Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “GPT”

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 OSTI2026

ChemGraph as an agentic framework for computational chemistry workflows

Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered by artificial intelligence and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows. ChemGraph leverages graph neural network-based foundation models for accurate yet computationally efficient calculations and large language models (LLMs) for natural language understanding, task planning, and scientific reasoning to provide an intuitive and interactive interface. We evaluate ChemGraph across 13 benchmark tasks and demonstrate that smaller LLMs (GPT-4o-mini, Claude-3.5-haiku, Qwen-2.5-14B) perform well on simple workflows, while more complex tasks benefit from using larger models. Importantly, we show that decomposing complex tasks into smaller subtasks through a multi-agent framework enables GPT-4o to reach perfect accuracy and smaller LLMs to match or exceed single-agent GPT-4o's performance in these benchmarks.

Computational chemistry↗
DOE OSTI2026

The ballad of LLM agents: philosophical reasoning for chemistry

Large language models (LLMs) show remarkable potential for scientific reasoning but often produce unreliable or scientifically unactionable outputs when faced with multi-step logic, domain grounding, and interpretability challenges, especially in complex fields like chemistry and materials science. Here, we introduce a framework of philosophical reasoning agents, inspired by canonical thinkers such as Socrates, Descartes, Kant, and Hume, to guide LLM behavior via structured prompt engineering. These agents embody distinct reasoning paradigms (dialectical inquiry, deductive logic, rule-based judgment, and empirical validation) and are evaluated across multiple chemistry subdomains, physical, analytical, general, inorganic, and organic chemistry, using the ChemBench benchmark. Our agentic prompting approach yields substantial accuracy gains on open-ended numerical chemistry questions, with gains of +11.5 percentage points for GPT-4o with Hume, +4.5 percentage points for GPT-5 with Kant, and +21.8 percentage points for GPT-5.1 with Socrates at the strict 1% error threshold, relative to the corresponding base models. Beyond accuracy, we observe benchmark-level model–agent performance patterns, suggesting that different prompting styles interact differently with each base model. These findings demonstrate that embedding philosophy-of-science principles into multi-agent frameworks can improve and produce interpretable, adaptive, and domain-aligned scientific LLMs.

Harb, Hassan [Argonne National Laboratory (ANL), A↗
DOE OSTI2024

Comparative Study of Large Language Model Architectures on Frontier

Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.

Yin, Junqi↗
DOE OSTI2025

Intelligent Manufacturing Support: Specialized LLMs for Composite Material Processing and Equipment Operation

Engineering educational curriculum and standards cover many material and manufacturing options. However, engineers and designers are often unfamiliar with certain composite materials or manufacturing techniques. Large language models (LLMs) could potentially bridge the gap. Their capacity to store and retrieve data from large databases provides them with a breadth of knowledge across disciplines. However, their generalized knowledge base can lack targeted, industry-specific knowledge. To this end, we present two LLM-based applications based on the GPT-4 architecture: (1) The Composites Guide: a system that provides expert knowledge on composites material and connects users with research and industry professionals who can provide additional support and (2) The Equipment Assistant: a system that provides guidance for manufacturing tool operation and material characterization. By combining the knowledge of general AI models with industry-specific knowledge, both applications are intended to provide more meaningful information for engineers. In this paper, we discuss the development of the applications and evaluate it through a benchmark and two informal user studies. The benchmark analysis uses the Rouge and Bertscore metrics to evaluate our models’ performance against GPT-4o. The results show that GPT-4o and the proposed models perform similarly or better on the ROUGE and BERTScore metrics. The two user studies supplement this quantitative evaluation by asking experts to provide qualitative and open-ended feedback about our model’s performance on a set of domain-specific questions. The results of both studies highlight a potential for more detailed and specific responses with the Composites Guide and the Equipment Assistant.

Kapoor, Gunnika [Oak Ridge National Laboratory (OR↗
DOE OSTI2024

Modelling Beam Loss Within the LANSCE Proton Storage Ring

Several upgrades are being considered for the proton storage ring (PSR) at the Los Alamos Neutron Science Center (LANSCE) to reduce beam loss and thereby reduce the cooldown period of the PSR following a beam run. First, we have considered an increased beam pipe diameter would reduce beam loss due to beam scraping caused by misalignments and tuning errors. However, this would require increased pole-to-pole gap height within the dipoles and quadrupoles, which would change their effective length and alter their fringe fields. The effect of different magnet gaps on the beam optical parameters and on beam loss was studied using the simulation codes MAD-X and PyORBIT. Second, we are developing a detailed particle tracking model within the framework of the simulation package General Particle Tracer (GPT) for the PSR H - stripping system. This model will be used to study the effect of the stripper foil parameters (position, composition, areal density, depth, etc.) on first-turn losses, where most of the observed beam loss and emittance growth occurs due to foil scattering, foil stripping, and Lorentz stripping. The model implements C++ custom elements created to model foil scattering, foil stripping, and Lorentz stripping, as these are not built-in features of GPT. The preliminary results of the MAD-X and PyORBIT simulations, as well as the GPT simulation model, is described in this tech note.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

