Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “generative AI”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Ecosystems for Scientific Computing in the Age of AI

Scientific computing is at an inflection point. Artificial intelligence (AI) is reshaping how scientific software is developed, how teams collaborate, how projects are governed, and how the next generation is trained. Drawing on insights from a 2025 workshop report, this article argues that the future of discovery will depend on agile, robust ecosystems built through socio-technical co-design—the intentional integration of technical and human systems. This perspective is essential for ensuring that future scientific computing remains trustworthy, sustainable, and scalable. It combines advances in AI, high-performance computing, and software with new models for cross-disciplinary collaboration, education, and workforce development. Key recommendations include building modular, trustworthy AI-enabled software ecosystems; enabling teams to integrate AI into scientific workflows while preserving human creativity, integrity, and rigor; and developing adaptive training pathways that keep pace with rapid technological change. By sharing these perspectives, we hope to stimulate broader community dialogue and encourage coordinated action.

AI↗
DOE OSTI2026

Genesis Data Card Schema, Template and Supporting Tools

Genesis Data Cards provide a standardized template and schema for documenting scientific datasets in support of discovery, access, interoperability, reusability, governed use, and AI usability. This release of the Genesis Data Card repository includes a versioned Markdown template, a LinkML schema with generated Pydantic and JSON artifacts, schema documentation, and example completed data cards. Validation tooling is provided to ensure that completed data cards conform to the schema prior to submission. Accompanying documentation for the structured metadata is provided as a Field Reference Guide. The schema and accompanying template provided in this repository address the call for actionable context that enables humans and AI systems to find, access, interpret, cite, and reuse data, and, when appropriate, integrate it into AI and machine learning workflows. The data card is intended to serve as a common metadata artifact intended to support standardized, cross-program dataset documentation across Department of Energy (DOE)-aligned efforts, including but not limited to Genesis Mission-related implementations, the Office of Science, National Nuclear Security Administration (NNSA), and Advanced Simulation and Computing (ASC) data governance and stewardship initiatives.

data card↗
DOE OSTI2021

The archives of the future

The term “artificial intelligence” (AI) - essentially programming machines to think like humans - conjures up different emotions in different people. Some view it with fear, imagining a malevolent AI similar to Skynet in the Terminator movies. Others see something benevolent, such as the character Data in Star Trek: The Next Generation . Still others see it as a means to advance the frontiers of science, engineering and technology to new levels not possible through traditional means. At the National Security Research Center (NSRC or the Center), which is the classified library at Los Alamos National Laboratory, we see AI as a tool to help us go through the monumental tasks we have in digitizing, cataloging, and searching our collections.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2024

Harnessing large language models’ zero-shot and few-shot learning capabilities for regulatory research

Abstract Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency’s local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Biochemistry & Molecular Biology↗
DOE OSTI2021

Artificial Intelligence for Energy Systems Cybersecurity

Artificial intelligence and machine learning systems have the potential to influence the future design and implementation of cybersecurity systems for the power grid. These systems may enhance the overall operation of the power system by leveraging and making sense of massive amounts of data. However, we must also understand how AI/ML will need to be protected from cyber threat actors. We discuss the existing insights the NREL team has developed using AI/ML systems and then present resources including ESIF and the Cyber Energy Emulation Platform that can be used to generate training data and insights. We end by offering suggestions on priority research paths for AI in cybersecurity.

artificial intelligence↗
DOE OSTI2018

Re-Evaluation of Active Interlock Envelopes Considering Insertion Device Correction Coils

