Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network reduction”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

SMALE: Enhancing Scalability of Machine Learning Algorithms on Extreme-Scale Computing Platforms

Deployment and execution of machine learning tasks on extreme-scale computing platforms face several significant technical challenges: 1) High computing cost incurred by dense networks – The computing workload of deep networks with densely-connected topology increases rapidly with the network size, imposing a non-scalable computing model of extreme-scale computing platforms; 2) Non-optimized workload distribution – Many advanced deep learning algorithms, e.g., sparsification and irregular net-work topology, produce very unbalanced workload distribution on extreme-scale computing platforms. The computation efficiency is greatly hindered by the incurred data and computation redundancies as well as long tails of the node with extensive workload; 3) Constraints in data movement and I/O bottle-neck – Inter-node data movement in extreme-scale computing platforms are associated with high energy and latency costs, and subject to the constraints of I/O bandwidth; and 4) Generalization of algorithm realization and acceleration on computing platforms – The large varieties of machine learning algorithms and structures of extreme-scale computing platforms make the derivation of a generalized algorithm realization and acceleration method very challenging, which, however, is the requirement by domain scientists and interested users. We call the above challenges Smale’s Problems in Machine Learning and Understanding for High-Performance Computing Scientific Discovery. The objective of our three-year research project is to develop a holistic innovation set at structure, assembly, and acceleration layers of machine learning algorithms to address the above challenges in algorithm deployment and execution. Three tasks are particularly performed, including: At the algorithm structure level, we investigate the techniques that can structurally sparsify on the topology of deep networks for computing workload reduction. We also study clustering and pruning techniques that can optimize the workload distributions over the extreme-scale computing platforms; At the algorithm assembly level, we derive a unified learning framework for unsupervised transfer learning and dynamic growing capabilities. Novel training methods are also exploited to enhance the training efficiency of the proposed framework; At the algorithm acceleration level, we will develop a series of techniques that can accelerate the computation of sparse matrix operations, which are one of the core executions in deep learning and optimize memory access of the concerned platforms. Our proposed techniques attack the fundamental problems in machine learning algorithms running on extreme-scale computing platforms by vertically integrating the solutions at three closely entangled layers, paving the long-term scaling path of machine learning applications under DOE context. Three tasks corresponding to the above respective research orientations are performed during the three-year project period with our collaborators at ORNL. The outcome of the proposed project is anticipated to form a holistic solution set of novel algorithms and network topologies, efficient training techniques, and fast acceleration methods to promote the computing scalability of the machine learning applications of particular interest to DOE.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Enhanced Stability of Li Metal Anodes by Synergetic Control of Nucleation and the Solid Electrolyte Interphase

Use of a protective coating on a lithium (Li) metal anode (LMA) is an effective approach to enhance its coulombic efficiency and cycling stability. Here we report a facile approach to produce uniform silver (Ag) nanoparticle-decorated LMAs for high-performance Li metal batteries (LMBs). This effective treatment can lead to well controlled nucleation and the formation of a stable solid electrolyte interphase (SEI). Ag nanoparticles embedded in the surface of Li anodes induced uniform Li plating/stripping morphologies with reduced overpotential. More importantly, cross-linked lithium fluoride (LiF) networks formed during Ag+ reduction enabled a highly stable SEI layer. Based on the Ag-LiF decorated anodes, LMBs with LiNi1/3Mn1/3Co1/3O2 cathode (~1.8 mAh cm-2) can retain >80% capacity over 500 cycles. The similar results were also obtained when the same approach was applied to the design of stable sodium (Na) anodes. These results indicate that synergetic control of the nucleation and SEI is an efficient approach to stabilize rechargeable metal batteries.

anode↗
DOE OSTI2024

DS-GL: Advancing Graph Learning via Harnessing the Power of Nature within Dynamic Systems

With the rapid digitization of the world, an increasing number of real-world applications are turning to nonEuclidean data, modeled as graphs. Due to their intrinsic high complexity and irregularity, learning from graph data demands tremendous computational power. Recently, CMOS-compatible Ising machines, i.e., dynamic systems composed of CMOS components, have emerged as a new approach that harnesses the inherent power of natural annealing within dynamic systems to efficiently resolve binary optimization problems and have been adopted for traditional graph computation, such as max-cut. However, when performing complex Graph Learning (GL) tasks, Ising machines face significant hurdles: (i) they are inherently binary and thus ill-suited for real-valued problems; (ii) their expensive all-to-all coupling network that guarantees effective natural annealing poses daunting scalability concerns. To address these challenges, this paper proposes a nature-powered graph learning framework dubbed DS-GL, which is the first effort to transform the process of solving graph learning problems into the natural annealing process within a parameterized dynamic system embodied as a CMOS chip. To tackle the two major hurdles, DS-GL first augments the Ising machine architecture to modify the self-reaction term of its Hamiltonian function from linear to quadratic, effectively serving as an energy regulator. This adjustment maintains the system’s original physical interpretation while enabling it to process continuous, real-valued data. Second, to address the scaling issue, DS-GL further upgrades the real-valued dense Ising machine by decomposing it into a mesh-based multi-PE dynamic system that supports efficient distributed spatial-temporal co-annealing across different PEs through sparse interconnects. By exploiting the inherent sparsity and component structures in real-world graphs, DS-GL is able to map complex graph learning tasks onto the scalable dynamic system while maintaining high accuracy. Evaluations with three diverse GL applications across six real-world datasets, including traffic flow and COVID-19 prediction, show that DS-GL can deliver from 102× to 106× speedups and 500× energy reduction over Graph Neural Networks on GPUs, with 5% - 20% accuracy enhancement.

