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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
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↗
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 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 OSTI2024

LUCID Thrust 1 - Dataset Identification and Biodata Catalog Creation

The LUCID DOE consortium, part of the Department of Energy’s Biological and Environmental Research (BER) program, advances Low Dose Radiation (LDR) research through multidisciplinary efforts across seven key thrusts. This document focuses on Thrust 1, which centers on the creation of curated multimodal population health datasets and supports broader efforts within the LUCID program, including AI-based hypothesis generation, experimental design, and the study of LDR-induced health risks. Specifically, it describes the identification and cataloging of Thrust 1’s curated LDR datasets and biodata, emphasizing their critical role in supporting various research thrusts within the consortium, with potential applications in healthcare and public policy. In addition, the document includes an evaluation of three Large Language Models (LLMs)—GPT-4, SOLAR-10B, and Mixtral-8x7B—based on their ability to extract features from 25 LDR studies. The results indicate that GPT-4 performed the best, while Mixtral-8x7B demonstrated limited knowledge. Overall, this work advances understanding in radiation protection, risk assessment, and medical treatments, while providing valuable resources for researchers, educators, and policymakers.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2025

Can Large Language Models Understand Intermediate Representations?

Intermediate Representations (IRs) are essential in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. This paper presents a pioneering empirical study to investigate the capabilities of LLMs, including GPT-4, GPT-3, Gemma 2, LLaMA 3.1, and Code Llama, in understanding IRs. We analyze their performance across four tasks: Control Flow Graph (CFG) reconstruction, decompilation, code summarization, and execution reasoning. Our results indicate that while LLMs demonstrate competence in parsing IR syntax and recognizing high-level structures, they struggle with control flow reasoning, execution semantics, and loop handling. Specifically, they often misinterpret branching instructions, omit critical IR operations, and rely on heuristic-based reasoning, leading to errors in CFG reconstruction, IR decompilation, and execution reasoning. The study underscores the necessity for IR-specific enhancements in LLMs, recommending fine-tuning on structured IR datasets and integration of explicit control flow models to augment their comprehension and handling of IR-related tasks.

Jiang, Hailong↗
DOE OSTI2025

DuctGPT: A Generative Transformer for Forward Screening of Ductile Refractory Multi-Principal Element Alloys

Designing ductile materials for extreme environments such as fusion reactors requires a deep understanding of the complex interplay between electronic structure, mechanical stability, and wide compositional space. Here, in this work, we introduce DuctGPT, a physics-informed, GPT-powered machine learning platform that enables rapid and accurate prediction of ductility across a wide range of refractory multi-principal element alloys (MPEAs). Trained on both experimental and high-fidelity computational data, DuctGPT integrates descriptors such as density of states at the Fermi level, elastic constants, and valence electron concentration to capture the fundamental mechanisms governing ductile versus brittle behavior. Using this framework, we screen over 1000 compositions in of body-centered cubic (BCC) MPEAs, including two new alloy classes, i.e., NbTa-rich (NbTa $>$ 50 at.%) NbTa-Ti-V and W-rich ($>$ 50 at.%) W-Ti-V MPEAs, to rapidly identify promising alloy compositions with enhanced ductility. Validation against experimental data confirms the model's ability to predict ductility with high fidelity and low uncertainty. By leveraging conversational AI and robust physical modeling, DuctGPT provides a blueprint for the next generation of alloy design assistants, enabling human-AI collaboration in the accelerated discovery of ductile, high-performance materials for fusion, aerospace, and advanced manufacturing.

