Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AI system”

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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
NASA NTRS1985

A.I.-based real-time support for high performance aircraft operations

Artificial intelligence (AI) based software and hardware concepts are applied to the handling system malfunctions during flight tests. A representation of malfunction procedure logic using Boolean normal forms are presented. The representation facilitates the automation of malfunction procedures and provides easy testing for the embedded rules. It also forms a potential basis for a parallel implementation in logic hardware. The extraction of logic control rules, from dynamic simulation and their adaptive revision after partial failure are examined. It uses a simplified 2-dimensional aircraft model with a controller that adaptively extracts control rules for directional thrust that satisfies a navigational goal without exceeding pre-established position and velocity limits. Failure recovery (rule adjusting) is examined after partial actuator failure. While this experiment was performed with primitive aircraft and mission models, it illustrates an important paradigm and provided complexity extrapolations for the proposed extraction of expertise from simulation, as discussed. The use of relaxation and inexact reasoning in expert systems was also investigated.

Vidal, J. J.↗
NASA NTRS1989

Proceedings of the NASA Conference on Space Telerobotics, volume 1

The theme of the Conference was man-machine collaboration in space. Topics addressed include: redundant manipulators; man-machine systems; telerobot architecture; remote sensing and planning; navigation; neural networks; fundamental AI research; and reasoning under uncertainty.

Rodriguez, Guillermo↗
DOE OSTI2023

High-performance computing leadership to enable advances in artificial intelligence and a thriving compute ecosystem

The past three decades have witnessed the widespread adoption of high-performance computing (HPC) as an essential tool in the advancement of science. From accelerating critical research in the wake of a global pandemic to climate modelling and national security, HPC has become integral to the most cutting-edge scientific research around the world and across application domains. The global competition to debut the next fastest supercomputer keeps pushing the field forward. Meanwhile, increasing capabilities are bringing hallmarks of science fiction, such as artificial intelligence (AI), into daily life. However, the tremendous power of new computing systems comes with an increased concern about equitable access to these resources and their impact on supporting a thriving workforce.

Tourassi, Georgia↗
NASA NTRSDate not supplied

Artificial Intelligence for Future Earth Science Information Systems and Earth System Digital Twins

NASA's Advanced Information Systems Technology (AIST) Program is one of several Technology programs managed by the Earth Science Technology Office (ESTO) in the Earth Science Division (ESD). The AIST Program focuses on advanced information systems and novel computer science technologies that will be needed by NASA Earth Science in the next 5 to 10 years. The three main thrusts of the AIST Program deal with Novel Observing Strategies (NOS), Analytic Collaborative Frameworks (ACF) and Earth System Digital Twins (ESDT). This presentation summarizes the AIST Program with a special focus on the Artificial Intelligence (AI) and Machine Learning (ML) technologies included in its funded projects.

Earth Science Remote Sensing; Information Systems↗
DOE OSTI2021

Cognitive analysis of metabolomics data for systems biology

Cognitive computing is revolutionizing the way big data are processed and integrated, with artificial intelligence (AI) natural language processing (NLP) platforms helping researchers to efficiently search and digest the vast scientific literature. Most available platforms have been developed for biomedical researchers, but new NLP tools are emerging for biologists in other fields and an important example is metabolomics. NLP provides literature-based contextualization of metabolic features that decreases the time and expert-level subject knowledge required during the prioritization, identification and interpretation steps in the metabolomics data analysis pipeline. Here, we describe and demonstrate four workflows that combine metabolomics data with NLP-based literature searches of scientific databases to aid in the analysis of metabolomics data and their biological interpretation. Additionally, the four procedures can be used in isolation or consecutively, depending on the research questions. The first, used for initial metabolite annotation and prioritization, creates a list of metabolites that would be interesting for follow-up. The second workflow finds literature evidence of the activity of metabolites and metabolic pathways in governing the biological condition on a systems biology level. The third is used to identify candidate biomarkers, and the fourth looks for metabolic conditions or drug-repurposing targets that the two diseases have in common. The protocol can take 1–4 h or more to complete, depending on the processing time of the various software used.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

