DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Gaussian mixture models as automated particle classifiers for fast neutron detectors

Abstract

Pulse shape discrimination (PSD) is the task of classifying electronic pulse shapes for different particle types such as gamma rays and fast neutrons interacting in scintillators and read out by photo sensitive detectors. This field has been limited in its adoption of techniques found in the statistical learning community. Methods initially employed in the 1960s for analog electronic circuitry persist in the current PSD literature describing operations performed on digitized pulses, which are amenable to statistical rigor. Despite vast amounts of data collected at low energy levels, traditional PSD methods are unable to discriminate particles below a certain threshold. As such, in this work, Gaussian mixture models (GMMs) are used as a clustering technique for fast neutron detection in the absence of labeled data. GMMs yield improvements spanning the energy spectrum in a desirably efficient, unsupervised fashion. An extension, the Dirichlet Process GMM, provides further flexibility and classification improvement.

Authors:
ORCiD logo [1];  [1];  [1];  [1];  [1];  [1];  [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States). Computational Engineering Division
Publication Date:
Research Org.:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation
OSTI Identifier:
1604282
Alternate Identifier(s):
OSTI ID: 1544913
Report Number(s):
LLNL-JRNL-752600
Journal ID: ISSN 1932-1864; 938753
Grant/Contract Number:  
AC52-07NA27344; AC52‐07NA27344
Resource Type:
Accepted Manuscript
Journal Name:
Statistical Analysis and Data Mining
Additional Journal Information:
Journal Volume: 12; Journal Issue: 6; Journal ID: ISSN 1932-1864
Publisher:
Wiley
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; classification; clustering; mixture models; pulse shape discrimination

Citation Formats

Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan, Ruz, Jaime, Simms, Lance, and Wurtz, Ron. Gaussian mixture models as automated particle classifiers for fast neutron detectors. United States: N. p., 2019. Web. doi:10.1002/sam.11432.
Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan, Ruz, Jaime, Simms, Lance, & Wurtz, Ron. Gaussian mixture models as automated particle classifiers for fast neutron detectors. United States. https://doi.org/10.1002/sam.11432
Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan, Ruz, Jaime, Simms, Lance, and Wurtz, Ron. Thu . "Gaussian mixture models as automated particle classifiers for fast neutron detectors". United States. https://doi.org/10.1002/sam.11432. https://www.osti.gov/servlets/purl/1604282.
@article{osti_1604282,
title = {Gaussian mixture models as automated particle classifiers for fast neutron detectors},
author = {Blair, Brenton and Chen, Cliff and Glenn, Andrew and Kaplan, Alan and Ruz, Jaime and Simms, Lance and Wurtz, Ron},
abstractNote = {Pulse shape discrimination (PSD) is the task of classifying electronic pulse shapes for different particle types such as gamma rays and fast neutrons interacting in scintillators and read out by photo sensitive detectors. This field has been limited in its adoption of techniques found in the statistical learning community. Methods initially employed in the 1960s for analog electronic circuitry persist in the current PSD literature describing operations performed on digitized pulses, which are amenable to statistical rigor. Despite vast amounts of data collected at low energy levels, traditional PSD methods are unable to discriminate particles below a certain threshold. As such, in this work, Gaussian mixture models (GMMs) are used as a clustering technique for fast neutron detection in the absence of labeled data. GMMs yield improvements spanning the energy spectrum in a desirably efficient, unsupervised fashion. An extension, the Dirichlet Process GMM, provides further flexibility and classification improvement.},
doi = {10.1002/sam.11432},
journal = {Statistical Analysis and Data Mining},
number = 6,
volume = 12,
place = {United States},
year = {Thu Jul 25 00:00:00 EDT 2019},
month = {Thu Jul 25 00:00:00 EDT 2019}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 9 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: High energy example pulses.

Save / Share:

Works referenced in this record:

Maximum Likelihood from Incomplete Data Via the EM Algorithm
journal, September 1977

  • Dempster, A. P.; Laird, N. M.; Rubin, D. B.
  • Journal of the Royal Statistical Society: Series B (Methodological), Vol. 39, Issue 1
  • DOI: 10.1111/j.2517-6161.1977.tb01600.x

Optimal Inversion of the Generalized Anscombe Transformation for Poisson-Gaussian Noise
journal, January 2013


A study on fast digital discrimination of neutron and gamma-ray for improvement neutron emission profile measurement
journal, November 2014

  • Uchida, Y.; Takada, E.; Fujisaki, A.
  • Review of Scientific Instruments, Vol. 85, Issue 11
  • DOI: 10.1063/1.4891711

Machine learning-based prediction of glioma margin from 5-ALA induced PpIX fluorescence spectroscopy
journal, January 2020


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
  • DOI: 10.1016/0029-554X(71)90054-1

Improved pulse shape discrimination in EJ-301 liquid scintillators
journal, June 2017

  • Lang, R. F.; Masson, D.; Pienaar, J.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 856
  • DOI: 10.1016/j.nima.2017.02.090

Pulse Shape Discrimination - A Survey of Current Teniques
journal, June 1962


Gibbs Sampling Methods for Stick-Breaking Priors
journal, March 2001

  • Ishwaran, Hemant; James, Lancelot F.
  • Journal of the American Statistical Association, Vol. 96, Issue 453
  • DOI: 10.1198/016214501750332758

Assessing and minimizing contamination in time of flight basedvalidation data
journal, October 2017

  • Lennox, Kristin P.; Rosenfield, Paul; Blair, Brenton
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 870
  • DOI: 10.1016/j.nima.2017.04.022

Variational inference for Dirichlet process mixtures
journal, March 2006

  • Blei, David M.; Jordan, Michael I.
  • Bayesian Analysis, Vol. 1, Issue 1
  • DOI: 10.1214/06-BA104

Application of Bayes׳ theorem for pulse shape discrimination
journal, September 2015

  • Monterial, Mateusz; Marleau, Peter; Clarke, Shaun
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 795
  • DOI: 10.1016/j.nima.2015.06.014

Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator
journal, September 2018

  • Wurtz, Ron; Blair, Brenton; Chen, Cliff
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 901
  • DOI: 10.1016/j.nima.2018.06.001

Bayesian Data Analysis
book, November 2013