Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ChatGPT”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

ChatBLAS: The First AI-Generated and Portable BLAS Library

We present ChatBLAS, the first AI-generated and portable Basic Linear Algebra Subprograms (BLAS) library on different CPU/GPU configurations. The purpose of this study is (i) to evaluate the capabilities of current large language models (LLMs) to generate a portable and HPC library for BLAS operations and (ii) to define the fundamental practices and criteria to interact with LLMs for HPC targets to elevate the trustworthiness and performance levels of the AI-generated HPC codes. The generated C/C++ codes must be highly optimized using device-specific solutions to reach high levels of performance. Additionally, these codes are very algorithm-dependent, thereby adding an extra dimension of complexity to this study. We used OpenAI’s LLM ChatGPT and focused on vector-vector BLAS level-1 operations. ChatBLAS can generate functional and correct codes, achieving high-trustworthiness levels, and can compete or even provide better performance against vendor libraries.

Valero Lara, Pedro↗
DOE OSTI2025

Chatbots can guide experimentalists to avoid many common mistakes in measuring fluorescence spectra

The concepts of fluorescence spectroscopy are well established, yet the experimental collection of a spectrum is susceptible to a range of errors. A recent study showed that chatbots – derived from substantial advances in artificial intelligence – can provide practical assistance to the experimentalist during collection of absorption spectra and thereby achieve improved quality. Fluorescence, while the complement of absorption, is prone to a far richer array of experimental errors encompassing environmental factors, instrumental settings, and experimentalist mistakes. Here, 10 chatbots (ChatGPT 5, Gemini 2.5 Pro, Microsoft Copilot, Meta AI Llama 4, Claude Sonnet 4.5, X.ai Grok 4, Perplexity Pro, DeepSeek V3.1, Z.ai GLM-4.6, and KIMI K2) have been evaluated for the suitability in providing quality-improvement advice to the experimentalist during acquisition of fluorescence spectra. Significant opportunities for practical assistance are noted, although intervention by a domain expert is often required. Here, if combined with image recognition and/or signal processing, chatbots embedded in instruments may enable real-time guidance during fluorescence data acquisition.

Artificial intelligence↗
DOE OSTI2025

Using AI tools to analyze periodic phenomena

Here, in this report, we describe how students can use natural language to prompt ChatGPT to conduct the analysis of complex periodic acceleration data collected using their smartphones. Students may use this approach to characterize human physiological tremor frequency. Students can choose to use their own data, or, for privacy purposes, use an anonymized set of data provided to them.

Klay, Jennifer L. [California Polytechnic State Un↗
DOE OSTI2025

ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem

ChatHPC democratizes large language models for the high-performance computing (HPC) community by providing the infrastructure, ecosystem, and knowledge needed to apply modern generative AI technologies to rapidly create specific capabilities for critical HPC components while using relatively modest computational resources. Our divide-and-conquer approach focuses on creating a collection of reliable, highly specialized, and optimized AI assistants for HPC based on the cost-effective and fast Code Llama fine-tuning processes and expert supervision. We target major components of the HPC software stack, including programming models, runtimes, I/O, tooling, and math libraries. Thanks to AI, ChatHPC provides a more productive HPC ecosystem by boosting important tasks related to portability, parallelization, optimization, scalability, and instrumentation, among others. With relatively small datasets (on the order of KB), the AI assistants, which are created in a few minutes by using one node with two NVIDIA H100 GPUs and the ChatHPC library, can create new capabilities with Meta’s 7-billion parameter Code Llama base model to produce high-quality software with a level of trustworthiness of up to 90% higher than the 1.8-trillion parameter OpenAI ChatGPT-4o model for critical programming tasks in the HPC software stack.

Young, Aaron [ORNL] (ORCID:0000000254484667)↗
DOE OSTI2025

Prompt-Based Development of Domain-Specific Taxonomies

Framework for interacting with prompt-based LLMs (Large Language Models such as, but not limited to, ChatGPT) in order to develop domain specific taxonomies. The software itself is a series of prompts designed to extract hierarchical taxonomy categories from an LLM, as well as guidelines for how to fine-tune LLMs in order to provide better domain-specific taxonomic categories.