Song, Ruibing↗
DOE OSTI2025

Temporally-consistent koopman autoencoders for forecasting dynamical systems

Absence of sufficiently high-quality data often poses a key challenge in data-driven modeling of high-dimensional spatio-temporal dynamical systems. Koopman Autoencoders (KAEs) harness the expressivity of deep neural networks (DNNs), the dimension reduction capabilities of autoencoders, and the spectral properties of the Koopman operator to learn a reduced-order feature space with simpler, linear dynamics. However, the effectiveness of KAEs is hindered by limited and noisy training datasets, leading to poor generalizability. To address this, we introduce the Temporally-Consistent Koopman Autoencoder (tcKAE), designed to generate accurate long-term predictions even with limited and noisy training data. This is achieved through a consistency regularization term that enforces prediction coherence across different time steps, thus enhancing the robustness and generalizability of tcKAE over existing models. We provide analytical justification for this approach based on Koopman spectral theory and empirically demonstrate tcKAE’s superior performance over state-of-the-art KAE models across a variety of test cases, including simple pendulum oscillations, kinetic plasma, and fluid flow data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗
DOE OSTI2014

Effects of nano-SiO{sub 2} particles on surface tracking characteristics of silicone rubber composites

Compared with neat silicone rubber composites (SiRCs), SiRCs filled with nano-sized SiO{sub 2} particles at weight ratios from 0.1 to 1.0 wt. % exhibit a higher surface flashover voltage and a greater resistance to surface tracking. Scanning electron microscopy images of tracking morphologies indicate that the SiO{sub 2} particles are situated in close proximity to the polymeric chains and act as bridges to stabilize the chains and maintain the structure of the composite. Higher concentrations of nano-sized SiO{sub 2} particles, however, (above 0.3 wt. %) produce defects in the molecular network which lead to reductions in both the surface flashover voltage and the resistance to surface tracking, although these reduced values are still superior to those of neat SiRCs. Therefore, SiRCs filled with nano-sized SiO{sub 2} particles, especially at an optimal weight ratio (0.1 to 0.3 wt. %), may have significant potential applications as outdoor insulators for power systems.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2022

Supervised and unsupervised machine learning of structural phases of polymers adsorbed to nanowires

Here, we identify configurational phases and structural transitions in a polymer nanotube composite by means of machine learning. We employ various unsupervised dimensionality reduction methods, conventional neural networks, as well as the confusion method, an unsupervised neural-network-based approach. We find neural networks are able to reliably recognize all configurational phases that have been found previously in experiment and simulation. Furthermore, we locate the boundaries between configurational phases in a way that removes human intuition or bias. This could be done before only by relying on preconceived, ad hoc order parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

Performance Evaluation of Next-Generation Grid Automation and Controls with High PV Penetration

This paper presents a hardware-in-the-loop (BIL) simulation to evaluate the performance of an advanced grid automation architecture, referred to as data-enhanced hierarchical control (DEHC), in achieving voltage regulation and conservation voltage reduction (CVR) in distribution networks with very high photovoltaic (PV) generation. This architecture comprises an advanced distribution management system (ADMS), a distributed energy resource management system (DERMS), and grid-edge devices working synergistically to provide the grid benefits. The HIL setup used for the evaluation includes ADMS, DERMS, and grid-edge devices. The DEHC performance is evaluated in two representative scenarios considering loose and tight constraints of the power factor at the substation. The results show that the DEHC architecture is effective in achieving voltage regulation and CVR and thus enables the grid integration of high levels of PV generation.