U.S. Solar Siting Regulation and Zoning Ordinances (2025)

A machine readable collection of documented solar siting ordinances at the state and local (e.g., county, township) level throughout the United States. The data were compiled using the Infrastructure Continuous Ordinance Mapping for Planning and Siting Systems (INFRA-COMPASS) tool, which leverages Large Language Models (LLMs) to automate the collection of local codes and ordinances applicable to energy infrastructure. URLs for the ordinance source documents are included in the Solar Ordinances spreadsheet. The GeoPackage file included below contains the jurisdiction shapes for each ordinance. Note that the GeoPackage file is formatted for ingestion by NLR's reVX setbacks tool and therefore does not contain any of the state-level regulations. NOTE: This data was collected with the help of generative AI. The Large Language Models used for this effort make mistakes. Always validate the data for critical use cases. This data is an update to a previously developed database of wind ordinances found in OEDI Submission 5734: see the "U.S. Solar Siting Regulation and Zoning Ordinances 2022" link below. INFRA-COMPASS version used for collection: v0.11.3 LLMs used for collection: GPT-4.1, GPT-4.1 mini, GPT-4.1 nano

14 SOLAR ENERGY↗
NASA NTRS1976

Comparison of ozone determinations by ultraviolet photometry and gas-phase titration

A comparison of ozone determinations based on ultraviolet absorption photometry and gas-phase titration (GPT) shows good agreement between the two methods. Together with other results, these findings indicate that three candidate reference methods for ozone, UV photometry, IR photometry, and GPT are in substantial agreement. However, the GPT method is not recommended for routine use by air pollution agencies for calibration of ozone monitors because of susceptibility to experimental error.

Demore, W. B.↗
DOE OSTI2017

Sensitivity Coefficients for Diffusion Coefficients and Other Reactor Physics Parameters using CE TSUNAMI-3D

The TSUNAMI (Tools for Sensitivity and Uncertainty Analysis Methodology Implementation) capabilities within the SCALE code system leverage sensitivity coefficients for many criticality safety applications, including quantifying the data-induced uncertainty in the eigenvalue of critical systems, quantifying computational biases, and selecting applicable benchmark experiments. TSUNAMI sensitivity and uncertainty analysis tools have traditionally been limited to criticality safety application spaces, but the introduction of Generalized Perturbation Theory (GPT) sensitivity methods by Jessee in 2009 and Perfetti in 2013 has extended the scope of SCALE adjoint-weighted sensitivity and uncertainty analysis to include reactor physics applications. The continuous-energy (CE) TSUNAMI-3D GPT sensitivity analysis methods were originally developed to calculate sensitivity coefficients for a limited number of reaction-rate responses using CE Monte Carlo methods. These tools were recently applied in an Oak Ridge National Laboratory (ORNL)-directed research and development project to improve the efficiency of {sup 252}Cf production in the High Flux Isotope Reactor (HFIR) by understanding the sensitivity of key heavy actinide capture-to- fission ratios to potential system design changes. This work further extends the applicability of the CE TSUNAMI- 3D GPT methods to reactor physics applications by enabling the calculation of sensitivity coefficients for an expanded set of reaction rate responses-including a first-ever capability for conducting sensitivity analysis of neutron diffusion coefficients.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2025

ON THE EFFECTIVENESS OF LLMS IN UNIT TEST GENERATION FOR STRUCTURED TEXT PROGRAMS

The reliability of industrial automation systems heavily depends on the correctness of Programmable Logic Controller (PLC) programs, which are often written in Structured Text (ST). While Large Language Models (LLMs) have shown promise in automating test generation for mainstream programming languages, their effectiveness for the syntactically strict ST language remains underexplored. This thesis presents a systematic empirical evaluation of three state-of-the-art LLMs—GPT-4o, Gemini 2.5 Pro, and Claude Sonnet 4.5—for generating ST unit tests. We examine three prompting strategies: Natural Language (NL), Code Language (CL), and Chain-of-Thought (CoT), across a curated set of 11 ST function blocks. The quality of the generated tests is assessed using Compilation Success Rate (CSR), Statement Coverage (SC), and Branch Coverage (BC). In the zero-shot setting, Claude Sonnet 4.5 achieves the highest CSR, while Gemini 2.5 Pro consistently delivers the best statement and branch coverage, particularly under CL prompts. By incorporating a one-shot CL prompt, all models exhibit substantial improvements—most notably GPT-4o, whose CSR increases from 45.45% to 90.91%, with substantial gains in both SC and BC. To further contextualize these findings, we compare GPT-4o’s one-shot results with PLCAutoTester, a state-ofthe- art ST unit test generation tool, on an additional benchmark dataset. While LLMgenerated tests approach competitive coverage levels, PLCAutoTester maintains significantly higher and more stable coverage across programs. This study provides the first comprehensive benchmark of modern LLMs for ST unit testing, highlighting their strengths, limitations, and improvements through one-shot prompting, and positioning their performance relative to specialized automated testing tools in industrial automation.

