Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Sparse Data”

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 1,153 records · Page 64
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Stochastic Gradients for Large-Scale Tensor Decomposition

Tensor decomposition is a well-known tool for multiway data analysis. This work proposes using stochastic gradients for efficient generalized canonical polyadic (GCP) tensor decomposition of large-scale tensors. GCP tensor decomposition is a recently proposed version of tensor decomposition that allows for a variety of loss functions such as Bernoulli loss for binary data or Huber loss for robust estimation. Here, the stochastic gradient is formed from randomly sampled elements of the tensor and is efficient because it can be computed using the sparse matricized-tensor times Khatri--Rao product tensor kernel. For dense tensors, we simply use uniform sampling. For sparse tensors, we propose two types of stratified sampling that give precedence to sampling nonzeros. Numerical results demonstrate the advantages of the proposed approach and its scalability to large-scale problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Fast and Scalable Sparse Triangular Solver for Multi-GPU Based HPC Architectures

Designing efficient and scalable sparse linear algebra kernels on modern multi-GPU based HPC systems is a daunting task due to significant irregular memory references and workload imbalance across the GPUs. This is particularly the case for \textit{Sparse Triangular Solver (SpTRSV)} which introduces additional two-dimensional computation dependencies among subsequent computation steps. Dependency information is exchanged and shared among GPUs, thus warrant for efficient memory allocation, data partitioning, and workload distribution as well as fine-grained communication and synchronization support. In this work, we demonstrate that directly adopting unified memory can adversely affect the performance of SpTRSV on multi-GPU architectures, despite linking via fast interconnect like NVLinks and NVSwitches. Alternatively, we employ the latest NVSHMEM technology based on Partitioned Global Address Space programming model to enable efficient fine-grained communication and drastic synchronization overhead reduction. Furthermore, to handle workload imbalance, we propose a malleable task-pool execution model which can further enhance the utilization of GPUs. By applying these techniques, our experiments on the NVIDIA multi-GPU supernode V100-DGX-1 and DGX-2 systems demonstrate that our design can achieve on average 3.53x (up to 9.86x) speedup on a DGX-1 system and 3.66x (up to 9.64x) speedup on a DGX-2 system with 4-GPUs over the Unified-Memory design. The comprehensive sensitivity and scalability studies also show that the proposed zero-copy SpTRSV is able to fully utilize the computing and communication resources of the multi-GPU system.

Xie, Chenhao↗
DOE OSTI2024

Using automated machine learning for the upscaling of gross primary productivity

Estimating gross primary productivity (GPP) over space and time is fundamental for understanding the response of the terrestrial biosphere to climate change. Eddy covariance flux towers provide in situ estimates of GPP at the ecosystem scale, but their sparse geographical distribution limits larger-scale inference. Machine learning (ML) techniques have been used to address this problem by extrapolating local GPP measurements over space using satellite remote sensing data. However, the accuracy of the regression model can be affected by uncertainties introduced by model selection, parameterization, and choice of explanatory features, among others. Recent advances in automated ML (AutoML) provide a novel automated way to select and synthesize different ML models. In this work, we explore the potential of AutoML by training three major AutoML frameworks on eddy covariance measurements of GPP at 243 globally distributed sites. We compared their ability to predict GPP and its spatial and temporal variability based on different sets of remote sensing explanatory variables. Explanatory variables from only Moderate Resolution Imaging Spectroradiometer (MODIS) surface reflectance data and photosynthetically active radiation explained over 70 % of the monthly variability in GPP, while satellite-derived proxies for canopy structure, photosynthetic activity, environmental stressors, and meteorological variables from reanalysis (ERA5-Land) further improved the frameworks' predictive ability. We found that the AutoML framework Auto-sklearn consistently outperformed other AutoML frameworks as well as a classical random forest regressor in predicting GPP but with small performance differences, reaching an r 2 of up to 0.75. We deployed the best-performing framework to generate global wall-to-wall maps highlighting GPP patterns in good agreement with satellite-derived reference data. This research benchmarks the application of AutoML in GPP estimation and assesses its potential and limitations in quantifying global photosynthetic activity.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1994

Regional and seasonal estimates of fractional storm coverage based on station precipitation observations

