Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational 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.

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

At least 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models

Modern machine learning and autonomous experimentation schemes in materials science rely on accurate analysis of the data ingested by these models. Unfortunately, accurate analysis of the underlying data can be difficult, even for domain experts, complicating the training of the models intended to drive experiments. This is especially true when the goal is to identify the presence of weak signatures in diffraction or spectroscopic datasets. In this work, we examine a set of as-obtained diffraction data that track the phase transition from monoclinic to tetragonal in a Nb-doped VO2 film as a function of temperature and dopant concentration. We then task a set of domain experts and a set of machine learning experts with identifying which phase is present in each diffraction pattern manually and algorithmically, respectively; in both cases, the labels can vary dramatically, especially at the phase boundaries. We use the mode of the labels and the Shannon entropy as a method to capture, preserve and propagate consensus labels and their variance. Further we use the expert labels as a benchmark and demonstrate the use of Shannon entropy weighted scoring to test the performance of machine learning generated labels. Finally, we propose a material data challenge centered around generating improved labeling algorithms. This real-world dataset curated with expert labels can act as test bed for new algorithms. The raw data, annotations and code used in this study are all available online at data.gov and the interested reader is encouraged to replicate and improve the existing models

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Rapid Adaptation of Chemical Named Entity Recognition Using Few-Shot Learning and LLM Distillation

Named entity recognition (NER) has been widely used in chemical text mining for the automatic identification and extraction of chemical entities. However, existing chemical NER systems primarily focus on scenarios with abundant training data, requiring significant human effort on annotations. This poses challenges for applications in the chemical field, such as catalysis, where many advancements have traditionally relied on trial-and-error investigations and incremental adjustment of variables. This hinders catalysis science and technology progress in addressing emerging energy and environmental crises. In this work, we propose a few-shot NER model that can quickly adapt to extract new types of chemical entities by using only a limited number of annotated examples. Our model employs a metric-learning approach to transfer entity similarity knowledge from high-resource chemical domains (with abundant annotations) to enable effective entity recognition in low-resource specialized domains (limited annotation). We validate the effectiveness of our model on a few-shot chemical NER benchmark built based on six existing chemical NER data sets. Experiments show that the proposed few-shot NER model can achieve reasonable performance with only 5 examples per entity type and shows consistent improvement as the number of examples increases. Furthermore, we demonstrate how the proposed model can be trained with large language model (LLM) annotated data, opening a new pathway for rapid adaptation of NER systems. Furthermore, our approach leverages the knowledge broadness of large language models for chemistry while distilling this knowledge into a lightweight model suitable for efficient and in-house use.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2014

Effect of time-of-flight and point spread function modeling on detectability of myocardial defects in PET

Purpose: A study was designed to investigate the impact of time-of-flight (TOF) and point spread function (PSF) modeling on the detectability of myocardial defects. Methods: Clinical FDG-PET data were used to generate populations of defect-present and defect-absent images. Defects were incorporated at three contrast levels, and images were reconstructed by ordered subset expectation maximization (OSEM) iterative methods including ordinary Poisson, alone and with PSF, TOF, and PSF+TOF. Channelized Hotelling observer signal-to-noise ratio (SNR) was the surrogate for human observer performance. Results: For three iterations, 12 subsets, and no postreconstruction smoothing, TOF improved overall defect detection SNR by 8.6% as compared to its non-TOF counterpart for all the defect contrasts. Due to the slow convergence of PSF reconstruction, PSF yielded 4.4% less SNR than non-PSF. For reconstruction parameters (iteration number and postreconstruction smoothing kernel size) optimizing observer SNR, PSF showed larger improvement for faint defects. The combination of TOF and PSF improved mean detection SNR as compared to non-TOF and non-PSF counterparts by 3.0% and 3.2%, respectively. Conclusions: For typical reconstruction protocol used in clinical practice, i.e., less than five iterations, TOF improved defect detectability. In contrast, PSF generally yielded less detectability. For large number of iterations, TOF+PSF yields the best observer performance.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2025

Model-based Hierarchical Reinforcement Learning for Improved Physical Security Design: A Prototype