42 ENGINEERING↗
DOE OSTI2024

Large language model evaluation for high–performance computing software development

We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Text Mining for Process–Structure–Properties Relationships in Metals

With the advent of large language models (LLMs), the vast unstructured text within millions of academic papers is increasingly accessible for materials discovery—although significant challenges remain. While LLMs offer promising few- and zero-shot learning capabilities, particularly valuable in the materials domain where expert annotations are scarce, general-purpose LLMs often fail to address key materials-specific queries without further adaptation. To bridge this gap, fine-tuning LLMs on human-labeled data is essential for effective structured knowledge extraction (Liu in The Importance of Human-Labeled Data in the Era of LLMs, 2023). Here, in this study, we introduce a novel annotation schema designed to extract generic process–structure–properties relationships from scientific literature. We demonstrate the utility of this approach using a dataset of 128 abstracts, with annotations drawn from two distinct domains: high-temperature materials (Domain I) and uncertainty quantification in simulating materials microstructure (Domain II). Initially, we developed a conditional random field (CRF) model based on MatBERT—a domain-specific BERT variant—and evaluated its performance on Domain I. Subsequently, we compared this model with a fine-tuned LLM (GPT-4o from OpenAI) under identical conditions. Our results indicate that fine-tuning LLMs can significantly improve entity extraction performance over the BERT-CRF baseline on Domain I. However, when additional examples from Domain II were incorporated, the performance of the BERT-CRF model became comparable to that of the GPT-4o model. These findings underscore the potential of our schema for structured knowledge extraction and highlight the complementary strengths of both modeling approaches.

Materials science↗
DOE OSTI2025

Simulation study of high-current 7 Li 3+ beam acceleration with laser ion source and RFQ linac using direct plasma injection

Accelerator-based neutron sources (ABNS) utilizing the 7 Li(p,n) 7 Be reaction in inverse kinematics offer strong forward-directed neutron emission, making them attractive for compact and clean neutron source with low background neutrons and unwanted radiation. However, practical use of such systems requires lithium ion beam currents that exceed the capability of conventional ion accelerators by two orders of magnitude. In this study, we numerically designed and evaluated a high-current acceleration system based on a direct plasma injection scheme (DPIS), combining a laser ion source (LIS) and a radio-frequency quadrupole (RFQ) linac. The ion extraction optics and RFQ entrance were optimized using IGUN, OPERA, and GPT, demonstrating that over 1.2 A-class beam current can be injected into the RFQ. The RFQ structure was designed under realistic engineering constraints including surface field strength (Kilpatrick factor) and RF power. GPT simulations showed that a 370 mA 7 Li 3+ beam can be successfully accelerated within a ±10 % energy spread. To validate downstream compatibility, we also designed a simplified medium-energy beam transport (MEBT) section and an interdigital H-type (IH) linac, confirming successful acceleration of a 320 mA beam to the total energy of 14 MeV. These results support the feasibility of the DPIS and RFQ approach as a promising solution for compact neutron sources and other high-intensity ion beam applications.

43 PARTICLE ACCELERATORS↗
DOE OSTI2015

The progression from a lower to a higher invasive stage of bladder cancer is associated with severe alterations in glucose and pyruvate metabolism

