Search NASA⌕ Search

SEARCH · Search NASA

Results for “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 1,351 records · Page 75

Towards an Introspective Dynamic Model of Globally Distributed Computing Infrastructures

Large-scale scientific collaborations like ATLAS, Belle II, CMS, DUNE, and others involve hundreds of research institutes and thousands of researchers spread across the globe. These experiments generate petabytes of data, with volumes soon expected to reach exabytes. Consequently, there is a growing need for computation, including structured data processing from raw data to consumer-ready derived data, extensive Monte Carlo simulation campaigns, and a wide range of end-user analysis. To manage these computational and storage demands, centralized workflow and data management systems are implemented. However, decisions regarding data placement and payload allocation are often made disjointly and via heuristic means. A significant obstacle in adopting more effective heuristic or AI-driven solutions is the absence of a quick and reliable introspective dynamic model to evaluate and refine alternative approaches. In this study, we aim to develop such an interactive system using real-world data. By examining job execution records from the PanDA workflow management system, we have pinpointed key performance indicators such as queuing time, error rate, and the extent of remote data access. The dataset includes five months of activity. Additionally, we are creating a generative AI model to simulate time series of payloads, which incorporate visible features like category, event count, and submitting group, as well as hidden features like the total computational load—derived from existing PanDA records and computing site capabilities. These hidden features, which are not visible to job allocators, whether heuristic or AI-driven, influence factors such as queuing times and data movement.

kilic, Ozgur Ozan [Brookhaven National Laboratory ↗

Anomalous yield reduction in direct-drive deuterium/tritium implosions due to {sup 3}He addition

Glass capsules were imploded in direct drive on the OMEGA laser [Boehly et al., Opt. Commun. 133, 495 (1997)] to look for anomalous degradation in deuterium/tritium (DT) yield and changes in reaction history with {sup 3}He addition. Such anomalies have previously been reported for D/{sup 3}He plasmas but had not yet been investigated for DT/{sup 3}He. Anomalies such as these provide fertile ground for furthering our physics understanding of inertial confinement fusion implosions and capsule performance. Anomalous degradation in the compression component of yield was observed, consistent with the ''factor of 2'' degradation previously reported by Massachusetts Institute of Technology (MIT) at a 50%{sup 3}He atom fraction in D{sub 2} using plastic capsules [Rygg, Phys. Plasmas 13, 052702 (2006)]. However, clean calculations (i.e., no fuel-shell mixing) predict the shock component of yield quite well, contrary to the result reported by MIT but consistent with Los Alamos National Laboratory results in D{sub 2}/{sup 3}He[Wilson et al., J. Phys.: Conf. Ser. 112, 022015 (2008)]. X-ray imaging suggests less-than-predicted compression of capsules containing {sup 3}He. Leading candidate explanations are poorly understood equation of state for gas mixtures and unanticipated particle pressure variation with increasing {sup 3}He addition.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Structures of the cGMP-dependent protein kinase in malaria parasites reveal a unique structural relay mechanism for activation

The cyclic guanosine-3',5'-monophosphate (cGMP)-dependent protein kinase (PKG) was identified >25 y ago; however, efforts to obtain a structure of the entire PKG enzyme or catalytic domain from any species have failed. In malaria parasites, cooperative activation of PKG triggers crucial developmental transitions throughout the complex life cycle. We have determined the cGMP-free crystallographic structures of PKG from Plasmodium falciparum and Plasmodium vivax, revealing how key structural components, including an N-terminal autoinhibitory segment (AIS), four predicted cyclic nucleotide-binding domains (CNBs), and a kinase domain (KD), are arranged when the enzyme is inactive. The four CNBs and the KD are in a pentagonal configuration, with the AIS docked in the substrate site of the KD in a swapped-domain dimeric arrangement. We show that although the protein is predominantly a monomer (the dimer is unlikely to be representative of the physiological form), the binding of the AIS is necessary to keep Plasmodium PKG inactive. A major feature is a helix serving the dual role of the N-terminal helix of the KD as well as the capping helix of the neighboring CNB. A network of connecting helices between neighboring CNBs contributes to maintaining the kinase in its inactive conformation. We propose a scheme in which cooperative binding of cGMP, beginning at the CNB closest to the KD, transmits conformational changes around the pentagonal molecule in a structural relay mechanism, enabling PKG to orchestrate rapid, highly regulated developmental switches in response to dynamic modulation of cGMP levels in the parasite.

59 BASIC BIOLOGICAL SCIENCES↗

Protein folds vs. protein folding: Differing questions, different challenges

We report protein fold prediction using deep-learning artificial intelligence (AI) has transformed the field of protein structure prediction. By combining physical and geometric constraints—and especially patterns extracted from the Protein Data Bank —these machine learning algorithms can predict protein structures at or near atomic resolution and do so in seconds. Today, these computational methods have now solved more than 200 million protein structures, which are accessible from the AlphaFold Protein Structure Database. This accomplishment seems all the more remarkable because few thought it possible or saw it coming. Deservedly, deep-learning AI was named Science magazine’s 2021 “breakthrough of the year”. Clearly, deep-learning AI represents a major advance in protein fold prediction.

54 ENVIRONMENTAL SCIENCES↗

Application of Artificial Intelligence in Detection and Mitigation of Human Factor Errors in Nuclear Power Plants: A Review

Human factors and ergonomics have played an essential role in increasing the safety and performance of operators in the nuclear energy industry. In this critical review, we examine how artificial intelligence (AI) technologies can be leveraged to mitigate human errors, thereby improving the safety and performance of operators in nuclear power plants (NPPs). First, we discuss the various causes of human errors in NPPs. Next, we examine the ways in which AI has been introduced to and incorporated into different types of operator support systems to mitigate these human errors. We specifically examine (1) operator support systems, including decision support systems, (2) sensor fault detection systems, (3) operation validation systems, (4) operator monitoring systems, (5) autonomous control systems, (6) predictive maintenance systems, (7) automated text analysis systems, and (8) safety assessment systems. Finally, we provide some of the shortcomings of the existing AI technologies and discuss the challenges still ahead for their further adoption and implementation to provide future research directions.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Laser resonance ionization spectroscopy of thorium

High-lying Rydberg and autoionizing (AI) states of thorium (Th) have been studied via resonance laser ionization spectroscopy at both TRIUMF Canada’s particle accelerator center and Oak Ridge National Lab (ORNL). Multiple Rydberg series converging to the ionization potential (IP) were observed via different stepwise laser excitation schemes and were assigned to be the 6d 2 7s ( 4 F 3/2 ) np, nd, and nf series. Analysis of these series enabled the determination of the IP to be 50 868.735(54) cm −1 , which improved the precision by two orders of magnitude over the current adopted NIST value of 50 867(2) cm −1 . Additionally, four AI Rydberg series were identified and assigned to nf and nd series converging to the 6d 2 7s 4 F 5/2 and 6d7s 2 2 D 3/2 metastable states of Th + . In conclusion, the measured energies of the Rydberg and AI Rydberg states are reported, and observed perturbations within the series are discussed.

Rydberg series↗

Artificial Intelligence for imaging Cherenkov detectors at the EIC

Abstract Imaging Cherenkov detectors form the backbone of particle identification (PID) at the future Electron Ion Collider (EIC). Currently all the designs for the first EIC detector proposal use a dual Ring Imaging CHerenkov (dRICH) detector in the hadron endcap, a Detector for Internally Reflected Cherenkov (DIRC) light in the barrel, and a modular RICH (mRICH) in the electron endcap. These detectors involve optical processes with many photons that need to be tracked through complex surfaces at the simulation level, while for reconstruction they rely on pattern recognition of ring images. This proceeding summarizes ongoing efforts and possible applications of AI for imaging Cherenkov detectors at EIC. In particular we will provide the example of the dRICH for the AI-assisted design and of the DIRC for simulation and particle identification from complex patterns and discuss possible advantages of using AI.

Instruments & Instrumentation↗

Towards a RAG-based summarization for the Electron Ion Collider

Abstract The complexity and sheer volume of information — encompassing documents, papers, data, and other resources — from large-scale experiments demand significant time and effort to navigate, making the task of accessing and utilizing these varied forms of information daunting, particularly for new collaborators and early-career scientists.To tackle this issue, a Retrieval Augmented Generation (RAG)-based Summarization AI for EIC (RAGS4EIC) is under development. This AI-Agent not only condenses information but also effectively references relevant responses, offering substantial advantages for collaborators. Our project involves a two-step approach: first, querying a comprehensive vector database containing all pertinent experiment information; second, utilizing a Large Language Model (LLM) to generate concise summaries enriched with citations based on user queries and retrieved data. We describe the evaluation methods that use RAG assessments (RAGAs) scoring mechanisms to assess the effectiveness of responses. Furthermore, we describe the concept of prompt template based instruction-tuning which provides flexibility and accuracy in summarization. Importantly, the implementation relies on LangChain [1], which serves as the foundation of our entire workflow. This integration ensures efficiency and scalability, facilitating smooth deployment and accessibility for various user groups within the Electron Ion Collider (EIC) community. This innovative AI-driven framework not only simplifies the understanding of vast datasets but also encourages collaborative participation, thereby empowering researchers. As a demonstration, a web application has been developed to explain each stage of the RAG Agent development in detail. The application can be accessed athttps://rags4eic-ai4eic.streamlit.app.[A tagged version of the source code can be found inhttps://github.com/ai4eic/EIC-RAG-Project/releases/tag/AI4EIC2023_PROCEEDING.]

Instruments & Instrumentation↗

A simple framework to characterize land aridity based on surface energy partitioning regimes

Land aridity is often characterized by the aridity index (AI), which does not account for land surface water-energy interactions that are crucially important in determining regional climate. Such interactions can be captured by the evaporative fraction (EF, ratio of evapotranspiration to available energy) regimes. As EF is subject to energy and water limitations in humid and dry areas, respectively, EF regimes may be used to characterize land aridity to account for the influence of complex land characteristics and their impact on water availability. Here, we propose a simple framework to characterize land aridity by statistically ranking the coupling strength between EF and surface energy and water terms. The framework is demonstrated using gridded data and compared with AI over the U.S. and China. Results show that regionalization of aridity zones based on EF regimes and a two-tiered classification scheme may provide information such as surface energy and water variability complementary to the background aridity depicted by AI, with implications for extreme events.

54 ENVIRONMENTAL SCIENCES↗

Xylem-dwelling pathogen unaffected by local xylem vessel network properties in grapevines ( Vitis spp.)

Abstract Background and aims Xylella fastidiosa (Xf) is the xylem-dwelling bacterium associated with Pierce’s disease (PD), which causes mortality in agriculturally important species, such as grapevine (Vitis vinifera). The development of PD symptoms in grapevines depends on the ability of Xf to produce cell-wall-degrading enzymes to break up intervessel pit membranes and systematically spread through the xylem vessel network. Our objective here was to investigate whether PD resistance could be mechanistically linked to xylem vessel network local connectivity. Methods We used high-resolution X-ray micro-computed tomography (microCT) imaging to identify and describe the type, area and spatial distribution of intervessel connections for six different grapevine genotypes from three genetic backgrounds, with varying resistance to PD (four PD resistant and two PD susceptible). Key results Our results suggest that PD resistance is unlikely to derive from local xylem network connectivity. The intervessel pit area (Ai) varied from 0.07 ± 0.01 mm2 mm−3 in Lenoir to 0.17 ± 0.03 mm2 mm−3 in Blanc do Bois, both PD resistant. Intervessel contact fraction (Cp) was not statically significant, but the two PD-susceptible genotypes, Syrah (0.056 ± 0.015) and Chardonnay (0.041 ± 0.013), were among the most highly connected vessel networks. Neither Ai nor Cp explained differences in PD resistance among the six genotypes. Bayesian re-analysis of our data shows moderate evidence against the effects of the traits analysed: Ai (BF01 = 4.88), mean vessel density (4.86), relay diameter (4.30), relay density (3.31) and solitary vessel proportion (3.19). Conclusions Our results show that radial and tangential xylem network connectivity is highly conserved within the six different Vitis genotypes we sampled. The way that Xf traverses the vessel network may limit the importance of local network properties to its spread and may confer greater importance on host biochemical responses.

