SEARCH · Search NASA

Results for “human performance modeling”

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.

SourceResearch connectionFrom yearThrough year

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

At least 145 records · Page 8

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Prediction of protein assemblies, the next frontier: The CASP14-CAPRI experiment

Here we present the results for CAPRI Round 50, the fourth joint CASP-CAPRI protein assembly prediction challenge. The Round comprised a total of twelve targets, including six dimers, three trimers, and three higher-order oligomers. Four of these were easy targets, for which good structural templates were available either for the full assembly, or for the main interfaces (of the higher-order oligomers). Eight were difficult targets for which only distantly related templates were found for the individual subunits. Twenty-five CAPRI groups including eight automatic servers submitted ~1250 models per target. Twenty groups including six servers participated in the CAPRI scoring challenge submitted ~190 models per target. The accuracy of the predicted models was evaluated using the classical CAPRI criteria. The prediction performance was measured by a weighted scoring scheme that takes into account the number of models of acceptable quality or higher submitted by each group as part of their five top-ranking models. Compared to the previous CASP-CAPRI challenge, top performing groups submitted such models for a larger fraction (70–75%) of the targets in this Round, but fewer of these models were of high accuracy. Scorer groups achieved stronger performance with more groups submitting correct models for 70–80% of the targets or achieving high accuracy predictions. Servers performed less well in general, except for the MDOCKPP and LZERD servers, who performed on par with human groups. In addition to these results, major advances in methodology are discussed, providing an informative overview of where the prediction of protein assemblies currently stands.

protein complexes↗

DOE OSTI2021

The value of human data annotation for machine learning based anomaly detection in environmental systems

Anomaly detection is the process of identifying unexpected data samples in datasets. Automated anomaly detection is either performed using supervised machine learning models, which require a labelled dataset for their calibration, or unsupervised models, which do not require labels. While academic research has produced a vast array of tools and machine learning models for automated anomaly detection, the research community focused on environmental systems still lacks a comparative analysis that is simultaneously comprehensive, objective, and systematic. This knowledge gap is addressed for the first time in this study, where 15 different supervised and unsupervised anomaly detection models are evaluated on 5 different environmental datasets from engineered and natural aquatic systems. To this end, anomaly detection performance, labelling efforts, as well as the impact of model and algorithm tuning are taken into account. As a result, our analysis reveals the relative strengths and weaknesses of the different approaches in an objective manner without bias for any particular paradigm in machine learning. Most importantly, our results show that expert-based data annotation is extremely valuable for anomaly detection based on machine learning.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Forecasting influenza activity using machine-learned mobility map

Human mobility is a primary driver of infectious disease spread. However, existing data is limited in availability, coverage, granularity, and timeliness. Data-driven forecasts of disease dynamics are crucial for decision-making by health officials and private citizens alike. In this work, we focus on a machine-learned anonymized mobility map (hereon referred to as AMM) aggregated over hundreds of millions of smartphones and evaluate its utility in forecasting epidemics. We factor AMM into a metapopulation model to retrospectively forecast influenza in the USA and Australia. We show that the AMM model performs on-par with those based on commuter surveys, which are sparsely available and expensive. We also compare it with gravity and radiation based models of mobility, and find that the radiation model’s performance is quite similar to AMM and commuter flows. Additionally, we demonstrate our model’s ability to predict disease spread even across state boundaries. Our work contributes towards developing timely infectious disease forecasting at a global scale using human mobility datasets expanding their applications in the area of infectious disease epidemiology.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Quantifying Impacts of Renewable Electricity Deployment on Air Quality and Human Health in Southeast Asia Based on Aims III Scenarios