The Active Interlock (AI) is a system that ensures that the beam position and angle through the NSLS-II storage ring is located so that the machine apertures that may be struck by synchrotron radiation are not exposed to high power beam which may compromise them. Of particular importance in the NSLS-II is to maintain the beam position and angle within the insertion device (ID) straights where insertions devices make high power x-ray beams for users which may compromise the storage ring vacuum chamber. The beam position and angle in the center of the insertion device is calculated using a pair of beam position monitors (BPMs) on either side of the device. The safe area of positions and angles within the insertion device is called the AI envelope. If there is a magnetic element between the BPMs, it needs to be accounted for in the calculation of the beam position and angle. In addition to the permanent magnet arrays that comprise the insertion device itself, there are correction coils that are used to correct any orbit distortions that are generated by imperfections in the device. It has recently come to our attention that these coils are not considered in the AI calculations, nor are the currents in these coils read by the AI. As it may be possible in theory for these coils to produce angles large enough that the synchrotron radiation beam may damage components, we analyzed the possibility for all ID types and configurations. In this report we show what changes are necessary for the AI envelope, and limits placed upon the correction coils to maintain operation of the storage ring without compromising protection.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Reducing Data Center Peak Cooling Demand and Energy Costs with Underground Thermal Energy Storage (UTES)

By recent estimates, data center energy demands are projected to consume between 6.7% and 12% of U.S. annual electricity generation by the year 2028, driven primarily by expanded demands from cloud services, big data analytics, and Artificial Intelligence (AI) (Shehabi et al., 2024). As much as 40% of data center total energy consumption are loads associated with the site infrastructure cooling systems, and these are often highly water consumptive (Aljbour et al., 2024). For energy system planners, this presents significant challenges to meeting and managing the anticipated loads, and especially the peak loads of projected data center deployments. Geothermal technologies offer two unique solutions to these challenges: 1) by serving loads through the deployment of new conventional and/or next-generation geothermal power technologies such as EGS and 2) through an often-overlooked opportunity to reduce data center peak cooling loads. The latter is the focus of this paper which explores Cold Underground Thermal Energy Storage ("Cold UTES") as an emerging industrial-scale geothermal cooling solution. This cooling solution is energy efficient, non-water-consumptive, and utilizes long duration energy storage (LDES) on both diurnal and seasonal time scales. Cold UTES has the potential to also function as a virtual power plant (VPP). The US Department of Energy's Geothermal Technologies Office is supporting R&D to understand the grid and system-wide value, costs, and impacts of deploying this emergent cooling solution at scale.

AI↗
DOE OSTI2022

Genetic programming for understanding cognitive biases that generate polarization in social networks

Recent studies have applied agent-based models to infer human-interpretable explanations of individual-scale behaviors that generate macro-scale patterns in complex social systems. Genetic programming has proven to be an ideal explainable AI tool for this purpose, where primitives may be expressed in an interpretable fashion and assembled into agent rules. Evolutionary model discovery (EMD) is a tool that combines genetic programming and random forest feature importance analysis, to infer individual-scale, human-interpretable explanations from agent-based models. We deploy EMD to investigate the cognitive biases behind the emergence of ideological polarization within a population. An agent-based model is developed to simulate a social network, where agents are able to create or sever links with one another, and update an internal ideological stance based on their neighbors' stances. Agent rules govern these actions and constitute of cognitive biases. A set of 7 cognitive biases are included as genetic program primitives in the search for rules that generate hyper-polarization among the population of agents. We find that heterogeneity in cognitive biases is more likely to generate polarized social networks. Highly polarized social networks are likely to emerge when individuals with confirmation bias are exposed to those with either attentional bias, egocentric bias, or cognitive dissonance.

Gunaratne, Chathika↗
DOE OSTI2025

Rapid data acquisition and machine learning-assisted composition design of functionally graded alloys via wire arc additive manufacturing

Abstract The lack of high-quality datasets in materials science hinders artificial intelligence (AI)-driven alloy design. To address this challenge, wire arc additive manufacturing (WAAM) was employed to fabricate graded alloys, generating extensive data for machine learning (ML)-assisted property prediction. ML models were developed using high-throughput experiments, computational models, and genetic algorithm to optimize feature selection, successfully predicting hardness and porosity. The ML model demonstrated its efficacy by designing a gradient alloy with enhanced properties. However, scaling up revealed uncertainties in tensile property and porosity due to differences in size and thermal conditions between the designed alloy build and the gradient print used to construct the ML model. This underscores the need for uncertainty quantification and process optimization in WAAM-driven alloy design. Our work advances AI-integrated additive manufacturing, offering a rapid approach to exploring process–structure–property relationships and accelerating materials development.

