Search NASA⌕ Search

SEARCH · Search NASA

Results for “Computational 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 1,477 records · Page 82

Introduction to structure from motion and its applications in remote sensing

This talk discusses my experience at Los Alamos National Laboratories developing the Wide Area Persistent Surveillance (WAPS) system AngelFire and the problems with working with low resolution surface models. This experience provided a motivation to seek solutions to utilize the redundant WAPS imagery to build surface models of the urban environment. Structure from Motion (SfM) is a process that takes multiple view imagery and compute the 3D structure of a scene. We will walk through the basic algorithm and discuss areas for optimization. Military services and intelligence agencies face long-standing challenges with processing, exploiting, and disseminating ISR data. The problem is that too much data is being produced and not enough people to look at it and the problem is not going away. As a result of this data overload, we need to shift the way we think about data and find creative ways to use and present it so it can be easily digested by decision makers. SfM also provides a means for developing a data processing and organization architecture. Applications for various remote sensing applications will be discussed for motivation for why SfM and Multi-View Stereo rendering is an important area that needs to be continued to be developed.

47 OTHER INSTRUMENTATION↗

A Benchmarking Framework for Evaluating Large Language Model Capabilities in Nuclear Reactor Safety Applications

Large language models (LLMs) are increasingly capable of answering technical questions, synthesizing domain knowledge, and supporting engineering workflows. For nuclear science and engineering, these capabilities require careful, domain-specific evaluation before they can be credibly incorporated into safety-related activities, regulatory review, or technical decision support. This paper presents preliminary results from benchmarking framework for evaluating LLM capabilities in nuclear contexts. The framework is organized into three evaluation categories: nuclear fundamentals, general dual-use knowledge, and plant specific knowledge. These categories are intended to distinguish general nuclear engineering competence from broader technical reasoning and more context-dependent nuclear knowledge. Initial evaluations focus on nuclear fundamentals using questions representative of the knowledge expected of a nuclear professional engineer. Results indicate that contemporary frontier models perform at a high level and substantially exceed the performance of older model generations, with some models approaching saturation of the current benchmark. These findings suggest both the rapid improvement of LLM capabilities in specialized technical domains and the need for more discriminating evaluation methods. The paper presents the benchmark structure, preliminary model-comparison results, and ongoing work. This work supports development of verifiable, responsible, and safety-conscious methods for assessing AI systems in nuclear engineering applications.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

Challenges in Securing the Interface Between the Cloud and Pervasive Systems

Cloud computing presents an opportunity for pervasive systems to leverage computational and storage resources to accomplish tasks that would not normally be possible on such resource-constrained devices. Cloud computing can enable hardware designers to build lighter systems that last longer and are more mobile. Despite the advantages cloud computing offers to the designers of pervasive systems, there are some limitations of leveraging cloud computing that must be addressed. We take the position that cloud-based pervasive system must be secured holistically and discuss ways this might be accomplished. In this paper, we discuss a pervasive system utilizing cloud computing resources and issues that must be addressed in such a system. In this system, the user's mobile device cannot always have network access to leverage resources from the cloud, so it must make intelligent decisions about what data should be stored locally and what processes should be run locally. As a result of these decisions, the user becomes vulnerable to attacks while interfacing with the pervasive system.

97 MATHEMATICS AND COMPUTING↗

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications

In this work we introduce a novel two-level overlapping additive Schwarz preconditioner for accelerating the training of scientific machine learning applications. The design of the proposed preconditioner is motivated by the nonlinear two-level overlapping additive Schwarz preconditioner. The neural network parameters are decomposed into groups (subdomains) with overlapping regions. In addition, the network’s feed-forward structure is indirectly imposed through a novel subdomain-wise synchronization strategy and a coarse-level training step. Through a series of numerical experiments, which consider physicsinformed neural networks and operator learning approaches, we demonstrate that the proposed two-level preconditioner significantly speeds up the convergence of the standard (LBFGS) optimizer while also yielding more accurate machine learning models. Moreover, the devised preconditioner is designed to take advantage of model-parallel computations, which can further reduce the training time.

