Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ITERATIVE NETWORK”

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 325 records · Page 18

Support of the Third Summer School and Workshop Focused on Theory and Applications of Time-Dependent Density Functional Theory, Electronic Excited States, and Excited State Dynamics

To create a community of scholars with a deep understanding of TDDFT and excited state methods, both their capabilities and limitations, and how they can be used to model the excited state properties and charge transfer in materials and molecules, we are planning the third iteration of a summer school and workshop focusing on theory and applications of TDDFT, Excited States, and Excited State Dynamics to be offered in the summer of 2023. The two iterations of the US-based school that we previously organized have been very successful with overwhelmingly positive feedback. There is a high level of engagement, enthusiasm, and active participation and networking amongst the students of the school and the scientists of the workshop.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Multi deep learning-based stochastic microstructure reconstruction and high-fidelity micromechanics simulation of time-dependent ceramic matrix composite response

A multi deep learning-based framework is developed for efficient, automated microstructure reconstruction and generation of stochastic representative volume elements (SRVEs) with periodic boundary conditions (PBCs) for accurate modeling of ceramic matrix composite (CMC) response. The methodology comprises a convolutional neural network coupled with regression layers to act as a vanilla regression network for semantic segmentation of the microstructure, allowing accurate characterization of the phases and their distributions at the microscale. Scanning electron microscope and confocal microscope are used to obtain C/SiNC and SiC/SiNC CMCs micrographs for vanilla regression testing. Microstructure variability in terms of fiber volume fraction and porosity are quantified through the output regression layer, ensuring accurate representation of material variability in SRVE construction. Generative adversarial network (GAN) and its variants are designed to produce high-fidelity SRVE, spanning CMCs microstructure variability space. A circular padding algorithm is developed to generate SRVEs with PBCs during training of GANs. The accuracy of the generated SRVEs is established through micromechanics simulations, where an efficient formulation of the high-fidelity generalized methods of cells (HFGMC) approach is used to compute the effective mechanical properties. Furthermore, an iterative algorithm is implemented in the HFGMC solver to simulate time-dependent deformation of SiC/SiNC subjected to creep loading conditions.

36 MATERIALS SCIENCE↗

The Distributed Grid Sensing Services (DGSS) platform: A scalable and decentralized sensor dissemination network

In this paper, a scalable, decentralized sensor-oriented, communication blueprint will be introduced. The proposed architecture has been specifically designed to support the mass deployment of sensors while enabling data consumers to access the underlying data streams using a distributed systems approach. With the proposed approach, sensors and data clients can be decoupled from the physical communication infrastructure and migrated into a modern, software-defined infrastructure ecosystem that can be configured to suit the end application’s demands. In its current iteration, the blueprint defines the interactions, processes, and expected outcomes that each individual component within the architecture must fulfill in order to support the overall ecosystem’s needs. Within this work, such assemble of services is referred the databus, and represents the heart of the Distributed Grid Sensing Services (DGSS) architecture, a multi-year project that aims to design, implement and test a dedicated sensor dissemination network that can support the needs of the extended grid state. It is our expectation, that the proposed blueprint presented in this paper will serve as a future guide to our implementation efforts

Sebastian Cardenas, David J.↗

NSFnets (Navier-Stokes flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations

In the last 50 years there has been a tremendous progress in solving numerically the Navier-Stokes equations using finite differences, finite elements, spectral, and even meshless methods. Yet, in many real cases, we still cannot incorporate seamlessly (multi-fidelity) data into existing algorithms, and for industrial-complexity applications the mesh generation is time consuming and still an art. Moreover, solving ill-posed problems (e.g., lacking boundary conditions) or inverse problems is often prohibitively expensive and requires different formulations and new computer codes. Here, we employ physics-informed neural networks (PINNs), encoding the governing equations directly into the deep neural network via automatic differentiation, to overcome some of the aforementioned limitations for simulating incompressible laminar and turbulent flows. We develop the Navier-Stokes flow nets (NSFnets) by considering two different mathematical formulations of the Navier-Stokes equations: the velocity-pressure (VP) formulation and the vorticity-velocity (VV) formulation. Since this is a new approach, we first select some standard benchmark problems to assess the accuracy, convergence rate, computational cost and flexibility of NSFnets; analytical solutions and direct numerical simulation (DNS) databases provide proper initial and boundary conditions for the NSFnet simulations. The spatial and temporal coordinates are the inputs of the NSFnets, while the instantaneous velocity and pressure fields are the outputs for the VP-NSFnet, and the instantaneous velocity and vorticity fields are the outputs for the VV-NSFnet. This is unsupervised learning and, hence, no labeled data are required beyond boundary and initial conditions and the fluid properties. The residuals of the VP or VV governing equations, together with the initial and boundary conditions, are embedded into the loss function of the NSFnets. No data is provided for the pressure to the VP-NSFnet, which is a hidden state and is obtained via the incompressibility constraint without extra computational cost. Unlike the traditional numerical methods, NSFnets inherit the properties of neural networks (NNs), hence the total error is composed of the approximation, the optimization, and the generalization errors. Here, we empirically attempt to quantify these errors by varying the sampling (“residual”) points, the iterative solvers, and the size of the NN architecture. For the laminar flow solutions, we show that both the VP and the VV formulations are comparable in accuracy but their best performance corresponds to different NN architectures. The initial convergence rate is fast but the error eventually saturates to a plateau due to the dominance of the optimization error. For the turbulent channel flow, we show that NSFnets can sustain turbulence at , but due to expensive training we only consider part of the channel domain and enforce velocity boundary conditions on the subdomain boundaries provided by the DNS data base. We also perform a systematic study on the weights used in the loss function for balancing the data and physics components, and investigate a new way of computing the weights dynamically to accelerate training and enhance accuracy. In the last part, we demonstrate how NSFnets should be used in practice, namely for ill-posed problems with incomplete or noisy boundary conditions as well as for inverse problems. We obtain reasonably accurate solutions for such cases as well without the need to change the NSFnets and at the same computational cost as in the forward well-posed problems. As a result, we also present a simple example of transfer learning that will aid in accelerating the training of NSFnets for different parameter settings.

97 MATHEMATICS AND COMPUTING↗

Fast neural network training on a cluster of GPUs for action recognition with high accuracy

In this work, we propose algorithms and techniques to accelerate training of deep neural networks for action recognition on a cluster of GPUs. The convergence analysis of our algorithm shows it is possible to reduce communication cost and at the same time minimize the number of iterations needed for convergence. We customize the Adam optimizer for our distributed algorithm to improve efficiency. In addition, we employ transfer-learning to further reduce training time while improving validation accuracy. For the UCF101 and HMDB51 datasets, the validation accuracies achieved are 93.1% and 67.9% respectively. With an additional end-to-end trained temporal stream, the validation accuracies achieved for UCF101 and HMDB51 are 93.47% and 81.24% respectively. As far as we know, these are the highest accuracies achieved with the two-stream approach using ResNet that does not involve computationally expensive 3D convolutions or pretraining on much larger datasets.

97 MATHEMATICS AND COMPUTING↗

Analysis of the ARTIC Version 3 and Version 4 SARS-CoV-2 Primers and Their Impact on the Detection of the G142D Amino Acid Substitution in the Spike Protein

