TY - JOUR
T1 - Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators
AU - Fu, C.
AU - Di Fulvio, A.
AU - Clarke, S. D.
AU - Wentzloff, D.
AU - Pozzi, S. A.
AU - Kim, H. S.
N1 - Publisher Copyright:
© 2018 Elsevier Ltd
PY - 2018/10
Y1 - 2018/10
N2 - 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.
AB - 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.
KW - Neural networks
KW - Organic scintillators
KW - Piled-up identification
KW - Pulse shape discrimination
UR - http://www.scopus.com/inward/record.url?scp=85048263733&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048263733&partnerID=8YFLogxK
U2 - 10.1016/j.anucene.2018.05.054
DO - 10.1016/j.anucene.2018.05.054
M3 - Article
AN - SCOPUS:85048263733
SN - 0306-4549
VL - 120
SP - 410
EP - 421
JO - Annals of Nuclear Energy
JF - Annals of Nuclear Energy
ER -