Search NASA⌕ Search

SEARCH · Search NASA

Results for “generative artificial intelligence”

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 469 records · Page 26
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Method to simultaneously facilitate all jet physics tasks

Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of jet physics are proceeding in parallel. We show that specially constructed machine learning models trained for a specific jet classification task can improve the accuracy, precision, or speed of all other jet physics tasks. This is demonstrated by training on a particular multiclass generation and classification task and then using the learned representation for different generation and classification tasks, for datasets with a different (full) detector simulation, for jets from a different collision system ($pp$ versus $ep$), for generative models, for likelihood ratio estimation, and for anomaly detection. We consider our omnilearn approach thus as a jet-physics foundation model. It is made publicly available for use in any area where state-of-the-art precision is required for analyses involving jets and their substructure.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRSDate not supplied

Creating Benchmark Data for Artificial Intelligence and Machine Learning Space Biology Research

To identify an appropriate AI/ML approach for a specific problem, the best practice is to measure algorithm performance through the benchmarking process. A scientific benchmark consists of an AI-ready dataset and a reference implementation on a specific scientific question. The NASA Science Mission Directorate (SMD) has started the “Benchmark Initiative for AI/ML to create scientific benchmark datasets in three applications: 1) scientific benchmarking, which finds the best algorithm for a specific problem; 2) application benchmarking, which measures algorithm performance against a set of parameters; and 3) system benchmarking, which evaluates performance of hardware and software architecture. Currently, there are no standardized datasets available to benchmark AI/ML algorithms in the domain of space biology. In this work, we constructed two AI/ML-ready biological datasets from experiments in space-flown mice: cellular imaging and RNA-seq. First, radiation-exposed immune cells harbor DNA damage foci that can be fluorescently marked to visualize the amount of damage following exposure to ionizing radiation. However, such large datasets are difficult to analyze visually, due to imaging inconsistencies and human bias, and classical image processing approaches can fail on imaging artifacts. AI/ML are therefore exciting alternative, providing the speed of machines and the accuracy of humans. We have made this dataset available at https://registry.opendata.aws/bps_microscopy/. Second, high-throughput nucleic acid sequencing (DNA-seq, RNA-seq) has become widespread in biomedical research due to the growing availability and affordability of these assays. However, most sequencing datasets suffer from high dimensionality and low sample count. In this work, we used a generative adversarial network to synthesize a standardized, AI-ready, publicly available benchmark dataset for space biology RNA-seq data with sufficient space-flown and ground control mouse liver samples from NASA GeneLab. This dataset is available at https://registry.opendata.aws/bps_rnaseq/. These datasets are now fully open the Space Biology community to test their favorite AI/ML approaches.

James Casaletto↗
NASA NTRS1996

Intelligent Planning and Scheduling for Controlled Life Support Systems

Planning in Controlled Ecological Life Support Systems (CELSS) requires special look ahead capabilities due to the complex and long-term dynamic behavior of biological systems. This project characterizes the behavior of CELSS, identifies the requirements of intelligent planning systems for CELSS, proposes the decomposition of the planning task into short-term and long-term planning, and studies the crop scheduling problem as an initial approach to long-term planning. CELSS is studied in the realm of Chaos. The amount of biomass in the system is modeled using a bounded quadratic iterator. The results suggests that closed ecological systems can exhibit periodic behavior when imposed external or artificial control. The main characteristics of CELSS from the planning and scheduling perspective are discussed and requirements for planning systems are given. Crop scheduling problem is identified as an important component of the required long-term lookahead capabilities of a CELSS planner. The main characteristics of crop scheduling are described and a model is proposed to represent the problem. A surrogate measure of the probability of survival is developed. The measure reflects the absolute deviation of the vital reservoir levels from their nominal values. The solution space is generated using a probability distribution which captures both knowledge about the system and the current state of affairs at each decision epoch. This probability distribution is used in the context of an evolution paradigm. The concepts developed serve as the basis for the development of a simple crop scheduling tool which is used to demonstrate its usefulness in the design and operation of CELSS.