The ARTIC Network provides a common resource of PCR primer sequences and recommendations for amplifying SARS-CoV-2 genomes. The initial tiling strategy was developed with the reference genome Wuhan-01, and subsequent iterations have addressed areas of low amplification and sequence drop out. Recently, a new version (V4) was released, based on new variant genome sequences, in response to the realization that some V3 primers were located in regions with key mutations. Herein, we compare the performance of the ARTIC V3 and V4 primer sets with a matched set of 663 SARS-CoV-2 clinical samples sequenced with an Illumina NovaSeq 6000 instrument. We observe general improvements in sequencing depth and quality, and improved resolution of the SNP causing the D950N variation in the spike protein. Importantly, we also find nearly universal presence of spike protein substitution G142D in Delta-lineage samples. Due to the prior release and widespread use of the ARTIC V3 primers during the initial surge of the Delta variant, it is likely that the G142D amino acid substitution is substantially underrepresented among early Delta variant genomes deposited in public repositories. In addition to the improved performance of the ARTIC V4 primer set, this study also illustrates the importance of the primer scheme in downstream analyses.

59 BASIC BIOLOGICAL SCIENCES↗

Multi-Sensor Optimal Motion Planning for Radiological Contamination Surveys by Using Prediction-Difference Maps

Distributed and networked mobile sensor platforms using unmanned aerial and/or ground vehicles to survey areas of interest offer a safer and more efficient method for radiological contamination mapping; however, most applications rely on uniformly sweeping of the area in a raster-type motion without utilizing the information available in a dynamic sense. We have developed a fully autonomous optimal motion planning procedure for networks with two or more mobile sensors. The procedure utilizes well-established concepts of Gaussian processes in combination with control laws based on centroidal Voronoi tessellations to achieve optimal next-iteration sensor movements. A new method of informing optimal motion planning is proposed, whereby the absolute difference between the prior and current full-map prediction, referred to as the prediction-difference map, is used as the spatial density function within each Voronoi cell, providing immediate and iterative feedback for dynamic use of available information. The Gaussian process regression model used to estimate the contamination in unvisited locations also provides prediction uncertainties, and can be used as a quantitative metric to assess the confidence in the calculated contamination map; these estimates and prediction uncertainties are unavailable for standard uniform survey routines as they can only produce maps in the vicinity of observed locations. We present through simulation the achievable performance gains from using this new method by directly comparing to a uniform survey method. Results show that using the prediction-difference maps to inform motion planning procedures offers a faster rate of producing an accurate and convergent map relative to a uniform survey route.

47 OTHER INSTRUMENTATION↗

Indicator-directed Dynamic Power Management for Iterative Workloads on GPU-Accelerated Systems

Modern high-performance and warehouse computing centers show strong interest in minimizing system power consumption while satisfying customers’ quality of service (QoS). Dynamic voltage and frequency scaling (DVFS) is effective for achieving this goal. Nevertheless, automating the process online and making it transparent to users must address three major challenges: (1) Complexity — today’s hardware components (e.g., CPUs, GPUs, memory, network, etc.) can be configured in several or dozens of frequency/voltage states for satisfying divergent system demands. Given their combination and the emergence of heterogeneity, searching the optimal configuration in the design space online can be timing consuming. (2) QoS guarantee — user-defined objectives such as power constraint and performance target must be monitored, predicted and ensured at the best effort. (3) Adaptability — various known and unknown workloads run on systems. Workloads characteristics should be quickly determined and configurations dynamically adjusted in accord with workloads and QoS. In this work, we focus on applications exhibiting an interesting feature – iterative or periodic, which is common among conventional HPC and emerging machine learning workloads. We propose an online dynamic power-performance (ODPP) management framework to dynamically adjust GPU DVFS configurations to meet performance and power objectives and constraints, without any code annotation or intrusion. Particularly, ODPP extracts the performance and power indicators for applications from their resources utilization profiles in a short episode. It further automatically constructs an accurate model that infers from the indicators how the application's performance and power vary with GPU core and memory frequencies. Aided with the model, for both seen and unseen applications, ODPP can quickly determine the most appropriate DVFS configuration for their execution. We evaluate ODPP on an NVIDIA GPU using multiple exascale computing (ECP) and deep learning applications.

