Search NASA⌕ Search

SEARCH · Search NASA

Results for “Large Language Model”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

An Integrated Framework for Risk Assessment of Safety-related Digital Instrumentation and Control Systems in Nuclear Power Plants: Methodology Advancement and Application

This report documents activities performed by Idaho National Laboratory (INL) during fiscal year (FY) 2024 for the U.S. Department of Energy (DOE) Light Water Reactor Sustainability (LWRS) Program, Risk Informed Systems Analysis (RISA) Pathway, Digital Instrumentation and Control (DI&C) Risk Assessment project. The goal of the RISA Pathway is to optimize safety margins and minimize uncertainties to achieve economic efficiencies while maintaining high levels of safety. This is accomplished by providing scientific basis to better represent safety margins and factors that contribute to cost and safety, and by developing new technologies that reduce operating costs. The research efforts for FY 2024 encompass methodology refinement and exploration. The efforts include: (1) The implementation of a natural language processing tool to expedite key aspects of the reliability analysis methods developed by INL; (2) advances to support intersystem CCF analysis by providing guidance for and identification of coupling mechanisms that may contribute to CCF; (3) the investigation of how generative artificial intelligence tools can aid in hazard analysis and diversity and defense in depth (i.e., D3) assessments; (4) Industry collaboration, allowing the demonstration of and INL's risk assessment tools to support risk assessment of DI&C systems at early and late stages of development; (4) a roadmap for the development of a software for each of INL's risk assessment tools; (5) The development of a theory and methodology manual for a risk quantification methodology; (6) the development of a reliability analysis for machine learning (ML)-integrated control systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Solar and Battery Storage Permitting and Siting Requirements - Solar Prize Round 7 (CRADA Final Report)

The purpose of this research project was to aggregate zoning and permitting data for utility-scale solar PV and battery energy storage systems. The ultimate goal of this collaboration is to lower solar and battery energy storage system soft costs by streamlining regulatory due diligence and reducing the burden of conducting feasibility assessments for solar and storage systems. The below sections describe the specific research completed by NLR (the contractor) in furtherance of the agreement with Vanox (the participant).

14 SOLAR ENERGY↗
DOE OSTI2025

Heuristic Evaluation Methods Applied to a Predictive Maintenance Chatbot

The need for an accessible iterative approach for evaluating prospective artificial intelligence (AI)/ML based technologies in the nuclear industry is needed, given the nature of algorithms and rapid advancements. This paper explores existing heuristic design principles for user-centered design and evaluates them based on their relevancy and usefulness for evaluating AI/ ML based technologies. Researchers at the Idaho National Laboratory (INL) have developed a machine learning software application called VIsualization for PrEdictive maintenance Recommendation (VIPER), which is used to help users understand and engage with the tool to learn more about work orders, data used, predictive maintenance, and machine learning (ML) algorithms. Early user research studies used to access VIPER’s technology readiness level have occurred; however, there is room for further improvement of the software through heuristic evaluations along with other methods and user testing. This work describes the applicability of heuristic evaluation methods and cognitive walkthroughs to help ensure human readiness for prospective AI/ ML based applications, using VIPER as a candidate use case. This work supports industry in ensuring that prospective AI/ML based technologies are usable and useful for plant personnel at nuclear power plants, ultimately leading to their safe, reliable, and efficient use.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images

Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning. In this paper, we evaluate the effectiveness of 12 state-of-the-art (SOTA) VLMs in the field of organismal biology using a novel dataset, VLM4Bio, consisting of 469K question8 answer pairs involving 30K images from three groups of organisms: fishes, birds, and butterflies, covering five biologically relevant tasks. We also explore the effects of applying prompting techniques and tests for reasoning hallucination on the performance of VLMs, shedding new light on the capabilities of current SOTA VLMs in answering biologically relevant questions using images

Maruf, M [Virginia Tech, Blacksburg]↗
DOE OSTI2025

pnnl/SciTune

Scientific multimodal instruction tuning with large language and vision models.