97 MATHEMATICS AND COMPUTING↗

From Chaos to Clarity: Autonomous Materials Discovery for Extreme Environments

The pursuit of advanced functional materials for energy applications demands an understanding of their behavior under the most challenging conditions. Extreme environments, characterized by intense radiation, high temperatures, and corrosive chemistries, push materials to their limits, often revealing unexpected behaviors and degradation pathways. Traditional materials research approaches, relying on trial-and-error experimentation, are often slow and resource-intensive, ill-suited to the complexities of extreme environments. This talk will explore the transformative potential of autonomous materials science in revolutionizing our understanding of materials synthesis and degradation in extreme environments. By integrating advanced microscopy techniques, artificial intelligence, and robotic experimentation, we can accelerate the discovery and design of resilient materials for a sustainable future. The presentation will highlight recent breakthroughs in autonomous microscopy, computer vision, and machine learning, showcasing their ability to unravel complex material transformations at the atomic scale. The talk will also delve into the challenges and opportunities associated with deploying autonomous systems to probe extreme environments, emphasizing the importance of robust algorithms, real-time data analysis, and adaptive experimentation. Our ultimate goal is to empower scientists with unprecedented capabilities to explore, understand, and engineer materials that can withstand the harshest conditions, paving the way for innovations in energy, aerospace, and beyond.

artificial intelligence↗

Lightweight Metal Stamping Optimization Enabled by Artificial Intelligence

Successfully manufacturing an automotive body structure made via the sheet metal stamping process depends upon simultaneous consideration of component design, tooling design, stamping process control, and material properties. In many cases, introducing lightweight sheet materials (e.g., aluminum alloys, magnesium alloys, advanced high strength steels) holds the potential to significantly reduce vehicle weight, but challenges the stamping process by introducing materials with inherently less ductility. Successful and repeatable applications require co-developing the stamping process controls with the varying material properties, including formability. During the stamping process, as soon as the forming limit of the sheet is exceeded, the material shows localized necking which quickly leads to splits. Controlling process variability to avoid these material splits will enable deployment of less formable, lighter, and stronger materials for stamped automotive components. A typical optimization procedure for manufacturing requires an iterative process involving parameter setting, execution of computational simulations, and modifying the parameters. The entire process demands substantial computational time, making it impractical for real-time feedback towards rapid corrective actions required for in-line control for running production processes. To overcome this challenge, artificial intelligence (AI) can be leveraged to determine optimal manufacturing parameters within a single manufacturing cycle time. This research proposes an in-line optimization framework incorporating a trained AI model to predict kidney-shaped die forming. Preliminary results indicate that the AI framework can accurately predict draw-in values based on a given parameter set, a process referred to as forward prediction. Furthermore, the AI framework can also predict the optimal parameter set that leads to the desired draw-in values, referred to as inverse optimization (or backward prediction). This research has been performed in collaborations with USCAR (US Council for Automotive Research) and AutoForm. The members of USCAR are Ford, GM, and Stellantis.

36 MATERIALS SCIENCE↗

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT), a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self-attention. The QGT models variable-length sentences as token graphs, where both the embedding encoding and the self-attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and 𝑘 -nearest-neighbor graph structures and evaluate it on five benchmark sentiment-classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving 29.4 × fewer parameters while requiring 3–5 × fewer samples to reach comparable performance. These findings highlight the potential of graph-based quantum models as scalable and data-efficient architectures for natural language understanding.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Of red planets and indigo computers: Mars database visualization as an example of platform downsizing

The last decade has witnessed tremendous advancements in the computer hardware and software used to perform scientific visualization. In this paper, we consider how the visualization of a particular data set, the digital terrain model derived from the Viking orbiter imagery, has been realized in four distinct projects over this period. These examples serve to demonstrate how the vast improvements in computational performance both decrease the cost of such visualization efforts and permit an increasing level of interactivity. We then consider how even today's graphical systems require the visualization designer to make intelligent choices and tradeoffs in database rendering. Finally, we discuss how insights gleaned from an understanding of human visual perception can guide these design decisions, and suggest new options for visualization hardware and software.