Zou, Pengfei↗

Data analysis and modeling pipelines for controlled networked social science experiments

There is large interest in networked social science experiments for understanding human behavior at-scale. Significant effort is required to perform data analytics on experimental outputs and for computational modeling of custom experiments. Moreover, experiments and modeling are often performed in a cycle, enabling iterative experimental refinement and data modeling to uncover interesting insights and to generate/refute hypotheses about social behaviors. The current practice for social analysts is to develop tailor-made computer programs and analytical scripts for experiments and modeling. This often leads to inefficiencies and duplication of effort. In this work, we propose a pipeline framework to take a significant step towards overcoming these challenges. Our contribution is to describe the design and implementation of a software system to automate many of the steps involved in analyzing social science experimental data, building models to capture the behavior of human subjects, and providing data to test hypotheses. The proposed pipeline framework consists of formal models, formal algorithms, and theoretical models as the basis for the design and implementation. We propose a formal data model, such that if an experiment can be described in terms of this model, then our pipeline software can be used to analyze data efficiently. The merits of the proposed pipeline framework is elaborated by several case studies of networked social science experiments.

97 MATHEMATICS AND COMPUTING↗

Improving an Acoustic Vehicle Detector Using an Iterative Self-Supervision Procedure

In many non-canonical data science scenarios, obtaining, detecting, attributing, and annotating enough high-quality training data is the primary barrier to developing highly effective models. Moreover, in many problems that are not sufficiently defined or constrained, manually developing a training dataset can often overlook interesting phenomena that should be included. To this end, we have developed and demonstrated an iterative self-supervised learning procedure, whereby models are successfully trained and applied to new data to extract new training examples that are added to the corpus of training data. Successive generations of classifiers are then trained on this augmented corpus. Using low-frequency acoustic data collected by a network of infrasound sensors deployed around the High Flux Isotope Reactor and Radiochemical Engineering Development Center at Oak Ridge National Laboratory, we test the viability of our proposed approach to develop a powerful classifier with the goal of identifying vehicles from continuously streamed data and differentiating these from other sources of noise such as tools, people, airplanes, and wind. Using a small collection of exhaustively manually labeled data, we test several implementation details of the procedure and demonstrate its success regardless of the fidelity of the initial model used to seed the iterative procedure. Finally, we demonstrate the method’s ability to update a model to accommodate changes in the data-generating distribution encountered during long-term persistent data collection.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Neural Networks-Based Inverter Control: Modeling and Adaptive Optimization for Smart Distribution Networks

The optimal voltage control of inverter-based resources, especially under the high penetration of solar photovoltaics, is critical to the stability of the distribution power system. However, the computational complexity as well as the coordinated operation performance of the voltage control optimization in the distribution power system limits the real-time applications. To mitigate this issue, a model-free based adaptive optimal control scheme for the smart inverter is proposed to maximize the active power generation, minimize the power loss, and maintain the bus voltages in smart distribution networks. An inverter-based optimization model for coordinated operation is first established, considering the uncertainties of renewable power generation. Subsequently, by collecting the data and control strategies, the neural networks (NNs) based algorithm is proposed to efficiently predict the best possible control strategy. The main objective of this scheme is to accurately predict candidate optimal solutions with near-negligible feasibility and optimization gaps, with the advantage of avoiding complicated iteration-based numerical algorithms. Thereafter, the co-simulation among OpenDSS, MATLAB, and Python is set up to fully take advantage of the three individual software. Experiments are conducted based on different control parameter characteristics and structures of NNs. Finally, the results reveal that an average mean squared error of 0.013 and 1 ms response time are achieved, which is lower than some state-of-the-art methods.

