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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Assessing Low-Temperature Geothermal Play Types: Relevant Data and Play Fairway Analysis Methods

The U.S. Department of Energy (DOE) Geothermal Technologies Office (GTO) is supporting the Geothermal Heating and Cooling Geospatial Datasets and Analysis project conducted by the National Renewable Energy Laboratory (NREL) as part of a broader effort to demonstrate the multi-faceted value of integrating geothermal power and geothermal heating and cooling (GHC) technologies into national decarbonization plans and community energy plans. Currently, there is a need to establish baseline low-temperature geothermal resource datasets and evaluate methods for deploying these technologies to provide the basis for supporting private sector investment. This project is focused on collecting baseline datasets, updating conceptual models, and creating Play Fairway Analysis (PFA) workflows for low-temperature (<150 degrees Celsius) geothermal resources of different geothermal play types (i.e., sedimentary basin, orogenic belts, and radiogenic geothermal play types) that could be used for geothermal heating and cooling (GHC), combined heat and power (CHP), and other geothermal direct uses (GDU) applications. Low-temperature geothermal resources are defined as reservoirs - natural or engineered - with temperatures <150 degrees Celsius. While the focus in the NREL effort is on GHC, resources at the upper end of this temperature range can also be used for small-scale power generation. This project does not include Ground Source Heat Pumps (GSHPs) technologies because they can be effectively developed almost anywhere. Low-temperature geothermal resources have not been studied as extensively as higher- to medium-temperature geothermal resources, but there is recent interest in improving understanding of these types of resources with an uptick of interest in geothermal technologies for decarbonizing heating and cooling systems. In addition, Enhanced Geothermal Systems (EGS) and other emerging technologies for exploiting petrothermal resources have opened the possibility of utilizing deep sedimentary basin systems, where porous media provide permeability and high temperatures can be reached at great depths. This project takes the approach of classifying low- temperature geothermal resources by geothermal play type (GPT). We defined and characterized three major classes of low-temperature GPT: sedimentary basins, orogenic systems, and radiogenic systems. We develop methodologies for evaluating and analyzing the potential for these resources building off the PFA approach to de-risking geothermal exploration and characterization. The proposed PFA approach for low-temperature geothermal resources includes: 1) identifying relevant data (e.g., datasets such bottom-hole temperatures from oil and gas wells, heat flow data, Quaternary faults and stress field data, geophysical data, etc.); 2) grouping and weighting of relevant datasets into PFA criteria (e.g., geological, risk, and economic criteria); 3) uncertainty quantification; 4) developing favorability or common risk maps for low-temperature geothermal resources to identify potential locations for more focused data collection; and 5) estimating electric power generation and heating potential at those locations using the GeoRePORT Resource Size Assessment Tool (RSAT). This project should facilitate future deployment of GHC, CHP, and GDU by providing data, tools, and a workflow applicable to low-temperature geothermal resources. Increased deployment of GHC and GDU will help achieve national and local decarbonization goals.

15 GEOTHERMAL ENERGY↗

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 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 OSTI2020

New Simulations for Ion-Production and Back-Bombardment in GaAs Photo-guns

GaAs-based DC high voltage photo-guns used at accelerators with extensive user programs must exhibit long photocathode operating lifetime. Achieving this goal represents a significant challenge for proposed high average current facilities that must operate at tens of milliamperes or more. Specifically, the operating lifetime is dominated by ion back-bombardment of the photocathode from ionized residual gas. While numerous experiments have been performed to characterize the operating lifetime under various conditions, detailed simulations of the ion back-bombardment mechanism that explains these experiments are lacking. Recently, a new user routine was implemented using the code General Particle Tracer (GPT) to simulate electron impact ionization of residual beam line gas and simultaneously track the incident electron, the ejected electron, and the newly formed ion. This new routine was benchmarked against analytical calculations and then applied to experiments performed at the CEBAF injector at the Thomas Jefferson National Accelerator Facility to study the effectiveness of limiting ions from entering the cathode-anode gap using a positively biased anode. These simulations were performed using detailed 3D field maps produced with CST Microwave Studio describing the photo-gun electrostatics. Discussion of the experiment and the application of this new GPT routine to model the experiments will be presented at the workshop.

Yoskowitz, Joshua↗

DOE OSTI2016

Transgenic plants with enhanced growth characteristics

The invention relates to transgenic plants exhibiting dramatically enhanced growth rates, greater seed and fruit/pod yields, earlier and more productive flowering, more efficient nitrogen utilization, increased tolerance to high salt conditions, and increased biomass yields. In one embodiment, transgenic plants engineered to over-express both glutamine phenylpyruvate transaminase (GPT) and glutamine synthetase (GS) are provided. The GPT+GS double-transgenic plants of the invention consistently exhibit enhanced growth characteristics, with T0 generation lines showing an increase in biomass over wild type counterparts of between 50% and 300%. Generations that result from sexual crosses and/or selfing typically perform even better, with some of the double-transgenic plants achieving an astounding four-fold biomass increase over wild type plants.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2018

Transgenic plants with enhanced growth characteristics

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Space Charge Effects in Low Energy Magnetized Electron Beams