Leon, V. Jorge↗
DOE OSTI2026

Tokamak Energy’s pre-concept design for a fusion power plant: an overview of ST-E1

Climate change and rapidly rising energy demand, driven in part by artificial intelligence and data-centre growth, create an urgent need for stable, low-carbon, and abundant power. Fusion is a promising long-term solution, yet its commercialisation faces a fundamental paradox in today’s investment environment: pilot plants are essential to de-risk physics, engineering, and operations, but their limited lifetime energy output and high upfront costs make them difficult to finance. This paper presents Tokamak Energy’s response: ST-E1, a pre-concept design for a low-aspect-ratio tokamak power plant engineered specifically to overcome this challenge. ST-E1 is designed from the outset for phased operation—pilot and commercial phases, with an upgrade phase in between—with emphasis on commercial viability, maintainability, nuclear engineering, modularity, and upgradability. A key design principle is the deliberate separation of long-lived assets, such as the magnet cage and vacuum vessel, from replaceable in-vessel systems. This provides an attractive and credible investment approach to generate operational data and de-risk key technologies while preserving most capital-intensive assets for later commercial phases. The architecture supports continuous optimisation toward high net electric power (targeting 800–1000 MW net electric), a normalised capital expenditure of $\$$ 12–14k/kW of net electric power, and high availability (targeting > 80%). A tokamak core with a 5 m major radius, aspect ratio of 2.3, and on-plasma axis toroidal field of 5.25 T was selected to meet these objectives. This paper summarises the ST-E1 design philosophy, principal features, and development methodology. It introduces a Focus Collection of 11 papers detailing the pre-concept design of the entire tokamak and corresponding plant.

ST-E1↗
DOE OSTI2025

Resimulation-based self-supervised learning for pretraining physics foundation models

Self-supervised learning (SSL) is at the core of training modern large machine learning models, providing a scheme for learning powerful representations that can be used in a variety of downstream tasks. However, SSL strategies must be adapted to the type of training data and downstream tasks required. We propose resimulation-based self-supervised representation learning (RS3L), a novel simulation-based SSL strategy that employs a method of resimulation to drive data augmentation for contrastive learning in the physical sciences, particularly, in fields that rely on stochastic simulators. By intervening in the middle of the simulation process and rerunning simulation components downstream of the intervention, we generate multiple realizations of an event, thus producing a set of augmentations covering all physics-driven variations available in the simulator. Using experiments from high-energy physics, we explore how this strategy may enable the development of a foundation model; we show how RS3L pretraining enables powerful performance in downstream tasks such as discrimination of a variety of objects and uncertainty mitigation. In addition to our results, we make the RS3L dataset publicly available for further studies on how to improve SSL strategies.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

FAIR Data and Interpretable AI Framework for Architectured Metamaterials (Final Report)

This research program established a transformative framework for the discovery and design of mechanical metamaterials, which are architected structures engineered to control physical phenomena like sound and vibration in ways natural materials cannot. To overcome the traditional reliance on trial-and-error, the project developed an interpretable Artificial Intelligence (AI) framework that moves beyond "black box" models to reveal the specific geometric patterns—such as "unit-cell templates"—that govern a material’s performance. A major breakthrough was the development of a hierarchical design method, which allows a single material to block vibrations across multiple frequency ranges simultaneously by layering patterns at different scales without them interfering with one another. This was further expanded to include irregular, graph-based designs that use spanning tree algorithms to ensure structural connectivity while allowing for customized, direction-dependent properties like stiffness and acoustic impedance. Beyond design, the project addressed the practicalities of real-world production by developing uncertainty quantification techniques that account for manufacturing defects and material variability, reducing the need for expensive physical testing by orders of magnitude. To speed up the discovery process, the team implemented Gaussian Process Regression and other surrogate models that provide accurate performance predictions at a fraction of the traditional computational cost. The AI-generated designs were successfully validated through fabrication of physical samples and wave propagation experiments, confirming their ability to accurately guide or reflect waves as predicted. By contributing these tools and high-quality FAIR benchmark datasets to the wider scientific community, this work provides a scalable foundation for advancing technologies in aerospace vibration control, medical imaging, and noise reduction.

