Search NASA⌕ Search

SEARCH · Search NASA

Results for “AI Evaluations”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Energy and AI: Evaluating Future Grid and Water Stress Due to Data Centers

Projections of the need for new data centers to support Artificial Intelligence (AI) are large but highly uncertain. Recent projections indicate up to a 15% annual growth rate in data center electricity demand within the next 5-10 years. Given that most electric utilities are required to have a reserve margin of roughly the same magnitude as the projected growth in demand, these new data center loads could soon threaten resource adequacy and reliability unless data centers build their own generation, interruptible loads are negotiated, commensurate new capacity and/or transmission is built, or some combination of these options. Similarly, depending on the cooling technology and geographic location of new data centers, they could threaten water adequacy in water scarce regions. This presentation highlights the grid and water implications of new data centers to support AI.

Mongird, Kendall (ORCID:0000000328077088)↗
NASA NTRS1985

Evaluation of AIS Data for Agronomic and Rangeland Vegetation: Preliminary Results for August 1984 Flight over Nebraska Sandhills Agricultural Laboratory

Since 1978 scientists from the Center for Agricultural Meteorology and Climatology at the University of Nebraska have been conducting research at the Sandhills Agricultural Laboratory on the effects of water stress on crop growth, development and yield using remote sensing techniques. We have been working to develop techniques, both remote and ground-based, to monitor water stress, phenological development, leaf area, phytomass production and grain yields of corn, soybeans and sorghum. Because of the sandy soils and relatively low rainfall at the site it is an excellent location to study water stress without the necessity of installing expensive rainout shelters. The primary objectives of research with the airborne imaging spectrometer (AIS) data collected during an August 1984 flight over the Sandhills Agricultural Laboratory are to evaluate the potential of using AIS to: (1) discriminate crop type; (2) to detect subtle architectural differences that exist among different cultivars or hybrids of agronomic crops; (3) to detect and quantify, if possible, the level of water stress imposed on the crops; and (4) to evaluate leaf area and biomass differences for different crops.

Blad, B. L.↗
DOE OSTI2026

A Benchmark Suite for Evaluating Scientific AI Workloads on GPUs

AI applications have been steadily increasing in the allocation portfolio among leadership computing facilities. These applications depend on deep learning frameworks with hardware acceleration and underlying software systems. With the rapid development of applications, software stacks, and hardware devices, it is essential to evaluate the performance of core operations in AI workloads for direction of optimizations and procurement of next-generation high-performance computing (HPC) infrastructures. Currently, most benchmarks lack scientific AI workloads. So, we present DeepKernelBench and the experimental results of evaluating the benchmark suite for early observations and performance comparisons on datacenter GPUs using representative workloads for scientific AI, including Attentions, General matrix multiplications, Geometrics and Fourier neural operations.

Jin, Zheming [Advanced Micro Devices (AMD)]↗
DOE OSTI2024

An Evaluation of AI Models’ Performance for Three Geothermal Sites

Current artificial intelligence (AI) applications in geothermal exploration are tailored to specific geothermal sites, limiting their transferability and broader applicability. This study aims to develop a globally applicable and transferable geothermal AI model to empower the exploration of geothermal resources. This study presents a methodology for adopting geothermal AI that utilizes known indicators of geothermal areas, including mineral markers, land surface temperature (LST), and faults. The proposed methodology involves a comparative analysis of three distinct geothermal sites—Brady, Desert Peak, and Coso. The research plan includes self-testing to understand the unique characteristics of each site, followed by dependent and independent tests to assess cross-compatibility and model transferability. The results indicate that Desert Peak and Coso geothermal sites are cross-compatible due to their similar geothermal characteristics, allowing the AI model to be transferable between these sites. However, Brady is found to be incompatible with both Desert Peak and Coso. The geothermal AI model developed in this study demonstrates the potential for transferability and applicability to other geothermal sites with similar characteristics, enhancing the efficiency and effectiveness of geothermal resource exploration. This advancement in geothermal AI modeling can significantly contribute to the global expansion of geothermal energy, supporting sustainable energy goals.

Energy & Fuels↗
NASA NTRS1985

Preliminary Evaluation of AIS Spectra Along a Topographic/moisture Gradient in the Nebraska Sandhills

Six spectral plots, each summarizing single-pixel reflectance for 128 channels of Airborne Imaging Spectrometer (AIS) data, were examined. The six sample pixels were located along a topographic/moisture gradient from lake surface to dune top in the Nebraska Sandhills. AIS spectra for various moisture regimes/vegetative zones appear quite logical, with a general positive relationship between increasing elevation (i.e., decreasing access of plant roots to water) and increasing reflectance in the spectral regions diagnostic of leaf-water content (i.e., bands centered on 1.65 and 2.20 microns).