Exposure to outdoor air pollution is the largest environmental risk factor for death and disease worldwide, associated with millions of cases of excess deaths (mortality) each year. Although there are many pollutants in the air that affect our health, the most important class of pollutants is fine particulate matter, PM 2.5 , which are airborne particles of diameter ≤2.5 micrometers (µm). These particles are small enough to deposit deep in the respiratory system where they can then enter the bloodstream, traveling and causing damage to other bodily systems. Exposure to outdoor (ambient) PM 2.5 has been found to be the most important environmental risk factor for mortality in Southeast Asia, associated with 130,000 - 320,000 excess deaths in Association of Southeast Asian Nations (ASEAN) member countries in 2019. Southeast Asia, especially its mega-cities, but also other areas, has some of the worst air quality in the world. Almost all human activity emits air pollutants. Fine particulate matter is both directly emitted and formed in the atmosphere through chemical reactions, the latter of which requires modeling to predict. Power generation is one of the major sources of air pollutants that lead to elevated concentrations of fine particulate matter, including in Southeast Asia. Fossil fuel combustion for power generation, especially coal but also diesel, is the main source of air pollutant emissions from power generation. While natural gas burns cleaner than coal or diesel, in the quantities combusted for power generation in Southeast Asia, it is also a significant emitter. This study augments the ASEAN Interconnection Masterplan Study III (AIMS III) by quantifying changes to air quality and human health that result from its renewable integration and transmission interconnection scenarios. Performing this analysis requires translation of the changes in projected generation from different power sector fuel sources in the AIMS III scenarios to changes in air pollutant emissions, developing what's known as an emissions inventory for each scenario and year evaluated. We then use for the first time a new global, reduced-complexity air quality model to transform the changes in emissions to changes in air pollutant concentration of the deadliest air pollutant for human health, fine particulate matter (or PM 2.5 ). The air quality model, Global InMAP, then utilizes the location of human population in ASEAN countries to calculate exposure to PM 2.5 concentration changes and translates that to estimates of excess mortality attributable to the AIMS III scenarios.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2023

Targeting tissues via dynamic human systems modeling in generative design

Drug discovery is a complex, costly process with high failure rates. A successful drug should bind to a target, be deliverable to an intended site of activity, and promote a desired pharmacological effect without causing toxicity. Typically, these factors are evaluated in series over the course of a pipeline where the number of candidates is sequentially whittled down from a very large initial pool. One promise of AI-driven discovery is the opportunity to evaluate multiple facets of drug performance in parallel. However, despite ML-driven advancements, current models for pharmacological property prediction are exclusively trained to predict molecular properties, ignoring important, dynamic biodistribution and bioactivity effects. Here, we present our progress towards incorporating quantitative systems physiology models into an AI-enabled drug design and molecular generation pipeline. Within a genetic algorithm, we include human-relevant physiologically based pharmacokinetic (PBPK) models. These PBPK models leverage properties that are predicted by a fine-tuned molecular language model. Together, these models will aid in capturing the mapping between molecules and therapeutic outcomes that is necessary to accelerate the drug discovery process.

Fox, Zach↗

DOE OSTI2021

A Structural Basis for Inhibition of the Complement Initiator Protease C1r by Lyme Disease Spirochetes

Abstract Complement evasion is a hallmark of extracellular microbial pathogens such as Borrelia burgdorferi, the causative agent of Lyme disease. Lyme disease spirochetes express nearly a dozen outer surface lipoproteins that bind complement components and interfere with their native activities. Among these, BBK32 is unique in its selective inhibition of the classical pathway. BBK32 blocks activation of this pathway by selectively binding and inhibiting the C1r serine protease of the first component of complement, C1. To understand the structural basis for BBK32-mediated C1r inhibition, we performed crystallography and size-exclusion chromatography–coupled small angle X-ray scattering experiments, which revealed a molecular model of BBK32-C in complex with activated human C1r. Structure-guided site-directed mutagenesis was combined with surface plasmon resonance binding experiments and assays of complement function to validate the predicted molecular interface. Analysis of the structures shows that BBK32 inhibits activated forms of C1r by occluding substrate interaction subsites (i.e., S1 and S1’) and reveals a surprising role for C1r B loop–interacting residues for full inhibitory activity of BBK32. The studies reported in this article provide for the first time (to our knowledge) a structural basis for classical pathway–specific inhibition by a human pathogen.

Garrigues, Ryan J. (ORCID:0000000259233250)↗

DOE OSTI2025

Consistent performance of large language models in rare disease diagnosis across ten languages and 4917 cases

