Expert‐in‐the‐loop design of integral nuclear data experiments
Authors: 
Isaac Michaud, Michael Grosskopf, Jesson Hutchinson, and Scott Vander WielAuthors Info & Claims
Isaac Michaud, Michael Grosskopf, Jesson Hutchinson, and Scott Vander WielAuthors Info & ClaimsAbstract
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 239Pu nuclear data.
References
[1]
A. V. Arun Kumar, S. Rana, A. Shilton, and S. Venkatesh, Human‐AI collaborative Bayesian optimisation, Adv. Neural Inf. Process. Syst. 35 (2022), 16233–16245.
[2]
J. D. Bess and T. Ivanova, “Current overview of ICSBEP and IRPHEP benchmark evaluation practices,” EPJ web of conferences, Vol 239, EDP Sciences, Beijing, 2020, pp. 18002.
[3]
J. Blair Briggs, L. Scott, and A. Nouri, The international criticality safety benchmark evaluation project, Nucl. Sci. Eng. 145 (2003), no. 1, 1–10.
[4]
B. L. Broadhead, B. T. Rearden, C. M. Hopper, J. J. Wagschal, and C. V. Parks, Sensitivity‐and uncertainty‐based criticality safety validation techniques, Nucl. Sci. Eng. 146 (2004), no. 3, 340–366.
[5]
D. A. Brown, M. B. Chadwick, R. Capote, A. C. Kahler, A. Trkov, M. W. Herman, A. A. Sonzogni, Y. Danon, A. D. Carlson, M. Dunn, D. L. Smith, G. M. Hale, G. Arbanas, R. Arcilla, C. R. Bates, B. Beck, B. Becker, F. Brown, R. J. Casperson, J. Conlin, D. E. Cullen, M.‐A. Descalle, R. Firestone, T. Gaines, K. H. Guber, A. I. Hawari, J. Holmes, T. D. Johnson, T. Kawano, B. C. Kiedrowski, A. J. Koning, S. Kopecky, L. Leal, J. P. Lestone, C. Lubitz, J. I. Márquez Damián, C. M. Mattoon, E. A. McCutchan, S. Mughabghab, P. Navratil, D. Neudecker, G. P. A. Nobre, G. Noguere, M. Paris, M. T. Pigni, A. J. Plompen, B. Pritychenko, V. G. Pronyaev, D. Roubtsov, D. Rochman, P. Romano, P. Schillebeeckx, S. Simakov, M. Sin, I. Sirakov, B. Sleaford, V. Sobes, E. S. Soukhovitskii, I. Stetcu, P. Talou, I. Thompson, S. van der Marck, L. Welser‐Sherrill, D. Wiarda, M. White, J. L. Wormald, R. Q. Wright, M. Zerkle, G. Žerovnik, and Y. Zhu, Endf/b‐viii.0: The 8th major release of the nuclear reaction data library with CIELO‐project cross sections, new standards and thermal scattering data, Nuclear Data Sheets 148 (2018), 1–142 Special Issue on Nuclear Reaction Data.
[6]
L. Chan, Y.‐C. Liao, G. B. Mo, J. J. Dudley, C.‐L. Cheng, P. O. Kristensson, and A. Oulasvirta, “Investigating positive and negative qualities of human‐in‐the‐loop optimization for designing interaction techniques,” Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, New Orleans 2022, pp. 1–14.
[7]
A. Cisse, X. Evangelopoulos, S. Carruthers, V. V. Gusev, and A. I. Cooper. Hypbo: Expert‐guided chemist‐in‐the‐loop Bayesian search for new materials. arXiv preprint arXiv:2308.11787 2023.
[8]
A. R. Clark, J. Mattingly, and J. A. Favorite, Application of neutron multiplicity counting experiments to optimal cross‐section adjustments, Nucl. Sci. Eng. 194 (2020), no. 4, 308–333.
[9]
T. Cutler, J. Hutchinson, N. Kleedtke, M. Rising, D. Neudecker, B. Little, and N. Thompson, Validation of jezebel reactivity coefficients and sensitivity analysis, Trans. Am. Nucl. Soc. 125 (2021), no. LA‐UR‐21‐26475, 627–630.
