Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators
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. Here, 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.
- Authors:
-
- Univ. of Michigan, Ann Arbor, MI (United States)
- Publication Date:
- Research Org.:
- Univ. of Michigan, Ann Arbor, MI (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1798642
- Alternate Identifier(s):
- OSTI ID: 1582705
- Grant/Contract Number:
- NA0002534
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Annals of Nuclear Energy (Oxford)
- Additional Journal Information:
- Journal Name: Annals of Nuclear Energy (Oxford); Journal Volume: 120; Journal ID: ISSN 0306-4549
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING; Neural networks; Organic scintillators; Piled-up identification; Pulse shape discrimination
Citation Formats
Fu, C., Di Fulvio, A., Clarke, S. D., Wentzloff, D., Pozzi, S. A., and Kim, H. S. Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators. United States: N. p., 2018.
Web. doi:10.1016/j.anucene.2018.05.054.
Fu, C., Di Fulvio, A., Clarke, S. D., Wentzloff, D., Pozzi, S. A., & Kim, H. S. Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators. United States. https://doi.org/10.1016/j.anucene.2018.05.054
Fu, C., Di Fulvio, A., Clarke, S. D., Wentzloff, D., Pozzi, S. A., and Kim, H. S. Thu .
"Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators". United States. https://doi.org/10.1016/j.anucene.2018.05.054. https://www.osti.gov/servlets/purl/1798642.
@article{osti_1798642,
title = {Artificial neural network algorithms for pulse shape discrimination and recovery of piled-up pulses in organic scintillators},
author = {Fu, C. and Di Fulvio, A. and Clarke, S. D. and Wentzloff, D. and Pozzi, S. A. and Kim, H. S.},
abstractNote = {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. Here, 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.},
doi = {10.1016/j.anucene.2018.05.054},
journal = {Annals of Nuclear Energy (Oxford)},
number = ,
volume = 120,
place = {United States},
year = {Thu Jun 14 00:00:00 EDT 2018},
month = {Thu Jun 14 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Neutron detection in a high-gamma field using solution-grown stilbene
journal, January 2016
- Bourne, M. M.; Clarke, S. D.; Adamowicz, N.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 806
Prompt neutrons from photofission and its use in homeland security applications
conference, November 2010
- Danagoulian, Areg; Bertozzi, William; Hicks, Curtis L.
- 2010 IEEE International Conference on Technologies for Homeland Security (HST)
FPGA-Based Pulse Pile-Up Correction With Energy and Timing Recovery
journal, October 2012
- Haselman, M. D.; Pasko, J.; Hauck, S.
- IEEE Transactions on Nuclear Science, Vol. 59, Issue 5
Digital Pulse Shape Discrimination in Triple-Layer Phoswich Detectors Using Fuzzy Logic
journal, October 2008
- Yousefi, S.; Lucchese, L.
- IEEE Transactions on Nuclear Science, Vol. 55, Issue 5
Pulse pile-up recovery for the front-end electronics of the PANDA Electromagnetic Calorimeter
conference, October 2011
- Tambave, G.; Guliyev, E.; Kavatsyuk, M.
- 2011 IEEE Nuclear Science Symposium and Medical Imaging Conference (2011 NSS/MIC), 2011 IEEE Nuclear Science Symposium Conference Record
Neutron and gamma ray discrimination for CLYC using normalized cross correlation analysis
conference, November 2014
- Chandhran, Premkumar; Holbert, Keith E.; Johnson, Erik B.
- 2014 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC)
Digital pile-up rejection for plutonium experiments with solution-grown stilbene
journal, January 2017
- Bourne, M. M.; Clarke, S. D.; Paff, M.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 842
Verification of the digital discrimination of neutrons and rays using pulse gradient analysis by digital measurement of time of flight
journal, December 2007
- Aspinall, M. D.; D’Mellow, B.; Mackin, R. O.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 583, Issue 2-3
Neural neutron/gamma discrimination in organic scintillators for fusion applications
conference, January 2004
- Esposito, B.; Fortuna, L.; Rizzo, A.
- 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
Passive assay of plutonium metal plates using a fast-neutron multiplicity counter
journal, May 2017
- Di Fulvio, A.; Shin, T. H.; Jordan, T.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 855
Digital pulse-shape discrimination of fast neutrons and rays
journal, August 2008
- Söderström, P.-A.; Nyberg, J.; Wolters, R.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 594, Issue 1, p. 79-89
An investigation of the digital discrimination of neutrons and γ rays with organic scintillation detectors using an artificial neural network
journal, August 2009
- Liu, G.; Aspinall, M. D.; Ma, X.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 607, Issue 3
A scaled conjugate gradient algorithm for fast supervised learning
journal, January 1993
- Møller, Martin Fodslette
- Neural Networks, Vol. 6, Issue 4
An algorithm for charge-integration, pulse-shape discrimination and estimation of neutron/photon misclassification in organic scintillators
journal, September 2015
- Polack, J. K.; Flaska, M.; Enqvist, A.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 795
Pulse Shape Discrimination of Neutrons and Gamma Rays Using Kohonen Artificial Neural Networks
journal, April 2013
- Tambouratzis, Tatiana; Chernikova, Dina; Pzsit, Imre
- Journal of Artificial Intelligence and Soft Computing Research, Vol. 3, Issue 2
Recursive algorithms for digital implementation of neutron/gamma discrimination in liquid scintillation detectors
journal, April 2012
- Nakhostin, M.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 672
Deep learning in neural networks: An overview
journal, January 2015
- Schmidhuber, Jürgen
- Neural Networks, Vol. 61
Pulse shape discrimination in inorganic and organic scintillators. I
journal, August 1971
- Winyard, R. A.; Lutkin, J. E.; McBeth, G. W.
- Nuclear Instruments and Methods, Vol. 95, Issue 1, p. 141-153
Active neutron and gamma-ray imaging of highly enriched uranium for treaty verification
journal, August 2017
- Hamel, Michael C.; Polack, J. Kyle; Ruch, Marc L.
- Scientific Reports, Vol. 7, Issue 1
Principal Component Analysis for pulse-shape discrimination of scintillation radiation detectors
journal, January 2016
- Alharbi, T.
- Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 806
Signal recognition efficiencies of artificial neural-network pulse-shape discrimination in HPGe $$\varvec{0\nu \beta \beta }$$ 0 ν β β -decay searches
journal, July 2015
- Caldwell, A.; Cossavella, F.; Majorovits, B.
- The European Physical Journal C, Vol. 75, Issue 7