Prior work in FY24 developed an adversarial AI agent aid in path analysis of physical protection systems. This agent, trained using a model-based reinforcement learning algorithm, was able to successfully learn the most vulnerable path in facilities. It was able to extend the current state of practice for physical protection design by exhibiting dynamic behavior based on current environmental conditions. Whereas PathTrace largely performs a static, graph-based analysis, the AI agent was able to make decisions based on relative position in the facility, current conditions (was the adversarial agnet discovered?), and proximity to secondary targets. The agent demonstrated some novel capabilities, but had limitations that need to be resolved before it can be used for production purposes. For example, the adversarial agent generalizes poorly and takes a relatively long time to train. Nonetheless, there is still considerable promise for developing the adversarial agent further in order to explore even richer, more dynamic behaviors (e.g., adversary motivations, environmental debris, and more). This work considers a complementary idea; development of a planning agent. The planning agent is envisioned as an auto-complete-like tool that can help accelerate security system design by human experts. The agent would respect existing barriers and sensors placed by a human expert while offering cost-effective suggestions (i.e., implicitly balancing effectiveness with cost) to improve the design. The goal is for this agent to be part of an expert’s toolbox, not to totally upend the current state-of-practice, or to displace human experts. The ultimate goal would be concurrent training of both the adversarial and planning agent together, to learn entirely through self-play. This would represent an entirely new way of performing system deign. We selected a hierarchical, model-based reinforcement learning algorithm to serve as the planning agent. This is an extension of concepts used in the prior FY24 adversarial agent work. There, we had a single agent acting an environment. Here, we have two different sub-agents (policies), working together, to form a complete agent. There is a manager policy, which can select abstract goals on slower time scales, and a worker, which performs primitive actions to reach goals selected by the manager. It is worth noting that this class of algorithm is challenging to work with. From our understanding, our work is one of the first successful uses of model-based reinforcement learning (MBRL) in nuclear energy1 , and likely the first hierarchical model-based reinforcement learning application in nuclear energy. Further, this work is one of the first known attempts to apply AI to perform a design tasks in nuclear energy. Consequently, there were significant implementation challenges and the bulk of the work was focused on successful implementation and algorithm design. The results presented here are very low technology readiness level as a consequence of the lack of related literature, but still represent a significant step forward in the pursuit of applied AI for design.

42 ENGINEERING↗
DOE OSTI2013

Assessment of Testing Options for the NTR at the INL (Final Report)

One of the main technologies that can be developed to dramatically enhance the human exploration of space is the nuclear thermal rocket (NTR). Several studies over the past thirty years have shown that the NTR can reduce the cost of a lunar outpost, reduce the risk of a human mission to Mars, enable fast transits for most missions throughout the solar system, and reduce the cost and time for robotic probes to deep space. Three separate committees of the National Research Council of the National Academy of Sciences have recommended that NASA develop the NTR. One of the primary issues in development of the NTR is the ability to verify a flight ready unit. Three main methods can be used to validate safe operation of a NTR: 1) Full power, full duration test in an above ground facility that scrubs the rocket exhaust clean of any fission products; 2) Full power , full duration test using the Subsurface Active Filtering of Exhaust (SAFE) technique to capture the exhaust in subsurface strata; 3) Test of the reactor fuel at temperature and power density in a driver reactor with subsequent first test of the fully integrated NTR in space. The first method, the above ground facility, has been studied in the past. The second method, SAFE, has been examined for application at the Nevada Test Site. The third method relies on the fact that the Nuclear Furnace series of tests in 1971 showed that the radioactive exhaust coming from graphite based fuel for the NTR could be completely scrubbed of fission products and the clean hydrogen flared into the atmosphere. Under funding from the MSFC, the Center for Space Nuclear Research (CSNR) at the Idaho National laboratory (INL) has completed a reexamination of Methods 2 and 3 for implementation at the INL site. In short, the effort performed the following: 1) Assess the geology of the INL site and determine a location suitable SAFE testing; 2) Perform calculations of gas transport throughout the geology; 3) Produce a cost estimate of a non-nuclear , sub-scale test using gas injection to validate the computational models; 4) Produce a preliminary cost estimate to build a nuclear furnace equivalent facility to test NTR fuel on a green field location on the INL site. The results show that the INL geology is substantially better suited to the SAFE testing method than the NTS site. The existence of impermeable interbeds just above the sub-surface aquifer ensure that no material from the test, radioactive or not, can enter the water table. Similar beds located just below the surface will prevent any gaseous products from reaching the surface for dispersion. The extremely high permeability of the strata between the interbeds allows rapid dispersion of the rocket exhaust. In addition, the high permeability suggests that a lower back-pressure may develop in the hole against the rocket thrust, which increases safety of operations. Finally, the cost of performing a sub-scale, non-nuclear verification experiment was determined to be $\$$3M. The third method was assessed through discussions with INL staff resident at the site. In essence, any new Category I facility on any DOE site will cost in excess of $\$$250M. Based on the results of this study, a cost estimate for testing a nuclear rocket at the INL site appears to be warranted. Given the fact that a new nuclear fuel may be possible that does not release any fission products, the SAFE testing option appears to be the most affordable.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2015

Russian anthropogenic black carbon: Emission reconstruction and Arctic black carbon simulation

Development of reliable source emission inventories is needed to advance the understanding of the origin of Arctic haze using chemical transport modeling. This paper develops a regional anthropogenic black carbon (BC) emission inventory for the Russian Federation, the largest country by land area in the Arctic Council. Activity data from combination of local Russia information and international resources, emission factors based on either Russian documents or adjusted values for local conditions, and other emission source data are used to approximate the BC emissions. Emissions are gridded at a resolution of 0.1° × 0.1° and developed into a monthly temporal profile. Total anthropogenic BC emission of Russia in 2010 is estimated to be around 224 Gg. Gas flaring, a commonly ignored black carbon source, contributes a significant fraction of 36.2% to Russia's total anthropogenic BC emissions. Other sectors, i.e., residential, transportation, industry, and power plants, contribute 25.0%, 20.3%, 13.1%, and 5.4%, respectively. Three major BC hot spot regions are identified: the European part of Russia, the southern central part of Russia where human population densities are relatively high, and the Urals Federal District where Russia's major oil and gas fields are located but with sparse human population. BC simulations are conducted using the hemispheric version of Community Multi-scale Air Quality Model with emission inputs from a global emission database EDGAR (Emissions Database for Global Atmospheric Research)-HTAPv2 (Hemispheric Transport of Air Pollution) and EDGAR-HTAPv2 with its Russian part replaced by the newly developed Russian BC emissions, respectively. The simulation using the new Russian BC emission inventory could improve 30–65% of absorption aerosol optical depth measured at the AERONET sites in Russia throughout the whole year as compared to that using the default HTAPv2 emissions. At the four ground monitoring sites (Zeppelin, Barrow, Alert, and Tiksi) in the Arctic Circle, surface BC simulations are improved the most during the Arctic haze periods (October–March). The poor performance of Arctic BC simulations in previous studies may be partly ascribed to the Russian BC emissions built on out-of-date and/or missing information, which could result in biases to both emission rates and the spatial distribution of emissions. Finally, this study highlights that the impact of Russian emissions on the Arctic haze has likely been underestimated, and its role in the Arctic climate system needs to be reassessed. The Russian black carbon emission source data generated in this study can be obtained via http://abci.ornl.gov/download.shtml or http://acs.engr.utk.edu/Data.php.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2016

SU-F-T-682: In-Vivo Simulation of the Relative Biological Effectiveness in Proton Therapy Using a Monte Carlo Method

Purpose: In proton therapy, the relative biological effectiveness (RBE) – compared with conventional photon therapy – is routinely set to 1.1. However, experimental in vitro studies indicate evidence for the variability of the RBE. To clarify the impact on patient treatment, investigation of the RBE in a preclinical case study should be performed. Methods: The Monte Carlo software TOPAS was used to simulate the radiation field of an irradiation setup at the experimental beamline of the proton therapy facility (OncoRay) in Dresden, Germany. Simulations were performed on cone beam CT-data (CBCT) of a xenogeneous mouse with an orthotopic lung carcinoma obtained by an in-house developed small animal image-guided radiotherapy device. A homogeneous physical fraction dose of 1.8Gy was prescribed for the contoured tumor volume. Simulated dose and linear energy transfer distributions were used to estimate RBE values in the mouse based on an RBE model by Wedenberg et al. To characterize radiation sensitivity of normal and tumor tissue, α/β-ratios were taken from the literature for NB1RGB (10.1Gy) and human squamous lung cancer (6.2Gy) cell lines, respectively. Results: Good dose coverage of the target volume was achieved with a spread-out Bragg peak (SOBP). The contra-lateral lung was completely spared from receiving radiation. An increase in RBE towards the distal end of the SOBP from 1.07 to 1.35 and from 1.05 to 1.3 was observed when considering normal tissue and tumor, respectively, with the highest RBE values located distal to the target volume. Conclusion: Modeled RBE values simulated on CBCT for experimental preclinical proton therapy varied with tissue type and depth in a mouse and differed therefore from a constant value of 1.1. Further translational work will include, first, conducting preclinical experiments and, second, analogous RBE studies in patients using experimentally verified simulation settings for our clinically used patient-specific beam conforming technique.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Visual feedback and guided balance training in an immersive virtual reality environment for lower extremity rehabilitation

Balance training is essential for physical rehabilitation procedures, as it can improve functional mobility and enhance cognitive coordination. However, conventional balance training methods may have limitations in terms of motivation, real-time objective feedback, and personalization, which a virtual reality (VR) setup may provide a better alternative. In this work, we present an immersive VR training environment for lower extremity balance rehabilitation with real-time guidance and feedback. The VR training environment immerses the user in a 3D ice rink model where a virtual coach (agent) leads them through a series of balance poses, and the user controls a trainee avatar with their own movements. Here we developed two coaching styles: positive-reinforcement and autonomous-supportive, and two viewpoints of the trainee avatar: first-person and third-person. The proposed environment was evaluated in a user study with healthy, non-clinical participants (n = 16, 24.4 ± 5.7 years old, 9 females). Our results show that participants showed stronger performance in the positive-reinforcement style compared to the autonomous-supportive style. Additionally, in the third-person viewpoint, the participants exhibited more stability in the positive-reinforcement style compared to the autonomous-supportive style. For viewpoint, participants exhibited stronger performance in the first-person viewpoint compared to third-person in the autonomous-supportive style, while they were comparable in the positive-reinforcement style. We observed no significant effects on the foot height and number of mistakes. Furthermore, we report the analysis of user performance with balance training poses and subjective measures based on questionnaires to assess the user experience, usability, and task load. The proposed VR balance training could offer an interactive, adaptive, and engaging environment and open new potential research directions for lower extremity rehabilitation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Data-Enabled Fusion Technology (Final Scientific/Technical Report)

Advancing Scientific Understanding in Fusion Energy and Machine Learning This research represented a significant step forward in machine learning (ML) applications for fusion energy experiments. The project integrated advanced data-driven modeling, optimization techniques, and artificial intelligence to enhance the predictive capabilities and operational efficiency of plasma-based fusion systems. Specifically, tasks focused on ML-enhanced diagnostics, operator guidance tools, and predictive modeling helped improve the ability to interpret complex fusion experiments. Key areas of advancement included: 1) data-driven plasma control, i.e., using ML algorithms to optimize experimental conditions and classify plasma behaviors based on historical data; 2) spectroscopy and diagnostics, i.e., applying AI models to extract previously inaccessible insights from experimental spectroscopy data; and 3) configuration mapping and operator guidance, i.e., developing a predictive framework to assist scientists in identifying the most effective experimental parameters, reducing reliance on manual adjustments. By refining these ML-driven techniques, the project contributed to the broader scientific community’s understanding of plasma dynamics and fusion energy viability. Technical Effectiveness and Economic Feasibility The methods investigated demonstrated high technical effectiveness, as reflected in milestones assessing the predictive accuracy, performance, and optimization of fusion configurations. The development of an Operator Guidance Tool (OGT), for example, led to more precise control of plasma conditions by learning from experimental data and offering real-time adjustments. From an economic standpoint, DeFT provided: 1) the ability to reduce trial-and-error experimentation, which lowered operational costs; 2) improved data interpretation methods, which enabled more efficient resource allocation in large-scale fusion research projects; and 3) the automation of key diagnostic tasks, which reduced manual labor and human error, increasing overall efficiency. 13 The final assessments of predictive models and optimization strategies demonstrated that these approaches were scalable and could be implemented across multiple fusion energy research programs. Public Benefit and Societal Impact This project contributed directly to the broader goal of achieving sustainable and commercially viable fusion energy, which had profound implications for clean energy production and climate change mitigation. The integration of AI-driven solutions into fusion research: 1) sped up scientific discovery, accelerating progress towards achieving energy breakthroughs; 2) reduced the cost of experimentation, making fusion research more accessible; and 3) provided a framework for future AI applications in high-energy physics, benefiting adjacent fields like space exploration, material science, and renewable energy. Additionally, by fostering collaborations between AI researchers and plasma physicists, this project promoted interdisciplinary innovation that could lead to broader applications beyond fusion research.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Operational Energy Life Cycle Data Development for the National Institute of Standards And Technology (NIST) Building Industry Reporting and Design for Sustainability (BIRDS) Neutral Environmental Software Tool (NEST)