NASA Center ARC↗

A survey on the structured singular value

The structured singular value, U, is an important linear algebra tool to study a class of matrix perturbation problems. It is useful for analyzing the robustness of stability and performance of uncertain, (nominally) linear systems. Computation of (M) is difficult, and usually, upper and lower bounds are all that can be reliably computed. Upper bounds give conservative estimates of the sizes of allowable perturbations. The maximum singular value of a matrix M is an upper bound for (M). As an upper bound, it can be improved by finding a transformations to the data (i.e. M) which do not change the structured singular value, but do reduce the maximum singular value. Typically, upper bound algorithms involve searches over sets of transformations to yield the tightest bound. Lower bound algorithms are intelligent searches for minimum-norm solutions to multivariable polynomial equations, and are based on various optimality conditions that hold at the global (and, unfortunately, some local) minima. The current methods to compute both of these types of bounds are reviewed. Theoretical justification and extensive numerical experience with the various algorithms are covered.

Packard, Andy↗

Quantifying effectiveness of failure prediction and response in HPC systems : methodology and example.

Effective failure prediction and mitigation strategies in high-performance computing systems could provide huge gains in resilience of tightly coupled large-scale scientific codes. These gains would come from prediction-directed process migration and resource servicing, intelligent resource allocation, and checkpointing driven by failure predictors rather than at regular intervals based on nominal mean time to failure. Given probabilistic associations of outlier behavior in hardware-related metrics with eventual failure in hardware, system software, and/or applications, this paper explores approaches for quantifying the effects of prediction and mitigation strategies and demonstrates these using actual production system data. We describe context-relevant methodologies for determining the accuracy and cost-benefit of predictors. While many research studies have quantified the expected impact of growing system size, and the associated shortened mean time to failure (MTTF), on application performance in large-scale high-performance computing (HPC) platforms, there has been little if any work to quantify the possible gains from predicting system resource failures with significant but imperfect accuracy. This possibly stems from HPC system complexity and the fact that, to date, no one has established any good predictors of failure in these systems. Our work in the OVIS project aims to discover these predictors via a variety of data collection techniques and statistical analysis methods that yield probabilistic predictions. The question then is, 'How good or useful are these predictions?' We investigate methods for answering this question in a general setting, and illustrate them using a specific failure predictor discovered on a production system at Sandia.

99 GENERAL AND MISCELLANEOUS↗

An artificial intelligence accelerated virtual screening platform for drug discovery

Abstract Structure-based virtual screening is a key tool in early drug discovery, with growing interest in the screening of multi-billion chemical compound libraries. However, the success of virtual screening crucially depends on the accuracy of the binding pose and binding affinity predicted by computational docking. Here we develop a highly accurate structure-based virtual screen method, RosettaVS, for predicting docking poses and binding affinities. Our approach outperforms other state-of-the-art methods on a wide range of benchmarks, partially due to our ability to model receptor flexibility. We incorporate this into a new open-source artificial intelligence accelerated virtual screening platform for drug discovery. Using this platform, we screen multi-billion compound libraries against two unrelated targets, a ubiquitin ligase target KLHDC2 and the human voltage-gated sodium channel Na V 1.7. For both targets, we discover hit compounds, including seven hits (14% hit rate) to KLHDC2 and four hits (44% hit rate) to Na V 1.7, all with single digit micromolar binding affinities. Screening in both cases is completed in less than seven days. Finally, a high resolution X-ray crystallographic structure validates the predicted docking pose for the KLHDC2 ligand complex, demonstrating the effectiveness of our method in lead discovery.