Simulated climates using numerical atmospheric general circulation models (GCMs) have been shown to be highly sensitive to the fraction of GCM grid area assumed to be wetted during rain events. The model hydrologic cycle and land-surface water and energy balance are influenced by the parameter bar-kappa, which is the dimensionless fractional wetted area for GCM grids. Hourly precipitation records for over 1700 precipitation stations within the contiguous United States are used to obtain observation-based estimates of fractional wetting that exhibit regional and seasonal variations. The spatial parameter bar-kappa is estimated from the temporal raingauge data using conditional probability relations. Monthly bar-kappa values are estimated for rectangular grid areas over the contiguous United States as defined by the Goddard Institute for Space Studies 4 deg x 5 deg GCM. A bias in the estimates is evident due to the unavoidably sparse raingauge network density, which causes some storms to go undetected by the network. This bias is corrected by deriving the probability of a storm escaping detection by the network. A Monte Carlo simulation study is also conducted that consists of synthetically generated storm arrivals over an artificial grid area. It is used to confirm the bar-kappa estimation procedure and to test the nature of the bias and its correction. These monthly fractional wetting estimates, based on the analysis of station precipitation data, provide an observational basis for assigning the influential parameter bar-kappa in GCM land-surface hydrology parameterizations.

Gong, Gavin↗
DOE OSTI2022

CodEx: A Modular Framework for Joint Temporal De-Blurring and Tomographic Reconstruction

In many computed tomography (CT) imaging applications, it is important to rapidly collect data from an object that is moving or changing with time. Tomographic acquisition is generally assumed to be step-and-shoot, where the object is rotated to each desired angle, and a view is taken. However, step-and-shoot acquisition is slow and can waste photons, so in practice fly-scanning is done where the object is continuously rotated while collecting data. However, this can result in motion-blurred views and consequently reconstructions with severe motion artifacts. In this paper, we introduce CodEx, a modular framework for joint de-blurring and tomographic reconstruction that can effectively invert the motion blur introduced in sparse view fly-scanning. The method is a synergistic combination of a novel acquisition method with a novel non-convex Bayesian reconstruction algorithm. CodEx works by encoding the acquisition with a known binary code that the reconstruction algorithm then inverts. Using a well chosen binary code to encode the measurements can improve the accuracy of the inversion process. The CodEx reconstruction method uses the alternating direction method of multipliers (ADMM) to split the inverse problem into iterative deblurring and reconstruction sub-problems, making reconstruction practical to implement. Here we present reconstruction results on both simulated and binned experimental data to demonstrate the effectiveness of our method.

42 ENGINEERING↗
NASA NTRS2009

Synthesis and Assimilation Systems - Essential Adjuncts to the Observing System

Assimilation systems synthesize diverse in-situ and satellite data streams into full four-dimensional state estimates by combining the strengths of each data set and also of the model. The resulting analysis provides an integrated view of the information in the various observations as well as derived estimates of unobserved quantities. Assimilation systems are particularly important for the ocean where subsurface observations, even today, are sparse and intermittent compared with the scales needed to represent ocean variability and where satellites only sense the surface. Increasingly, models and assimilation systems are being used to provide information about the current observing system and to help in the design plans for new observations. Whether it is as a user of observations or a contributor to evaluation of the observing system, ocean synthesis and assimilation systems are now an integral part of the global ocean observing and information system. Major advances have been made over the last decade under the auspices of WCRP's Climate Variability and Predictability Project (CLIVAR) and the Global Ocean Data Assimilation Experiment (GODAE). In addition to advances in the assimilation systems, there have been major developments in the observing system, with satellite altimetry, the tropical moored buoy arrays in the Pacific and Atlantic, and more recently Argo. These developments have led to significant advances in our understanding and prediction of ocean variations at both mesoscale and climate scales. Many challenges remain. Some of these challenges lie in the observations themselves, some in the assimilation systems that, even in the more recent era of unprecedented observations from satellite altimetry and Argo, provide different views of climate variations. Yet there are many examples of successful applications from ocean assimilation products. Use of these systems for assessing the observing system helps identify the strengths of each observation type, and indicates that none of the current observations is redundant. Indeed, the indication is that the ocean remains under-sampled and that further improvements in the observing system are needed for both climate monitoring and prediction. Future developments will be increasingly towards consistent analyses across components of the Earth system using, e.g., coupled atmosphere-ocean models.

Rienecker, Michele M.↗
NASA NTRS1989

Integration of active and passive sensors for obstacle avoidance

The automatic obstacle-avoidance guidance problem is studied under the operational constraints imposed by the rotorcraft nap-of-the-earth (NOE) environment. The problem is discussed for two different circumstances. The first assumes that a full range map is available, irrespective of the type of sensor being used. Two approaches are proposed to extend a two-dimensional obstacle-avoidance concept presented by Cheng (1988). The situation where only a sparse range map is available from a passive sensor is also treated. An integrated approach that augments the passive sensor with an active one is discussed, along with the problem of data fusion and how it is affected by the characteristics of NOE flight.