Magnetized electron cooling of the ion beam is one of the major approaches towards obtaining the required high luminosity in the proposed Electron-Ion Collider (EIC). To increase the cooling efficiency, a bunched electron beam with a high bunch charge and high repetition rate is required. However, these features can combine to enhance the collective interactions, such as the space charge effect. A magnetized electron beam was successfully generated at the Thomas Jefferson National Accelerator Facility (JLab) using a compact, 300 kV DC high voltage photo-gun with an inverted insulator geometry and bi-alkali antimonide photocathode. The beam magnetization was characterized using a modest diagnostic beamline to measure beam sizes, rotation angles, and normalized transverse emittance as a function of magnetic field at the photocathode, laser spot size, and gun high-voltage. Simultaneously, simulations were performed using the A Space Charge Tracking Algorithm (ASTRA) and General Particle Tracer (GPT) programs. Further, sustained high average current magnetized beam up to 28 mA was demonstrated, and the photocathode lifetime for different magnetized electron beam currents was investigated. In the second part of the project, the space charge effect in low-energy magnetized electron beams was studied and compared with GPT simulations. The high bunch charge studies showed evidence of space charge current limitations starting at 0.3 nC and limited the maximum delivered bunch charge to 0.7 nC. To reach the high bunch charge goal of a few nC, the existing DC photo-gun design was modified using CST Studio Suite’s electromagnetic field solver, and a way to cancel the beam deflection exerted by the non-symmetric nature of the inverted insulator photo-gun geometry was discovered. This thesis presents a detailed description of the generation, characterization, and simulation of high current, high bunch charge magnetized electron beams at JLab, as well as the modified photo-gun design. Together with measurements and simulations, the purpose of this thesis is to provide a solid background on the theoretical aspects and the experimental challenges associated with magnetized electron beams for accelerator applications.

Wijethunga, W M Sajini↗

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 OSTI2023

A survey of techniques for optimizing transformer inference

Recent years have seen a phenomenal rise in the performance and applications of transformer neural networks. The family of transformer networks, including Bidirectional Encoder Representations from Transformer (BERT), Generative Pretrained Transformer (GPT) and Vision Transformer (ViT), have shown their effectiveness across Natural Language Processing (NLP) and Computer Vision (CV) domains. Transformer-based networks such as ChatGPT have impacted the lives of common men. However, the quest for high predictive performance has led to an exponential increase in transformers' memory and compute footprint. Researchers have proposed techniques to optimize transformer inference at all levels of abstraction. Further, this paper presents a comprehensive survey of techniques for optimizing the inference phase of transformer networks. We survey techniques such as knowledge distillation, pruning, quantization, neural architecture search and lightweight network design at the algorithmic level. We further review hardware-level optimization techniques and the design of novel hardware accelerators for transformers. We summarize the quantitative results on the number of parameters/FLOPs and the accuracy of several models/techniques to showcase the tradeoff exercised by them. We also outline future directions in this rapidly evolving field of research. We believe that this survey will educate both novice and seasoned researchers and also spark a plethora of research efforts in this field.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Evaluation of pre-training large language models on leadership-class supercomputers

Large language models (LLMs) have arisen rapidly to the center stage of artificial intelligence as the foundation models applicable to many downstream learning tasks. However, how to effectively build, train, and serve such models for many high-stake and first-principle-based scientific use cases are both of great interests and of great challenges. Moreover, pre-training LLMs with billions or even trillions of parameters can be prohibitively expensive not just for academic institutions, but also for well-funded industrial and government labs. Furthermore, the energy cost and the environmental impact of developing LLMs must be kept in mind. Here, in this work, we conduct a first-of-its-kind performance analysis to understand the time and energy cost of pre-training LLMs on the Department of Energy (DOE)’s leadership-class supercomputers. Employing state-of-the-art distributed training techniques, we evaluate the computational performance of various parallelization approaches at scale for a range of model sizes, and establish a projection model for the cost of full training. Our findings provide baseline results, best practices, and heuristics for pre-training such large models that should be valuable to HPC community at large. We also offer insights and optimization strategies for using the first exascale computing system, Frontier, to train models of the size of GPT-3 and beyond.

97 MATHEMATICS AND COMPUTING↗

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 OSTI2022

Nitrogen-Doped PtNi Catalysts on Polybenzimidazole-Functionalized Carbon Support for the Oxygen Reduction Reaction in Polymer Electrolyte Membrane Fuel Cells

PtM (M = 3d transition metals) alloys are known as the promising oxygen reduction reaction catalysts and have been considered as the replacement of pure Pt catalysts for the commercialization of proton exchange membrane fuel cells. Although great progress has been made in the past three decades, the performance and durability of PtM catalysts still face stringent challenges from practical applications. Functionalization of a catalyst carbon support with nitrogen-contained groups can add charges onto its surface, which can be utilized to build a more complete ionomer/catalyst interface, to reduce the catalyst particle size, and to improve particle size distribution. Nitriding of PtNi catalysts can effectively improve the catalyst activity and stability by the modification of lattice strain. Hereby, we propose a synergistic approach of combining polybenzimidazole-grafted Vulcan XC72 carbon as the catalyst carbon support and the nitriding of PtNi to develop PtNiN/XC72-polybenzimidazole catalysts. Such PtNiN/XC72-PBI catalysts exhibit the excellent performance of fuel cell membrane electrode assembly (i.e., mass activity, 440 mA mgPt –1 ; electrochemical surface area, 51 m 2 gPt –1 ; and rated power density, 836 mW cm –2 ) as well as promising catalyst stability. The developed PtNiN/XC72-PBI meets the US DOE 2020 targets of mass activity for the fuel cell catalysts. This work provides a novel approach and a promising pathway on the development of the catalyst using such a synergistic approach-modification of the catalyst structure by nitrogen doping and functionalization of carbon support by polybenzimidazole for both high performance and high durability.

25 ENERGY STORAGE↗