Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Common data models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 343 records · Page 19
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Vectorization of Dynamic Subgraphs via Generative Models (Final Report)

An important class of data analysis tasks stem from comparing subsets of connected records within massive sets of complex relational data. A common approach is to represent each set of connected records with a small graph, or set of data entities (graph vertices) and their relationships (graph edges), and efficient methods to gauge similarity for pairs of graphs are of high interest. This project concentrated on dynamic graphs, where each edge record has an associated timestamp denoting the time of observation. Pre-existing techniques for comparing dynamic graphs concentrate on either computing graph edit distance (number of vertex and edge deletion, addition, and timestamp modifications) or vectorizing the graph with counts of a limited set of dynamic graph motifs (tiny fundamental subgraphs) and computing distances between the vectors. These approaches are less able to see similarities in graphs that are fairly different in size but come from identical graph generation processes. The motif counting approach can be improved for graphs from the same process, but suffers from requiring many types of motifs meaning it is expensive. Moreover, many motifs are not present for small graphs, meaning realizing a a much larger graph came from the same process is difficult.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Thermochemical Modeling in Molten Fluoride Salts for Radionuclide Speciation

An important aspect of the licensing process for nuclear reactors is providing a reasonable assurance of safety to the general public. This includes modeling potential radionuclide releases from the reactor during normal operations and accident scenarios, which is known as the reactor’s source term. A new class of advanced (non-LWR) reactors are being developed which use molten salts as the coolant fluid. Because the molten salt coolant represents a credited barrier for radionuclide transport between the fuel and the environment, a necessary aspect of mechanistic source term (MST) analysis for the KP-FHR is modeling the thermochemistry of molten salts. Provided here is a review of the theory of the thermodynamic principles governing multicomponent phase equilibria, the background of molten salt thermochemistry research, and a summary of the thermochemical data relevant to the KP-FHR coolant salt, Li 2 BeF 4 , commonly referred to as “FLiBe”. A review of literature is followed by a brief introduction to methods that can be used to model the thermochemical behavior of molten salt mixtures. The methodology outlined is based on the use of a commercial thermodynamic modeling software called FactSage, which is one of only a few available softwares based on the modified quasichemical model(MQM), which is the recommended solution model for molten salts.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

A fusion relevant data-driven engineering void swelling model for 9Cr tempered martensitic steels

The UCSB database on cavity evolution in 9-12Cr tempered martensitic steels (TMS), includes the results for both dual heavy and helium ion (DII), and High Flux Isotope Reactor (HFIR) in situ helium injection (ISHI) neutron irradiations at 500°C. These results were combined with literature single ion and fission neutron irradiation data to derive a model for the void volume fraction, f v , as a function of displacements per atom (dpa) and transmutant helium concentrations in atomic parts per million (appm). The scientific foundation for the paper is described in a companion paper entitled “Cavity Evolution and Void Swelling in Dual Ion Irradiated Tempered Martensitic Steels”. Here, in this study, we show that f v (dpa, He/dpa) is described by the incubation dose, dpa i , for the onset of void growth, and the post-incubation growth rate, f v ’(%/dpa). Both dpa i and f v ’ decrease with increasing He/dpa at > ~ 5. The dpa i is also lower for the ISHI neutron irradiations at the same He/dpa. Single heavy ion and fission reactor neutron irradiations, with low He/dpa ratios, have a much larger dpa i . Based on a combined analysis of DII, single ion, ISHI and fission neutron data, we further show that the post-incubation f v data analyzed here have a common empirical curve shape, with f v ’ reaching up to ~ 0.2%/dpa at very high dpa. We also show that f v ’ can be predicted based on a physical model of defect partitioning between evolving sinks. At 500°C and fusion relevant He/dpa ≈ 10, the best-fit model predicts nominal swelling, S = f v /(1-f v ), of ~ 1.1, 4.9 and 16% at 50, 100 and 200 dpa, respectively. The physically motivated, data-driven model includes estimated uncertainties for both dpa i and f v ’.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Algorithms in Diffraction Profile Analysis