2022 Operational Assessment Report - Argonne Leadership Computing Facility

This Operational Assessment Report describes how the Argonne Leadership Computing Facility (ALCF) met or exceeded every one of its goals for the calendar year (CY) 2022. In CY 2022, ALCF operated Theta, an Intel-based Cray XC40 system (11.7 petaflops) augmented with 24 NVIDIA DGX A100-based nodes (3.9 petaflops), that supports diverse workloads, integrating data analytics with artificial intelligence (AI) training and learning in a single platform; and Polaris, a 44-petaflop AMD and NVIDIA-based HPE Apollo 6500 Gen10+ system that provides a powerful new platform to prepare applications and workloads for Aurora, Argonne National Laboratory’s (Argonne’s) upcoming Intel-Hewlett Packard Enterprise (HPE) exascale supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

The DOE E3SM v1.2 Cryosphere Configuration: Description and Simulated Antarctic Ice‐Shelf Basal Melting

Abstract The processes responsible for freshwater flux from the Antarctic Ice Sheet (AIS), ice‐shelf basal melting and iceberg calving, are generally poorly represented in current Earth System Models (ESMs). Here we document the cryosphere configuration of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SM) v1.2. This includes simulating Antarctic ice‐shelf basal melting, which has been implemented through simulating the ocean circulation within static Antarctic ice‐shelf cavities, allowing for the ability to calculate ice‐shelf basal melt rates from the associated heat and freshwater fluxes. In addition, we added the capability to prescribe forcing from iceberg melt, allowing for realistic representation of the other dominant mass loss process from the AIS. In standard resolution simulations (using a noneddying ocean) under preindustrial climate forcing, we find high sensitivity of modeled ocean/ice shelf interactions to the ocean state, which can result in a transition to a high basal melt regime under the Filchner‐Ronne Ice Shelf (FRIS), presenting a significant challenge to representing the ocean/ice shelf system in a coupled ESM. We show that inclusion of a spatially dependent parameterization of eddy‐induced transport reduces biases in water mass properties on the Antarctic continental shelf. With these improvements, E3SM produces realistic ice‐shelf basal melt rates across the continent that are generally within the range inferred from observations. The accurate representation of ice‐shelf basal melting within a coupled ESM is an important step toward reducing uncertainties in projections of the Antarctic response to climate change and Antarctica's contribution to global sea‐level rise.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

End-to-End Differentiable Modeling and Management of the Environment

Focal Area: (2) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization. We emphasize the importance of leveraging optimization techniques from AI/machine learning (ML) to solve challenging problems in Earth system modeling. Science Challenge: Automatic differentiation has had a transformative effect on ML by allowing the calculation of gradients of arbitrary functions in an incredibly large class of models. We can potentially realize similar improvements in parameter estimation and control for Earth system models (ESMs) by reimplementing them in computational frameworks from ML. Practitioners working with large (>10 7 parameters) models in ML and AI can obtain good predictive performance in a range of spatiotemporal tasks by making use of optimization via stochastic gradient descent and incorporating prior knowledge at multiple levels. We propose writing ESMs in open-source computational frameworks such as Torch, Tensorflow, and JAX to greatly expand the scope of environmental forecasting and management challenges, which can be addressed by leveraging automatic differentiation and gradient descent-like algorithms. We do not call for a wholesale replacement of physical models with data-driven surrogates, but rather advocate for interleaving physical and empirical equations in a manner that is most faithful to the extent of our scientific knowledge and observational data. Central to this topic is the merging of differentiable physical simulations with differentiable optimization layers, which are now both beginning to come to the forefront.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1992

Space Communication Artificial Intelligence for Link Evaluation Terminal (SCAILET)