36 MATERIALS SCIENCE↗
NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗
NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗
NASA NTRSDate not supplied

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT - Poster

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗
NASA NTRS1994

Using AI Planning Techniques to Automatically Generate Image Processing Procedures: A Preliminary Report

This paper describes work on the Multimission VICAR Planner (MVP) system to automatically construct executable image processing procedures for custom image processing requests for the JPL Multimission Image Processing Lab (MIPL). This paper focuses on two issues. First, large search spaces caused by complex plans required the use of hand encoded control information. In order to address this in a manner similar to that used by human experts, MVP uses a decomposition-based planner to implement hierarchical/skeletal planning at the higher level and then uses a classical operator based planner to solve subproblems in contexts defined by the high-level decomposition.

Laboratory MIPL VICAR artificial intelligence AI↗
DOE OSTI2024

Moment extraction using an unfolding protocol without binning

Deconvolving (“unfolding”) detector distortions is a critical step in the comparison of cross-section measurements with theoretical predictions in particle and nuclear physics. However, most existing approaches require histogram binning while many theoretical predictions are at the level of statistical moments. We develop a new approach to directly unfold distribution moments as a function of another observable without having to first discretize the data. Our moment unfolding technique uses machine learning and is inspired by Boltzmann weight factors and generative adversarial networks (GANs). We demonstrate the performance of this approach using jet substructure measurements in collider physics. With this illustrative example, we find that our moment unfolding protocol is more precise than bin-based approaches and is as or more precise than completely unbinned methods.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Efficient Monte Carlo event generation for neutrino-nucleus exclusive cross sections

Modern neutrino-nucleus cross section computations need to incorporate sophisticated nuclear models to achieve greater predictive precision. However, the computational complexity of these advanced models often limits their practicality for experimental analyses. To address this challenge, we introduce a new Monte Carlo method utilizing normalizing flows to generate surrogate cross sections that closely approximate those of the original model while significantly reducing computational overhead. As a case study, we built a Monte Carlo event generator for the neutrino-nucleus cross section model developed by the Ghent group. This model employs a Hartree-Fock procedure to establish a quantum mechanical framework in which both the bound and scattering nucleon states are solutions to the mean-field nuclear potential. The surrogate cross sections generated by our method demonstrate excellent accuracy with a relative effective sample size of more than 98.4%, providing a computationally efficient alternative to traditional Monte Carlo sampling methods for differential cross sections.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1990

Discrete event simulation tool for analysis of qualitative models of continuous processing systems

An artificial intelligence design and qualitative modeling tool is disclosed for creating computer models and simulating continuous activities, functions, and/or behavior using developed discrete event techniques. Conveniently, the tool is organized in four modules: library design module, model construction module, simulation module, and experimentation and analysis. The library design module supports the building of library knowledge including component classes and elements pertinent to a particular domain of continuous activities, functions, and behavior being modeled. The continuous behavior is defined discretely with respect to invocation statements, effect statements, and time delays. The functionality of the components is defined in terms of variable cluster instances, independent processes, and modes, further defined in terms of mode transition processes and mode dependent processes. Model construction utilizes the hierarchy of libraries and connects them with appropriate relations. The simulation executes a specialized initialization routine and executes events in a manner that includes selective inherency of characteristics through a time and event schema until the event queue in the simulator is emptied. The experimentation and analysis module supports analysis through the generation of appropriate log files and graphics developments and includes the ability of log file comparisons.

Malin, Jane T.↗
DOE OSTI2025

Lessons Learned from AskGDR: Usage and Impact Analysis of the Geothermal Data Repository's AI Research Assistant: Preprint

In October of 2024, the Department of Energy's (DOE) Geothermal Data Repository (GDR) team officially launched AskGDR, an AI research assistant resulting from the integration of a Large Language Model (LLM) with the metadata and supporting documents associated with GDR datasets. AskGDR allows GDR users to ask deeper questions about the origin of datasets, the methods used to collect them, and the findings they help support. Using Retrieval Augmented Generation (RAG), AskGDR can be used to summarize findings spread across dozens of papers and technical reports or to extract relevant information describing a single data field. However, generative AI is experimental. The National Renewable Energy Laboratory (NREL) has been collecting metrics on AskGDR and documenting lessons learned during its deployment. This paper will outline the efficacy and impact of AskGDR through analysis of its use, operating costs, number and types of questions asked, and the quality of answers provided.

