Search NASA⌕ Search

SEARCH · Search NASA

Results for “Knowledge 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 OSTI2025

RAG for FLAG: AI Assistance for a Physics Code

Artificial intelligence (AI) has quickly become an important tool in scientific research, where significant efforts are underway to develop tools that will expedite the research process. One area of particular impact is scientific software, which can be particularly complex, and therefore time consuming to learn and use effectively. AI assistants are increasingly helping to streamline the process by performing tasks such as interactively answering user questions or suggesting solutions. Los Alamos National Laboratory (LANL) develops several advanced scientific codes, such as FLAG, which can be used to run multiphysics simulations. With this study, our goal was to develop an AI assistant for FLAG that could help make the process of understanding the software and running physics simulations more efficient. To develop an AI assistant for FLAG, we used a method called retrieval-augmented generation (RAG), which is a technique that uses information from relevant data sources to enhance the accuracy of large language models (LLMs). We used the FLAG user manual and other FLAG documentation as the knowledge base for the RAG system. When a user provides a query, RAG retrieves relevant sections from the knowledge base in response, then uses those excerpts to generate grounded and contextually rich answers. We found that our AI assistant was able to provide context aware answers and source references to user queries. To evaluate performance, we developed a set of 40 benchmark questions and compared the accuracy of the responses to those of two standard LLMs without retrieval. Our AI assistant significantly outperformed the standard LLMs at answering FLAG-related questions, with an 82.5% accuracy rate, compared to 47.5% for both of the standard LLMs. This has the potential to make the process of learning and using FLAG much easier, especially for new users. Ultimately, it supports LANL’s broader mission by empowering scientists and engineers to focus more on discovery and analysis rather than on navigating complex software systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Estimating the Contribution of the Nickel to Protium Loading of Full-Length Getters

The full-length getter (FLG) is a critical component of the tritium producing burnable absorber rod (TPBAR), designed to capture tritium produced within the lithium aluminate pellets. However, due to the chemical similarity between protium (¹H) and tritium (³H), the FLG readily absorbs protium, reducing its capacity to absorb tritium and increasing the risk of tritium permeation into the reactor coolant. This study evaluates protium produced from neutron irradiation of nickel plating on the FLG through 5?Ni(n,p) reactions, quantifies its contribution to the total protium observed, and informs models of tritium and hydrogen transport within TPBARs. During irradiation, neutron capture by 58Ni results in the formation of 5?Ni, which undergoes neutron bombardment to produce 4He via 5?Ni(n,a) reactions and protium via 5?Ni(n,p) reactions. The measured helium content post-irradiation provides insight into the neutron capture processes within the getter. The 4He measured within the getter may be useful in determining hydrogen produced by the nickel plating on FLG because 59Ni also produces protium in a 59Ni(n, p) reaction. The contribution of 1H from the nickel in FLG contributed less than 1% of the measured H2 gas in PIE, ranging from 0.005% to 0.614%. These findings refine current knowledge of the protium-tritium interplay in TPBARs and support the development of improved transport models for tritium and hydrogen, ultimately aiding in the optimization of TPBAR design and reactor operations.

Arbova, Dana L.↗
DOE OSTI2025

LLM Generation of Online Courses from a Curated Set of Documents in the Nuclear Safeguards Domain

A multidisciplinary team at Argonne National Laboratory explores the application of advanced technologies to enhance knowledge transfer and retention within the nuclear safeguards domain. Specifically, it examines the feasibility of leveraging secure large language models (LLMs) to streamline the creation of e-learning modules for the U.S. National Nuclear Security Administration (NNSA) Office of International Nuclear Safeguards (NA-241). The initiative addresses the critical need for preserving institutional memory and accelerating skill development amidst the imminent retirement of senior professionals in the field in addition to supporting good knowledge management practices. The project integrates instructional design theory with cutting-edge AI technologies to transform curated document sets from the Safeguards Knowledge Repository (SKR) into modular online courses. By automating the generation of learning objectives and instructional content, the effort aims to reduce manual effort while maintaining high-quality educational outcomes. A limited measure of human supervision, however, ensures accuracy, relevance, and alignment with NNSA’s strategic priorities. Key findings highlight the potential of AI-assisted course generation to support safeguards professionals by creating structured, interactive learning experiences. The report underscores the importance of SME validation to address limitations in AI-generated content, such as terminology errors and gaps in coverage. Recommendations include adopting a structured workflow combining LLM acceleration with expert oversight to ensure accuracy, usability, and alignment with learner needs. This work demonstrates Argonne’s commitment to advancing national security and scientific excellence through innovative knowledge management solutions.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2026

From Rules to Reasoning: A Survey of Large Language Model-Based Approaches to Scientific Hypothesis and Idea Generation

Scientific hypothesis generation represents a fundamental challenge in contemporary research due to exponentially expanding literature volumes and increasing disciplinary specialization. Large language models (LLMs) have emerged as transformative tools for automated scientific discovery, moving beyond traditional rule-based and literature-mining approaches. Four paradigmatic approaches define current LLM-driven hypothesis generation: direct prompting and fine-tuning methods, knowledge-enhanced frameworks integrating retrieval-augmented generation (RAG), multi-agent collaborative systems simulating research teams, and reasoning-focused approaches implementing cognitive architectures. Domain-specific applications demonstrate statistical equivalence to human expert performance in social psychology, experimental validation in biomedical research, and near-expert quality in astronomy. Evaluation methodologies encompass human expert assessment, LLM-as-judge frameworks, and comprehensive benchmarking systems. Technical challenges include hallucination management, knowledge integration limitations, and balancing novelty with feasibility. Future directions emphasize hybrid neural-symbolic architectures and sophisticated human-AI collaboration models for responsible scientific discovery acceleration.

AI-driven discovery↗
DOE OSTI2024

Study of ablation and shock generation across three orders of magnitude of laser intensity with 100 ps laser pulses

The laser ablation and subsequent shock generation in solid targets plays an important role in a variety of research topics from equation of state models for materials to inertial confinement fusion. One of the long-standing issues is the knowledge of ablation depth in the picosecond time regime. Here, we report on a direct technique for determining the ablation depth in aluminum using x-ray diffraction data from Linac Coherent Light Source at the Stanford Linear Accelerator Center. This technique gives a direct measurement of the shock wave propagation in the bulk target, enabling an ability to discern early timescale physics from late timescale effects not available in postmortem analysis. We find that the ablation depths only vary by 0.2 μm across three orders of magnitude of laser intensity, while the pressure increased by a factor of 10 following a square root dependence on laser pulse energy. We further observe that the ablation depth in this intensity range (10 11 –10 13 W/cm 2 in intensity, corresponding to 0.8–80 J/cm 2 in fluence) cannot be modeled by a universal scaling law, given the complexity of the mechanisms governing laser ablation in this intensity regime.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

New technology for an ancient fish: A lamprey life cycle modeling tool with an R Shiny application

Lampreys (Petromyzontiformes) are an ancient group of fishes with complex life histories. We created a life cycle model that includes an R Shiny interactive web application interface to simulate abundance by life stage. This will allow scientists and managers to connect available demographic information in a framework that can be applied to questions regarding lamprey biology and conservation. We used Pacific lamprey ( Entosphenus tridentatus ) as a case study to highlight the utility of this model. We applied a global sensitivity analysis to explore the importance of individual life stage parameters to overall population size, and to better understand the implications of existing gaps in knowledge. We also provided example analyses of selected management scenarios (dam passage, fish translocations, and hatchery additions) influencing Pacific lamprey in fresh water. These applications illustrate how the model can be applied to inform conservation efforts. This tool will provide new capabilities for users to explore their own questions about lamprey biology and conservation. Simulations can hone hypotheses and predictions, which can then be empirically tested in the real world.

Gomes, Dylan G. E. (ORCID:0000000226423728)↗
DOE OSTI2025

GIScience in the era of Artificial Intelligence: a research agenda towards Autonomous GIS

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modelling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, we emphasize that as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future.

Autonomous GI↗
DOE OSTI2025

Transformers and Long Short-Term Memory Transfer Learning for GenIV Reactor Temperature Time Series Forecasting

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors.

LSTM↗
DOE OSTI2024

Cities Are Concentrators of Complex, MultiSectoral Interactions Within the Human-Earth System

Cities are concentrators of complex, multi-sectoral interactions. As keystones in the interconnected human-Earth system, cities have an outsized impact on the Earth system. We describe a multi-lens framework for organizing our understanding of the complexity of urban systems and scientific research on urban systems, which may be useful for natural system scientists exploring the ways their work can be made more actionable. We then describe four critical dimensions along which improvements are needed to advance the urban research that addresses urgent climate challenges: (a) solutions-oriented research, (b) equity-centered assessments which rely on fine-scale human and ecological data, (c) co-production of knowledge, and (d) better integration of human and natural systems occurring through theory, observation, and modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Extraction of ground-state nuclear deformations from ultrarelativistic heavy-ion collisions: Nuclear structure physics context

The collective-flow-assisted nuclear shape-imaging method in ultrarelativistic heavy-ion collisions (UHICs) has recently been used to characterize nuclear collective states. In this paper, we assess the foundations of the shape-imaging technique employed in these studies. We argue that some current UHIC nuclear imaging techniques neglect fundamental aspects of spontaneous symmetry breaking and symmetry restoration in colliding ions and incorrectly infer one-body multipole moments from studies of nucleonic correlations. Therefore, the impact of this approach on nuclear structure research has been overstated. Conversely, efforts to incorporate existing knowledge on nuclear shapes into analysis pipelines can be beneficial for benchmarking tools and calibrating models used to extract information from ultrarelativistic heavy-ion experiments.

Nuclear data analysis & compilation↗
DOE OSTI2024

Outcomes of HPC User Support using a Science Gateway AI Assistant

High Performance Computing (HPC) is a vital resource for nuclear energy research, facilitating advanced simulations and complex modeling of the quantification and qualification of advanced reactor technology. However, a common gap in knowledge exists around utilizing HPC systems, particularly for nuclear energy researchers unfamiliar with specific HPC systems. A researcher may be well-versed in using one HPC system and understanding its associated processes. Yet, they might struggle when faced with a different HPC system and its unique processes. HPC support staff play a crucial role in addressing these challenges by providing educational resources and assisting users. However, they also face the challenge of maintaining these systems and ensuring they run efficiently for all users, a responsibility that can be challenging to scale effectively with the increasing demand and expansion of HPC systems. This paper addresses this knowledge gap with an artificial intelligence (AI) assistant that offers on-demand, site-specific HPC support for researchers. Idaho National Laboratory (INL) has deployed an AI assistant that is intended to supplement expert HPC support staff and assist nuclear energy researchers. This paper reports on a four-and-a-half-month study evaluating the integration of an AI assistant within a science gateway, with the goal of enhancing existing HPC support.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Mapping Spiking Neural Networks to Heterogeneous Crossbar Architectures using Integer Linear Programming

Advances in novel hardware devices and architectures allow Spiking Neural Network (SNN) evaluation using ultra-low power, mixed-signal, memristor crossbar arrays. As individual network sizes quickly scale beyond the dimensional capabilities of single crossbars, networks must be mapped onto multiple crossbars. Crossbar sizes within modern Memristor Crossbar Architectures (MCAs) are determined predominately not by device technology but by network topology; more, smaller crossbars consume less area thanks to the high structural sparsity found in larger, brain-inspired SNNs. Motivated by continuing increases in SNN sparsity due to improvements in training methods, we propose utilizing heterogeneous crossbar sizes to further reduce area consumption. This approach was previously unachievable as prior compiler studies only explored solutions targeting homogeneous MCAs. Our work improves on the state-of-the-art by providing Integer Linear Programming (ILP) formulations supporting arbitrarily heterogeneous architectures. By modeling axonal interactions between neurons, our methods produce better mappings while removing inhibitive a priori knowledge requirements. We first show a 16.7-27.6% reduction in area consumption for square-crossbar homogeneous architectures. Then, we demonstrate 66.9-72.7% further reduction when using a reasonable configuration of heterogeneous crossbar dimensions. Next, we present a new optimization formulation capable of minimizing the number of inter-crossbar routes. When applied to solutions already near-optimal in area, an 11.9-26.4% routing reduction is observed without impacting area consumption. Finally, we present a profile-guided optimization capable of minimizing the number of runtime spikes between crossbars. Compared to the best-area-then-route optimized solutions, we observe a further 0.5-14.8% inter-crossbar spike reduction while requiring 1–3 orders of magnitude less solver time.

Pohl, Devin [ORNL] (ORCID:0009000040149027)↗
DOE OSTI2025

A Risk-Informed Approach to Trustworthiness Assessment in Digital Twins-Based Autonomous Control

In autonomous control systems, digital twins (DTs) are used to perform diagnostic and prognostic functions. The trustworthiness of these DTs is dependent on quality and coverage of the training data, model accuracy and integrity of sensor data. This work introduces a methodology to determine the trustworthiness of a DT system given faulty sensor data using a risk informed approach. Bayesian Belief Networks (BBNs) are used to propagate uncertainties and determine the probability of trustable recommendations. The decision to trust the control action provided by the DT is based on the DT output, expert opinion, and severity of problems. The performance of DTs is reliant on the data they are trained on. When they encounter out of distribution data, the trustworthiness of the recommendations decreases. To address this issue, we include an expert component that provides input on sensor degradation. For this, we utilize a generative artificial intelligence (AI) model, such as Generative Pretrained Transformer (GPT). The GPT functions as an expert with broad knowledge. The GPT is fine-tuned to understand and discriminate sensor degradation scenarios using manufactured data. This methodology is demonstrated through a case study on a Nearly Autonomous Management and Control System (NAMAC) during a steady state scenario. Various sensor degradation types with different severity levels are considered. Degraded sensor data is processed by the DT system and the fine-tuned GPT. Finally, using the BBN, we combine the GPT information and the DT output with its sources of uncertainty. This provides an output regarding the trustworthiness of the DT recommendation.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Integrated Hydro-terrestrial Modeling 2.0: Progress and Path Forward on Building a National Capability