This chapter introduces several approaches to crystallographic structure refinement from diffraction profile data including the Rietveld method, global optimization methods, and Bayesian modeling. First, the Rietveld method and related nonlinear least squares approaches to analyzing diffraction profiles are briefly discussed. We then review the most common algorithms within global optimization as alternative methods of structure solution: grid search, simulated annealing, and genetic algorithms. As the Rietveld method is the standard tool for analyzing diffraction profile data, we catalogue its challenges and limitations. A Bayesian approach to diffraction profile analysis is presented as an alternative, along with several sampling algorithms including Gibbs sampling, variants of Metropolis sampling, Hamiltonian Monte Carlo, and approximate Bayesian computing. These sampling algorithms are applied to the fitting of a neutron diffraction profile from a National Institute of Standards and Technology silicon standard reference material, and their results are compared.

Singh, Susheela↗
DOE OSTI2022

Impact of nuclear data covariance libraries on uncertainty quantification of sodium cooled fast reactor simulation

Uncertainty quantification in core modelling to assess reactor performance is a regular practice to identify design safety limits. Best-estimate plus uncertainty (BEPU) methods are commonly used to propagate uncertainties to core responses from input parameters, characterized by variance-covariance libraries. This study evaluates the impact of different covariance libraries on the uncertainty associated with core safety parameters and their propagation through reactor transient modelling for a metallic core (ABR-1000). The COMAC-1.0, COMMARA-2.0, and COMMARA-2.1 covariance libraries are used to propagate nuclear data uncertainties to neutron feedback coefficients using the Generalized Perturbation Theory, then through transient safety analyses to establish the confidence interval for safety performance of the reactor using stochastic sampling. The considered transients include Unprotected Transient Over Power and Unprotected Loss Of Flow. Most influential nuclide and reaction pairs in different variance-covariance libraries are identified and their impact on the uncertainty of safety parameters are evaluated. Significant differences were observed between uncertainties from COMAC compared to COMMARA libraries. Uncertainties from COMMARA libraries were consistently larger than COMAC for all cases. For structure, coolant density feedback coefficients and control rod worth, total nuclear data uncertainties were approximately 50% larger for COMMARA than COMAC. Differences were also observed in identification of top contributors of uncertainty in terms of reaction-cross sections. For instance, largest contribution to total uncertainty of radial expansion coefficient from COMMARA-2.0 and 2.1 originates from Na{sup 23} P1 Elastic cross section (0.81%) but from Pu{sup 239} Fission (0.53%) with COM C-1.0. Such differences are evaluated in this research for all quantities of interest. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2020

Measuring the oscillator strength of intercombination lines of helium-like V ions in a laser-produced-plasma

In this work, we present results of measurements of the oscillator strength of intercombination lines of He-like Vanadium ions in high energy density (HED) laser-produced-plasmas and compare them with the simulations from commonly used codes and data from the NIST database. Whilst not yet sufficiently accurate to constrain different trusted atomic-physics models for the particular system studied, our results are in agreement with the available data within experimental error bars, yet differ from cruder approximations of the oscillator strength used in certain atomic-kinetics packages, suggesting that this general method could be further extended to be used as a measurement of the oscillator strength of additional atomic transitions under the extreme conditions that are achieved in HED experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

The state of the art for neutron irradiation experiments from the perspective of the High Flux Isotope Reactor (HFIR)

Irradiation experiment campaigns are critical to advancing nuclear energy technologies by providing data on material performance under relevant radiation conditions. Successful irradiation experiments require integrated design efforts that balance technical goals with facility constraints. Here, this paper presents an expert-informed overview of irradiation experiment design at the High Flux Isotope Reactor. It addresses the nuclear materials research and irradiation experiment communities to guide them toward developing technically sound, facility-compatible campaigns. The High Flux Isotope Reactor is a multipurpose reactor supporting isotope production, neutron scattering, and materials testing. Its high, steady-state neutron flux is ideal for irradiation experiments, but successful execution demands coordinated thermal, structural, and reactor physics analyses. The paper outlines the complete development workflow from concept definition and design optimization to safety qualification and post-irradiation examination. Standardized capsule platforms are also discussed in terms of flexibility, specimen capacity, and thermal performance. Common failure modes such as unanticipated geometric variations, can impact temperature-dose profiles and compromise data reliability. Therefore, detailed thermal modeling and accurate as-built characterization are essential for meaningful post-irradiation data interpretation. Key recommendations include early engagement all stakeholders, clearly defined design expectations, and alignment of specimen geometries with post-irradiation examination capabilities. This approach reduces design iterations, enhances data quality, and supports more efficient use of irradiation resources. Strategic and well-planned irradiation testing not only improves individual campaign success but also accelerates the deployment of advanced nuclear technologies. By closing critical data gaps and reducing development risks, the nuclear materials community can more effectively contribute to the future of clean, resilient energy systems.

