Modeling nuclear data uncertainties using deep neural networks

Majdi I. Radaideh, Dean Price, Tomasz Kozlowski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A new concept using deep learning in neural networks is investigated to characterize the underlying uncertainty of nuclear data. Analysis is performed on multi-group neutron cross-sections (56 energy groups) for the GODIVA U-235 sphere. A deep model is trained with cross-validation using 1000 nuclear data random samples to fit 336 nuclear data parameters. Although of the very limited sample size (1000 samples) available in this study, the trained models demonstrate promising performance, where a prediction error of about 166 pcm is found for keff in the test set. In addition, the deep model's sensitivity and uncertainty are validated. The comparison of importance ranking of the principal fast fission energy groups with adjoint methods shows fair agreement, while a very good agreement is observed when comparing the global keff uncertainty with sampling methods. The findings of this work shall motivate additional efforts on using machine learning to unravel complexities in nuclear data research.

Original languageEnglish (US)
Title of host publicationInternational Conference on Physics of Reactors
Subtitle of host publicationTransition to a Scalable Nuclear Future, PHYSOR 2020
EditorsMarat Margulis, Partrick Blaise
PublisherEDP Sciences - Web of Conferences
Pages2583-2590
Number of pages8
ISBN (Electronic)9781713827245
DOIs
StatePublished - 2020
Externally publishedYes
Event2020 International Conference on Physics of Reactors: Transition to a Scalable Nuclear Future, PHYSOR 2020 - Cambridge, United Kingdom
Duration: Mar 28 2020Apr 2 2020

Publication series

NameInternational Conference on Physics of Reactors: Transition to a Scalable Nuclear Future, PHYSOR 2020
Volume2020-March

Conference

Conference2020 International Conference on Physics of Reactors: Transition to a Scalable Nuclear Future, PHYSOR 2020
Country/TerritoryUnited Kingdom
CityCambridge
Period3/28/204/2/20

Keywords

  • DNN
  • Nuclear data
  • SCALE/sampler
  • Sensitivity analysis
  • Uncertainty quantification

ASJC Scopus subject areas

  • Nuclear Energy and Engineering
  • Safety, Risk, Reliability and Quality
  • Nuclear and High Energy Physics
  • Radiation

Fingerprint

Dive into the research topics of 'Modeling nuclear data uncertainties using deep neural networks'. Together they form a unique fingerprint.

Cite this