A software application to assist end-users of the high burst rate (HBR) link evaluation terminal (LET) for satellite communications is being developed. The HBR LET system developed at NASA Lewis Research Center is an element of the Advanced Communications Technology Satellite (ACTS) Project. The HBR LET is divided into seven major subsystems, each with its own expert. Programming scripts, test procedures defined by design engineers, set up the HBR LET system. These programming scripts are cryptic, hard to maintain and require a steep learning curve. These scripts were developed by the system engineers who will not be available for the end-users of the system. To increase end-user productivity a friendly interface needs to be added to the system. One possible solution is to provide the user with adequate documentation to perform the needed tasks. With the complexity of this system the vast amount of documentation needed would be overwhelming and the information would be hard to retrieve. With limited resources, maintenance is another reason for not using this form of documentation. An advanced form of interaction is being explored using current computer techniques. This application, which incorporates a combination of multimedia and artificial intelligence (AI) techniques to provided end-users with an intelligent interface to the HBR LET system, is comprised of an intelligent assistant, intelligent tutoring, and hypermedia documentation. The intelligent assistant and tutoring systems address the critical programming needs of the end-user.

Shahidi, Anoosh K.↗
DOE OSTI2025

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗
NASA NTRS1993

Crisis action planning and replanning using SIPE-2

Rome Laboratory and DARPA are jointly sponsoring an initiative to develop the next generation of AI planning and scheduling technology focused on military operations planning, especially for crisis situations. SRI International has demonstrated their knowledge-based planning technology in this domain with a system called SOCAP, System for Operations Crisis Action Planning. SOCAP's underlying power comes from SIPE-2, a hierarchical, domain-independent, nonlinear AI planner also developed at SRI. This paper discusses the features of SIPE-2 that made it an ideal choice for military operations planning and which contributed greatly to SOCAP's success.

Skidmore, Jennifer D.↗
DOE OSTI2022

Developments in Online Monitoring Technologies for Autonomous Microreactor Operations

This report presents the results of an ongoing research and development (R&D) effort to develop an online monitoring (OLM) system to support autonomous microreactor operations. A key component of this work is an evaluation of Artificial Intelligence (AI) and Machine Learning (ML) techniques to identify, diagnose, and predict problems with sensors and processes of the reactor. As described herein, selected methods of AI/ML were used to identify and diagnose anomalous sensor and system behaviors using data from a thermal-hydraulic flow loop and from operating nuclear power plants. This work serves to further the state-of-the-art in OLM technologies for nuclear reactor applications and will ultimately result in a comprehensive system to enable OLM of critical structures, systems, components, and processes in microreactors.

Machine learning↗
NASA NTRS2018

Metrology-based Techniques for Optical System Alignment for the OSIRIS-Rx Visual and InfraRed Spectrometer

The alignment, integration, and test group (AI&T) in the optics branch at NASA Goddard Space Flight Center (GSFC) specializes in optical and opto-mechanical alignment and metrology for project ranging from building and testing instrument such as spectrometers and cameras to larger structures such as telescopes to large volume metrology and alignment at the observatory level for spacecraft payloads. One of the projects that involved the support of the AI&T group was the OSIRIS-Rex Visual and Infra-Red Spectrometer (OVIRS) for the Origins-Spectral Interpretation-Resource Identification-Security-Regolith Explorer (OSIRIS-Rex) mission. The purpose of this report is to outline the tools, methods, and approaches to metrology utilized by the AI&T group and how they were applied specifically to the optical alignment of the elements on OVIRS during the ambient I&T phase.