AI/ML↗
DOE OSTI2024

Leveraging generative AI for urban digital twins: a scoping review on the autonomous generation of urban data, scenarios, designs, and 3D city models for smart city advancement

The digital transformation of modern cities by integrating advanced information, communication, and computing technologies has marked the epoch of data-driven smart city applications for efficient and sustainable urban management. Despite their effectiveness, these applications often rely on massive amounts of high-dimensional and multi-domain data for monitoring and characterizing different urban sub-systems, presenting challenges in application areas that are limited by data quality and availability, as well as costly efforts for generating urban scenarios and design alternatives. As an emerging research area in deep learning, Generative Artificial Intelligence (GenAI) models have demonstrated their unique values in content generation. This paper aims to explore the innovative integration of GenAI techniques and urban digital twins to address challenges in the planning and management of built environments with focuses on various urban sub-systems, such as transportation, energy, water, and building and infrastructure. The survey starts with the introduction of cutting-edge generative AI models, such as the Generative Adversarial Networks (GAN), Variational Autoencoders (VAEs), Generative Pre-trained Transformer (GPT), followed by a scoping review of the existing urban science applications that leverage the intelligent and autonomous capability of these techniques to facilitate the research, operations, and management of critical urban subsystems, as well as the holistic planning and design of the built environment. Based on the review, we discuss potential opportunities and technical strategies that integrate GenAI models into the next-generation urban digital twins for more intelligent, scalable, and automated smart city development and management.

3D city modeling↗
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
DOE OSTI2026

Hierarchical low Pt-loading “core-shell” electrocatalysts for the oxygen reduction reaction in fuel cells

The sluggish kinetics of the oxygen reduction reaction (ORR) hinder cost-effective polymer electrolyte fuel cells (PEFCs), which rely on scarce, expensive platinum-based electrocatalysts (ECs). Here, we present a novel synthesis method for ORR ECs achieving exceptional platinum utilization. The design features a hierarchical “multi-carbon” support comprising carbon nanoparticles interacting with graphene nanoplatelets as the “core”, encapsulated by a porous carbon nitride (CN) “shell”. This configuration promotes strong core/shell interactions and a bimodal active site distribution, consisting of chemically dispersed Pt and Ni single-atom complexes and PtNix alloy nanoclusters embedded in the CN shell. These advantages enable high activity and durability, achieving an ORR activity of 1.6 A mgPt−1 at 0.9 V vs. RHE-an order of magnitude higher than Pt/C (0.17 A mgPt−1). A proof-of-concept PEFC demonstrates a specific power of 12.0 kW gPt−1 at 0.60 V. This approach offers a significant step toward more efficient and sustainable PEFC technologies.

Pagot, Gioele [University of Padova, Italy]↗
DOE OSTI2026

A unified large language model–based framework for heterogeneous PV image diagnosis

With advances in imaging technologies, modern photovoltaic (PV) systems generate large volumes of heterogeneous image data, including visible, electroluminescence (EL), and infrared (IR) images. Existing PV image analysis models, particularly deep learning approaches, are typically task-specific and lack cross-modality generalization. To address this limitation, this paper proposes an open-source large language model (LLM)–based unified framework for heterogeneous PV image diagnostics. Through task-aware diagnostic prompting, the framework enables analysis of visible, EL, and IR images within a single pipeline, supporting both zero-shot and few-shot inference and binary and multiclass classification. It is compatible with state-of-the-art multimodal LLMs, including ChatGPT, Gemini, Claude, Qwen, and CLIP. The framework is evaluated on PV module condition classification (clean, soiling, snow, hail, and bird droppings) using visible images, cell crack detection using EL images, and hotspot detection using IR images. GPT-5.1 in few-shot mode achieves the best performance, with classification accuracy exceeding 97.3%. Open-source models such as Qwen and CLIP also deliver competitive results on visible images (around 90% accuracy), though their performance is more limited on EL and IR modalities. On the full ELPV dataset, the framework achieves 83.5% zero-shot accuracy, within 2.8% of the supervised CNN baseline, confirming scalability to larger benchmarks. Practical aspects such as reproducibility, response latency, and confidence estimation are systematically analyzed. The framework operates across PV image modalities without modality- or task-specific training, making it well suited as a rapid pre-screening tool to support downstream detailed diagnostics. A benchmark dataset of diverse labeled PV images is also released.

Li, Baojie↗
DOE OSTI2025

Extracting Material Property Measurements from Scientific Literature with Limited Annotations

Extracting material property data from scientific text is pivotal for advancing data-driven research in chemistry and materials science; however, the extensive annotation effort required to produce training data for named entity recognition (NER) models for this task often makes it a barrier to extracting specialized data sets. Here, in this work, we present a comparative study of the conventional, supervised NER methodology to alternative few-shot learning architectures and large language model (LLM)-based approaches that mitigate the need to label large training data sets. We find that the best-performing LLM (GPT-4o) not only excels in directly extracting relevant material properties based on limited examples but also enhances supervised learning through data augmentation. We supplement our findings with error and data quality assessments to provide a nuanced understanding of factors that impact property measurement extraction.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Bayesian Optimization of Catalysis with In-Context Learning

Large language models (LLMs) can perform accurate classification with zero or few examples through in-context learning (ICL), allowing the model to observe query-relevant examples at inference time and eliminating the need for additional weight updates to generalize beyond its original training data. We extend this capability to regression with uncertainty estimation using frozen LLMs (e.g., GPT-4o, Gemini), enabling Bayesian optimization (BO) in natural language without explicit model training or feature engineering. We apply this to materials discovery by representing materials as synthesis and testing procedures for use in natural language prompts. This Bayesian, design-first approach prioritizes optimization toward target material properties before detailed characterization, in contrast to conventional experimental workflows that often emphasize characterization of suboptimal materials. On benchmarks like aqueous solubility and oxidative coupling of methane (OCM), BO-ICL matches or outperforms Gaussian processes. In live experiments on the reverse water–gas shift (RWGS) reaction, BO-ICL identifies multimetallic catalysts that approach equilibrium CO yield within 6 and 10 iterations from a pool of 3,700 and 360,000 candidates, respectively. Our method redefines materials representation and accelerates discovery, with broad applications across catalysis, materials science, and AI.

Calibration↗
DOE OSTI2024

RNA language models predict mutations that improve RNA function

Structured RNA lies at the heart of many central biological processes, from gene expression to catalysis. RNA structure prediction is not yet possible due to a lack of high-quality reference data associated with organismal phenotypes that could inform RNA function. We present GARNET (Gtdb Acquired RNa with Environmental Temperatures), a new database for RNA structural and functional analysis anchored to the Genome Taxonomy Database (GTDB). GARNET links RNA sequences to experimental and predicted optimal growth temperatures of GTDB reference organisms. Using GARNET, we develop sequence- and structure-aware RNA generative models, with overlapping triplet tokenization providing optimal encoding for a GPT-like model. Leveraging hyperthermophilic RNAs in GARNET and these RNA generative models, we identify mutations in ribosomal RNA that confer increased thermostability to the Escherichia coli ribosome. The GTDB-derived data and deep learning models presented here provide a foundation for understanding the connections between RNA sequence, structure, and function.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

A multimodal large language model for materials science

Understanding and predicting the properties of inorganic materials is crucial for accelerating advancements in materials science and driving applications in energy, electronics and beyond. Integrating material structure data with language-based information through multimodal large language models (LLMs) offers great potential to support these efforts by enhancing human–artificial intelligence interaction. However, a key challenge lies in integrating atomic structures at full resolution into LLMs. In this work, we introduce MatterChat, a versatile structure-aware multimodal LLM that unifies material structural data and textual inputs into a single cohesive model. MatterChat uses a bridging module to effectively align a pretrained universal machine learning interatomic potential with a pretrained LLM, reducing training costs and enhancing flexibility. Our results demonstrate that MatterChat greatly improves performance in material property prediction and human–artificial intelligence interaction, surpassing general-purpose LLMs such as GPT-4. We also demonstrate its usefulness in applications such as more advanced scientific reasoning and step-by-step material synthesis.

Tang, Yingheng [Lawrence Berkeley National Laborat↗