[10]
T. Endo and A. Yamamoto, Data assimilation using subcritical measurement of prompt neutron decay constant, Nucl. Sci. Eng. 194 (2020), no. 11, 1089–1104.
[11]
J. A. Favorite, Sensmg: First‐order sensitivities of neutron reaction rates, reaction‐rate ratios, leakage, keff, and α$$ \alpha $$ using PARTISN, Nucl. Sci. Eng. 192 (2018), no. 1, 80–114.
[12]
M. A. Gibson, S. R. Oleson, D. I. Poston, and P. McClure, “NASA's Kilopower reactor development and the path to higher power missions,” 2017 IEEE aerospace conference, IEEE 2017, pp. 1–14.
[13]
J. Guo, B. Ranković, and P. Schwaller, Bayesian optimization for chemical reactions, Chimia 77 (2023), no. 1/2, 31–38.
[14]
A. Holzinger, Interactive machine learning for health informatics: When do we need the human‐in‐the‐loop? Brain Inform. 3 (2016), no. 2, 119–131.
[15]
J. Hutchinson, J. Alwin, A. R. Clark, T. Cutler, M. J. Grosskopf, W. Haeck, M. W. Herman, N. Kleedtke, J. Lamproe, R. C. Little, I. J. Michaud, D. Neudecker, M. E. Rising, T. Smith, N. Thompson, S. Vander Wiel, and N. Wynne, Euclid: A new approach to constrain nuclear data via optimized validation experiments using machine learning, EPJ Web Conf. 284 (2023), 15006.
[16]
J. D. Hutchinson, N. A. Kleedtke, J. L. Alwin, A. R. Clark, T. E. Cutler, W. Haeck, R. C. Little, D. Neudecker, M. E. Rising, T. A. Smith, et al., Investigation of delayed neutron sensitivities for several ICSBEP benchmarks using MCNP, Trans. Am. Nucl. Soc. 125 (2021), no. LA‐UR‐21‐26405, 623‐626.
[17]
Y. Jin and P. V. Kumar, Bayesian optimisation for efficient material discovery: A mini review, Nanoscale 15 (2023), 10975–10984.
[18]
B. C. Kiedrowski, F. B. Brown, J. L. Conlin, J. A. Favorite, A. C. Kahler, A. R. Kersting, D. Kent Parsons, and J. L. Walker, Whisper: Sensitivity/uncertainty‐based computational methods and software for determining baseline upper subcritical limits, Nucl. Sci. Eng. 181 (2015), no. 1, 17–47.
[19]
M. Kim, Y. Ding, P. Malcolm, J. Speeckaert, C. J. Siviy, C. J. Walsh, and S. Kuindersma, Human‐in‐the‐loop Bayesian optimization of wearable device parameters, PLoS One 12 (2017), no. 9, e0184054.
[20]
N. A. Kleedtke, J. D. Hutchinson, M. Y. Hua, and M. E. Rising, Sensitivity coefficients calculated for the prompt neutron decay constant at or near delayed critical. Technical report, Los Alamos National Lab, Los Alamos, NM, USA, 2022.
[21]
I. Michaud, N. Kleedtke, J. Hutchinson, T. Smith, R. Little, T. Grove, and M. Rising, Designing critical experiments using Gaussian process optimization, Trans. Am. Nucl. Soc. 121 (2019), no. LA‐UR‐19‐31529, 1035‐1038.
[22]
D. Neudecker, M. J. Grosskopf, W. Haeck, P. Grechanuk, S. Vander Wiel, M. Rising, N. Sly, and P. Talou, Enhancing nuclear data validation analysis by using machine learning, Nuclear Data Sheets 167 (2020), 36–60.
[23]
D. Neudecker, O. Cabellos, A. R. Clark, M. J. Grosskopf, W. Haeck, M. W. Herman, J. Hutchinson, T. Kawano, A. E. Lovell, I. Stetcu, P. Talou, and S. Vander Wiel, Informing nuclear physics via machine learning methods with differential and integral experiments, Phys. Rev. C 104 (2021), no. 3, 034611.