For this analysis, regionalized life cycle assessment (LCA) results for environmental impacts (using the Tool for Reduction and Assessment of Chemicals and Other Environmental Impacts [TRACI] 2.1) and cumulative energy demand (using the Federal Life Cycle Analysis Commons Elementary Flow List [FEDEFL] Inventory Methods v1.0.0) were evaluated for the production and utilization of electricity, natural gas, fuel oil, and propane as commodities within residential and commercial buildings. These results can used as a framework for future research into net zero, high-performance buildings, such as done here for the Building Industry Reporting and Design for Sustainability (BIRDS) database by the National Institute of Standards and Technology (NIST) Engineering Laboratory. The geographical results were assigned to each United States (U.S.) Zone Improvement Plan (ZIP) code based on the ZIP code location and corresponding Balancing Authority Area, natural gas basin, and Petroleum Administration for Defense Districts (PADDs). Additionally, previously developed models were utilized to develop future life cycle profiles. Projections were based on data available from the U.S. Energy Information Administration Annual Energy Outlook 2022 through 2050 (AEO 2022). Electricity LCA models were updated based on AEO 2022 projected annual generation mixes, while the natural gas baseline model was updated based on projected shares of natural gas types (conventional, shale, tight, and coalbed methane). Projections of crude oil production rates and export rates were applied to the petroleum baseline model in five-year increments to investigate their effects on the life cycle profile of fuel oil and propane. While only 100-year Global Warming Potential (GWP-100) with climate carbon feedback (CC-FB) and Cumulative Energy Demand are shown in Section 4: Results, the complete results, including Acidification Potential, Eutrophication Potential, Freshwater Ecotoxicity Potential, GWP-100 without inclusion of CC-FB, Human Health Impacts Potentials (Cancer, Non-Cancer), Ozone Depletion Potential, Particulate Matter Formation Potential, and Photochemical Smog Formation Potential, are tabulated for each ZIP code in the Excel worksheets that accompany this analysis. For the Excel spreadsheet tools associated with this report, please go to https://www.netl.doe.gov/energy-analysis/details?id=f8890fac-be55-44ac-aaa9-e2888bfabe93

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2018

Numerical Modelling of Radionuclide Migration in the Context of a Near-Surface LILW Disposal Facility - 18618

The reference solution for the management of low and intermediate level short-lived waste (LILW) in France consists in their emplacement in concrete vaults built at the near-surface. The corresponding disposal facility under operation by the French waste management organization (Andra), is located in North-eastern France and planned to be closed in 2060. The safety case developed by Andra has to show the evidence that, amongst other aspects, the radionuclide transfer through the confinement barriers will occur in such a way that the human and environmental exposure will be as low as reasonably achievable (ALARA) and in accordance with the dose constraints. For this purpose, modelling is used to integrate uncertainties about the characteristics of concrete components, waste and water table and their evolution in time and space. At last, modelling is finally used to investigate the radiological impact of specific scenarios in which the failure of safety barriers occurs. In the frame of its technical review of the safety assessment, the French Institute for Radiological Protection and Nuclear Safety (IRSN) also performs such kind of numerical modelling of radionuclide fate from the waste to the hydrogeological outlets, in order to check whether the assessment performed by Andra takes into account sufficiently conservative assumptions. The present work aims to evaluate the role of components of the vaults on radionuclide transport during the post-closure period over a few thousand years. For this purpose, IRSN carries out numerical calculations with MELODIE software, which simulates water flow and transport of species, in order to simulate radionuclide migration from waste packages emplaced in a concrete vault to the surrounding groundwater. The developed transport model focuses on 3-H radionuclide and integrates Andra's main assumptions (release model from the waste packages, chemical and hydraulic properties of the vault components, shrinkage and cracks in concrete components). An adaptive mesh method, based on an a posteriori error estimator, was used to model the cracks and the consideration of a strong heterogeneity in the hydraulic and transport parameters values in the different components of the model. This method shows an improvement of results of about 40 times, whereas the mesh size was increased by only 2%. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2026