Plant Sciences↗

Prototyping method for Bragg-type atom interferometers

We present a method for rapid modeling of new Bragg ultracold atom-interferometer (AI) designs useful for assessing the performance of such interferometers. The method simulates the overall effect on the condensate wave function in a given AI design using two separate elements. These are (1) modeling the effect of a Bragg pulse on the wave function and (2) approximating the evolution of the wave function during the intervals between the pulses. The actual sequence of these pulses and intervals is then followed to determine the approximate final wave function from which the interference pattern can be calculated. The exact evolution between pulses is assumed to be governed by the Gross-Pitaevskii (GP) equation whose solution is approximated using a Lagrangian variational method to facilitate rapid estimation of performance. The method presented here is an extension of an earlier one that was used to analyze the results of an experiment [J. E. Simsarian et al., Phys. Rev. Lett. 85, 2040 (2000)], where the phase of a Bose-Einstein condensate was measured using a Mach-Zehnder-type Bragg AI. We have developed both 1D and 3D versions of this method and we have determined their validity by comparing their predicted interference patterns with those obtained by numerical integration of the 1D GP equation and with the results of the above experiment. We find excellent agreement between the 1D interference patterns predicted by this method and those found by the GP equation. We show that we can reproduce all of the results of that experiment without recourse to an ad hoc velocity-kick correction needed by the earlier method, including some experimental results that the earlier model did not predict. We also found that this method provides estimates of 1D interference patterns at least four orders-of-magnitude faster than direct numerical solution of the 1D GP equation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

An Artificial Neural Network System for Photon-Based Active Interrogation Applications

Active interrogation (AI) is a promising technique to detect shielded special nuclear materials (SNMs). At the University of Michigan, we are developing a photon-based AI system that uses bremsstrahlung radiation from an electron linear accelerator (linac) as an ionizing source and stilbene organic scintillating detectors for neutron detection. Stilbene scintillators are sensitive to fast neutrons and photons and have excellent pulse shape discrimination (PSD) capabilities. The traditional charge integration (CI) method commonly used for PSD analysis eliminates piled-up pulses and relies on a particle discrimination line to separate neutrons and photons. The presence of the intense photon flux during AI creates a significant number of piled-up events in the stilbene scintillator, thereby posing a great challenge to the traditional CI method. Identifying true single neutron pulses becomes challenging due to the presence of a pile-up cloud and overlapping neutron, photon and pile-up clouds in the PSD analysis. To mitigate the effect of pulse pile up and identify true single neutron pulses from stilbene scintillators, an artificial neural network (ANN) system is developed. The developed ANN system identifies single neutron pulses and neutron-photon combinations from piled-up events. The results obtained from a 252Cf measurement in the presence of the intense photon flux show that the developed ANN system outperforms the traditional CI method. Since many piled-up events lie above the particle discrimination line, they get misclassified as neutrons by the traditional CI method resulting in 25% overestimation of the net neutron count rate during the linac pulse. The overall net neutron count rate (single and restored neutrons) during the linac pulse, estimated by the ANN system is 60% of the ground truth. Energy spectroscopy of the ANN attributed single neutron pulses further provides evidence on the detection of prompt fission neutrons from the 252Cf fission source.

42 ENGINEERING↗

The Effects of Compounded Model Size Reductions on Adversarial Robustness

Recent advances in Edge AI and Tiny Machine Learning (TinyML) have enabled the deployment of machine learning models on resource-constrained environments. However, deploying these models on edge devices, such as micro-controllers, requires significant model footprint reduction through a variety of techniques such as quantization, pruning, and clustering. While these optimization methods offer considerable advantages, they potentially introduce AI-related security vulnerabilities, particularly concerning model robustness with respect to adversarial AI attacks. Prior research has extensively examined the impact of quantization on adversarial robustness; however, the effects of alternative reduction techniques and their combinations remain understudied. This paper investigates the impact of model size reduction techniques on adversarial robustness, when applied individually and combined. We utilized Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks to generate adversarial perturbations for both training and testing data, and then evaluated the models' accuracy under adversarial training conditions. Our findings revealed that reduction techniques generally diminished robustness; although, combining techniques was not found to make robustness any worse than when applied individually. Moreover, specific techniques can potentially enhance resistance to small size perturbations. This research provides insights into the trade-offs between model size reduction and security, establishing a foundation for future investigations into improving adversarial training techniques and methodologies for maintaining robustness while preserving memory footprint benefits.

