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

Title: Informing nuclear physics via machine learning methods with differential and integral experiments

Journal Article · · Physical Review C
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Univ. Politécnica de Madrid (Spain)

Information from differential nuclear-physics experiments and theory is often too uncertain to accurately define nuclear-physics observables such as cross sections or energy spectra. Integral experimental data, representing the applications of these observables, are often more precise but depend simultaneously on too many of them to unambiguously identify issues in the observable with human expert analysis alone. Here, we explore how we can leverage physics knowledge gained from differential experimental data, nuclear theory, integral experiments, and neutron-transport calculations to better understand nuclear-physics observables in the context of the application area represented by integral experiments. We support this task with machine-learning methods to discern trends in a large amount of convoluted data. Differential and integral information was used in an analysis augmented by the random forest and the Shapley additive explanations metric. We chose as an application area one that is represented by criticality measurements and pulsed-sphere neutron-leakage spectra. We show one representative example (241Pu fission observables) where the combination of differential and integral information allowed to resolve issues in data representing these observables. As a starting point, the machine learning (ML) algorithms highlighted several observables as leading potentially to bias in simulating integral experiments. Differential information, paired with sensitivity to integral quantities, allowed us then to pinpoint one specific observable (241Pu fission cross section) as the main driver of bias. The comparison to integral experiments, on the other hand, allowed us to indicate a likely reliable experiment among several discrepant ones for this observables. In other cases (e.g., 239Pu observables), we were not able to resolve the confounding introduced by integral experiments but instead highlighted the need for targeted new experiments and theory developments to better constrain the nuclear-physics space for the application area represented by integral experiments. We were able to combine information from differential experimental data, nuclear-physics theory, integral experiments, and neutron-transport simulations of the latter experiments with the help of the random forest algorithm and expert judgment. This combination of knowledge allows to improve our description of nuclear-physics observables as applied to a particular application area.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA), Nuclear Criticality Safety Program (NCSP)
Grant/Contract Number:
89233218CNA000001
OSTI ID:
1822758
Report Number(s):
LA-UR-21-22465; TRN: US2214502
Journal Information:
Physical Review C, Vol. 104, Issue 3; ISSN 2469-9985
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English

References (53)