42 ENGINEERING↗

The glass transition in cured epoxy thermosets: A comparative molecular dynamics study in coarse-grained and atomistic resolution

We investigate the volumetric glass transition temperature T{sub g} in epoxy thermosets by means of molecular dynamics simulations. The epoxy thermosets consist of the resin bisphenol A diglycidyl ether and the hardener diethylenetriamine. A structure based coarse-grained (CG) force field has been derived using iterative Boltzmann inversion in order to facilitate simulations of larger length scales. We observe that T{sub g} increases clearly with the degree of cross-linking for all-atomistic (AA) and CG simulations. The transition T{sub g} in CG simulations of uncured mixtures is much lower than in AA-simulations due to the soft nature of the CG potentials, but increases all the more with the formation of rigid cross-links. Additional simulations of the CG mixtures in contact with a surface show the existence of an interphase region of about 3 nm thickness in which the network properties deviate significantly from the bulk. In accordance to experimental studies, we observe that T{sub g} is reduced in this interphase region and gradually increases to its bulk value with distance from the surface. The present study shows that the glass transition is a local phenomenon that depends on the network structure in the immediate environment.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Efficient Training of Deep Neural Operator Networks via Randomized Sampling

Neural operators (NOs) employ deep neural networks to learn the mappings between infinitedimensional function spaces. Deep operator network (DeepONet), a popular NO architecture, has demonstrated success in the real-time prediction of complex dynamics across various scientific and engineering applications. In this work, we introduce a random sampling technique to be adopted during the training of DeepONet, aimed at improving the generalization ability of the model, while significantly reducing the computational time. The proposed approach targets the trunk network of the DeepONet model that outputs the basis functions corresponding to the spatiotemporal locations of the bounded domain on which the physical system is defined. While constructing the loss function, DeepONet training traditionally considers a uniform grid of spatiotemporal points at which all the output functions are evaluated for each iteration. This approach leads to a larger batch size, resulting in poor generalization and increased memory demands, due to the limitations of the stochastic gradient descent (SGD) optimizer. The proposed random sampling over the inputs of the trunk net mitigates these challenges, improving generalization and reducing the memory requirements during training, resulting in significant computational gains. We validate our hypothesis through three benchmark examples, demonstrating substantial reductions in training time while achieving comparable or lower overall test errors relative to the traditional training approach. Our results indicate that incorporating randomization in the trunk network inputs during training enhances the efficiency and robustness of DeepONet, offering a promising avenue for improving the framework’s performance in modeling complex physical systems.

Karumuri, Sharmila [Department of Civil & Systems ↗

Intertidal Creeks and Overmarsh Circulation in a Small Salt Marsh Basin

The role of intertidal creek networks in overmarsh circulation is not well constrained. In this study, we systematically remove intertidal creeks from a high-resolution salt marsh digital elevation model and conduct new flow simulations with each iteration. Overall, removal of first- and second-order creeks reduced drainage density by 65%, and this had a negligible effect on overmarsh circulation and tracer distribution. However, upon removal of third- and fourth-order creeks, drainage density was reduced by 80% of the original value, and changes in peak velocity magnitude across various spatial and temporal scales reveal a system-wide switch from ebb to flood dominance. This response coincides with the interruption of topographically connected creeks that facilitate the direct exchange of water and tracer between the marsh interior and the larger subtidal system. Further, this reduction in hydraulic connectivity gives rise to less expansive tracer dispersal and a systematic decline in tracer residence time. Together, these results reveal that for the Groves Creek marsh, lower-order intertidal creeks have a minor role in overmarsh circulation, while higher-order creeks increase the potential for short circuiting of flow; they greatly influence overall flood and ebb dominance, and net tracer dispersal and associated retention time. Moreover, results reported here provide new insight on, for example, salt marsh restoration and the requisite digital elevation model bathymetry for robust simulations of overmarsh circulation.