Young, Jerrod↗
DOE OSTI2025

Techno-economics of hydrocarbon fuel production and recyclables recovery from landfill-destined municipal solid waste: AI-enhanced materials recovery facility design

Sustainable aviation fuels (SAF) production from cellulosic paper fractions of municipal solid waste (MSW) destined for landfills has strong potential to advance environmental, social, and economic sustainability across the aviation and waste sectors. This study proposes an artificial intelligence-enabled material recovery facility (AI-MRF) design to efficiently characterize, separate, process, and convert recovered paper waste from MSW into intermediate chemicals and SAF. The AI-MRF, designed to process 233,091 metric tons of MSW annually, integrates smart manufacturing technologies including AI, visual and hyperspectral imaging, multi-sensor data, and traditional sorting systems. Well-characterized and sorted cellulosic paper waste was utilized for chemical and fuel production scenarios, while clean plastics, metals, and glass were considered for recycling. Conversion of paper waste into intermediate sugars achieved a net present value (NPV) of up to $\$67$ million. For sugar-to-SAF production scenarios, the minimum fuel selling price (MFSP) was calculated at $\$6.11$ per gasoline gallon equivalent (GGE) when excluding recyclable revenue, and $\$4.03$ per GGE when halving recyclable revenue. The MFSP was further reduced to $\$1.96$ per GGE when accounting for SAF sales and recyclables. Nationally, this approach could yield about 2 billion GGE of hydrocarbon fuel annually from available MSW in the United States.

09 BIOMASS FUELS↗
DOE OSTI2021

Appendices for Geothermal Exploration Artificial Intelligence Report

The Geothermal Exploration Artificial Intelligence looks to use machine learning to spot geothermal identifiers from land maps. This is done to remotely detect geothermal sites for the purpose of energy uses. Such uses include enhanced geothermal system (EGS) applications, especially regarding finding locations for viable EGS sites. This submission includes the appendices and reports formerly attached to the Geothermal Exploration Artificial Intelligence Quarterly and Final Reports. The appendices below include methodologies, results, and some data regarding what was used to train the Geothermal Exploration AI. The methodology reports explain how specific anomaly detection modes were selected for use with the Geo Exploration AI. This also includes how the detection mode is useful for finding geothermal sites. Some methodology reports also include small amounts of code. Results from these reports explain the accuracy of methods used for the selected sites (Brady Desert Peak and Salton Sea). Data from these detection modes can be found in some of the reports, such as the Mineral Markers Maps, but most of the raw data is included the DOE Database which includes Brady, Desert Peak, and Salton Sea Geothermal Sites.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Navier: Dataflow Architecture for Computation Chemistry

Navier’s objectives were two evaluate the use of emerging technologies, especially dataflow accelerators, for high-performance computing (HPC) applications, specifically in the domain of chemistry, and to develop a prototype software stack to support such applications. Navier builds on capabilities previously developed by synergistic projects, such as PNNL Data Model Convergence (DMC) LDRD Hardware Advanced Workflows (HAW) and DuOMO, as well as DOE ARIAA. Throughout its 18 months, the Navier team developed new capabilities and artifacts at all levels of the HW/SW stack, provided a seamless way to integrate novel computing architectures (Sambanova SN10 and Xilinx Versal AI) into an existing software stack, developed chemistry workflows, data analytics tools, and HPC molecular dynamics workflows that leverage the developed stack and PNNL institutional investments in emerging architectures. Navier also explored the use of active learning to accelerate a computational chemistry workflow for organic molecules on PNNL Junction cluster (in collaboration with AMD/Xilinx). Navier developed tools, methodologies, and studies for hardware software co-design and (sparse) dataflow accelerators that are composable and can be used together or separately. These methodologies are now used in other projects, such as DOE AMAIS and HPDA. This report describes Navier’s achievement, the developed tools and methodologies, and the research findings and conclusions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Level-2 Milestone 9009: Flux and Rabbit Capabilities on El Capitan

This document is the milestone delivery report for the ASC 2025 L2 milestone (See Table 1) for advanced I/O capabilities for El Capitan via Flux Workload Manager support and the new I/O hardware designed for El Capitan, the Rabbit Storage System. In this document we describe the design of the Rabbit Storage System and how it is managed by Flux. We evaluate the performance and usability of Rabbit using ARES, IOR, and an AI inference workload. Overall, we find that Rabbit shows good scalability, especially in node-local storage configurations, and is more scalable than the global Lustre parallel file system.

97 MATHEMATICS AND COMPUTING↗