ADMS↗
DOE OSTI2024

Online MCMC Thinning with Kernelized Stein Discrepancy

A fundamental challenge in Bayesian inference is efficient representation of a target distribution. Many nonparametric approaches do so by sampling a large number of points using variants of Markov chain Monte Carlo (MCMC). Here, we propose an MCMC variant that retains only those posterior samples which exceed a kernelized Stein discrepancy (KSD) threshold, which we call KSD thinning. We establish the convergence and complexity trade-offs for several settings of KSD thinning as a function of the KSD threshold parameter, sample size, and other problem parameters. We provide experimental comparisons against other online nonparametric Bayesian methods that generate low-complexity posterior representations. We observe superior consistency/complexity trade-offs across a range of settings including MCMC sampling on two Bayesian inference problems from the biological sciences, and 10 × inference speedup and storage reduction for Bayesian neural networks with no loss of accuracy and no increase in training time. Our code is available at https://github.com/colehawkins/KSD-Thinning.

Bayesian inference↗
DOE OSTI2025

Quantum Instrumentation and Control Kit (QICK) for Quantum Networks

We report the first demonstration of using the Quantum Instrumentation and Control Kit (QICK) system on RFSoC FPGA technology to drive an entangled photon pair source and to detect the photon signals. With the QICK system, we achieve high levels of performance metrics including coincidence-to-accidental ratio exceeding 150, and entanglement visibility exceeding 95%, consistent with performance metrics achieved using conventional waveform generators. We also demonstrate simultaneous detector readout using the digitization functional of QICK, achieving internal system synchronization time resolution of 3.2 ps. The work reported in this paper represents an explicit demonstration of the feasibility for replacing commercial waveform generators and time taggers with RFSoC-FPGA technology in the operation of a quantum network, representing a cost reduction of more than an order of magnitude.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2026

SAM Code Enhancements for Fission Product Tracking of Noble Gases and Metals in MSRs

This report documents fiscal year 2026 enhancements to the System Analysis Module (SAM) for modeling fission product transport in liquid-fueled molten salt reactors (MSRs). The work advances three principal areas: noble gas transport, noble metal deposition, and user interface improvements. The noble gas transport capability integrates drift-flux gas transport, Henry’s law two-film interphase mass transfer with pressure-based nucleation suppression, Knudsen-regime pore diffusion into porous graphite with a conjugate salt-graphite interface constraint, built-in material properties, five Sherwood-number mass transfer correlations including three derived from high-fidelity NekRS simulations, and xenon-135 reactivity feedback through SAM’s point-kinetics model. This work also presents a comprehensive verification test suite, including new analytically verified cases for pressure-dependent onset of interphase gas transfer in a stagnant vertical pipe, a postulated FLiBe-graphite Xe extraction permeator, a gravity riser with a fission-product source, and a descending pipe with gas redissolution driven by hydrostatic pressure. A machine learning framework for bubble rise velocity prediction in molten salt systems is developed and benchmarked on molten-salt and diverse aqueous bubble datasets. The best-performing fine-tuned transfer-learning networks achieve an 82% reduction in RMSE relative to the Clift correlation, and is implemented directly in SAM. The noble metal transport capability is developed, including a liquid-wall deposition model and a gas-surface flotation mechanism that transfers insoluble particles entrained by sparging gas to wetted structures. Verification tests and demonstration cases cover the surface deposition, flotation efflux, and flotation shedding. Finally, a new [SpeciesTransport] input structure replaces positional global vectors with selfcontained, order-independent, named species blocks, simplifies the specification of multiphase species and decay chains, and remains fully compatible with existing SAM input files. Together, these developments improve the physical fidelity, verification basis, and usability of SAM for system-level analyses of fissionproduct behavior in MSRs.

Mui, Travis (ORCID:0000000303736470)↗
DOE OSTI2021

An out-of-distribution-aware autoencoder model for reduced chemical kinetics

While detailed chemical kinetic models have been successful in representing rates of chemical reactions in continuum scale computational fluid dynamics (CFD) simulations, applying the models in simulations for engineering device conditions is computationally prohibitive. To reduce the cost, data-driven methods, e.g., autoencoders, have been used to construct reduced chemical kinetic models for CFD simulations. Despite their success, data-driven methods rely heavily on training data sets and can be unreliable when used in out-of-distribution (OOD) regions (i.e., when extrapolating outside of the training set). In this paper, we present an enhanced autoencoder model for combustion chemical kinetics with uncertainty quantification to enable the detection of model usage in OOD regions, and thereby creating an OOD-aware autoencoder model that contributes to more robust CFD simulations of reacting flows.Here, we first demonstrate the effectiveness of the method in OOD detection in two well-known datasets, MNIST and Fashion-MNIST, in comparison with the deep ensemble method, and then present the OOD-aware autoencoder for reduced chemistry model in syngas combustion.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2005

Large decreases in ionospheric total electron content as a result of thermospheric composition changes during geomagnetic storms

The geomagnetic storms of April 17-21,2002 and May 29-30,2003 caused large decreases in the O/N2 column density ratio in the thermosphere. For these storms, ON2 column density decreases of greater than 50% were observed to extend to mid-to-low latitudes with the FUV sensitive Earth Camera of the Visible Imaging System (VIS) on the Polar spacecraft. Simultaneously in these same regions, the ground-based GPS network observed approximately 80% reductions in the Total Electron Content (TEC) of the ionosphere. The reduction in the Om2 column density ratio is due mainly to increases in the molecular species that have welled-up into the thermosphere from the lower levels of the atmosphere due to auroral heating. The geomagnetic-storm driven increase in molecular densities at typical ionospheric heights rapidly charge exchange with the ambient ionized atoms and subsequently dissociatively recombine with the ionospheric electrons leading to a reduction in the total charge density. The transition boundaries between high and low regions of O/N2 as well as TEC can be tracked in the images and the thermospheric winds can be determined from the motion of the boundaries. The motion of these boundaries during the development of the geomagnetic storm will be discussed.

Sigwarth, J. B.↗
NASA NTRS2005

The Dynamics of Thermospheric Composition and Ionospheric Total Electron Content During Geomagnetic Storms

The geomagnetic storms of April 17-21,2002 and May 29-30,2003 caused large decreases in the O/N2 column density ratio in the thermosphere. For these storms, O/N2 column density decreases of greater than 50% were observed to extend to mid-to-low latitudes with the FUV sensitive Earth Camera of the Visible Imaging System (VIS) on the Polar spacecraft. Simultaneously in these same regions, the ground-based GPS network observed approximately 80% reductions in the Total Electron Content (TEC) of the ionosphere. The reduction in the O/N2 column density ratio is due mainly to increases in the molecular species that have welled-up into the thermosphere from the lower levels of the atmosphere due to auroral heating. The geomagnetic-storm driven increase in molecular densities at typical ionospheric heights rapidly charge exchange with the ambient ionized atoms and subsequently dissociatively recombine with the ionospheric electrons leading to a reduction in the total charge density. The transition boundaries between high and low regions of O/N2 as well as TEC can be tracked in the images and the thermospheric winds may be inferred from the motion of the boundaries. The motion of these boundaries during the development of the geomagnetic storm will be discussed.

Sigwarth, John B.↗
NASA NTRS2004

Neural network tracking and extension of positive tracking periods

Feature detectors have been considered for the role of supplying additional information to a neural network tracker. The feature detector focuses on areas of the image with significant information. Basically, if a picture says a thousand words, the feature detectors are looking for the key phrases (keypoints). These keypoints are rotationally invariant and may be matched across frames. Application of these advanced feature detectors to the neural network tracking system at JPL has promising potential. As part of an ongoing program, an advanced feature detector was tested for augmentation of a neural network based tracker. The advance feature detector extended tracking periods in test sequences including aircraft tracking, rover tracking, and simulated Martian landing. Future directions of research are also discussed.

feature extraction↗
NASA NTRS2014

Sao Paulo Lightning Mapping Array (SP-LMA): Network Assessment and Analyses for Intercomparison Studies and GOES-R Proxy Activities

A 12 station Lightning Mapping Array (LMA) network was deployed during October 2011 in the vicinity of Sao Paulo, Brazil (SP-LMA) to contribute total lightning measurements to an international field campaign [CHUVA - Cloud processes of tHe main precipitation systems in Brazil: A contribUtion to cloud resolVing modeling and to the GPM (GlobAl Precipitation Measurement)]. The SP-LMA was operational from November 2011 through March 2012 during the Vale do Paraiba campaign. Sensor spacing was on the order of 15-30 km, with a network diameter on the order of 40-50km. The SP-LMA provides good 3-D lightning mapping out to 150 km from the network center, with 2-D coverage considerably farther. In addition to supporting CHUVA science/mission objectives, the SP-LMA is supporting the generation of unique proxy data for the Geostationary Lightning Mapper (GLM) and Advanced Baseline Imager (ABI), on NOAA's Geostationary Operational Environmental Satellite-R (GOES-R: scheduled for a 2015 launch). These proxy data will be used to develop and validate operational algorithms so that they will be ready to use on "day1" following the GOES-R launch. As the CHUVA Vale do Paraiba campaign opportunity was formulated, a broad community-based interest developed for a comprehensive Lightning Location System (LLS) intercomparison and assessment study, leading to the participation and/or deployment of eight other ground-based networks and the space-based Lightning Imaging Sensor (LIS). The SP-LMA data is being intercompared with lightning observations from other deployed lightning networks to advance our understanding of the capabilities/contributions of each of these networks toward GLM proxy and validation activities. This paper addresses the network assessment including noise reduction criteria, detection efficiency estimates, and statistical and climatological (both temporal and spatially) analyses for intercomparison studies and GOES-R proxy activities.

Bailey, J. C.↗