58 GEOSCIENCES↗

Self-supervised physics-informed generative networks for phase retrieval from a single X-ray hologram

X-ray phase contrast imaging significantly improves the visualization of structures with weak or uniform absorption, broadening its applications across a wide range of scientific disciplines. Propagation-based phase contrast is particularly suitable for time- or dose-critical in vivo/in situ/operando (tomography) experiments because it requires only a single intensity measurement. However, the phase information of the wave field is lost during the measurement and must be recovered. Conventional algebraic and iterative methods often rely on specific approximations or boundary conditions that may not be met by many samples or experimental setups. In addition, they require manual tuning of reconstruction parameters by experts, making them less adaptable for complex or variable conditions. Here we present a self-learning approach for solving the inverse problem of phase retrieval in the near-field regime of Fresnel theory using a single intensity measurement (hologram). A physics-informed generative adversarial network is employed to reconstruct both the phase and absorbance of the unpropagated wave field in the sample plane from a single hologram. Unlike most state-of-the-art deep learning approaches for phase retrieval, our approach does not require paired, unpaired, or simulated training data. This significantly broadens the applicability of our approach, as acquiring or generating suitable training data remains a major challenge due to the wide variability in sample types and experimental configurations. The algorithm demonstrates robust and consistent performance across diverse imaging conditions and sample types, delivering quantitative, high-quality reconstructions for both simulated data and experimental datasets acquired at beamline P05 at PETRA III (DESY, Hamburg), operated by Helmholtz-Zentrum Hereon. Furthermore, it enables the simultaneous retrieval of both phase and absorption information.

36 MATERIALS SCIENCE↗

From Escherichia coli mutant 13 C labeling data to a core kinetic model: A kinetic model parameterization pipeline

Kinetic models of metabolic networks offer the promise of quantitative phenotype prediction. The mechanistic characterization of enzyme catalyzed reactions allows for tracing the effect of perturbations in metabolite concentrations and reaction fluxes in response to genetic and environmental perturbation that are beyond the scope of stoichiometric models. In this study, we develop a two-step computational pipeline for the rapid parameterization of kinetic models of metabolic networks using a curated metabolic model and available 13 C-labeling distributions under multiple genetic and environmental perturbations. The first step involves the elucidation of all intracellular fluxes in a core model of E. coli containing 74 reactions and 61 metabolites using 13 C-Metabolic Flux Analysis ( 13 C-MFA). Here, fluxes corresponding to the mid-exponential growth phase are elucidated for seven single gene deletion mutants from upper glycolysis, pentose phosphate pathway and the Entner-Doudoroff pathway. The computed flux ranges are then used to parameterize the same (i.e., k-ecoli74) core kinetic model for E. coli with 55 substrate-level regulations using the newly developed K-FIT parameterization algorithm. The K-FIT algorithm employs a combination of equation decomposition and iterative solution techniques to evaluate steady-state fluxes in response to genetic perturbations. k-ecoli74 predicted 86% of flux values for strains used during fitting within a single standard deviation of 13 C-MFA estimated values. By performing both tasks using the same network, errors associated with lack of congruity between the two networks are avoided, allowing for seamless integration of data with model building. Product yield predictions and comparison with previously developed kinetic models indicate shifts in flux ranges and the presence or absence of mutant strains delivering flux towards pathways of interest from training data significantly impact predictive capabilities. Using this workflow, the impact of completeness of fluxomic datasets and the importance of specific genetic perturbations on uncertainties in kinetic parameter estimation are evaluated.

59 BASIC BIOLOGICAL SCIENCES↗

TOPS2 - Towards Optimal Petascale Simulations

Our goal in this project was to design scalable numerical algorithms needed by SciDAC applications that adapt to use evolving hardware resources as efficiently as possible. Our primary challenge is minimizing communication costs, where communication means moving data either between levels of a memory hierarchy (L1 cache to L2 cache to main memory etc.) or between processors over a network. Floating point rates are improving exponentially faster than bandwidth, which is improving exponentially faster than latency. So our goal is to minimize communication. We describe our progress in this area, both for direct and iterative linear algebra. In both areas we have (1) identified lower bounds on the amount of communication (measured both by the number of words moved and the number of messages) required to perform these algorithms, (2) analyzed existing algorithms, which by and large do not attain these lower bounds, and (3) identified or invented new algorithms that do attain them, and evaluated their speedups, which can be quite large.

97 MATHEMATICS AND COMPUTING↗