Which nuclear data can be validated with LLNL pulsed-sphere experiments? journal September 2021
Nuclear mass predictions for the crustal composition of neutron stars: A Bayesian neural network approach journal January 2016
JENDL-4.0: A New Library for Nuclear Science and Engineering journal January 2011
Monte Carlo Hauser-Feshbach predictions of prompt fission γ rays: Application to n th + 235 U, n th + 239 Pu, and 252 Cf (sf) journal January 2013
Neutron Drip Line in the Ca Region from Bayesian Model Averaging journal February 2019
Measurement of the Pu 239 ( n , f ) prompt fission neutron spectrum from 10 keV to 10 MeV induced by neutrons of energy 1–20 MeV journal September 2020
Nuclear data uncertainty propagation to integral responses using SANDY journal March 2017
A Measurement of the Fission Cross Section of Plutonium-241 from 8 eV to 70 keV journal June 1977
Cross Sections for 239 Pu( n , f ) and 241 Pu( n , f ) in the Range E n = 0.01 eV to 200 MeV journal June 2010
Measurement of prompt neutron spectra from the 239 Pu( n , f ) fission reaction for incident neutron energies from 1 to 200 MeV journal January 2014
Machine learning the deuteron journal October 2020
Evaluating 239Pu(n,f) cross sections via machine learning using experimental data, covariances, and measurement features
  • Whewell, B.; Grosskopf, M.; Neudecker, D.
  • Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, Vol. 978 https://doi.org/10.1016/j.nima.2020.164305
journal October 2020
Neutron-Induced Fission of Pu 241 journal February 1962
Extension of the Hauser-Feshbach fission fragment decay model to multichance fission journal January 2021
Sensitivity of neutron observables to the model input in simulations of 252 Cf ( sf ) journal May 2019
The impact of individual nuclear properties on r -process nucleosynthesis journal January 2016
Fast-Neutron-Induced Fission Cross Sections of Pu 241 and Am 243 journal November 1961
Development of a Comprehensive Code for Nuclear Data Evaluation, CCONE, and Validation Using Neutron-Induced Cross Sections for Uranium Isotopes journal May 2007
Variational Monte Carlo Calculations of A ≤ 4 Nuclei with an Artificial Neural-Network Correlator Ansatz journal July 2021
Prompt Fission Neutron Spectra of Actinides journal January 2016
Energy dependence of for neutron-induced fission of 235U, 238U and 239Pu from 1·3 to 15 MeV journal May 1969
Prompt-fission-neutron spectra in the Pu 239 ( n , f ) reaction journal April 2020
Preequilibrium Asymmetries in the Pu 239 ( n , f ) Prompt Fission Neutron Spectrum journal February 2019
Energy Spectrum of Neutrons from Thermal Fission of U 235 journal September 1952
Evaluation of the Neutron Data Standards journal February 2018
Neutron Yield of Cf 252 Based on Absolute Measurements of the Neutron Rate and Fission Rate journal February 1970
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
Towards a More Complete and Accurate Experimental Nuclear Reaction Data Library (EXFOR): International Collaboration Between Nuclear Reaction Data Centres (NRDC) journal June 2014
Neutron-Induced Fission of 233 U, 238 U, 232 Th, 239 Pu, 237 Np, nat Pb and 209 Bi Relative to 235 U in the Energy Range 1-200 MeV journal August 2002
Determination of Resonance Parameters and their Covariances from Neutron Induced Reaction Cross Section Data journal December 2012
Development and verification of a new nuclear data processing system FRENDY journal April 2017
Fission Reaction Event Yield Algorithm FREYA 2.0.2 journal January 2018
Enhancing nuclear data validation analysis by using machine learning journal July 2020
A Measurement of the Fission Cross Section of Plutonium-241 Relative to Uranium-235 journal June 1973
ENDF/B-VII.1 Neutron Cross Section Data Testing with Critical Assembly Benchmarks and Reactor Experiments journal December 2011
Quantifying uncertainties on fission fragment mass yields with mixture density networks journal September 2020
Nuclear charge radii: density functional theory meets Bayesian neural networks journal October 2016
Toward a deeper understanding of how experiments constrain the underlying physics of heavy-ion collisions journal February 2016
Fission modelling with FIFRELIN journal December 2015
Bayesian Evaluation of Incomplete Fission Yields journal September 2019
Bayesian approach to model-based extrapolation of nuclear observables journal September 2018
Using Machine Learning Methods to Predict Bias in Nuclear Criticality Safety journal September 2018
Fission Neutron Spectra and Nuclear Temperatures journal January 1959
Simultaneous Evaluation of Fission Cross Sections of Uranium and Plutonium Isotopes for JENDL-3.3 journal April 2000
Neutron-Induced Fission Cross-Section Ratios for 239 Pu, 240 Pu, 242 Pu, and 244 Pu Relative to 235 U from 0.5 to 400 MeV journal June 1998
Measurement of the233U and241Pu fission cross sections relative to the235U fission cross section in the neutron energy range 0.024?7.4 MeV journal March 1978
Fission fragment decay simulations with the CGMF code journal December 2021
Impact of individual nuclear masses on r -process abundances journal September 2015
235 U(n, f) Independent fission product yield and isomeric ratio calculated with the statistical Hauser–Feshbach theory journal April 2018
Random Forests journal January 2001
New Calculation of Prompt Fission Neutron Spectra and Average Prompt Neutron Multiplicities journal June 1982
Bayesian truncation errors in chiral effective field theory: Nucleon-nucleon observables journal August 2017
Pre-equilibrium processes in nuclear reaction theory: the state of the art and beyond journal July 1986

Figures / Tables (10)