15 GEOTHERMAL ENERGY↗
DOE OSTI2026

ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling

Traditional entropy-based methods—such as cross-entropy loss in classification problems—have long been essential tools for representing the information uncertainty and physical disorder in data and for developing artificial intelligence algorithms. However, the rapid growth of data across various domains has introduced new challenges, particularly the integration of heterogeneous datasets with intrinsic disparities. To address this, we introduce a zentropy-enhanced neural network (ZENN), extending zentropy theory into the data science domain via intrinsic entropy, enabling more effective learning from heterogeneous data sources. ZENN simultaneously learns both energy and intrinsic entropy components, capturing the underlying structure of multisource data. To support this, we redesign the neural network architecture to better reflect the intrinsic properties and variability inherent in diverse datasets. We demonstrate the effectiveness of ZENN on classification tasks and energy landscape reconstructions, showing its superior generalization capabilities and robustness-particularly in predicting high-order derivatives. In image and text classification tasks, ZENN demonstrates superior generalization by introducing a learnable temperature variable that models latent multisource heterogeneity, allowing it to surpass state-of-the-art models on CIFAR-10/100, BBC News, and AG News. As a practical application in materials science, we employ ZENN to reconstruct the Helmholtz energy landscape of Fe3Pt using data generated from density functional theory and capture key material behaviors, including negative thermal expansion and the critical point in the temperature–pressure space. Overall, this work presents a zentropy-grounded framework for data-driven machine learning, positioning ZENN as a versatile and robust approach for scientific problems involving complex, heterogeneous datasets.

36 MATERIALS SCIENCE↗
NASA NTRSDate not supplied

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗
DOE OSTI2026

Energy-efficient scientific computing using chemical reservoirs

The rapid growth of computing demands driven by scientific computing, data analytics, and artificial intelligence (AI) advancements has exposed the limitations of traditional digital processing systems. These systems are nearing physical energy barriers, making significant gains in energy efficiency increasingly unattainable. As we advance toward post-exascale computing, disruptive approaches are critical to overcoming these limitations. Among emerging analog solutions, biochemical computing offers a transformative path for achieving orders-of-magnitude improvements in energy efficiency. By leveraging the natural optimization capabilities of chemical reaction networks (CRNs), biochemical systems have the potential to meet high-performance computing needs through natural scalability. However, numerous challenges remain, including theoretical limitations in mapping computational problems to CRNs and practical barriers in implementing biochemical computing devices. In this paper, we present a framework for chemical computation using biochemical systems and introduce key components of our approach for energy-efficient scientific computing. We showcase the feasibility of this framework by solving a system of ordinary differential equations by emulating a chemical reservoir device, demonstrating its potential for addressing modern computing challenges. This work lays a foundational step toward harnessing the computational power of chemistry to design energy-efficient, scalable, high-performance next-generation computing systems.

Johnson, Connah G. M. [Pacific Northwest National ↗
DOE OSTI2025

Inverse mapping of properties to composition through generative modeling for designing molten salts

Generative modeling (GM) has been increasingly used for the inverse design and optimization of materials, yet its application to molten salt mixtures remains unexplored despite how a successful approach to the inverse design of molten salts would contribute to efficiently exploiting their customizability and unlocking their advantages in applications, such as energy production and energy storage. This work presents a workflow for the inverse design of molten salts with targeted density values, addressing the challenge of representing these complex mixtures in GM. A dataset of critically evaluated molten salt densities is used to train a variational autoencoder coupled with a predictive deep neural network, which then can be used to generate new molten salt compositions with desired density values. The effectiveness of the approach is demonstrated by designing mixtures with distinct densities and validating the predicted values using ab initio molecular dynamics simulations.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