Wang, Xin↗
DOE OSTI2025

AutoFocus: AI/ML-driven real-time wavefront diagnostics to autonomously align and optimize X-ray optics

We present an integrated system that combines advanced wavefront diagnostics with artificial intelligence (AI) to automate and optimize X-ray optics at synchrotron beamlines. This system couples real-time wavefront sensing with AI-driven control algorithms to achieve precise beam alignment, stabilization, and performance optimization. A key feature is the use of multi-fidelity transfer learning, which enables knowledge gained from both real-world beamline optimizations and ultra-realistic digital twin simulations to be effectively applied to in situ optimization. By leveraging multi-objective bayesian optimization, the system continuously refines its performance, reducing optimization time and minimizing the need for manual adjustments. Designed for seamless deployment, it operates with existing beamline hardware and provides an intuitive graphical interface. Initial deployments at the advanced photon source beamlines have demonstrated its ability to enhance beam stability, improve reproducibility, and significantly streamline alignment procedures. This AI-enhanced control framework represents a significant step toward fully autonomous beamline operation in next-generation synchrotron facilities.

Rebuffi, Luca [Argonne National Laboratory (ANL), ↗
NASA NTRS1992

Situation assessment in the Paladin tactical decision generation system

Paladin is a real-time tactical decision generator for air combat engagements. Paladin uses specialized knowledge-based systems and other Artificial Intelligence (AI) programming techniques to address the modern air combat environment and agile aircraft in a clear and concise manner. Paladin is designed to provide insight into both the tactical benefits and the costs of enhanced agility. The system was developed using the Lisp programming language on a specialized AI workstation. Paladin utilizes a set of air combat rules, an active throttle controller, and a situation assessment module that have been implemented as a set of highly specialized knowledge-based systems. The situation assessment module was developed to determine the tactical mode of operation (aggressive, defensive, neutral, evasive, or disengagement) used by Paladin at each decision point in the air combat engagement. Paladin uses the situation assessment module; the situationally dependent modes of operation to more accurately represent the complex decision-making process of human pilots. This allows Paladin to adapt its tactics to the current situation and improves system performance. Discussed here are the details of Paladin's situation assessment and modes of operation. The results of simulation testing showing the error introduced into the situation assessment module due to estimation errors in positional and geometric data for the opponent aircraft are presented. Implementation issues for real-time performance are discussed and several solutions are presented, including Paladin's use of an inference engine designed for real-time execution.

Mcmanus, John W.↗
NASA NTRSDate not supplied

The BioMole Facility: Advancement of In Situ Microbiome Analysis for the International Space Station

Characterization of the International Space Station (ISS) microbiome has been enabled by sample return and Earth-based analysis. As human exploration pushes beyond low-Earth orbit, microbial-related crew health, planetary protection, and space research requires in situ capabilities. Steps toward reducing Earth-dependence for complex sample analysis began in 2016 with the amplification of DNA within the miniPCR thermal cycler and DNA sequencing with the MinION sequencer onboard the ISS; for both, samples were prepared on Earth. In 2017, these platforms synergistically enabled the in-situ identification of unknown bacteria collected and cultured from ISS surfaces, thereby shifting the paradigm that microbial cultures had to be returned to Earth. The following year, a culture-independent, swab-to-sequencer method further advanced spaceflight microbiology, demonstrating that culturing could be excluded and provided enhanced insight into the bacterial profile of ISS surfaces. Based on the success of these payloads in confirming the ability to meet crew health identification requirements and the benefits accompanying a culture-independent method, the BioMole Facility was established by the medical operations Crew Health Care Systems team. BioMole is the set of hardware, consumables, and procedures required to support sample preparation and nanopore sequencing onboard the ISS. BioMole goals include expanding sample sources, comparing data to previous methods, demonstrating onboard data analytics, and validating new hardware. To date, comparative surface analysis, molecular- and culture-based, has been completed. Additionally, the demonstration of a sample-to-answer process was achieved when BioMole data was processed onboard using the IBM Open Data and AI Edge software platform installed on the ISS-residing Spaceborne Computer-2. The taxonomic profiles generated from the edge analysis were as expected and paralleled that of the downlinked processed data. Future BioMole efforts involve microbial profiling of the ISS water system, ISS validation of the MinION Mk1C, and an expansion to a research facility available to investigators.

