skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]

Abstract

In this study, we present novel methods for automated pulse shape discrimination. The classifiers are trained using simple radionuclide sources and do not require ground truth labeling. We test their performance using labels derived from time of flight experiments and present the results in terms of energy-dependent Receiver Operating Characteristic (ROC) curves. In addition, we also train and test standard pulse shape discrimination methods on the same data for comparison. We find multiple methods that can yield similar false neutron and true neutron rates at 24 keVee as tail-to-total or Gatti’s optimal linear filter yield at 54 keVee.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1];  [1];  [1]
  1. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1479077
Alternate Identifier(s):
OSTI ID: 1548113
Report Number(s):
LLNL-JRNL-744406
Journal ID: ISSN 0168-9002; 899021
Grant/Contract Number:  
AC52-07NA27344
Resource Type:
Accepted Manuscript
Journal Name:
Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment
Additional Journal Information:
Journal Volume: 901; Journal Issue: C; Journal ID: ISSN 0168-9002
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
73 NUCLEAR PHYSICS AND RADIATION PHYSICS; Pulse shape discrimination; Bayes classifier; Density estimation; Neutron detection

Citation Formats

Wurtz, Ron, Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan D., Rosenfield, Paul, Ruz, Jaime, and Simms, Lance M. Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]. United States: N. p., 2018. Web. doi:10.1016/j.nima.2018.06.001.
Wurtz, Ron, Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan D., Rosenfield, Paul, Ruz, Jaime, & Simms, Lance M. Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]. United States. doi:10.1016/j.nima.2018.06.001.
Wurtz, Ron, Blair, Brenton, Chen, Cliff, Glenn, Andrew, Kaplan, Alan D., Rosenfield, Paul, Ruz, Jaime, and Simms, Lance M. Sat . "Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]". United States. doi:10.1016/j.nima.2018.06.001. https://www.osti.gov/servlets/purl/1479077.
@article{osti_1479077,
title = {Methodology and performance comparison of statistical learning pulse shape classifiers as demonstrated with organic liquid scintillator [Performance comparison of statistical learning pulse shape classifiers]},
author = {Wurtz, Ron and Blair, Brenton and Chen, Cliff and Glenn, Andrew and Kaplan, Alan D. and Rosenfield, Paul and Ruz, Jaime and Simms, Lance M.},
abstractNote = {In this study, we present novel methods for automated pulse shape discrimination. The classifiers are trained using simple radionuclide sources and do not require ground truth labeling. We test their performance using labels derived from time of flight experiments and present the results in terms of energy-dependent Receiver Operating Characteristic (ROC) curves. In addition, we also train and test standard pulse shape discrimination methods on the same data for comparison. We find multiple methods that can yield similar false neutron and true neutron rates at 24 keVee as tail-to-total or Gatti’s optimal linear filter yield at 54 keVee.},
doi = {10.1016/j.nima.2018.06.001},
journal = {Nuclear Instruments and Methods in Physics Research. Section A, Accelerators, Spectrometers, Detectors and Associated Equipment},
number = C,
volume = 901,
place = {United States},
year = {2018},
month = {6}
}

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

Citation Metrics:
Cited by: 1 work
Citation information provided by
Web of Science

Save / Share: