Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 145 records · Page 8

Robust Design Under Uncertainty in Quantum Error Mitigation

Error mitigation techniques are crucial to achieving near-term quantum advantage. Classical postprocessing of quantum computation outcomes is a popular approach for error mitigation, which includes methods, such as zero noise extrapolation, virtual distillation, and learning-based error mitigation. However, these techniques have limitations due to the propagation of uncertainty resulting from the finite shot number of a quantum measurement. In this work, we introduce general and unbiased methods for quantifying the uncertainty and error of error-mitigated observables based on the strategic sampling of error mitigation outcomes. We then extend our approach to demonstrate the optimization of performance and robustness of error mitigation under uncertainty. To illustrate our methods, we apply them to zero noise extrapolation and Clifford date regression in the ground state of the XY model simulated using depolarizing and International Business Machines Corporation (IBM) Toronto noise models, respectively. In particular, we optimize the choice of noise levels and the allocation of shots for zero noise extrapolation and the distribution of the training circuits for Clifford data regression. While our methods are readily applicable to any postprocessing-based error mitigation approach, in practice they must not be prohibitively expensive—even though they perform optimizations of the error mitigation hyperparameters requiring sampling of a statistical distribution of error mitigation outcomes. By leveraging surrogate-based optimization, we show that our methods can efficiently perform optimal design for a zero noise extrapolation implementation. We then further demonstrate the transferability of learned zero noise extrapolation hyperparameters to other similar circuits.

97 MATHEMATICS AND COMPUTING↗

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.

Wang, Tianqi↗

Use of Combined A-Train Observations to Validate GEOS Model Simulated Dust Distributions During NAMMA

During August 2006, the NASA African Multidisciplinary Analyses Mission (NAMMA) field experiment was conducted to characterize the structure of African Easterly Waves and their evolution into tropical storms. Mineral dust aerosols affect tropical storm development, although their exact role remains to be understood. To better understand the role of dust on tropical cyclogenesis, we have implemented a dust source, transport, and optical model in the NASA Goddard Earth Observing System (GEOS) atmospheric general circulation model and data assimilation system. Our dust source scheme is more physically based scheme than previous incarnations of the model, and we introduce improved dust optical and microphysical processes through inclusion of a detailed microphysical scheme. Here we use A-Train observations from MODIS, OMI, and CALIPSO with NAMMA DC-8 flight data to evaluate the simulated dust distributions and microphysical properties. Our goal is to synthesize the multi-spectral observations from the A-Train sensors to arrive at a consistent set of optical properties for the dust aerosols suitable for direct forcing calculations.

Nowottnick, E.↗

A selection of giant radio sources from NVSS

Results of the application of pattern-recognition techniques to the problem of identifying giant radio sources (GRSs) from the data in the NVSS catalog are presented, and issues affecting the process are explored. Decision-tree pattern-recognition software was applied to training-set source pairs developed from known NVSS large-angular-size radio galaxies. The full training set consisted of 51,195 source pairs, 48 of which were known GRSs for which each lobe was primarily represented by a single catalog component. The source pairs had a maximum separation of $20^{\prime} $ and a minimum component area of 1.87 square arcmin at the 1.4 mJy level. The importance of comparing the resulting probability distributions of the training and application sets for cases of unknown class ratio is demonstrated. The probability of correctly ranking a randomly selected (GRS, non-GRS) pair from the best of the tested classifiers was determined to be 97.8 ± 1.5%. The best classifiers were applied to the over 870,000 candidate pairs from the entire catalog. Images of higher-ranked sources were visually screened, and a table of over 1600 candidates, including morphological annotation, is presented. These systems include doubles and triples, wide-angle tail and narrow-angle tail, S- or Z-shaped systems, and core-jets and resolved cores. In conclusion, while some resolved-lobe systems are recovered with this technique, generally it is expected that such systems would require a different approach.

79 ASTRONOMY AND ASTROPHYSICS↗

Development of physics-consistent conditional diffusion model to overcome data scarcity in critical heat flux

Deep generative modeling provides a powerful pathway to overcome data scarcity in energy-related applications where experimental data are often limited. By learning the underlying probability distribution of the training dataset, deep generative models, such as the diffusion model, can generate high-fidelity synthetic samples that statistically resemble the training data. Such synthetic data generation can significantly enrich the size and diversity of the available training data, and more importantly, improve the robustness of downstream machine learning models in predictive tasks. The objective of this paper is to investigate the effectiveness of diffusion models for overcoming data scarcity in nuclear energy applications. By leveraging a public dataset on critical heat flux which covers a wide range of commercial nuclear reactor operational conditions, we developed a diffusion model that can generate an arbitrary amount of synthetic samples. Since a vanilla diffusion model can only generate samples randomly, we also developed a conditional diffusion model capable of generating targeted critical heat flux data under user-specified thermal-hydraulic conditions. The performance of the diffusion model was evaluated based on its ability to capture empirical feature distributions and pair-wise correlations, as well as to maintain physical consistency. The results showed that both the diffusion model and conditional diffusion model can successfully generate realistic and physics-consistent critical heat flux data. Furthermore, uncertainty quantification results demonstrate that the conditional diffusion model is highly effective in augmenting critical heat flux data while maintaining acceptable levels of uncertainty.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Energy Security and Restoration Exercise Program/Best Practices and Information Sharing

The first year of this cooperative agreement focused on the following elements: curriculum development and presentation, curriculum maintenance, enhancements, and effectiveness, and smart card initiative. During the second year of this grant, with redirection from DOE, the IUOE modified its mission statement under the cooperative agreement. It states: 'The mission of the IUOE is to provide expertise to provide best practices, information sharing, and develop scenarios and conduct exercises ranging in size and complexity from table top to national level to prepare all stakeholders to protect and restore energy infrastructure should an event, terrorist or natural, occur'. The Program developed a number of products under this Cooperative Agreement. These products include: FOSTER (Facility Operations Safety Training Event Response) Curriculum and Training Models, Alternative Energy Supply - Generators Training Module, Liquefied Natural Gas Training Module, Education Program - Distributed Generations, Compendium of Resources and References, Energy Security and Restoration Training Manual, Manual of Situations and Scenarios Developed for Emergency Exercises, Manual of Best Practices/Lessons Learned for Energy Load Management, Training Plan, Strategic Information and Exercise Plan, National Certification Plan Report, and a Smart Card Project Report.

03 NATURAL GAS↗

Training site statistics from Landsat and Seasat satellite imagery registered to a common map base

Landsat and Seasat satellite imagery and training site boundary coordinates were registered to a common Universal Transverse Mercator map base in the Newport Beach area of Orange County, California. The purpose was to establish a spatially-registered, multi-sensor data base which would test the use of Seasat synthetic aperture radar imagery to improve spectral separability of channels used for land use classification of an urban area. Digital image processing techniques originally developed for the digital mosaics of the California Desert and the State of Arizona were adapted to spatially register multispectral and radar data. Techniques included control point selection from imagery and USGS topographic quadrangle maps, control point cataloguing with the Image Based Information System, and spatial and spectral rectifications of the imagery. The radar imagery was pre-processed to reduce its tendency toward uniform data distributions, so that training site statistics for selected Landsat and pre-processed Seasat imagery indicated good spectral separation between channels.

Clark, J.↗

Application of Unbiased Estimators to Group Classification Risk Estimation

We consider the problem of construction of point and interval estimators for the Bayesian risk of a group classification decision rule provided that the elements of training samples have distributions belonging to the same one-parameter exponential family. We propose a solution to this problem using the asymptotic normality and efficiency of an unbiased risk estimator. An example of application of the obtained theoretical results is given.