Sarah L. Castro-Wallace↗
DOE OSTI2025

Ensuring Safe, Effective, and Reliable Use of Artificial Intelligence-Based Applications for Nuclear Electricity Generation through a Systems Approach

There is a significant potential to reduce operating and maintenance cost at nuclear power plants using artificial intelligence (AI) and machine learning (ML). For instance, AI/ML has the potential to significant improve work management processes, condition reporting, and plant surveillance activities. However, the nuclear industry has been slow in adopting AI/ML due to several multifaceted barriers discussed in this paper. This work presents such multidisciplinary approach intended to 1) accelerate industry adoption of AI/ML-based applications at nuclear power plants and 2) ensure their safe, reliable, and effective use. This approach is discussed further in this work and will be used to address overarching challenges associated with AI deployment at scale to provide industry guidance that support accelerated adoption of AI/ML technologies throughout the industry.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

Perspectives on AI Architectures and Codesign for Earth System Predictability

Abstract Recently, the U.S. Department of Energy (DOE), Office of Science, Biological and Environmental Research (BER), and Advanced Scientific Computing Research (ASCR) programs organized and held the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop series. From this workshop, a critical conclusion that the DOE BER and ASCR community came to is the requirement to develop a new paradigm for Earth system predictability focused on enabling artificial intelligence (AI) across the field, laboratory, modeling, and analysis activities, called model experimentation (ModEx). BER’s ModEx is an iterative approach that enables process models to generate hypotheses. The developed hypotheses inform field and laboratory efforts to collect measurement and observation data, which are subsequently used to parameterize, drive, and test model (e.g., process based) predictions. A total of 17 technical sessions were held in this AI4ESP workshop series. This paper discusses the topic of the AI Architectures and Codesign session and associated outcomes. The AI Architectures and Codesign session included two invited talks, two plenary discussion panels, and three breakout rooms that covered specific topics, including 1) DOE high-performance computing (HPC) systems, 2) cloud HPC systems, and 3) edge computing and Internet of Things (IoT). We also provide forward-looking ideas and perspectives on potential research in this codesign area that can be achieved by synergies with the other 16 session topics. These ideas include topics such as 1) reimagining codesign, 2) data acquisition to distribution, 3) heterogeneous HPC solutions for integration of AI/ML and other data analytics like uncertainty quantification with Earth system modeling and simulation, and 4) AI-enabled sensor integration into Earth system measurements and observations. Such perspectives are a distinguishing aspect of this paper. Significance Statement This study aims to provide perspectives on AI architectures and codesign approaches for Earth system predictability. Such visionary perspectives are essential because AI-enabled model-data integration has shown promise in improving predictions associated with climate change, perturbations, and extreme events. Our forward-looking ideas guide what is next in codesign to enhance Earth system models, observations, and theory using state-of-the-art and futuristic computational infrastructure.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Perspectives on AI Architectures and Co-design for Earth System Predictability