Runquist, D. C.↗
NASA NTRS1987

Evaluation of AIS-2 (1986) data over hydrothermally altered granitoid rocks of the Singatse Range (Yerington) Nevada and comparison with 1985 AIS-1 data

The Airborne Imaging Spectrometer-2 (AIS-2) flights along 2 subparallel lines (bearing 013) were designed to traverse 3 major rock assemblages - the Triassic sedimentary sequence; the granitoid rocks of the Yerington batholith and the Tertiary ignimbritic ash flow and ash fall tuffs. The first 2 sites are hydrothermally altered to a quartz-sericite-tourmaline mineralogy. The first AIS-2 data set showed numerous line dropouts and a considerable number of randomly distributed dark pixels. A second decommutation reduced the dropout essentially to near zero and the dark pixels by about 75 percent. Vertical striping was removed by histogram matching, column by column. A log residual spectrum was calculated which showed the departure of a 2 x 2 pixel area from the spatially and spectrally averaged scene. A 1:1 correlation was found with the log residual AIS-2 data and a large open pit area of gypsum. An area with known sericite agreed with the overflight data, and an area known to be free of any significant amount of O-H bearing materials showed no evidence of any in the AIS-2 log residuals.

Lyon, R. J. P.↗
DOE OSTI2025

Ranking and Classifying AI Benchmarks

We created a set of standards to efficiently evaluate AI benchmarks through objective means. Although prevalent, especially in recent times, AI benchmarks have no single way to measure their effectiveness. The MLCommons team provided a set of criteria for evaluating benchmarks, although the criteria lacks a clearly defined set of evaluation rules. We created a rubric with preset factors to efficiently and objectively evaluate a benchmark s quality. We created a software framework for processing lists of benchmarks for visualization. The framework and rating system allows researchers to quickly check if their benchmarks are effective.

Shiraishi, Reece C. [Cornell U.]↗
DOE OSTI2025

Classifying and rating AI benchmarks

We created a set of standards to efficiently evaluate AI benchmarks through objective means. Although prevalent, especially in recent times, AI benchmarks have no single way to measure their effectiveness. The MLCommons team provided a set of criteria for evaluating benchmarks, although the criteria lacks a clearly defined set of evaluation rules. We created a rubric with preset factors to efficiently and objectively evaluate a benchmark’s quality. We created a software framework for processing lists of benchmarks for visualization. The framework and rating system allows researchers to quickly check if their benchmarks are effective.

Shiraishi, Reece [Fermilab]↗
NASA NTRS2004

Approach for Autonomous Control of Unmanned Aerial Vehicle Using Intelligent Agents for Knowledge Creation

This paper describes the development of a planned approach for Autonomous operation of an Unmanned Aerial Vehicle (UAV). A Hybrid approach will seek to provide Knowledge Generation thru the application of Artificial Intelligence (AI) and Intelligent Agents (IA) for UAV control. The application of many different types of AI techniques for flight will be explored during this research effort. The research concentration will be directed to the application of different AI methods within the UAV arena. By evaluating AI approaches, which will include Expert Systems, Neural Networks, Intelligent Agents, Fuzzy Logic, and Complex Adaptive Systems, a new insight may be gained into the benefits of AI techniques applied to achieving true autonomous operation of these systems thus providing new intellectual merit to this research field. The major area of discussion will be limited to the UAV. The systems of interest include small aircraft, insects, and miniature aircraft. Although flight systems will be explored, the benefits should apply to many Unmanned Vehicles such as: Rovers, Ocean Explorers, Robots, and autonomous operation systems. The flight system will be broken down into control agents that will represent the intelligent agent approach used in AI. After the completion of a successful approach, a framework of applying a Security Overseer will be added in an attempt to address errors, emergencies, failures, damage, or over dynamic environment. The chosen control problem was the landing phase of UAV operation. The initial results from simulation in FlightGear are presented.

Dufrene, Warren R., Jr.↗
NASA NTRS2004

Approach for Autonomous Control of Unmanned Aerial Vehicle Using Intelligent Agents for Knowledge Creation

This paper describes the development of a planned approach for Autonomous operation of an Unmanned Aerial Vehicle (UAV). A Hybrid approach will seek to provide Knowledge Generation through the application of Artificial Intelligence (AI) and Intelligent Agents (IA) for UAV control. The applications of several different types of AI techniques for flight are explored during this research effort. The research concentration is directed to the application of different AI methods within the UAV arena. By evaluating AI and biological system approaches. which include Expert Systems, Neural Networks. Intelligent Agents, Fuzzy Logic, and Complex Adaptive Systems, a new insight may be gained into the benefits of AI and CAS techniques applied to achieving true autonomous operation of these systems. Although flight systems were explored, the benefits should apply to many Unmanned Vehicles such as: Rovers. Ocean Explorers, Robots, and autonomous operation systems. A portion of the flight system is broken down into control agents that represent the intelligent agent approach used in AI. After the completion of a successful approach, a framework for applying an intelligent agent is presented. The initial results from simulation of a security agent for communication are presented.

Dufrene, Warren R., Jr.↗
DOE OSTI2025

Construction of approximate invariants for nonintegrable Hamiltonian systems

We present a method to construct high-order polynomial approximate invariants (AI) for nonintegrable Hamiltonian dynamical systems and apply it to a modern ring-based particle accelerator. Taking advantage of a special property of one-turn transformation maps expressed as square matrices, AIs can be constructed order by order iteratively. Evaluating AI with simulation data, we observe that AI’s fluctuation is actually a measure of chaos. Through minimizing the fluctuations, the stable region of long-term motions, i.e., the dynamic aperture of the accelerator, could be enlarged.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Construction of approximate invariants for non-integrable Hamiltonian systems

We present a method to construct high-order polynomial approximate invariants (AI) for non integrable Hamiltonian dynamical systems, and apply it to a modern ring-based particle accelerator. Taking advantage of a special property of one-turn transformation maps in the form of a square matrix, AIs can be constructed order-by-order iteratively. Evaluating AI with simulation data, we observe that AI’s fluctuation is actually a measure of chaos. Through minimizing the fluctuations, the stable region of long-term motions, i.e., the dynamic aperture of the accelerator, could be enlarged.

43 PARTICLE ACCELERATORS↗
DOE OSTI2026

Poster: Responsible Adoption of Artificial Intelligence (AI) in Electric Grid Operations

The rapid integration of artificial intelligence (AI) in the utility transmission and distribution (T&D) sector is revolutionizing traditional grid management practices. As utilities encounter complexities from evolving consumer behaviors and energy integration, AI becomes a critical solution for enhancing grid monitoring, fault detection, and operational optimization. However, increased reliance on interconnected technologies introduces significant cybersecurity risks, regulatory compliance challenges, and human factors concerns. This study proposes a strategic, responsible and consequence-driven approach to AI implementation, examining the dual nature of AI adoption by highlighting its transformative benefits for utilities and associated risks. It provides utilities with a framework for evaluating AI integration, enabling them to navigate challenges and capitalize on opportunities to achieve greater reliability, efficiency, and resilience in an increasingly complex energy landscape.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Evaluation of AI-enabled Digital Documented Safety Analysis

The National Reactor Innovation Center (NRIC) is leading a transformative initiative to accelerate advanced reactor deployment by fundamentally reimagining how nuclear safety basis documentation is developed, reviewed, and maintained. Traditional Documented Safety Analysis (DSA) processes for DOE-authorized facilities rely on static, document-centric workflows that consume significant time and resources, exemplified by recent major licensing efforts requiring hundreds of thousands of staff hours and millions of pages of documentation review. These conventional approaches create barriers to the rapid, cost-effective deployment of advanced reactors that America's future energy needs demand. NRIC's DOE Authorization Digital Transformation Project addresses these challenges through an innovative framework that integrates artificial intelligence (AI), digital engineering, and systems-based data management into a cohesive digital ecosystem. This white paper presents NRIC's methodology for evaluating AI-enabled document generation capabilities within this broader digital infrastructure, using the Demonstration of Microreactor Experiments (DOME) facility as a pilot case study. The evaluation will assess an AI tool's ability to generate a Preliminary Documented Safety Analysis (PDSA) through progressive integration stages—from standalone document processing to full digital thread connectivity—while maintaining rigorous verification, validation, and regulatory acceptance standards. By establishing dynamic, traceable connections between design data and safety documentation, NRIC's approach has the potential to reduce both document development time and regulatory review cycles by as much as 50%, while simultaneously improving accuracy, consistency, and traceability. This initiative represents a critical step toward establishing reusable digital infrastructure that reactor developers can leverage to accelerate their path from concept to commercial operation, directly supporting NRIC's mission to demonstrate and deploy advanced nuclear energy technologies.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Evaluation of AI-Enabled Digital Documented Safety Analysis: A Case Study

Safety basis documentation development and review under U.S. Department of Energy (DOE) authorization have emerged as critical constraint throttling deployment of advanced nuclear reactors, with traditional processes demanding extraordinary resource investment that delays the delivery of these technologies. Traditional Documented Safety Analysis (DSA) processes rely on static documents with limited traceability [U.S. DOE]. The regulatory review and engagement processes are similarly constrained, often requiring significant effort and extensive manual verification. The scale of this challenge is exemplified by the U.S. Nuclear Regulatory Commission (NRC) review of the NuScale application, which required over 250,000 staff hours and the evaluation of approximately two million pages of documentation [Bergman 2021]. The volume and complexity of information within nuclear licensing applications or authorization reviews demands innovative approaches to document generation and data management.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