Experiments↗
DOE OSTI2025

Does provable absence of barren plateaus imply classical simulability?

A large amount of effort has recently been put into understanding the barren plateau phenomenon. In this perspective article, we face the increasingly loud elephant in the room and ask a question that has been hinted at by many but not explicitly addressed: Can the structure that allows one to avoid barren plateaus also be leveraged to efficiently simulate the loss classically? We collect evidence-on a case-by-case basis-that many commonly used models whose loss landscapes avoid barren plateaus can also admit classical simulation, provided that one can collect some classical data from quantum devices during an initial data acquisition phase. This follows from the observation that barren plateaus result from a curse of dimensionality, and that current approaches for solving them end up encoding the problem into some small, classically simulable, subspaces. Thus, while stressing that quantum computers can be essential for collecting data, our analysis sheds doubt on the information processing capabilities of many parametrized quantum circuits with provably barren plateau-free landscapes. We end by discussing the (many) caveats in our arguments including the limitations of average case arguments, the role of smart initializations, models that fall outside our assumptions, the potential for provably superpolynomial advantages and the possibility that, once larger devices become available, parametrized quantum circuits could heuristically outperform our analytic expectations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Understanding Peelle’s Pertinent Puzzle bias in generalized least squares regression through eigenspectrum analysis

Certain correlation structures in the data covariance matrix (DCM) used for generalized least squares (GLS) regression can result in biased estimates, commonly known in the field of nuclear data evaluation as Peele’s Pertinent Puzzle (PPP). This article introduces a generative, forward modeling framework within which the PPP bias is characterized through an eigenspectrum analysis of the DCM. This analysis highlights the root cause of the bias, generalizes the problem beyond the nuclear data field, and provides insight to the problem regimes where it can occur. What follows is an understanding that the bias can show up for any experimental neutron time-of-flight data for which systematic uncertainties have been quantified. Lastly, a discussion of the adaptation of cross validation approaches that require pre-whitening to incorporate the known ‘fix’ to the PPP bias in the GLS estimator.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2020

Modern Senicide in the Face of a Pandemic: An Examination of Public Discourse and Sentiment About Older Adults and COVID-19 Using Machine Learning

Objectives This study examined public discourse and sentiment regarding older adults and COVID-19 on social media and assessed the extent of ageism in public discourse. Methods Twitter data (N = 82,893) related to both older adults and COVID-19 and dated from January 23 to May 20, 2020, were analyzed. We used a combination of data science methods (including supervised machine learning, topic modeling, and sentiment analysis), qualitative thematic analysis, and conventional statistics. Results The most common category in the coded tweets was “personal opinions” (66.2%), followed by “informative” (24.7%), “jokes/ridicule” (4.8%), and “personal experiences” (4.3%). The daily average of ageist content was 18%, with the highest of 52.8% on March 11, 2020. Specifically, more than 1 in 10 (11.5%) tweets implied that the life of older adults is less valuable or downplayed the pandemic because it mostly harms older adults. A small proportion (4.6%) explicitly supported the idea of just isolating older adults. Almost three-quarters (72.9%) within “jokes/ridicule” targeted older adults, half of which were “death jokes.” Also, 14 themes were extracted, such as perceptions of lockdown and risk. A bivariate Granger causality test suggested that informative tweets regarding at-risk populations increased the prevalence of tweets that downplayed the pandemic. Discussion Ageist content in the context of COVID-19 was prevalent on Twitter. Information about COVID-19 on Twitter influenced public perceptions of risk and acceptable ways of controlling the pandemic. Finaly, public education on the risk of severe illness is needed to correct misperceptions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Progenitors and explosion properties of supernova remnants hosting central compact objects: II. A global systematic study with a comparison to nucleosynthesis models