Background Large language models (LLMs) are increasingly used medicine for diverse applications including differential diagnostic support. The training data used to create LLMs such as the Generative Pretrained Transformer (GPT) predominantly consist of English-language texts, but LLMs could be used across the globe to support diagnostics if language barriers could be overcome. Initial pilot studies on the utility of LLMs for differential diagnosis in languages other than English have shown promise, but a large-scale assessment on the relative performance of these models in a variety of European and non-European languages on a comprehensive corpus of challenging rare-disease cases is lacking. Methods We created 4917 clinical vignettes using structured data captured with Human Phenotype Ontology (HPO) terms with the Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema. These clinical vignettes span a total of 360 distinct genetic diseases with 2525 associated phenotypic features. We used translations of the Human Phenotype Ontology together with language-specific templates to generate prompts in English, Chinese, Czech, Dutch, French, German, Italian, Japanese, Spanish, and Turkish. We applied GPT-4o, version gpt-4o-2024-08-06, and the medically fine-tuned Meditron3-70B to the task of delivering a ranked differential diagnosis using a zero-shot prompt. An ontology-based approach with the Mondo disease ontology was used to map synonyms and to map disease subtypes to clinical diagnoses in order to automate evaluation of LLM responses. Findings For English, GPT-4o placed the correct diagnosis at the first rank 19.9% and within the top-3 ranks 27.0% of the time. In comparison, for the nine non-English languages tested here the correct diagnosis was placed at rank 1 between 16.9% and 20.6%, within top-3 between 25.4% and 28.6% of cases. The Meditron3 model placed the correct diagnosis within the first 3 ranks for 20.9% of cases in English and between 19.9% and 24.0% for the other nine languages. Interpretation The differential diagnostic performance of LLMs across a comprehensive corpus of rare-disease cases was largely consistent across the ten languages tested. This suggests that the utility of LLMs in clinical settings may extend to non-English clinical settings.

Artificial intelligence↗

DOE OSTI2024

Innovating the next generation of commercial smart building software

Nearly 30% of commercial building energy use is wasted due to equipment faults and HVAC controls problems. The result is increased emissions, compromised comfort and productivity, and less reliable coordination of building power needs with a clean grid. The energy impact alone represents $17 billion in potential savings. Today’s smart building software provides a robust solution to address these operational deficiencies. Energy management and information systems (EMIS) are saving up to 9% on average, with two-year paybacks. They are being incorporated into energy management processes, commissioning services, and utility programs. As effective as they are, two barriers prevent even deeper benefits; limited personnel to fix problems once they are identified, and the expense and time to manually implement changes in control systems. In partnership with the research community, the EMIS industry is developing new capabilities to overcome these barriers. Moving beyond siloed products for either fault detection and diagnostics, or optimal control, these new capabilities empower users to not only automatically identify faults, but also to push corrective action, and control improvements to their buildings. In this paper, several areas for enhancements are documented: ‘one-time’ correction of faults such as setpoints, schedules, and economizer lockouts; short-term active testing for automated proportional integral derivative (PID) loop tuning and functional testing; and continuous supervisory control for demand flexibility and year-round efficiency. Results are presented from a pair of partner implementations out of a dozen providers integrating these enhancements into their products, including field tests from across the country, and insights into operator acceptance and integration into operations and maintenance practices.

Casillas, Armando↗

DOE OSTI2020

Veridical data science

Building and expanding on principles of statistics, machine learning, and scientific inquiry, we propose the predictability, computability, and stability (PCS) framework for veridical data science. Our framework, composed of both a workflow and documentation, aims to provide responsible, reliable, reproducible, and transparent results across the data science life cycle. The PCS workflow uses predictability as a reality check and considers the importance of computation in data collection/storage and algorithm design. It augments predictability and computability with an overarching stability principle. Stability expands on statistical uncertainty considerations to assess how human judgment calls impact data results through data and model/algorithm perturbations. As part of the PCS workflow, we develop PCS inference procedures, namely PCS perturbation intervals and PCS hypothesis testing, to investigate the stability of data results relative to problem formulation, data cleaning, modeling decisions, and interpretations. We illustrate PCS inference through neuroscience and genomics projects of our own and others. Moreover, we demonstrate its favorable performance over existing methods in terms of receiver operating characteristic (ROC) curves in high-dimensional, sparse linear model simulations, including a wide range of misspecified models. Finally, we propose PCS documentation based on R Markdown or Jupyter Notebook, with publicly available, reproducible codes and narratives to back up human choices made throughout an analysis. The PCS workflow and documentation are demonstrated in a genomics case study available on Zenodo.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Development of Human and Technology Integration Guidance for Work Optimization and Effective Use of Information