Cancer cells present a particular metabolic behavior. We hypothesized that the progression of bladder cancer could be accompanied by changes in cells glycolytic profile. We studied two human bladder cancer cells, RT4 and TCCSUP, in which the latter represents a more invasive stage. The levels of glucose, pyruvate, alanine and lactate in the extracellular media were measured by Proton Nuclear Magnetic Resonance. The protein expression levels of glucose transporters 1 (GLUT1) and 3 (GLUT3), monocarboxylate transporter 4 (MCT4), phosphofructokinase-1 (PFK1), glutamic-pyruvate transaminase (GPT) and lactate dehydrogenase (LDH) were determined. Our data showed that glucose consumption and GLUT3 levels were similar in both cell lines, but TCCSUP cells displayed lower levels of GLUT1 and PFK expression. An increase in pyruvate consumption, concordant with the higher levels of lactate and alanine production, was also detected in TCCSUP cells. Moreover, TCCSUP cells presented lower protein expression levels of GPT and LDH. These results illustrate that bladder cancer progression is associated with alterations in cells glycolytic profile, namely the switch from glucose to pyruvate consumption in the more aggressive stage. This may be useful to develop new therapies and to identify biomarkers for cancer progression. - Highlights: • Metabolic phenotype of less and high invasive bladder cancer cells was studied. • Bladder cancer progression involves alterations in cells glycolytic profile. • More invasive bladder cancer cells switch from glucose to pyruvate consumption. • Our results may help to identify metabolic biomarkers of bladder cancer progression.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

Parameters estimation using the first passage times method in a jump-diffusion model

The main purposes of this paper are two contributions: (1) it presents a new method, which is the first passage time (FPT method) generalized for all passage times (GPT method), in order to estimate the parameters of stochastic Jump-Diffusion process. (2) it compares in a time series model, share price of gold, the empirical results of the estimation and forecasts obtained with the GPT method and those obtained by the moments method and the FPT method applied to the Merton Jump-Diffusion (MJD) model.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

FEgen (v.1): Field Emission Distribution Generator Freeware Based on Fowler–Nordheim Equation

This work presents an open-source code, FEgen, that generates initial field emission distributions based on the time-dependent Fowler–Nordheim equation. Current in-demand and open-source beam tracking software—such as ASTRA, IMPACT-T, and GPT—do not contain native distribution generator functions suitable for field emitted electron tracking and phase space analysis. Furthermore, the intuitive graphical user interface of FEgen generates input files shown to be fully compatible with both ASTRA and GPT. Here, detailed application examples demonstrating a subset of FEgen’s capabilities are given by creating a customized emitter pattern with application to transverse beam shaping and longitudinal beam dynamic experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2021

Improving the Operational Lifetime of the CEBAF Photo-Gun by Anode Biasing

The operating lifetime of GaAs-based photocathodes in DC high voltage electron photo-guns is dominated by the ionization rate of residual beamline gas molecules. In this work, experiments were performed to quantify the improvement in photocathode charge lifetime by biasing the photo-gun anode with a positive voltage, which repels ions generated downstream of the anode. The photo-cathode charge lifetime improved by almost a factor of two when the anode was biased compared to the usual grounded configuration. Simulations were performed using the particle tracking code General Particle Tracer (GPT) with a new custom element. The simulation results showed that both the number and energy of ions play a role in the pattern of QE degradation. The experiment results and conclusions supported by GPT simulations will be presented.

Yoskowitz, J. T.↗
DOE OSTI2022

(U) SENSMG: First-Order Sensitivities of Neutron Reaction Rates, Reaction-Rate Ratios, Leakage, k eff , α , and Subcritical Multiplication Using PARTISN

SENSMG is a tool for computing first-order sensitivities of neutron reaction rates, reaction-rate ratios, leakage, k eff , α, and subcritical multiplication using the PARTISN multigroup discrete-ordinates code. SENSMG computes sensitivities to all of the transport cross sections and data (total, fission, a nu, chi, and all scattering moments), two edit cross sections (absorption and capture), and the density for every nuclide and energy group. It also computes sensitivities to the mass density for every material and derivatives with respect to all interface locations and outer boundaries. It computes sensitivities to user specified reactions whose cross sections are available in a user-supplied NJOY output file. The tool can be used for one-dimensional spherical and slab (r) and two-dimensional cylindrical (r-z) geometries. The tool can be used for fixed-source and eigenvalue problems. For most responses, the tool implements Generalized Perturbation Theory (GPT) as discussed by Williams and Stacey. The tool is thus limited to computing sensitivities only for GPT-allowable responses. For subcritical multiplication, the tool implements sensitivities derived by O’Brien and Clark. SENSMG has a similar role as the old SWANLAKE (Ref. 8), FORSS (Ref. 9), and SENSIT (Ref. 10) codes. It has capabilities similar to those of SUSD3D (Refs. 11 and 12), which also uses PARTISN. Section II of this report describes the theory behind adjoint-based sensitivities, gives the equations that SENSMG solves, and defines the sensitivities that are output. Section III describes the user interface, including the input file and command line options. Section IV describes the output. Section V gives some notes about the coding that may be of interest. Section VI presents some sample problems and discusses verification, which is ongoing. Section VII lists needs and ideas for future work. Appendix A lists most of the input files whose results are presented in Sec. VI. Appendix B provides some useful details on one of the cross-section libraries that SENSMG supports.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