It is the role of the U.S. federal government and its supporting agencies, including academia and future scientists, to ensure that its people have sustained and equitable freshwater services, as well as the critical knowledge necessary to make decisions about the future as it relates to freshwater services. Clear and consistent information and guidance from federal agencies is critical. Integrated Hydro-Terrestrial Modeling (IHTM), as a United States (U.S.) national capability, focuses on understanding, quantifying, and managing the replenishment of water supply through hydrologic cycle processes and their governing forces. To provide that information, we need enhanced IHTM capabilities that capitalize on the strengths of each U.S. governmental agency and its core mission. The first IHTM workshop was held in 2019, and its subsequent report was published in 2020. The U.S. Global Change Research Program (USGCRP) and member agencies held a second IHTM workshop (IHTM 2.0) from October 31 to November 2, 2023 in Reston, Virginia. The IHTM 2.0 workshop focused on the need to support a multiscale framework to accelerate research insights, better integrate operational and planning perspectives, and bridge national-to-regional capabilities to address major interdependent societal water challenges. The workshop was organized according to a “WHAT” and “HOW” framework, with the common underlying “WHY” being the integrated water resource challenges and the “WHO” defined through interagency and cooperating academic partners. The report provides a summary of plenary presentations and breakout discussions, and a road map that focuses on near-term activities.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Exploring Black-box Adversarial Attacks on Low-rank Constrained Neural Networks

Low-rank compression has been shown as an effective tool to reduce parameter counts of convolutional and vision transformer architectures; however, low-rank training often reduces model robustness to adversarial perturbations. In this work, we explore the effects of low-rank training on black-box attacks, where attacked images are generated without knowledge of the low-rank parameters. We find that low-rank training is not sufficient as a black-box defense and can sometimes produce worse than expected as compared to baseline models. Influencing the spectrum of the low-rank models during training, which is known to increase model robustness against white-box attacks, improves black-box performance as well.

Schnake, Stefan [ORNL] (ORCID:0000000215183538)↗
DOE OSTI2024

FTL: Transfer Learning Nonlinear Plasma Dynamic Transitions in Low Dimensional Embeddings (FTL) v1.0

Fusion Transfer Learning (FTL) model provides a new paradigm to study high-dimensional dynamical behaviors, such as those in fusion plasma systems. The knowledge transfer process leverages a pre-trained neural encoder-decoder network, initially trained on linear simulations, to effectively capture nonlinear dynamics. The low-dimensional embeddings extract the coherent structures of interest, while preserving the inherent dynamics of the complex system. Experimental results highlight FTL's capacity to capture transitional behaviors and dynamical features in plasma dynamics -- a task often challenging for conventional methods. The model developed in this study is generalizable and can be extended broadly through transfer learning to address various magnetohydrodynamics (MHD) modes.

Bai, Zhe↗
DOE OSTI2025

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes (NLP). The complexity of EHR presents challenges in feature representation, information extraction, and uncertainty quantification. Here, to address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: Using data from 12.5 million Veterans Affairs patients, ARCH first derives embedding vectors and generates similarities along with associated p-values to measure the strength of relatedness between clinical features with statistical certainty quantification. Next, ARCH performs a sparse embedding regression to remove indirect linkage between features to build a sparse KG. Finally, ARCH was validated on various clinical tasks, including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer’s disease patients. Results: ARCH produces high-quality clinical embeddings and KG for over 60,000 codified and narrative EHR concepts. The KG and embeddings are visualized in the R-shiny powered web-API.3 ARCH achieved high accuracy in detecting EHR concept relationships, with AUCs of 0.926 (codified) and 0.861 (NLP) for similar EHR concepts, and 0.810 (codified) and 0.843 (NLP) for related pairs. It detected drug side effects with a 0.723 AUC, which improved to 0.826 after fine-tuning. Using both codified and NLP features, the detection power increased significantly. Compared to other methods, ARCH has superior accuracy and enhances weakly supervised phenotyping algorithms’ performance. Notably, it successfully categorized Alzheimer’s patients into two subgroups with varying mortality rates. Conclusion: The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

Electronic health records↗