Existing nuclear power contributes to roughly 20% of the total electricity generation, and consistently provides the highest capacity factor of any other electricity generating resource in the United States. Despite these advantages, the existing nuclear power plant fleet in the United States has been enduring significant challenges in providing electricity in a cost-competitive manner, which has ultimately threatened the long-term economic viability of these plants. A major contributor to these increased operating and maintenance costs has been the continued reliance of a large workforce who perform their work under an operating model that has largely remained unchanged since the commissioning of these nuclear power plants. Unfortunately, while this operating model has provided safe and reliable electricity, other industries have already began transforming their workforce through the use of advanced digital technology and automation that has reduced their operating and maintenance cost significantly. In order for the United States nuclear industry to remain economically viable, a similar transformation must be considered in which digital technologies and automation capabilities are brought in to support key plant functions across all work functions across plant operation, maintenance, and support. To effectively integrate digital technology and automation in the existing nuclear power plant operating model, a multidisciplinary approach is needed that addresses technological and sociotechnical (i.e., human and technology integration) considerations. This report describes an extension to the human and technology integration methodology, herein referred to as Human Integration and Technology Task Force for Work Management Optimization (HITT), to support the safe, reliable, and efficient use of proposed innovations with the intended users in their intended environment to perform their intended tasks. By effectively incorporating human and technology integration into a plant modernization effort by using HITT, we believe that a utility can significantly improve work performance and overall workforce quality of life. For instance, if HITT is performed to optimize work management, scheduling performance and scope stability can be improved by up to 10%. HITT enables these benefits through developing a rich understanding of the work being performed, the utility’s vision, and the opportunities that provide greatest value to optimize performance through a 10-step process illustrated below as a quick guide. The quick guide contains links in the righthand side of each step that allows for navigation to the detailed section (Section 4) of HITT in this technical report.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2020

Issue Resolution During the Development of the Performance Assessment for the Savannah River Site Saltstone Disposal Facility - 20125

In 2019, Savannah River Remediation developed a revision to the performance assessment (PA) on behalf of the U.S. Department of Energy (DOE) Savannah River Operations Office (SR) for the near-surface disposal of low-level waste at the Savannah River Site (SRS) Saltstone Disposal Facility (SDF). Soluble waste from SRS Tank Farms undergoes salt processing to remove cesium and other high-activity constituents. The low-activity decontaminated salt solution (DSS) is then immobilized by mixing it into a cementitious waste form known as saltstone. After mixing, the saltstone is poured into leak-tight concrete vaults, known as saltstone disposal units (SDUs), where the waste form cures. By the time of facility closure, the SDF is expected to consist of 15 SDUs with a combined capacity of 1.06 E+09 L (280 Mgal) of cured saltstone. The facility operates under a Disposal Authorization Statement from DOE and a permit from the South Carolina Department of Health and Environmental Control (SCDHEC). Since the start of operations in 1990, the SDF has received almost 6.7 E+07 L (18 Mgal) of DSS, resulting in the safe disposal of 2.7 E+16 Bq (7.3 E+05 Ci) of activity. Due to the radioactive decay of short-lived contaminants, the total remaining activity in the disposed waste is estimated to be approximately 1.4 E+16 Bq (3.9 E+05 Ci), as of September 2018. The Disposal Authorization Statement requires a demonstration that the system of engineered and natural features of the disposal facility will limit releases from the facility and be protective of human health and the environment for at least the next 1,000 years. The long-term performance of the facility was evaluated under the requirements of the DoE's Radioactive Waste Management Manual (US DOE Manual 435.1-1). Simulations were performed to demonstrate that the disposal facility would meet performance objectives specified in the manual. The evaluation was based on numerical models that simulate the releases of contaminants from the saltstone waste form. Contaminants were transported through groundwater and air pathways to points of assessment to evaluate compliance (i.e., 100 m from the SDUs). In addition, the potential consequences of an inadvertent human intrusion (IHI) were also evaluated. A number of issues were overcome during the development of these simulations. These issues were identified as part of internal technical reviews. Simulations are developed by people and people make mistakes, so the internal technical review process is a vital step in PA development. Specific examples of resolved issues include a unit-conversion error, an inappropriate definition for a model boundary condition, a model time-stepping issue, and an error in the calculation for the buildup of contaminants in soil. Actions taken to address these issues resulted in an improved product with a better supported technical basis and more defensible results. The identification and correction of these issues are discussed. By understanding these issues, model developers and technical reviewers working on PAs in the future may avoid repeating these types of mistakes. Transparency with respect to these mistakes builds trust between waste management sites, regulators, and stakeholders. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2026

A prototype cooling blanket for mitigating occupant overheating risk in a hot indoor environment: Modeling and assessments