Horawalavithana, Sameera [Pacific Northwest Nation↗
DOE OSTI2026

pas

PAS: Prelim Attention Score for Detecting Object Hallucinations in Large Vision-Language Models

Bhattarai, Manish↗
DOE OSTI2026

Foundation models for atomistic simulation of chemistry and materials

Conventional computational methods for modeling chemical and materials systems are limited by system size and timescale, forcing a trade-off between quantum-mechanical accuracy and the sampling needed for realistic observables. Large language and vision foundation models — pre-trained on massive datasets using transformer architectures — have revolutionized many fields. It is thus interesting to ask whether a foundation model — subject to suitable data, parameter scaling and training — could enable learned simulations of chemistry and materials. Here, in this study, we review the field of machine-learned interatomic potentials (MLIPs) and posit that scaling up large and diverse chemical and materials datasets and highly expressive architectures using advanced training strategies should result in models that are: more efficient, transferable, robust to out-of-distribution scenarios, and easier to fine-tune to a variety of downstream physical observables than models trained from scratch on small datasets corresponding to specific, targeted atomistic simulation tasks. We provide specific criteria for creating such large-scale MLIP foundation models, coordinated strategies for their development, evaluation and deployment, and highlight potential emergent capabilities that could transform predictive simulations in chemistry and materials science and accelerate discovery across multiple technological domains.

Yuan, Eric C.-Y. [University of California, Berkel↗
DOE OSTI2025

Chemical classification program synthesis using generative artificial intelligence

Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write chemical classifier programs for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators.

Artificial Intelligence↗
DOE OSTI2026

Genomic Language model for Annotation of Repetitive Elements (GLARE) v1.0

GLARE (Genomic Language model for Annotation of Repetitive Elements) is a tool that classifies transposable elements (TEs)—the mobile, repetitive DNA sequences that make up large fractions of eukaryotic genomes. GLARE fine-tunes the NTv3-650M genomic language model on a harmonized collection of curated TE sequences from the PanTEon and Repbase reference databases, assigning each input sequence to one of 11 orders and 32 superfamilies in a Wicker-compatible taxonomy. Features. From nucleotide FASTA input, GLARE outputs per-sequence predictions, class summaries, composition figures, and an annotated FASTA. It provides calibrated confidence scores with optional abstention and runs on CPU or GPU. Uses. GLARE serves as a classification component in genome-annotation pipelines, downstream of TE discovery, supporting genome annotation and comparative and evolutionary genomics. Advantages. GLARE is the first repeat-element classifier to leverage a pretrained genomic language model. Combined with multi-database training, this approach outperformed all nine classifiers in the PanTEon benchmark, generalized better to unseen taxonomic clades, and remained robust to sequence orientation—a common failure mode of existing tools.

Bruna, Tomas [Lawrence Berkeley National Laborator↗
DOE OSTI2026

Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator

We present a language-model-driven agentic artificial intelligence (AI) system to autonomously execute multistage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by 2 orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Accelerator/storage ring control systems↗
DOE OSTI2026

System-Level Integration of Modular Language Models for Real-Time Risk Assessment in Third-Party Risk Management Systems

Large enterprises typically rely on dedicated teams to govern and implement security measures throughout their supply chains, ensuring compliance with enterprise security procedures. There is a significant reliance on Third-Party Risk Management (TPRM) platforms, which often require complete, highly structured information from potential vendors. The review and compliance assurance processes are time- and labor intensive, often requiring several rounds of review between the supply chain security risk management teams, business users, and potential vendors, leading to delays in the supply chain processing and consumer experience. Significant challenges in the risk management paradigm include handling unstructured data in various formats and providing real-time feedback to users to reduce the required review time. This paper presents a novel solution to these challenges. A modular multi-step system architecture is proposed using advances in language processing, specifically for unstructured responses and provides real-time feedback (i.e., 3 seconds) so that users can improve their responses before the TPSRM team review. This novel system architecture will increase information accuracy and significantly reduce time and labor during the review process.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

A case study in contrastive learning information combination: Application to technical forensics of additive manufacturing filament source identification