Building MCP-native hierarchical AI scientist ecosystems: a perspective on scaling multi-agent scientific discovery

Large language models (LLMs) are evolving from chatbots with limited tool-using capabilities to agentic AI systems that can perform deep research, assist in proposing hypotheses, help design experiments, automate data analysis, and draft scientific reports. However, there are currently two bottlenecks limiting LLMs' real-world impact on the broader scientific research community beyond academic demonstrations: lack of interoperability (repetitive manual tool-integration is required across scenarios) and the need for scalable coordination (unstructured communication and memory become brittle as the number of agents grows). In this Perspective, we argue that the next phase of agentic scientific discovery requires the development of an ecosystem of protocol-native agents and tools organized through hierarchies inspired by human society, beyond the current paradigm of a single monolithic “AI scientist”. We use Model Context Protocol (MCP) as a concrete example of an emerging interoperability layer for scientific tool and context exchange, and we propose three complementary pathways to increase the scaling capabilities of an MCP-native scientific ecosystem by addressing the composability issues: (1) MCP servers for high-value scientific tools maintained by domain experts, (2) automated transformation of existing code repositories into MCP services, and (3) autonomous invention and evolution of new agents and workflows. Finally, we provide a practical roadmap for scaling AI-driven scientific discovery by expanding tool supply and coordination in MCP-native scientific ecosystems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2015

WE-G-BRA-06: Application of Systems and Control Theory-Based Hazard Analysis to Radiotherapy

Purpose: The process of delivering radiation occurs in a complex socio-technical system heavily reliant on human operators. Furthermore, both humans and software are notoriously challenging to account for in traditional hazard analysis models. High reliability industries such as aviation have approached this problem through using hazard analysis techniques grounded in systems and control theory. The purpose of this work is to apply the Systems Theoretic Accident Model Processes (STAMP) hazard model to radiotherapy. In particular, the System-Theoretic Process Analysis (STPA) approach is used to perform a hazard analysis of a proposed on-line adaptive cranial radiosurgery procedure that omits the CT Simulation step and uses only CBCT for planning, localization, and treatment. Methods: The STPA procedure first requires the definition of high-level accidents and hazards leading to those accidents. From there, hierarchical control structures were created followed by the identification and description of control actions for each control structure. Utilizing these control structures, unsafe states of each control action were created. Scenarios contributing to unsafe control action states were then identified and translated into system requirements to constrain process behavior within safe boundaries. Results: Ten control structures were created for this new CBCT-only process which covered the areas of hospital and department management, treatment design and delivery, and vendor service. Twenty three control actions were identified that contributed to over 80 unsafe states of those control actions resulting in over 220 failure scenarios. Conclusion: The interaction of people, hardware, and software are highlighted through the STPA approach. STPA provides a hierarchical model for understanding the role of management decisions in impacting system safety so that a process design requirement can be traced back to the hazard and accident that it is intended to mitigate. Varian Medical Systems, Inc.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Evaluation of an open forecasting challenge to assess skill of West Nile virus neuroinvasive disease prediction

Abstract Background West Nile virus (WNV) is the leading cause of mosquito-borne illness in the continental USA. WNV occurrence has high spatiotemporal variation, and current approaches to targeted control of the virus are limited, making forecasting a public health priority. However, little research has been done to compare strengths and weaknesses of WNV disease forecasting approaches on the national scale. We used forecasts submitted to the 2020 WNV Forecasting Challenge, an open challenge organized by the Centers for Disease Control and Prevention, to assess the status of WNV neuroinvasive disease (WNND) prediction and identify avenues for improvement. Methods We performed a multi-model comparative assessment of probabilistic forecasts submitted by 15 teams for annual WNND cases in US counties for 2020 and assessed forecast accuracy, calibration, and discriminatory power. In the evaluation, we included forecasts produced by comparison models of varying complexity as benchmarks of forecast performance. We also used regression analysis to identify modeling approaches and contextual factors that were associated with forecast skill. Results Simple models based on historical WNND cases generally scored better than more complex models and combined higher discriminatory power with better calibration of uncertainty. Forecast skill improved across updated forecast submissions submitted during the 2020 season. Among models using additional data, inclusion of climate or human demographic data was associated with higher skill, while inclusion of mosquito or land use data was associated with lower skill. We also identified population size, extreme minimum winter temperature, and interannual variation in WNND cases as county-level characteristics associated with variation in forecast skill. Conclusions Historical WNND cases were strong predictors of future cases with minimal increase in skill achieved by models that included other factors. Although opportunities might exist to specifically improve predictions for areas with large populations and low or high winter temperatures, areas with high case-count variability are intrinsically more difficult to predict. Also, the prediction of outbreaks, which are outliers relative to typical case numbers, remains difficult. Further improvements to prediction could be obtained with improved calibration of forecast uncertainty and access to real-time data streams (e.g. current weather and preliminary human cases). Graphical Abstract

