Title: Expert‐in‐the‐loop design of integral nuclear data experiments

Journal Article · · Statistical Analysis and Data Mining
DOI: https://doi.org/10.1002/sam.11677 · OSTI ID:2332898

Abstract Nuclear data are fundamental inputs to radiation transport codes used for reactor design and criticality safety. The design of experiments to reduce nuclear data uncertainty has been a challenge for many years, but advances in the sensitivity calculations of radiation transport codes within the last two decades have made optimal experimental design possible. The design of integral nuclear experiments poses numerous challenges not emphasized in classical optimal design, in particular, constrained design spaces (in both a statistical and engineering sense), severely under‐determined systems, and optimality uncertainty. We present a design pipeline to optimize critical experiments that uses constrained Bayesian optimization within an iterative expert‐in‐the‐loop framework. We show a successfully completed experiment campaign designed with this framework that involved two critical configurations and multiple measurements that targeted compensating errors in 239 Pu nuclear data.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE; USDOE Laboratory Directed Research and Development (LDRD) Program; USDOE National Nuclear Security Administration (NNSA), Nuclear Criticality Safety Program (NCSP)
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2332898
Report Number(s):
LA-UR-23-26536; e11677
Journal Information:
Statistical Analysis and Data Mining, Journal Name: Statistical Analysis and Data Mining Journal Issue: 2 Vol. 17; ISSN 1932-1864
Publisher:
Wiley Blackwell (John Wiley & Sons)Copyright Statement
Country of Publication:
United States
Language:
English

References (24)

Interactive machine learning for health informatics: when do we need the human-in-the-loop? journal March 2016
Constrained Bayesian optimization of criticality experiments journal February 2021
ENDF/B-VIII.0: The 8 th Major Release of the Nuclear Reaction Data Library with CIELO-project Cross Sections, New Standards and Thermal Scattering Data journal February 2018
Enhancing nuclear data validation analysis by using machine learning journal July 2020
Bayesian optimisation for efficient material discovery: a mini review journal January 2023
Current overview of ICSBEP and IRPhEP benchmark evaluation practices journal January 2020
EUCLID: A New Approach to Constrain Nuclear Data via Optimized Validation Experiments using Machine Learning journal January 2023
SENSMG: First-Order Sensitivities of Neutron Reaction Rates, Reaction-Rate Ratios, Leakage, k eff , and α Using PARTISN journal July 2018
Application of Neutron Multiplicity Counting Experiments to Optimal Cross-Section Adjustments journal February 2020
Data Assimilation Using Subcritical Measurement of Prompt Neutron Decay Constant journal March 2020
Quantile-Based Optimization of Noisy Computer Experiments With Tunable Precision journal July 2012
Informing nuclear physics via machine learning methods with differential and integral experiments journal September 2021
NASA's Kilopower reactor development and the path to higher power missions conference March 2017
Taking the Human Out of the Loop: A Review of Bayesian Optimization journal January 2016
Towards Robot Scientists for autonomous scientific discovery journal January 2010
Human-in-the-loop assisted de novo molecular design journal December 2022
The International Criticality Safety Benchmark Evaluation Project journal September 2003
DICE: Database for the International Criticality Safety Benchmark Evaluation Program Handbook journal September 2003
Sensitivity- and Uncertainty-Based Criticality Safety Validation Techniques journal March 2004
Whisper: Sensitivity/Uncertainty-Based Computational Methods and Software for Determining Baseline Upper Subcritical Limits journal September 2015
Sensitivity Coefficients Calculated for the Prompt Neutron Decay Constant at or near Delayed Critical conference January 2022
Human-in-the-loop Bayesian optimization of wearable device parameters journal September 2017
Neutron Leakage Spectra Sensitivities for ICSBEP Benchmarks [Slides]
  • Thompson, Nicholas; Hutchinson, Jesson; Alwin, Jennifer
  • 2022 ANS Winter Meeting and Technology Expo, Phoenix, AZ (United States), 13-17 Nov 2022 https://doi.org/10.2172/1923310
conference November 2022
Bayesian Optimization for Chemical Reactions journal February 2023