Conventional ways of cooling a room or an entire house for occupant thermal comfort during summer consume a significant amount of energy and are vulnerable to overheating risk during power outages that lead to loss of cooling system operations. This study investigates a low-power cooling blanket, as a Personal Cooling System (PCS), that covers the upper human body for direct cooling during a five-day heat wave in a single-family house. A modeling framework is developed for evaluating the thermal and energy performance of the cooling blanket, which builds upon the co-simulation of three models: a house energy model, a personal thermal comfort model, and a cooling blanket model. Simulation results show that under the power outage scenario, the cooling blanket can greatly reduce the occupant heat stress with a reduction of daily hours of exceedance (discomfort hours defined as TSV>2) by up to 17.2 h (a 95.3 % improvement from the baseline power outage without the blanket). The cooling blanket, equipped with an innovative electrocaloric heat pump (COP as high as 10.1) consumes 6.31 W and can be operated by a portable battery for several days. The cooling blanket consumes only 0.28 % of the electricity of a central air-conditioning system running to provide cooling for the whole house during the five-day heatwave period. The findings justify further research of electrocaloric wearable PCS as low-power effective cooling to ensure thermal survivability of occupants during extreme indoor environments.

Electrocaloric heat pump↗

DOE OSTI2023

3D Modeling of Safety-Related Upgrade Pilot Project

Constellation Energy and the United States Department of Energy (DOE) have established a public/private partnership to implement a pilot digital upgrade to replace legacy analog, safety-related reactor protection and emergency safety feature actuation systems (RPS/ESFAS) with modern digital systems. This effort is occurring at Constellation’s Limerick Generating Station. This project is being performed in accordance with industry processes that have been adapted to better support digital upgrades. These processes include IP-ENG-001, Standard Design Process, NISP-EN-04, Standard Digital Engineering Process and Electric Power Research Institute Report 3002011816, Digital Engineering Guide. The Light Water Reactor Sustainability (LWRS) Program at the Idaho National Laboratory (INL) has been supporting this effort. Latest INL HFE efforts in support of this project have focused on definition and implementation of the Human Factors Engineering (HFE) Program in support of Constellation design and related licensing efforts. This paper will present the development of the HFE 3D modeling execution of the Main Control Room safety upgrades. New equipment and modifications are planned for upgrading the new safety systems. 3D modeling allows for visualization of the new equipment and modifications to be shared with engineering and design teams for evaluation and review. Anthropometric considerations such as sight lines and functional reach can be evaluated directly using the 3D model. This effort has helped to provide visualizations for additional review with operations personnel and project stakeholders.

3D Modeling↗

DOE OSTI2020

Addressing Human and Organizational Factors in Nuclear Industry Modernization: An Operationally Focused Approach to Process and Methodology

Utility owners and operators of commercial nuclear power plants in the United States (U.S.) are and will be modernizing their nuclear power plants by performing a digital transformation involving design of an integrated set of systems that together enable a technology centric operating plant. The Plant Modernization Pathway of the U.S. Department of Energy Light Water Reactor Sustainability Program has a strategic action plan that lays the groundwork for a digital transformation of the nuclear industry. The model for this transformation is an advanced concept of operations, with an end point vision, “To achieve the maximum aggregate benefit enabled by this digital transformation.” To achieve this, the digital infrastructure for a nuclear plant must be designed as an integrated set of systems that together enable a technology centric operating model. The digital transformation process obviously needs to involve technology considerations and systems engineering, but it also needs to include human and organizational expertise. Thus, human and organizational factors, including sociotechnical systems methods and techniques (e.g., Cognitive Systems Engineering, Systems Theoretic Accident Modeling and Processes, human systems integration, and Macroergonomics) need to be considered for digital transformation projects in order to effectively integrate human and organizational expertise efforts into the new work system that results from nuclear power plant digital modernization. That is, the work system is the basic unit of sociotechnical systems analysis and contains three components: personnel, technical, and organization and management. These components should be jointly optimized with respect to the interdependence of systems performance criteria of effectiveness, efficiency and safety. Joint optimization can be achieved through the application of three human and organization functions: knowledge representation, knowledge elicitation, and cross-functional integration. This report provides a strategic framework for effective integration of human and organizational expertise within nuclear power plant digital modernization efforts.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2026

Systematic benchmarking demonstrates large language models have not reached the diagnostic accuracy of traditional rare-disease decision support tools