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Explainable AI for Multivariate Time Series Pattern Exploration: Latent Space Visual Analytics With Temporal Fusion Transformer and Variational Autoencoders in Power Grid Event Diagnosis

Detecting and analyzing complex patterns in multivariate time-series data is crucial for decision-making in urban and environmental system operations. However, challenges arise from the high dimensionality, intricate complexity, and interconnected nature of complex patterns, which hinder the understanding of their underlying physical processes. Existing AI methods often face limitations in interpretability, computational efficiency, and scalability, reducing their applicability in real-world scenarios. This paper proposes a novel visual analytics framework that integrates two generative AI models, Temporal Fusion Transformer (TFT) and Variational Autoencoders (VAEs), to reduce complex patterns into lower-dimensional latent spaces and visualize them in 2D using dimensionality reduction techniques such as PCA, t-SNE, and UMAP with DBSCAN. These visualizations, presented through coordinated and interactive views and tailored glyphs, enable intuitive exploration of complex multivariate temporal patterns, identifying patterns’ similarities and uncover their potential correlations for a better interpretability of the AI outputs. The framework is demonstrated through a case study on power grid signal data, where it identifies multi-label grid event signatures, including faults and anomalies with diverse root causes. Additionally, novel metrics and visualizations are introduced to validate the models and assess the performance, efficiency, and consistency of latent maps generated by VAE, which have been utilized in prior studies for latent space cartography and used as a benchmark in this study, and the emerging TFT architecture under various configurations. These analyses provide actionable insights for model parameter tuning and reliability improvements. Comparative results highlight that TFT achieves shorter run times and superior scalability to diverse time-series data shapes compared to VAE. This work advances fault diagnosis in multivariate time series, fostering explainable AI to support critical system operations.

Explainable AI↗
DOE OSTI2025

Hestia-SWIFL: hourly anthropogenic fossil fuel CO2 and heat on the 2km WRF grid, version 1.1

The Hestia-SWIFL version 1.1 anthropogenic heat (AH) and fossil fuel CO2 (FFCO2) emissions data product represent emissions due to the combustion of fossil fuel and cement production within the state of Arizona from 2019 to 2022. This product was developed as part of the Southwest Urban Corridor Integrated Field Laboratory (SW-IFL) project, which aims to provide new knowledge and tools that address extreme heat, air quality, climate change and related urban environmental issues by integrating high-resolution observations, modeling, and civic engagement. The emissions are generated using a bottom-up/engineering approach and are tied to results generated by the Vulcan Project version 4, an effort to quantify space/time-resolved FFCO2 & AH emissions for the entire United States landscape. A large number of data sources are combined to best estimate the emissions at fine scales such as air quality emissions data, traffic flow data, building information, sociodemographic information, and fuel statistics. The AH product provides emissions for two emissions sources (transportation and point source emissions) in units of Watts per hour per square meter (W/m2) per year (annual files) or per hour (hourly files). The FFCO2 product provides emissions from nine individual emission sectors as well as the total, and in units of tons of carbon (tC) per grid cell per year or per hour. The output made available here places the native spatial resolution of the Hestia FFCO2 & AH emissions data product (points, lines, and polygons) into a regularized 2km x 2km grid at hourly and annual temporal resolutions, and stored in netCDF files. The exact spatial extent is defined by the ASU Weather Research Forecast (WRF) simulation grid. All data are processed using R/Python pm high-performance computing system. 2-27-2026 updates: Bugs in airport hourly profile (both AH and FFCO2) and building spatial patterns (FFCO2 only) were fixed. Hourly emissions are reprocessed for all years to reflect those changes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Models and Strategies for Optimal Demand Side Management in the Chemical Industries

