EUCLID: A New Approach to Improve Nuclear Data Coupling Optimized Experiments with Validation using Machine Learning [Slides]

Hutchinson, Jesson D.; Alwin, Jennifer Louise; Clark, Alexander Rich; Cutler, Theresa; Grosskopf, M.J.; Haeck, Wim; Herman, M.; Kleedtke, Noah Andrew; Lamproe, Juliann Rose; Little, Robert C.; Michaud, Isaac; Neudecker, Denise; Rising, Michael Evan; Smith, Travis Austin; Thompson, Nicholas; Wiel, Scott Alan Vander

doi:10.2172/1898108

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments Underpinned by Computational Learning for Improvements in Nuclear Data (EUCLID) is a LANL Laboratory Directed Research & Development project focused on identifying and resolving compensating errors in nuclear data (Hutchinson et al, 2022a;Neudecker et al, 2022a;Neudecker et al, 2022b;Clark et al, 2022;Kleedtke et al, 2022;Rising and Clark, 2022). As part of this project, an experiment series at NCERC was designed using machine learning tools.…”

Section: Euclidmentioning

confidence: 99%

The National Criticality Experiments Research Center and its role in support of advanced reactor design

Thompson

Maldonado²,

Cutler³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

The National Criticality Experiments Research Center (NCERC) located at the Nevada National Security Site (NNSS) in the Device Assembly Facility (DAF) and operated by Los Alamos National Laboratory (LANL) is the only general purpose critical experiments facility in the United States. Experiments from subcritical to critical and above prompt critical are carried out at NCERC on a regular basis. In recent years, NCERC has become more involved in experiments related to nuclear energy, including the Kilopower/KRUSTY demonstration and the recent Hypatia experiment. Multiple nuclear energy related projects are currently ongoing at NCERC. This paper discusses NCERC’s role in advanced reactor design and how that role may change in the future.

show abstract

Section: Euclidmentioning

confidence: 99%

The National Criticality Experiments Research Center and its role in support of advanced reactor design

Thompson

Maldonado²,

Cutler³

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…Many responses were measured but this analysis will consider only

{k}_{\mathrm{eff}}

. While experiment details are beyond the scope of this article, the physical configuration was designed using Bayesian optimization with the objective of reducing

{}^{239}

Pu nuclear data uncertainty for a subset of physical quantities from 0.1–5 MeV as discussed in [24, 25].…”

Section: Impact Of a New Experimentsmentioning

confidence: 99%

Driving mode analysis—How uncertain functional inputs propagate to an output

Vander Wiel,

Grosskopf,

Michaud

et al. 2023

Statistical Analysis

View full text Add to dashboard Cite

Driving mode analysis elucidates how correlated features of uncertain functional inputs jointly propagate to produce uncertainty in the output of a computation. Uncertain input functions are decomposed into three terms: the mean functions, a zero‐mean driving mode, and zero‐mean residual. The random driving mode varies along a single direction, having fixed functional shape and random scale. It is uncorrelated with the residual, and under linear error propagation, it produces an output variance equal to that of the full input uncertainty. Finally, the driving mode best represents how input uncertainties propagate to the output because it minimizes expected squared Mahalanobis distance amongst competitors. These characteristics recommend interpretation of the driving mode as the single‐degree‐of‐freedom component of input uncertainty that drives output uncertainty. We derive the functional driving mode, show its superiority to other seemingly sensible definitions, and demonstrate the utility of driving mode analysis in an application. The application is the simulation of neutron transport in criticality experiments. The uncertain input functions are nuclear data that describe how Pu reacts to bombardment by neutrons. Visualization of the driving mode helps scientists understand what aspects of correlated functional uncertainty have effects that either reinforce or cancel one another in propagating to the output of the simulation.

show abstract

“…Powered by open-source frameworks, research into ML methods has seen a recent resurgence in nuclear physics [13]. ML approaches have shown promise in optimizing data and experiments [14], building surrogate models of density functional theory [15], and describing quantum many-body wave functions for light nuclei [16,17].…”

Section: Introductionmentioning

confidence: 99%

Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach

Mumpower

Sprouse

et al. 2023

Front. Phys.

View full text Add to dashboard Cite

We present global predictions of the ground state mass of atomic nuclei based on a novel Machine Learning algorithm. We combine precision nuclear experimental measurements together with theoretical predictions of unmeasured nuclei. This hybrid data set is used to train a probabilistic neural network. In addition to training on this data, a physics-based loss function is employed to help refine the solutions. The resultant Bayesian averaged predictions have excellent performance compared to the testing set and come with well-quantified uncertainties which are critical for contemporary scientific applications. We assess extrapolations of the model’s predictions and estimate the growth of uncertainties in the region far from measurements.

show abstract

EUCLID: A New Approach to Improve Nuclear Data Coupling Optimized Experiments with Validation using Machine Learning [Slides]

Cited by 5 publications

References 0 publications

The National Criticality Experiments Research Center and its role in support of advanced reactor design

The National Criticality Experiments Research Center and its role in support of advanced reactor design

Driving mode analysis—How uncertain functional inputs propagate to an output

Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach

Contact Info

Product

Resources

About