97 MATHEMATICS AND COMPUTING↗

A hybrid deep neural operator/finite element method for ice-sheet modeling

One of the most challenging and consequential problems in climate modeling is to provide probabilistic projections of sea level rise. A large part of the uncertainty of sea level projections is due to uncertainty in ice sheet dynamics. At the moment, accurate quantification of the uncertainty is hindered by the cost of ice sheet computational models. In this work we develop a hybrid approach to approximate existing ice sheet models at a fraction of their cost. Our approach consists of replacing the finite element model for the momentum equations for the ice velocity, the most expensive part of an ice sheet model, with a Deep Operator Network, while we retain a classic finite element discretization for the evolution of the ice thickness. We show that the resulting hybrid model is very accurate and it is an order of magnitude faster than the traditional finite element model. Further, a distinctive feature of the proposed model, compared to other neural network approaches, is that it can handle high-dimensional parameter spaces (parameter fields) such as the basal friction at the bed of the glacier and can therefore be used for generating samples for uncertainty quantification. Further, we study the impact of hyper-parameters, number of unknowns and correlation length of the parameter distribution on the training and accuracy of the Deep Operator Network on a synthetic ice sheet model. We then target the evolution of the Humboldt glacier in Greenland and show that our hybrid model can provide accurate statistics of the glacier mass loss and can be effectively used to accelerate the quantification of uncertainty.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Deep learning for visualization and novelty detection in large X-ray diffraction datasets

Abstract We apply variational autoencoders (VAE) to X-ray diffraction (XRD) data analysis on both simulated and experimental thin-film data. We show that crystal structure representations learned by a VAE reveal latent information, such as the structural similarity of textured diffraction patterns. While other artificial intelligence (AI) agents are effective at classifying XRD data into known phases, a similarly conditioned VAE is uniquely effective at knowing what it doesn’t know: it can rapidly identify data outside the distribution it was trained on, such as novel phases and mixtures. These capabilities demonstrate that a VAE is a valuable AI agent for aiding materials discovery and understanding XRD measurements both ‘on-the-fly’ and during post hoc analysis.

36 MATERIALS SCIENCE↗

Electron Bunch Timing with Femtosecond Precision in a Superconducting Free-Electron Laser

High-gain free-electron lasers (FELs) are capable of generating femtosecond x-ray pulses with peak brilliances many orders of magnitude higher than at other existing x-ray sources. In order to fully exploit the opportunities offered by these femtosecond light pulses in time-resolved experiments, an unprecedented synchronization accuracy is required. In this Letter, we distributed the pulse train of a mode-locked fiber laser with femtosecond stability to different locations in the linear accelerator of the soft x-ray FEL FLASH. A novel electro-optic detection scheme was applied to measure the electron bunch arrival time with an as yet unrivaled precision of 6 fs (rms). With two beam-based feedback systems we succeeded in stabilizing both the arrival time and the electron bunch compression process within two magnetic chicanes, yielding a significant reduction of the FEL pulse energy jitter.

43 PARTICLE ACCELERATORS↗

Scalable Multi-Facility Workflows for Artificial Intelligence Applications in Climate Research

Earth observation satellites and earth system models are sources of vast, multi-modal datasets that are invaluable for advancing climate and environmental research. However, their scale and complexity pose significant challenges for processing and analysis. In this paper we discuss our experiences in developing and using a scientific research application using an automated multi-facility workflow that orchestrates data collection, preprocessing, artificial intelligence (AI) inferencing, and data movement across diverse computational resources, leveraging the Advanced Computing Ecosystem Testbed at the Oak Ridge Leadership Computing Facility (OLCF). We demonstrate that our workflow can be seamlessly integrated and orchestrated across research facilities managed by different federal agencies, thus allowing users to extract new scientific insights from climate datasets. The experimental results indicate that the multi-facility workflow significantly reduces processing time, enhances scalability, and maintains high efficiency across varying workloads. Notably, our workflow processes 12,000 high-resolution satellite images in just 44 seconds using 80 workers distributed across 10 nodes on the OLCF systems. Such high throughput is essential for dynamic tokenization and sharding of petascale satellite data for distributed AI model training and inferencing at scale across thousands of GPUs.