Deregulation and the increase of renewable electricity generation from wind and solar photovoltaics have transformed the U.S. electricity market. Economic and environmental benefits notwithstanding, the presence of renewables has increased variability and uncertainty on the supply side of the grid. Managing demand, rather than generation – a strategy referred to as “demand response (DR)” – is an attractive approach for mitigating this imbalance. DR efforts aim to reduce electricity usage during peak demand times, lessening stress on the grid. Industrial users are particularly attractive entities for DR participation since they present large, localized loads that can provide significant relief on grid demand and –unlike other large loads, such as buildings – are minimally dependent on human needs and preferences. In this project, we accomplished three main objectives. (1) We developed data-driven low-order DR scheduling-relevant dynamic models of chemical processes. Concurrently, we studied the formulation and solution of the associated optimal DR production scheduling problems. (a) A prototype air separation unit (ASU) model was used to generate simulated operating data for initial modeling efforts, which enabled the later use of industrial data for data-driven modeling. (b) We utilized Hammerstein-Wiener (HW) and Finite Step Response (FSR) models to represent nonlinear plant dynamics. (c) The HW models were linearized using exact linearization so they could potentially be embedded in power system models, which are formulated as mixed integer linear programs (MILPs). (d) We solved DR optimization problems under uncertainty and found that even naïve predictions of electricity price and product demand led to significant cost savings benefits. (2) Our DR scheduling optimization problem formulations are amenable to real-time solution. (a) We utilized Lagrangian Relaxation (LR) to efficiently solve the optimization problem by decoupling subproblems linked by complicating constraints. (b) We have achieved computation times for the 3-day DR scheduling problem of an ASU as low as 1.88 minutes. (3) Our representations of the DR behavior of chemical process as grid-level batteries were embedded in power system models. (a) For a small-scale grid, we found that incorporating the dynamics of the chemical plant in the optimal power flow calculations resulted in better resource management leading to up to 15% and 46% cost reduction for the grid and chemical plant operations, respectively, during periods of power line congestion. We have published several works dedicated to modeling and solving DR optimization problems from the user side. These were published in top peer-reviewed journals and are summarized in this report. The most recent work (and papers in preparation) considers DR scheduling from the grid side. Future efforts will consider networked plants (e.g., air separation units operating on a common pipeline) for DR participation, which is expected to amplify the capabilities of industrial DR participants to perform load-shifting. Our consideration of uncertainty in DR has inspired future directions in this area as well: we plan to develop multistage methods to fully account for the effects of uncertainty in DR scheduling.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2016

An ensemble model of QSAR tools for regulatory risk assessment

Quantitative structure activity relationships (QSARs) are theoretical models that relate a quantitative measure of chemical structure to a physical property or a biological effect. QSAR predictions can be used for chemical risk assessment for protection of human and environmental health, which makes them interesting to regulators, especially in the absence of experimental data. For compatibility with regulatory use, QSAR models should be transparent, reproducible and optimized to minimize the number of false negatives. In silico QSAR tools are gaining wide acceptance as a faster alternative to otherwise time-consuming clinical and animal testing methods. However, different QSAR tools often make conflicting predictions for a given chemical and may also vary in their predictive performance across different chemical datasets. In a regulatory context, conflicting predictions raise interpretation, validation and adequacy concerns. To address these concerns, ensemble learning techniques in the machine learning paradigm can be used to integrate predictions from multiple tools. By leveraging various underlying QSAR algorithms and training datasets, the resulting consensus prediction should yield better overall predictive ability. We present a novel ensemble QSAR model using Bayesian classification. The model allows for varying a cut-off parameter that allows for a selection in the desirable trade-off between model sensitivity and specificity. The predictive performance of the ensemble model is compared with four in silico tools (Toxtree, Lazar, OECD Toolbox, and Danish QSAR) to predict carcinogenicity for a dataset of air toxins (332 chemicals) and a subset of the gold carcinogenic potency database (480 chemicals). Leave-one-out cross validation results show that the ensemble model achieves the best trade-off between sensitivity and specificity (accuracy: 83.8 % and 80.4 %, and balanced accuracy: 80.6 % and 80.8 %) and highest inter-rater agreement [kappa (κ): 0.63 and 0.62] for both the datasets. The ROC curves demonstrate the utility of the cut-off feature in the predictive ability of the ensemble model. In conclusion, this feature provides an additional control to the regulators in grading a chemical based on the severity of the toxic endpoint under study.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