Cheng, Victor H. L.↗
NASA NTRS2011

A High-Resolution Capability for Large-Eddy Simulation of Jet Flows

A large-eddy simulation (LES) code that utilizes high-resolution numerical schemes is described and applied to a compressible jet flow. The code is written in a general manner such that the accuracy/resolution of the simulation can be selected by the user. Time discretization is performed using a family of low-dispersion Runge-Kutta schemes, selectable from first- to fourth-order. Spatial discretization is performed using central differencing schemes. Both standard schemes, second- to twelfth-order (3 to 13 point stencils) and Dispersion Relation Preserving schemes from 7 to 13 point stencils are available. The code is written in Fortran 90 and uses hybrid MPI/OpenMP parallelization. The code is applied to the simulation of a Mach 0.9 jet flow. Four-stage third-order Runge-Kutta time stepping and the 13 point DRP spatial discretization scheme of Bogey and Bailly are used. The high resolution numerics used allows for the use of relatively sparse grids. Three levels of grid resolution are examined, 3.5, 6.5, and 9.2 million points. Mean flow, first-order turbulent statistics and turbulent spectra are reported. Good agreement with experimental data for mean flow and first-order turbulent statistics is shown.

DeBonis, James R.↗
NASA NTRS2017

Numerical and Analytical Assessment of a Coupled Rotating Detonation Engine and Turbine Experiment

An analysis is presented of an experimental rig comprising a rotating detonation engine (RDE) with bypass ejector flow coupled to a downstream turbine. The analysis used a validated computational fluid dynamics RDE simulation combined with straightforward algebraic mixing equations for the bypass flow. The objectives of the analysis were to supplement and interpret the necessarily sparse measurements from the rig, and to assess the performance of the RDE itself, which was not instrumented in this installation. The analysis is seen to agree reasonably well with available data. It shows that the RDE is operating in an unusual fashion, with subsonic flow throughout the exhaust plane. The detonation event itself is producing a total pressure rise relative to the pre-detonative pressure; however, the length of the device and the substantial flow restriction at the inlet yield an overall pressure loss. This is not surprising since the objective of the rig test was primarily aimed at investigating RDE/turbine interactions, and not on performance optimization. Furthermore, the RDE was designed for fundamental detonation studies and not performance. Nevertheless, the analysis indicates that with some small alterations to the design, an RDE with an overall pressure rise is possible.

detonation↗
NASA NTRS2017

Numerical and Analytical Assessment of a Coupled Rotating Detonation Engine and Turbine Experiment

An analysis is presented of an experimental rig comprising a rotating detonation engine (RDE) with bypass ejector flow coupled to a downstream turbine. The analysis used a validated computational fluid dynamics RDE simulation combined with straightforward algebraic mixing equations for the bypass flow. The objectives of the analysis were to supplement and interpret the necessarily sparse measurements from the rig, and to assess the performance of the RDE itself, which was not instrumented in this installation. The analysis is seen to agree reasonably well with available data. It shows that the RDE is operating in an unusual fashion, with subsonic flow throughout the exhaust plane. The detonation event itself is producing a total pressure rise relative to the pre-detonative pressure; however, the length of the device and the substantial flow restriction at the inlet yield an overall pressure loss. This is not surprising since the objective of the rig test was primarily aimed at investigating RDE turbine interactions, and not on performance optimization. Furthermore, the RDE was designed for fundamental detonation studies and not performance. Nevertheless, the analysis indicates that with some small alterations to the design, an RDE with an overall pressure rise is possible.

propulsion↗
NASA NTRS2017

Numerical and Analytical Assessment of a Coupled Rotating Detonation Engine and Turbine Experiment

An analysis is presented of an experimental rig comprising a rotating detonation engine (RDE) with bypass flow coupled to a downstream turbine. The analysis used a validated computational fluid dynamics RDE simulation combined with straightforward algebraic mixing equations for the bypass flow. The objectives of the analysis were to supplement and interpret the necessarily sparse measurements from the rig, and to assess the performance of the RDE itself (which was not instrumented in this installation). The analysis is seen to agree reasonably well with available data. It shows that the RDE is operating in an unusual fashion, with subsonic flow throughout the exhaust plane. The detonation event itself is producing a total pressure rise relative to the pre-detonative pressure; however, the length of the device and the substantial flow restriction at the inlet yield an overall pressure loss. This is not surprising since the objective of the rig test was primarily aimed at investigating RDEturbine interactions, and not on performance optimization. Furthermore, the RDE was designed for fundamental detonation studies and not performance. Nevertheless, the analysis indicates that with some small alterations to the design, an RDE with an overall pressure rise is possible.