Science & Technology - Other Topics↗

Applying queueing theory to evaluate wait-time-savings of triage algorithms

Abstract In the past decade, artificial intelligence (AI) algorithms have made promising impacts in many areas of healthcare. One application is AI-enabled prioritization software known as computer-aided triage and notification (CADt). This type of software as a medical device is intended to prioritize reviews of radiological images with time-sensitive findings, thus shortening the waiting time for patients with these findings. While many CADt devices have been deployed into clinical workflows and have been shown to improve patient treatment and clinical outcomes, quantitative methods to evaluate the wait-time-savings from their deployment are not yet available. In this paper, we apply queueing theory methods to evaluate the wait-time-savings of a CADt by calculating the average waiting time per patient image without and with a CADt device being deployed. We study two workflow models with one or multiple radiologists (servers) for a range of AI diagnostic performances, radiologist’s reading rates, and patient image (customer) arrival rates. To evaluate the time-saving performance of a CADt, we use the difference in the mean waiting time between the diseased patient images in the with-CADt scenario and that in the without-CADt scenario as our performance metric. As part of this effort, we have developed and also share a software tool to simulate the radiology workflow around medical image interpretation, to verify theoretical results, and to provide confidence intervals for the performance metric we defined. We show quantitatively that a CADt triage device is more effective in a busy, short-staffed reading setting, which is consistent with our clinical intuition and simulation results. Although this work is motivated by the need for evaluating CADt devices, the evaluation methodology presented in this paper can be applied to assess the time-saving performance of other types of algorithms that prioritize a subset of customers based on binary outputs.

Thompson, Yee Lam Elim (ORCID:0000000196537707)↗

Management and development of local area network upgrade prototype

Given the situation of having management and development users accessing a central computing facility and given the fact that these same users have the need for local computation and storage, the utilization of a commercially available networking system such as CP/NET from Digital Research provides the building blocks for communicating intelligent microsystems to file and print services. The major problems to be overcome in the implementation of such a network are the dearth of intelligent communication front-ends for the microcomputers and the lack of a rich set of management and software development tools.

Fouser, T. J.↗

An efficient representation of spatial information for expert reasoning in robotic vehicles

The previous generation of robotic vehicles and drones was designed for a specific task, with limited flexibility in executing their mission. This limited flexibility arises because the robotic vehicles do not possess the intelligence and knowledge upon which to make significant tactical decisions. Current development of robotic vehicles is toward increased intelligence and capabilities, adapting to a changing environment and altering mission objectives. The latest techniques in artificial intelligence (AI) are being employed to increase the robotic vehicle's intelligent decision-making capabilities. This document describes the design of the SARA spatial database tool, which is composed of request parser, reasoning, computations, and database modules that collectively manage and derive information useful for robotic vehicles.

Scott, Steven↗

Space communications scheduler: A rule-based approach to adaptive deadline scheduling

Job scheduling is a deceptively complex subfield of computer science. The highly combinatorial nature of the problem, which is NP-complete in nearly all cases, requires a scheduling program to intelligently transverse an immense search tree to create the best possible schedule in a minimal amount of time. In addition, the program must continually make adjustments to the initial schedule when faced with last-minute user requests, cancellations, unexpected device failures, quests, cancellations, unexpected device failures, etc. A good scheduler must be quick, flexible, and efficient, even at the expense of generating slightly less-than-optimal schedules. The Space Communication Scheduler (SCS) is an intelligent rule-based scheduling system. SCS is an adaptive deadline scheduler which allocates modular communications resources to meet an ordered set of user-specified job requests on board the NASA Space Station. SCS uses pattern matching techniques to detect potential conflicts through algorithmic and heuristic means. As a result, the system generates and maintains high density schedules without relying heavily on backtracking or blind search techniques. SCS is suitable for many common real-world applications.

Straguzzi, Nicholas↗

The use of artificial neural networks in experimental data acquisition and aerodynamic design

It is proposed that an artificial neural network be used to construct an intelligent data acquisition system. The artificial neural networks (ANN) model has a potential for replacing traditional procedures as well as for use in computational fluid dynamics validation. Potential advantages of the ANN model are listed. As a proof of concept, the author modeled a NACA 0012 airfoil at specific conditions, using the neural network simulator NETS, developed by James Baffes of the NASA Johnson Space Center. The neural network predictions were compared to the actual data. It is concluded that artificial neural networks can provide an elegant and valuable class of mathematical tools for data analysis.

Meade, Andrew J., Jr.↗