Recently, the U.S. Department of Energy (DOE), Office of Science, Biological and Environmental Research (BER), and Advanced Scientific Computing Research (ASCR) programs organized and held the Artificial Intelligence for Earth System Predictability (AI4ESP) workshop series. From this workshop, a critical conclusion that the DOE BER and ASCR community came to is the requirement to develop a new paradigm for Earth system predictability focused on enabling artificial intelligence (AI) across the field, laboratory, modeling, and analysis activities, called model experimentation (ModEx). BER’s ModEx is an iterative approach that enables process models to generate hypotheses. The developed hypotheses inform field and laboratory efforts to collect measurement and observation data, which are subsequently used to parameterize, drive, and test model (e.g., process based) predictions. A total of 17 technical sessions were held in this AI4ESP workshop series. This paper discusses the topic of the AI Architectures and Codesign session and associated outcomes. The AI Architectures and Codesign session included two invited talks, two plenary discussion panels, and three breakout rooms that covered specific topics, including 1) DOE high-performance computing (HPC) systems, 2) cloud HPC systems, and 3) edge computing and Internet of Things (IoT). We also provide forward-looking ideas and perspectives on potential research in this codesign area that can be achieved by synergies with the other 16 session topics. These ideas include topics such as 1) reimagining codesign, 2) data acquisition to distribution, 3) heterogeneous HPC solutions for integration of AI/ML and other data analytics like uncertainty quantification with Earth system modeling and simulation, and 4) AI-enabled sensor integration into Earth system measurements and observations. Such perspectives are a distinguishing aspect of this paper.

58 GEOSCIENCES↗
DOE OSTI2026

Interpretable Deep Learning for Advancing Field-Enhanced Catalysis

This DOE Early Career project developed a physics-informed, interpretable AI-and-modeling framework to understand and exploit electric-field effects in heterogeneous catalysis, with ammonia cracking and synthesis as a representative pathway. The team built and validated methods to map local electric fields on metal surfaces and nanoparticles, showing that low-coordination features (tips/edges/corners) can concentrate fields by several-fold relative to flat facets. Using DFT-generated datasets, the project created physics-guided machine learning models that rapidly predict local electric fields and field-dependent adsorption energetics with near-DFT accuracy while reducing computational cost by orders of magnitude. These predictions were integrated with microkinetic modeling to quantify how field-dipole interactions reshape reaction energetics and mechanisms, enabling large increases in predicted catalytic rates and substantial reductions in operating temperature under favorable field conditions. To accelerate discovery of earth-abundant catalysts, the project combined interpretable ML screening (with electronic-structure descriptors identified as key drivers) with a generative inverse-design workflow based on diffusion models and physics constraints. The resulting closed-loop approach, linking simulation, mechanistic modeling, and AI, provides reusable tools and datasets for designing catalysts and operating conditions in field-enhanced catalysis, with broad relevance to electrostatic catalysis, plasma catalysis, electrocatalysis, and other energy-related chemical transformations.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2026

Beyond sequence similarity: toward function-based screening of nucleic acid synthesis

Synthetic nucleic acids are a key input to modern biotechnology, yet they represent dual-use materials that require robust screening to mitigate biosecurity risks. The prevailing screening paradigm, which identifies sequences of concern (SoCs) through sequence similarity to controlled pathogens and toxins, may not fully capture risks posed by AI tools that can decouple biomolecular function from reliance on known sequences. Rapidly advancing biodesign capabilities enable the generation of genes and proteins that might evade sequence-based detection. We highlight the critical need for function-based screening approaches that can detect sequences capable of hazardous biological functions, regardless of similarity to known SoCs. We examine the feasibility of function-based screening with an initial focus on proteins, arguing that, while protein sequence space is vast, biologically functional proteins are significantly constrained by biophysical and biochemical requirements that can be learned and modeled. We propose a concrete implementation framework organized along a continuum of complexity, starting with toxins as the most tractable targets before expanding to more complex pathogenic functions. We then discuss open challenges and describe a research and development strategy to address them.

59 BASIC BIOLOGICAL SCIENCES↗