ABSTRACT Core-collapse explosions of massive stars leave behind neutron stars, with a known diversity that includes the ‘Central Compact Objects’ (CCOs). Typified by the neutron star discovered near the centre of the Cas A supernova remnant (SNR), CCOs have been observed to shine only in X-rays. To address their supernova progenitors, we perform a systematic study of SNRs that contain a CCO and display X-ray emission from their shock-heated ejecta. We make use of X-ray data primarily using the Chandra X-ray observatory, complemented with XMM–Newton. This study uses a systematic approach to the analysis of each SNR aimed at addressing the supernova progenitor as well as the explosion properties (energy and ambient density). After fitting for the ejecta abundances estimated from a spatially resolved spectroscopic study, we compare the data to six nucleosynthesis models making predictions on supernova ejecta yields in core-collapse explosions. We find that the explosion models commonly used by the astrophysics community do not match the ejecta yields for any of the SNRs, suggesting additional physics, for example multidimensional explosion models or updated progenitor structures, are required. Overall we find low-mass (≤25 solar masses) progenitors among the massive stars population and low-energy explosions (<1051 ergs). We discuss degeneracies in our model fitting, particularly how altering the explosion energy affects the estimate of the progenitor mass. Our systematic study highlights the need for improving on the theoretical models for nucleosynthesis predictions as well as for sensitive, high-resolution spectroscopy observations to be acquired with next generation X-ray missions.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

β-decay feeding intensity distributions for 103,104m Nb

The β decays of 103,104m Nb were studied with the Summing NaI(Tl) (SuN) detector at the National Superconducting Cyclotron Laboratory. The β-decay feeding intensity distribution I β (E) for each isotope was extracted by measuring γ rays in coincidence with an emitted electron. The I β (E) was extracted via the total absorption spectroscopy technique. The I β (E) for each nucleus was compared to predictions made by the quasiparticle random-phase approximation (QRPA) model which is commonly used to calculate β-decay properties for astrophysical applications. The main goal was to provide experimental data for neutron-rich nuclei, relevant to the astrophysical r process. In addition, the extracted β-decay feeding intensity distributions can lead to a better understanding of nuclear structure in a region of rapid structure changes around A = 100. Finally, experimental data for 104m Nb are also of interest to antineutrino studies of nuclear reactors

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

Regional Relative Risk, a Physics-Based Metric for Characterizing Airborne Infectious Disease Transmission

Airborne infectious disease transmission events occur over a wide range of spatial scales and can be an important means of disease transmission. Physics- and biology-based models can assist in predicting airborne transmission events, overall disease incidence, and disease control strategy efficacy. We describe a new theory that extends current approaches for the case in which an individual is infected by a single airborne particle, including the scenario in which numerous infectious particles are present in the air but only one causes infection. A single infectious particle can contain more than one pathogenic microorganism and be physically larger than the pathogen itself. This approach allows robust relative risk estimates even when there is wide variation in (i) individual exposures and (ii) the individual response to that exposure (the pathogen dose-response function can take any mathematical form and vary by individual). Based on this theory, we propose the regional relative risk—a new metric, distinct from the traditional relative risk metric, that compares the risk between two regions. In theory, these regions can range from individual rooms to large geographic areas. In this paper, we apply the regional relative risk metric to outdoor disease transmission events over spatial scales ranging from 50 m to 20 km, demonstrating that in many common cases minimal input information is required to use the metric. Also, we demonstrate that the model predictions are consistent with data from prior outbreaks. Future efforts could apply and validate this theory for other spatial scales, such as transmission within indoor environments. This work provides context for (i) the initial stages of an airborne disease outbreak and (ii) larger-scale disease spread, including unexpected low-probability disease “sparks” that potentially affect remote populations, a key practical issue in controlling airborne disease outbreaks.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Quantifying Leaf Chlorophyll Concentration of Sorghum from Hyperspectral Data Using Derivative Calculus and Machine Learning