Grundy, Jon [Pacific Northwest National Laboratory↗
DOE OSTI2024

AI Design Assistant

SAND2025-01930O The AI Design Assistant uses ChatGPT to provide a natural language interface to airfoil analysis tools (XFOIL). Most of the code base is glue code, connecting XFOIL (a tool for analyzing airfoils) to the OpenAI interface. Among the more novel features are an airfoil geometry class and methods on how to extract detailed data from XFOIL. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Karcher, Cody↗
DOE OSTI2024

An evaluation of GPT models for phenotype concept recognition

Clinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field. These processes rely on using ontology concepts, often from the Human Phenotype Ontology, in conjunction with a phenotype concept recognition task (supported usually by machine learning methods) to curate patient profiles or existing scientific literature. With the significant shift in the use of large language models (LLMs) for most NLP tasks, we examine the performance of the latest Generative Pre-trained Transformer (GPT) models underpinning ChatGPT as a foundation for the tasks of clinical phenotyping and phenotype annotation. The experimental setup of the study included seven prompts of various levels of specificity, two GPT models (gpt-3.5-turbo and gpt-4.0) and two established gold standard corpora for phenotype recognition, one consisting of publication abstracts and the other clinical observations. The best run, using in-context learning, achieved 0.58 document-level F1 score on publication abstracts and 0.75 document-level F1 score on clinical observations, as well as a mention-level F1 score of 0.7, which surpasses the current best in class tool. Without in-context learning, however, performance is significantly below the existing approaches. Our experiments show that gpt-4.0 surpasses the state of the art performance if the task is constrained to a subset of the target ontology where there is prior knowledge of the terms that are expected to be matched. While the results are promising, the non-deterministic nature of the outcomes, the high cost and the lack of concordance between different runs using the same prompt and input make the use of these LLMs challenging for this particular task.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Enabling AI in synthetic biology through Construction File specification

The Construction File (CF) specification establishes a standardized interface for molecular biology operations, laying a foundation for automation and enhanced efficiency in experiment design. It is implemented across three distinct software projects: PyDNA_CF_Simulator, a Python project featuring a ChatGPT plugin for interactive parsing and simulating experiments; ConstructionFileSimulator, a field-tested Java project that showcases 'Experiment' objects expressed as flat files; and C6-Tools, a JavaScript project integrated with Google Sheets via Apps Script, providing a user-friendly interface for authoring and simulation of CF. The CF specification not only standardizes and modularizes molecular biology operations but also promotes collaboration, automation, and reuse, significantly reducing potential errors. The potential integration of CF with artificial intelligence, particularly GPT-4, suggests innovative automation strategies for synthetic biology. While challenges such as token limits, data storage, and biosecurity remain, proposed solutions promise a way forward in harnessing AI for experiment design. This shift from human-driven design to AI-assisted workflows, steered by high-level objectives, charts a potential future path in synthetic biology, envisioning an environment where complexities are managed more effectively.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

MyCrunchGPT: A LLM Assisted Framework for Scientific Machine Learning

Scientific machine learning (SciML) has advanced recently across many different areas in computational science and engineering. Here, the objective is to integrate data and physics seamlessly without the need of employing elaborate and computationally taxing data assimilation schemes. However, preprocessing, problem formulation, code generation, postprocessing, and analysis are still time- consuming and may prevent SciML from wide applicability in industrial applications and in digital twin frameworks. Here, we integrate the various stages of SciML under the umbrella of ChatGPT, to formulate MyCrunchGPT, which plays the role of a conductor orchestrating the entire workflow of SciML based on simple prompts by the user. Specifically, we present two examples that demonstrate the potential use of MyCrunchGPT in optimizing airfoils in aerodynamics, and in obtaining flow fields in various geometries in interactive mode, with emphasis on the validation stage. To demonstrate the flow of the MyCrunchGPT, and create an infrastructure that can facilitate a broader vision, we built a web app based guided user interface, that includes options for a comprehensive summary report. The overall objective is to extend MyCrunchGPT to handle diverse problems in computational mechanics, design, optimization and controls, and general scientific computing tasks involved in SciML, hence using it as a research assistant tool but also as an educational tool. While here the examples focus on fluid mechanics, future versions will target solid mechanics and materials science, geophysics, systems biology, and bioinformatics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

LLM integration into EPICS

The utilization of large language models (LLMs) such as ChatGPT has seen a remarkable increase in various fields over the past few years. These models have demonstrated their versatility and capability in understanding and generating human-like text, making them invaluable tools in numerous applications. In this project, we explore the integration of a LLM into the Experimental Physics and Industrial Control System (EPICS). The primary focus of this integration is to employ the LLM for advanced image processing and spatial analysis on images obtained from the beamlines. By leveraging the capabilities of the LLM, we aim to enhance the accuracy and efficiency of image interpretation, enabling more precise data analysis and decision-making within the EPICS framework. This integration not only showcases the potential of LLMs in scientific and industrial applications but also sets the stage for future advancements in automated control systems.