detonation↗
NASA NTRS2017

Assimilation of AERONET and MODIS AOT Observations Using Variational and Ensemble Data Assimilation Methods and Its Impact on Aerosol Forecasting Skill

Data assimilation of Aerosol Robotic Network (AERONET) and Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol optical thickness (AOT) for aerosol forecasting was tested within the Navy Aerosol Analysis Prediction System (NAAPS) framework, using variational and ensemble data assimilation methods. Navy aerosol forecasting currently makes use of a deterministic NAAPS simulation coupled to Navy Variational Data Assimilation System for aerosol optical depth, a two-dimensional variational data assimilation system, for MODIS AOT assimilation. An ensemble version of NAAPS (ENAAPS) coupled to an ensemble adjustment Kalman filter (EAKF) from the Data Assimilation Research Testbed was recently developed, allowing for a range of data assimilation and forecasting experiments to be run with deterministic NAAPS and ENAAPS. The main findings are that the EAKF, with its flow-dependent error covariances, makes better use of sparse observations such as AERONET AOT. Assimilating individual AERONET observations in the two-dimensional variational system can increase the analysis errors when observations are located in high AOT gradient regions. By including AERONET with MODIS AOT assimilation, the magnitudes of peak aerosol events (AOT> 1) were better captured with improved temporal variability, especially in India and Asia where aerosol prediction is a challenge. Assimilating AERONET AOT with MODIS had little impact on the 24 h forecast skill compared to MODIS assimilation only, but differences were found downwind of AERONET sites. The 24 h forecast skill was approximately the same for forecasts initialized with analyses from AERONET AOT assimilation alone compared to MODIS assimilation, particularly in regions where the AERONET network is dense; including the United States and Europe, indicating that AERONET could serve as a backup observation network for over-land synoptic-scale aerosol events.

Rubin, Juli I.↗
NASA NTRSDate not supplied

Memory Optimizations for Sparse Linear Algebra on GPU Hardware

An effort to maximize memory bandwidth utilization for a sparse linear algebra kernel executing on NVIDIA® Tesla V100 and A100 Graphics Processing Units (GPUs) is described. The kernel consists of a block-sparse matrix-vector product and a series of forward/backward triangular solves. The computation is memory-bound and exhibits low arithmetic intensity. Along with a relatively small block size, the data layout poses a challenge to effectively utilize the available memory bandwidth on common GPU architectures. An earlier implementation using a warp to process a single row of the matrix was found to yield good memory performance on the V100 architecture. However, anew approach, which assigns a warp to six rows of the matrix, is proposed for the A100. In addition, two new features offered by the A100 architecture are explored.L2residency control enables a portion of theL2cache to be used for persistent data access, and the asynchronous copy instruction allows data to be loaded directly from main memory into shared memory. Demonstrations show that the new implementation improves memory bandwidth utilization from 71.5% to 81.2% of the peak available on theA100 architecture.

GPU↗
NASA NTRS2026

Measure sea level air pressure from space to improve knowledge and forecasting of the atmospheric state

Modern numerical weather prediction (NWP) and analysis models require globally-observed meteorological data including sea-level pressure (SLP) for accurate operations. Up until now, SLP has only been measured by in situ instruments from ships, buoys, and ocean platforms. These measurements are sparse with large gaps, leaving models starved of this critical information to constrain the atmospheric state. Recent advancements in differential absorption radar (DAR) provide a path to close this critical observation gap through spaceborne observations in the coming decade, improving the analysis models relied upon for atmospheric research and the weather forecasts depended upon daily for public safety and commerce.

Matthew L Walker McLinden↗
DOE OSTI2022

Compressed basis GMRES on high-performance graphics processing units

Krylov methods provide a fast and highly parallel numerical tool for the iterative solution of many large-scale sparse linear systems. To a large extent, the performance of practical realizations of these methods is constrained by the communication bandwidth in current computer architectures, motivating the investigation of sophisticated techniques to avoid, reduce, and/or hide the message-passing costs (in distributed platforms) and the memory accesses (in all architectures). This article leverages Ginkgo’s memory accessor in order to integrate a communication-reduction strategy into the (Krylov) GMRES solver that decouples the storage format (i.e., the data representation in memory) of the orthogonal basis from the arithmetic precision that is employed during the operations with that basis. Given that the execution time of the GMRES solver is largely determined by the memory accesses, the cost of the datatype transforms can be mostly hidden, resulting in the acceleration of the iterative step via a decrease in the volume of bits being retrieved from memory. Together with the special properties of the orthonormal basis (whose elements are all bounded by 1), this paves the road toward the aggressive customization of the storage format, which includes some floating-point as well as fixed-point formats with mild impact on the convergence of the iterative process. We develop a high-performance implementation of the “compressed basis GMRES” solver in the Ginkgo sparse linear algebra library using a large set of test problems from the SuiteSparse Matrix Collection. We demonstrate robustness and performance advantages on a modern NVIDIA V100 graphics processing unit (GPU) of up to 50% over the standard GMRES solver that stores all data in IEEE double-precision.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Development and Demonstration of a Prototype Molten Salt Sampling System