Leaf chlorophyll concentration (LCC) is an important indicator of plant health, vigor, physiological status, productivity, and nutrient deficiencies. Hyperspectral spectroscopy at leaf level has been widely used to estimate LCC accurately and non-destructively. This study utilized leaf-level hyperspectral data with derivative calculus and machine learning to estimate LCC of sorghum. We calculated fractional derivative (FD) orders starting from 0.2 to 2.0 with 0.2 order increments. Additionally, 43 common vegetation indices (VIs) were calculated from leaf spectral reflectance factor to make comparisons with reflectance-based data. Within the modeling pipeline, three feature selection methods were assessed: Pearson’s correlation coefficient (PCC), partial least squares based variable importance in the projection (VIP), and random forest-based mean decrease impurity (MDI). Finally, we used partial least squares regression (PLSR), random forest regression (RFR), support vector regression (SVR), and extreme learning regression (ELR) to estimate the LCC of sorghum. Results showed that: (1) increasing derivative order can show improved model performance until certain order for reflectance-based analysis; however, it is inconclusive to state that a particular order is optimal for estimating LCC of sorghum; (2) VI-based modeling outperformed derivative augmented reflectance factor-based modeling; (3) mean decrease impurity was found effective in selecting sensitive features from large feature space (reflectance-based analysis), whereas simple Pearson’s correlation coefficient worked better with smaller feature space (VI-based analysis); and (4) SVR outperformed all other models within reflectance-based analysis; alternatively, ELR with VIs from original reflectance yielded slightly better results compared to all other models.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Phase-curve Pollution of Exoplanet Transit Depths

The next generation of space telescopes will enable transformative science to understand the nature and origin of exoplanets. In particular, transit spectroscopy will reveal the chemical composition of the exoplanet atmospheres with unprecedented detail thanks to precise measurements of the visible-to-infrared transit depths down to 10 parts per million. Such a level of instrumental precision raises the challenge to obtain even more precise astrophysical models so as not to significantly influence the interpretation of the observed data. We must therefore critically revisit some of the commonly accepted assumptions that were adequate for analyzing past and current observations. A common approximation in the analysis of exoplanetary primary transits is that the planet does not contribute to the recorded flux, so-called dark planet hypothesis. In this paper, we investigate the impact of the dark planet hypothesis on the parameters obtained from the analysis of transits with particular attention to the transit depth. We develop mathematical formulae and release new software to estimate the magnitude of the potential bias. These tools will be useful in the preparation of observing proposals, as well as within the scientific consortia of the James Webb Space Telescope (JWST) and the Atmospheric Remote-sensing Infrared Exoplanet Large-survey (ARIEL) missions. We probe the accuracy of the mathematical formulae through the analysis of synthetic observations with the JWST Mid-InfraRed Instrument. We find that self-blending from nightside emission attenuates the transit depth by >3σ for some of the known exoplanet systems, in agreement with previous work. An additional unreported effect caused by the nightside rotating into view can also impart a significant effect, but in the opposite direction (increasing the transit depth); this effect can largely be removed with conventional detrending practices, at the expense of a slight increase in noise, and mixing astrophysical variations and instrumental drifts.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

Many workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to bring this emerging paradigm to HEP pipelines. The framework enables LLMs to interface with domain-specific tools, construct and manage simulation workflows, and assist in common utility and data analysis tasks through schema-validated operations and run-card-driven configuration. To demonstrate these capabilities, we consider a representative Beyond the Standard Model (BSM) Monte Carlo validation pipeline that spans model generation, event simulation, and downstream analysis within a unified, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for transparent, human-in-the-loop systems.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗
DOE OSTI2024

Simulation-based inference for parameter estimation of complex watershed simulators

