-network-based algorithms for pulse shape discrimination. Algorithms tested on high count rate data sets (100, 000 cps). The new algorithms show lower misclassification rates compared to traditional approaches. Abstract: We developed two neural-network (NN)-based algorithms (fully-connected neural network (Fc-NN) and recurrent neural network (RNN)) to perform pulse shape discrimination (PSD) and identification of piled-up pulses produced by organic scintillators, upon interaction with neutrons and gamma rays. We tested the algorithms on measured and verification sets of data and compared their classification performances to standard approaches. At a high acquisition count rate (100, 000 counts per second, cps), in the presence of a gamma-to-neutron ratio of approximately 400–1, the proposed NN-based algorithm achieves a fraction of misclassified neutron, gamma, and piled-up pulses of approximately 1%, 1.8%, and 0.6%, respectively. Compared to the traditional approach, it exhibits 3×, 14×, and 11× improved (lower) miscalculation rates for neutron, gamma, and piled-up pulses, respectively. We also demonstrate the capability of NN-based algorithms of successfully recovering and identifying neutron and gamma ray compositions from piled-up pulses in challenging, high pulse count rate conditions.