Kurihana, Takuya [ORNL] (ORCID:0000000156698565)↗

DiHydrogen

DiHydrogen is the second version of the Hydrogen fork of the well-known distributed linear algebra library, Elemental. DiHydrogen is a GPU-accelerated distributed multilinear algebra interface with a particular emphasis on the needs of the scalable distributed deep learning training and inference. DiHydrogen is part of the Livermore Big Artificial Neural Network (LBANN) software stack.

Maruyama, Naoya↗

Applications of Federated Learning in Semiconductor Manufacturing [Poster]

As semiconductor manufacturers explore advanced data analytics and modeling techniques and data hungry machine learning models increase in popularity due to their accuracy in solving generalized problems and ability to learn complex relationships, federated learning emerges as a privacy preserving machine learning technique for preserving data privacy and ensuring intellectual property protection. Federated Learning is a machine learning technique focused on training models using distributed data that never needs to be centrally stored, allowing the use of advanced machine learning techniques without compromising data privacy, and in the semiconductor manufacturing industry advanced machine learning techniques can reduce cost and time, but maintaining data privacy is essential to maintaining a competitive advantage. This paper systematically reviews existing literature on applications of federated learning in the semiconductor manufacturing industry with a focus on identifying common themes, algorithms, and gaps within the literature to drive future research directions. The findings reveal five key themes, including improvements in quality assurance, virtual models, privacy preservation, reliable data practices, and emerging trends and developments. By identifying key themes in literature on federated learning and semiconductor manufacturing and analyzing gaps and discussed methodologies, this study highlights several potential future research directions to expand the application of federated learning techniques in the semiconductor manufacturing domain.

42 ENGINEERING↗

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗

Centennial of Flight Educational Outreach

The Centennial of Flight Education Outreach project worked with community partners to disseminate NASA Education materials and the Centennial of Flight CD-ROM as a vehicle to increase national awareness of NASA's Aerospace Education products, services and programs. The Azimuth Education Foundation and the Ninety Nines, an International Women Pilots Association, Inc. were chartered to conduct education outreach to the formal and informal educational community. The Dryden Education Office supported the development of a training and information distribution program that established a national group of prepared Centennial of Flight Ambassadors, with a mission of community education outreach. These Ambassadors are members of the Ninety Nines and through the Azimuth Foundation, they assisted the AECC on the national level to promote and disseminate Centennial of Flight and other educational products. Our objectives were to explore partnership outreach growth opportunities with consortium efforts between organizations. This project directly responded to the highlights of NASA s Implementation Plan for Education. It was structured to network, involve the community, and provide a solid link to active educators and current students with NASA education information. Licensed female pilots who live and work in local communities across the nation carried the link. This partnership has been extremely gratifying to all of those Ninety-Nines involved, and they eagerly look forward to further work opportunities.

McCarthy, Marianne↗

Coordinated Science Campaign Scheduling for Sensor Webs

Future Earth observing missions will study different aspects and interacting pieces of the Earth's eco-system. Scientists are designing increasingly complex, interdisciplinary campaigns to exploit the diverse capabilities of multiple Earth sensing assets. In addition, spacecraft platforms are being configured into clusters, trains, or other distributed organizations in order to improve either the quality or the coverage of observations. These simultaneous advances in the design of science campaigns and in the missions that will provide the sensing resources to support them offer new challenges in the coordination of data and operations that are not addressed by current practice. For example, the scheduling of scientific observations for satellites in low Earth orbit is currently conducted independently by each mission operations center. An absence of an information infrastructure to enable the scheduling of coordinated observations involving multiple sensors makes it difficult to execute campaigns involving multiple assets. This paper proposes a software architecture and describes a prototype system called DESOPS (Distributed Earth Science Observation Planning and Scheduling) that will address this deficiency.

Edgington, Will↗