Adams, Ethan↗
DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗
DOE OSTI2023

A Collaboration Website for Muon Catalyzed Fusion and Muon Beam Production

This project sets up a website to support the nascent Muon Catalyzed Fusion collaboration including development of particle accelerators and transport beamlines for muon beams. The website is envisioned as having the general public information pages and private pages for collaboration members. Multimedia elements like images, text animations, and video lectures, covering a broad spectrum of topics will populate the educational site, covering muon facilities, to comprehensive explorations and seminal documents that define the science of Muon Catalyzed Fusion, Acceleration, Applications, Instrumentation, Beamline Design, and beam dynamics design codes. Ensuring compatibility across devices and operating systems, it also features integration with Google Docs for collaboration, a code repository (GitHub), a blog platform with comments (WordPress), the potential for ChatGPT integration and interactive graph plotting with Python Plotty to enhance data visualization. This project will maintain public and protected private pages, due to the proprietary nature of the work or research in progress. The public sections will be built to foster dissemination of information and highlight recent work within the NK Labs collaboration, including lectures, published papers, and regular blog posts with open commenting. The private section will support unpublished or nonpublic research, by facilitating collaborative efforts through integrated Google Docs and Python Plotty for shared graphing work. Ultimately, this project strives to make complex scientific knowledge more accessible to the public, foster enhanced collaboration, and serve as a platform for sharing cutting-edge research in Muon Catalyzed Fusion and Accelerators.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Assessing the nature of large language models: A caution against anthropocentrism.

Generative AI models garnered a large amount of public attention and speculation with the release of OpenAI’s chatbot, ChatGPT in November of 2022. At least two opinion camps exist – one that is excited about the possibilities these models offer for fundamental changes to human tasks, and another that is highly concerned about the power these models seem to have – especially since the release of GPT-4, which was trained on multimodal data and has ~1.7 trillion (T) parameters. We evaluated some concerns regarding these models’ power by assessing GPT-3.5 using standard, normed, and validated cognitive and personality measures. These measures come from the tradition of psychometrics in experimental psychology and have a long history of providing valuable insights and predictive distinctions in humans. For this seedling project, we developed a battery of tests that allowed us to estimate the boundaries of some of these models’ capabilities, how stable those capabilities are over a short period of time, and how they compare to humans.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Assessing the nature of large language models: A caution against anthropocentrism

Generative AI models garnered a large amount of public attention and speculation with the release of OpenAI’s chatbot, ChatGPT in November of 2022. At least two opinion camps exist – one that is excited about the possibilities these models offer for fundamental changes to human tasks, and another that is highly concerned about the power these models seem to have – especially since the release of GPT-4, which was trained on multimodal data and has ~1.7 trillion (T) parameters. We evaluated some concerns regarding these models’ power by assessing GPT 3.5 using standard, normed, and validated cognitive and personality measures. These measures come from the tradition of psychometrics in experimental psychology and have a long history of providing valuable insights and predictive distinctions in humans. For this seedling project, we developed a battery of tests that allowed us to estimate the boundaries of some of these models’ capabilities, how stable those capabilities are over a short period of time, and how they compare to humans.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Future of End-User Support

IT Service Management (ITSM) is an inimitable, ever-changing practice that is critical to all far-reaching organizations, including Sandia National Laboratories. With recent developments in technology and society – spurred by major events like the advent of ChatGPT and the pandemic – it is as important as ever to consider the implications and opportunities for ITSM. This report strategically synthesizes existing information about ITSM structures and examines the current state of Sandia’s service management entity: CCHD. Then, it looks at the emerging state of the world, culminating in CCHD-tailored recommendations for continual service improvement (CSI). Ultimately, the biggest matters to address are staff tenure, ticket documentation, and self-service facilitation. The next step might be to introduce AI to service channels in a non-system-invasive manner, namely a chatbot on the main CCHD page. All would serve to enhance end-user experiences, and by proxy Sandia’s output.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Artificial Intelligence for Climate Change Mitigation Roadmap (Second Edition)

The first ICEF Artificial Intelligence for Climate Change Mitigation Roadmap was released in December 2023. Since that time, attention to artificial intelligence (AI) has continued to grow at a rapid pace. Tens of billions of dollars have poured into AI projects, policymakers around the world have considered new AI policies, and OpenAI reports that each month more than 200 million people now use ChatGPT. Signs of a changing climate continue to grow as well. Based on global average temperatures, July 22, 2024 was the warmest day ever recorded; 2023 was the warmest year ever recorded; and the 10 warmest years on record are the past 10 years. Yet global emissions of greenhouse gases continue to climb. Can AI help cut emissions of greenhouse gases? This Roadmap explores that question. In this second edition of the Artificial Intelligence for Climate Change Mitigation Roadmap, a team of 25 co-authors builds on last year’s roadmap—comprehensively updating all old chapters, adding six new chapters and offering 5–10 specific, actionable recommendations in each chapter. Our goal is to provide a useful resource for experts and non-experts alike. In Part I of this Roadmap, we provide brief introductions to both AI and climate change. In Part II, we explore eight sectors in which AI is helping respond to climate change and could do much more. In Part III, we explore crosscutting issues. We close with findings and recommendations.

54 ENVIRONMENTAL SCIENCES↗