Austria, Phillipe [ORNL] (ORCID:0000000236223973)↗

Measurement and applications: Exploring the challenges and opportunities of hierarchical federated learning in sensor applications

Sensor applications have become ubiquitous in modern society as the digital age continues to advance. AI-based techniques (e.g., machine learning) are effective at extracting actionable information from large amounts of data. An example would be an automated water irrigation system that uses AI-based techniques on soil quality data to decide how to best distribute water. However, these AI-based techniques are costly in terms of hardware resources, and Internet-of-Things (IoT) sensors are resource-constrained with respect to processing power, energy, and storage capacity. These limitations can compromise the security, performance, and reliability of sensor-driven applications. To address these concerns, cloud computing services can be used by sensor applications for data storage and processing. Unfortunately, cloud-based sensor applications that require real-time processing, such as medical applications (e.g., fall detection and stroke prediction), are vulnerable to issues such as network latency due to the sparse and unreliable networks between the sensor nodes and the cloud server [1]. As users approach the edge of the communications network, latency issues become more severe and frequent. A promising alternative is edge computing, which provides cloud-like capabilities at the edge of the network by pushing storage and processing capabilities from centralized nodes to edge devices that are closer to where the data are gathered, resulting in reduced network delays [2], [3].

Po-Leen Ooi, Melanie↗

Climbing the Summit and Pushing the Frontier of Mixed Precision Benchmarks at Extreme Scale

The rise of machine learning (ML) applications and their use of mixed precision to perform interesting science are driving forces behind AI for science on HPC. The convergence of ML and HPC with mixed precision offers the possibility of transformational changes in computational science. The HPL-AI benchmark is designed to measure the performance of mixed precision arithmetic as opposed to the HPL benchmark which measures double precision performance. Pushing the limits of systems at extreme scale is nontrivial -little public literature explores optimization of mixed precision computations at this scale. In this work, we demonstrate how to scale up the HPL-AI benchmark on the pre-exascale Summit and exascale Frontier systems at the Oak Ridge Leadership Computing Facility (OLCF) with a cross-platform design. We present the implementation, performance results, and a guideline of optimization strategies employed for delivering portable performance on both AMD and NVIDIA GPUs at extreme scale.

Lu, Hao↗

ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Wang, Xiao↗

Learning error distribution kernel‐enhanced neural network methodology for multi‐intersection signal control optimization

Traffic congestion has substantially induced significant mobility and energy inefficiency. Many research challenges are identified in traffic signal control and management associated with artificial intelligence (AI)-based models. For example, developing AI-driven dynamic traffic system models that accurately capture high-resolution traffic attributes and formulate robust control algorithms for traffic signal optimization is difficult. Additionally, uncertainties in traffic system modeling and control processes can further complicate traffic signal system controllability. To partially address these challenges, this study presents a novel, hybrid neural network model enhanced with a probability density function kernel shaping technique to formulate traffic system dynamics better and improve comprehensive traffic network modeling and control. The numerical experimental tests were conducted, and the results demonstrate that the proposed control approach outperforms the baseline control strategies and reduces overall average delays by 11.64% on average. By leveraging the capabilities of this innovative model, this study aims to address major challenges related to traffic congestion and energy inefficiency toward more effective and adaptable AI-based traffic control systems.

Wang, Hong [Oak Ridge National Laboratory (ORNL), ↗

On the compatibility of established methods with emerging artificial intelligence and machine learning methods for disaster risk analysis

Abstract There is growing interest in leveraging advanced analytics, including artificial intelligence (AI) and machine learning (ML), for disaster risk analysis (RA) applications. These emerging methods offer unprecedented abilities to assess risk in settings where threats can emerge and transform quickly by relying on “learning” through datasets. There is a need to understand these emerging methods in comparison to the more established set of risk assessment methods commonly used in practice. These existing methods are generally accepted by the risk community and are grounded in use across various risk application areas. The next frontier in RA with emerging methods is to develop insights for evaluating the compatibility of those risk methods with more recent advancements in AI/ML, particularly with consideration of usefulness, trust, explainability, and other factors. This article leverages inputs from RA and AI experts to investigate the compatibility of various risk assessment methods, including both established methods and an example of a commonly used AI‐based method for disaster RA applications. This article utilizes empirical evidence from expert perspectives to support key insights on those methods and the compatibility of those methods. This article will be of interest to researchers and practitioners in risk‐analytics disciplines who leverage AI/ML methods.

Mathematical Methods In Social Sciences↗