[24]
D. Neudecker, M. J. Grosskopf, J. L. Alwin, T. E. Cutler, S. C. Frankle, N. Gibson, W. Haeck, M. W. Herman, J. D. Hutchinson, N. A. Kleedtke, et al., “Understanding the impact of nuclear‐data covariances on various integral responses using adjustment,” EPJ web of conferences (online), Vol 281, Los Alamos National Lab, Los Alamos, NM (United States), 2023.
[25]
A. Nouri, J. Pierre Nagel, B. Briggs, and T. Ivanova, Dice: Database for the international criticality safety benchmark evaluation program handbook, Nucl. Sci. Eng. 145 (2003), no. 1, 11–19.
[26]
V. Picheny, D. Ginsbourger, Y. Richet, and G. Caplin, Quantile‐based optimization of noisy computer experiments with tunable precision, Technometrics 55 (2013), no. 1, 2–13.
[27]
D. I. Poston, M. Gibson, and P. McClure, “Kilopower reactors for potential space exploration missions,” Nuclear and emerging Technologies for Space, American Nuclear Society Topical Meeting ANS 2019.
[28]
B. Shahriari, K. Swersky, Z. Wang, R. P. Adams, and N. De Freitas, Taking the human out of the loop: A review of Bayesian optimization, Proc. IEEE 104 (2015), no. 1, 148–175.
[29]
D. Siefman, C. Percher, J. Norris, A. Kersting, and D. Heinrichs, Constrained Bayesian optimization of criticality experiments, Ann. Nucl. Energy 151 (2021), 107894.
[30]
D. L. Smith, A least‐squares computational “tool kit”. Technical report, Argonne National Lab, Argonne, IL, 1993.
[31]
A. Sparkes, W. Aubrey, E. Byrne, A. Clare, M. N. Khan, M. Liakata, M. Markham, J. Rowland, L. N. Soldatova, K. E. Whelan, M. Young, and R. D. King, Towards robot scientists for autonomous scientific discovery, Autom. Exp. 2 (2010), 1–11.
[32]
I. Sundin, A. Voronov, H. Xiao, K. Papadopoulos, E. J. Bjerrum, M. Heinonen, A. Patronov, S. Kaski, and O. Engkvist, Human‐in‐the‐loop assisted de novo molecular design, J. Cheminf. 14 (2022), no. 1, 1–16.
[33]
N. Thompson, J. Hutchinson, J. Alwin, A. Clark, T. Cutler, M. Grosskopf, W. Haeck, M. Herman, N. Kleedtke, J. Lamproe, et al., Neutron leakage spectra sensitivities for icsbep benchmarks. Technical report, Los Alamos National Lab, Los Alamos, NM, USA, 2022.
Recommendations
Generating exact D-optimal designs for polynomial models
SpringSim '07: Proceedings of the 2007 spring simulation multiconference - Volume 3This paper compares several optimization algorithms that can be used to generate exact D-optimal designs (i.e., designs for a specified number of runs) for any polynomial model. The merits and limitations of each algorithm are demonstrated on several ...
A-Optimal Design of Experiments for Infinite-Dimensional Bayesian Linear Inverse Problems with Regularized $\ell_0$-Sparsification
† Special Section on Two Themes: Planet Earth and Big DataWe present an efficient method for computing A-optimal experimental designs for infinite-dimensional Bayesian linear inverse problems governed by partial differential equations (PDEs). Specifically, we address the problem of optimizing the location of ...
Experimental Design for Biological Systems
Many problems in biology are governed by a dynamical system of differential equations with unknown parameters. To have a meaningful representation of the system, these parameters need to be evaluated from observations. Experimentalists face the dilemma ...
Comments
Information & Contributors
Information
Published In
Published 2024. This article is a U.S. Government work and is in the public domain in the USA. Statistical Analysis and Data Mining: The ASA Data Science Journal published by Wiley Periodicals LLC.
This is an open access article under the terms of the Creative Commons Attribution‐NonCommercial‐NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
Publisher
John Wiley & Sons, Inc.
United States
Publication History
Published: 02 April 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in