Large language models (LLMs) show promise in supporting differential diagnosis, but their performance is challenging to evaluate due to the unstructured nature of their responses, and their accuracy compared to existing diagnostic tools is not well characterized. To assess the current capabilities of LLMs to diagnose genetic diseases, we benchmarked these models on 5213 previously published case reports using the Phenopacket Schema, the Human Phenotype Ontology and Mondo disease ontology. Prompts generated from each phenopacket were sent to seven LLMs, including four generalist models and three LLMs specialized for medical applications. The same phenopackets were used as input to a widely used diagnostic tool, Exomiser, in phenotype-only mode. The best LLM ranked the correct diagnosis first in 23.6% of cases, whereas Exomiser did so in 35.5% of cases. While the performance of LLMs for supporting differential diagnosis has been improving, it has not reached the level of commonly used traditional bioinformatics tools. Future research is needed to determine the best approach to incorporate LLMs into diagnostic pipelines.

Reese, Justin T. [Lawrence Berkeley National Labor↗

DOE OSTI2026

Hierarchical semi-Markov models with duration-aware dynamics for activity sequences

Residential electricity demand at granular scales is driven by what people do and for how long. Accurately forecasting this demand for applications like microgrid management and demand response therefore requires generative models for activities that can produce realistic daily activity sequences, capturing both the timing and duration of human behavior. This paper develops a generative model of human activity sequences using nationally representative time-use diaries at a 10-min resolution. We use this model to quantify which demographic factors are most critical for improving predictive performance. We propose a hierarchical semi-Markov framework that addresses two key modeling challenges. First, a time-inhomogeneous Markov router learns the patterns of “which activity comes next.” Second, a semi-Markov hazard component explicitly models activity durations, capturing “how long” activities realistically last. To ensure statistical stability when data are sparse, the model pools information across related demographic groups and time blocks. The entire framework is trained and evaluated using survey design weights to ensure our findings are representative of the U.S. population. On a held-out test set, we demonstrate that explicitly modeling durations with the hazard component provides a substantial and statistically significant improvement over purely Markovian models. Furthermore, our analysis reveals a clear hierarchy of demographic factors: Sex, Day-Type, and Household Size provide the largest predictive gains, while Region and Season, though important for energy calculations, contribute little to predicting the activity sequence itself. The result is an interpretable and robust generator of synthetic activity traces, providing a high-fidelity foundation for downstream energy systems modeling.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2026

An agentic artificially intelligent X-ray scientist

Executing experimental tasks in both normal research laboratories and large-scale scientific facilities often requires extensive human supervision and remains a key challenge on the path to fully autonomous, artificial intelligence (AI)-driven science. Here we demonstrate a large language model-driven agent that autonomously performs X-ray sample alignment on a synchrotron beamline by planning actions, executing instrumental commands, interpreting observations and iterating towards experimental goals. Based on existing large language models with structured tool-use via the model context protocol, our AI X-ray scientist was guided and tested using an in-house-built virtual experimental setup that mirrors a six-circle diffractometer at an operational synchrotron beamline. The agentic workflow developed in the virtual environment was directly deployed on a real beamline, where it correctly identified reference reflections and determined the orientation matrix, an essential first step in any type of single-crystal scattering experiment. Our AI X-ray scientist responded effectively to unexpected experimental conditions, demonstrating adaptive problem-solving and readiness for addressing practical experimental situations. Our study provides a step towards autonomous operation across diverse experimental environments at large-scale scattering facilities.

Chen, Zhantao (ORCID:0000000319543868)↗

DOE OSTI2025

Detection of Diversion in a Realistic Heat Pipe Microreactor Using Supervised Machine Learning

Microreactors (MRs) pose new challenges for international safeguards. Here, their small size and mass reproducibility make them ideal for deployment in greater numbers and in remote locations, making the job of safeguards inspectors more challenging. Machine learning (ML) is currently being applied to many fields to augment human performance and increase automation; in particular, ML could be used to provide insight for international inspectors to help detect the diversion of nuclear fuel from MR cores. Four ML model types (k-nearest neighbors, decision tree, random forest, and histogram-based gradient boosted ensemble) were trained on integrated flux and critical control drum angle data generated with Serpent 2 for a realistic heat pipe MR design, achieving nearly 100% binary classification accuracy of nominal and diversion core configurations by the end of 1 full power year for three of the four model types. Regression model variants were also trained, using the same input data, for predicting the number of fuel pins diverted. Root-mean-square errors below 5% of the total number of fuel pins were achieved by the 1 full power year mark for all models.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