Combination of information from disparate data sources into a single decision is a core challenge in many fields, including the field of technical forensics. Technical forensics (TF) utilizes technical characterization of questioned samples to determine properties of that sample; these properties are then used to infer information of forensic interest, such as provenance, age, or attribution. TF is utilized in traditional forensic applications, such as the attribution of material fragments from an explosive, and in nuclear forensic applications, such as the attribution of actinides which have been interdicted out of regulatory control. The challenge of combining information from disparate sources, described alternately by many terms including “Data Fusion” and “Data Integration”, is exacerbated in the technical forensics domain due to at least two factors: the challenge of interpreting each information source singularly, and the relatively small data set sizes available. Extensive literature exists attempting to combine technical forensics information sources, both in manual and automated processes. These attempts are often bespoke to the specific information sources (such as the bi-, tri-, or quad-isotope chart (Moody, Grant, and Hutcheon 2005)), with some emerging examples of simple early- and late- fusion (, respectively). Simultaneous to the information combination efforts described in the previous paragraph, the field of natural language processing attempted (and largely succeeded) in combining information from multiple non-technical information sources. The ecosystem of “multi-modal” language models, which can take text and images as input, and generate text and images as output, became large and diverse by 2025 (Khan et al. 2025). In a generalized sense, many of these methods are trained by learning neural networks which can convert raw text or images into a vector of numbers describing the text or image, hereafter called “embeddings” and the neural networks performing the conversion are called “embedders”. By using a separate embedder for text and images, finding coincident text and images (such as images with their captions), and optimizing the parameters of the embedders such that the embeddings for the text and the image are similar, the field has found a bridge between text and images (Girdhar et al. 2023). It is the contention of the authors of this report that this insight is not limited to text and images but instead can be extended to any modality which can be found coincidently. The subject of the rest of this report is the application of this method to example multi-modal technical forensic data. Some details about the data used in this report are not appropriate for this report, and are included in a companion report (PNNL-38669).

36 MATERIALS SCIENCE↗
DOE OSTI2024

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗
DOE OSTI2025

Autogenerating a Domain-Specific Question-Answering Data Set from a Thermoelectric Materials Database to Enable High-Performing BERT Models

We present a method for autogenerating a large domain-specific question-answering (QA) dataset from a thermoelectric materials database. We show that a small language model, BERT, once fine-tuned on this automatically generated dataset of 99,757 QA pairs about thermoelectric materials, affords better performance in the field of thermoelectric materials compared to a BERT model fine-tuned on the generic English-language QA data set, SQuAD-v2. We further show that mixing the two data sets (ours and SQuAD-v2), which have significantly different syntactic and semantic scopes, allows the BERT model to achieve even better performance. The best-performing BERT model fine-tuned on the mixed data set outperforms the models fine-tuned on the other two data sets by scoring an exact match of 67.93% and an F1 score of 72.29% when evaluated on our test data set. This has important implications as it demonstrates the ability to realize high-performing small language models, with modest computational resources, empowered by domain-specific materials data sets which can be generated according to our method.

biological databases↗
DOE OSTI2024

Dynamic Model of Back-to-Back Converter for System Level Phasor Simulation

The power system is expected to evolve rapidly with increasing deployment of power electronic interface and conditioning systems, microgrids, and hybrid AC/DC grids. Among power electronic systems, back-to-back (BTB) converters can be a powerful interface to integrate microgrids and networked microgrids. However, in system level dynamic simulations for synchronous machine dominated system with BTB converters, a detailed electromagnetic sinusoidal models is not warranted as these simulations are focused on electromechanical transients. This paper focus on developing a simple phasor model for back- to-back converters that can be easily integrated into powerflow solvers to facilitate large-scale power system simulations. The model is implemented using C++ language and integrated into GridLAB-D software as a potential new capability. The GridLAB-D phasor domain model is validated against the electromagnetic transient (EMT) simulation of the detailed switching model. Simulation results show that the phasor model successfully captures the dominant dynamics of the converters.

Mahmood, Hisham↗