High-resolution, spatially distributed process-based (PB) simulators are widely employed in the study of complex catchment processes and their responses to a changing climate. However, calibrating these PB simulators using observed data remains a significant challenge due to several persistent issues, including the following: (1) intractability stemming from the computational demands and complex responses of simulators, which renders infeasible calculation of the conditional probability of parameters and data, and (2) uncertainty stemming from the choice of simplified representations of complex natural hydrologic processes. Here, we demonstrate how simulation-based inference (SBI) can help address both of these challenges with respect to parameter estimation. SBI uses a learned mapping between the parameter space and observed data to estimate parameters for the generation of calibrated simulations. To demonstrate the potential of SBI in hydrologic modeling, we conduct a set of synthetic experiments to infer two common physical parameters – Manning's coefficient and hydraulic conductivity – using a representation of a snowmelt-dominated catchment in Colorado, USA. We introduce novel deep-learning (DL) components to the SBI approach, including an “emulator” as a surrogate for the PB simulator to rapidly explore parameter responses. We also employ a density-based neural network to represent the joint probability of parameters and data without strong assumptions about its functional form. While addressing intractability, we also show that, if the simulator does not represent the system under study well enough, SBI can yield unreliable parameter estimates. Approaches to adopting the SBI framework for cases in which multiple simulator(s) may be adequate are introduced using a performance-weighting approach. The synthetic experiments presented here test the performance of SBI, using the relationship between the surrogate and PB simulators as a proxy for the real case.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Considerations regarding the Use of Computer Vision Machine Learning in Safety-Related or Risk-Significant Applications in Nuclear Power Plants

With the advancements made to date in the field of artificial intelligence (AI), significant potential exists to utilize AI capabilities for nuclear power plant (NPP) applications. AI can replicate human decision making and it is usually faster and more accurate than humans. For implementations that impact critical NPP applications (e.g., safety-related or non-safety systems that potentially affect overall plant risk), a deeper safety analysis of the AI methods is necessary. AI applied to NPP operations could resemble the use of digital I&C (DI&C) because such applications involve digital computer hardware and custom-designed software that input plant data, execute complex software algorithms, and output the results to a system or licensed human operator to potentially provoke an action. For AI methods to be compliant with current safety requirements for DI&C, AI compatibility must be evaluated, and AI-related gaps may exist that prevent the prompt deployment of AI in NPPs. This effort aims to evaluate how example AI technologies align with the DI&C safety framework, and discusses how they could be analyzed, modeled, tested, and validated in a manner similar to typical DI&C technologies. Because AI is a broad field that encompasses areas such as machine learning (ML), natural language processing, and computer vision, this research focused on a subset of methods categorized as the computer vision ML (CVML) methods. This report explores two CVML use cases, gauge reading and fire watch, considered relevant to the DI&C standards, as they could play a safety-critical role. For the gauge reading use case, a CVML-enabled technology that can read gauges at oblique angles is utilized. For the fire watch use case, a CVML-enabled technology is utilized that migrates fire watch from a manual (human) approach to automated fire detection. These use cases are mainly intended to give context to the CVML system discussion. This effort assumes the worst-case scenario, with the CVML system being used to replace a safety-related or risk-significant system, thus requiring evaluation. Evaluating CVML against most of the relevant safety requirements for DI&C yielded several CVML-specific considerations due to the uniqueness of its characteristics in comparison with typical DI&C systems. For example, CVML models often employ commonly used (open-source) datasets, and it is not always possible to determine the level of overlap among open-source datasets. Therefore, the independence of the developed CVML models when demonstrating diversity is questionable, therefore creating vulnerability to common cause failure (CCF). The design verification process is also impacted since the data overlap could result in overestimation of the software validation and verification (V&V) performance results. Section 2 of this report evaluates a list of the identified CVML-specific characteristics and discusses the resulting considerations and potential solutions in the context of each referenced requirement. A summation is provided in Section 3. This report is not to be used as a guideline. It was developed to identify and consider issues in the implementation of ML technologies used to augment activities that may have a bearing on plant operation. The report draws parallels to the use of DI&C technologies, for which many standards are available to guide their use in nuclear plant operation. It considers the technologies and some of the potential implications of their use in safety-related applications but is not intended to address regulatory or licensing related issues.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