Molten salt reactors (MSRs) offer potential operability and safety advantages when compared to commercial light water reactors (LWRs). However, operating experience with MSRs is sparse in comparison to what exists for LWRs. Further, the chemical and isotopic composition of the fuel and/or coolant salt is dynamic and difficult to characterize continuously, posing potential safety, operability, and safeguards unknowns that need to be addressed. A molten salt sampling system (MSSS) is regarded as a necessary subsystem within first generation MSRs used to obtain samples of salt for chemical and isotopic analysis in support of the need to monitor and control salt composition during operation. The MSSS is being developed using the Safety-in-Design (SiD) methodology, which incorporates incremental integration of safety analysis into the design process. The MSSS conceptual design emerging from the application of the early stages of the SiD methodology consists of a sample collection system and its housing, a freeze port, and inert gas control and delivery systems. This article describes the prototypes developed to test the functions of these MSSS subsystems, presents the results of testing in both dry and molten salt environments (including reliability data collection performed in accordance with the principles of SiD and the development of a semiquantitative fault tree model), and summarizes the opportunities for future design and testing enhancements based on the results of prototype testing.

molten salt reactor↗
DOE OSTI2022

Physics-Informed Sparse Gaussian Process for Probabilistic Stability Analysis of Large-Scale Power System with Dynamic PVs and Loads

This work proposes a physics-informed sparse Gaussian process (SGP) for probabilistic stability assessment of large-scale power systems in the presence of uncertain dynamic PVs and loads. The differential and algebraic equations considering uncertainties from dynamic PVs and loads are reformulated to a nonlinear mapping relationship that allows the application of SGP. Thanks to the nonparametric characteristic of Gaussian process, the proposed framework does not require distributions of uncertain inputs and this distinguishes it from existing approaches. As the original Gaussian process is not scalable to large-scale systems with high dimensional uncertain inputs, this paper develops the SGP with a stochastic variational inference technique. It leads to approximately two orders of complex reduction. A data pre-processing step is also introduced to tackle the coexistence of stable and unstable cases by sample clustering and constructing separate SGPs. The probabilistic transient stability index is analyzed to assess system stability under different uncertain dynamics loads and PVs. Comparisons are performed with the sampling-based, the polynomial chaos expansion-based, and traditional Gaussian process-based methods on the modified IEEE 118-bus and Texas 2000-bus systems under various scenarios, including different levels of uncertainties and the existence of nonlinear correlations among dynamic PVs. The impacts of data quality and quantity issues are also investigated. It is shown that the proposed SGP achieves significantly improved computational efficiency while maintaining high accuracy with a limited number of data.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Leveraging Optimal Sparse Sensor Placement to Aggregate a Network of Digital Twins for Nuclear Subsystems

Nuclear power plants (NPPs) require continuous monitoring of various systems, structures, and components to ensure safe and efficient operations. The critical safety testing of new fuel compositions and the analysis of the effects of power transients on core temperatures can be achieved through modeling and simulations. They capture the dynamics of the physical phenomenon associated with failure modes and facilitate the creation of digital twins (DTs). Accurate reconstruction of fields of interest (e.g., temperature, pressure, velocity) from sensor measurements is crucial to establish a two-way communication between physical experiments and models. Sensor placement is highly constrained in most nuclear subsystems due to challenging operating conditions and inherent spatial limitations. This study develops optimized data-driven sensor placements for full-field reconstruction within reactor and steam generator subsystems of NPPs. Optimized constrained sensors reconstruct field of interest within a tri-structural isotropic (TRISO) fuel irradiation experiment, a lumped parameter model of a nuclear fuel test rod and a steam generator. The optimization procedure leverages reduced-order models of flow physics to provide a highly accurate full-field reconstruction of responses of interest, noise-induced uncertainty quantification and physically feasible sensor locations. Accurate sensor-based reconstructions establish a foundation for the digital twinning of subsystems, culminating in a comprehensive DT aggregate of an NPP.

42 ENGINEERING↗