Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Models”

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 1,459 records · Page 81

PyTorch Implementation of Log-Additive Convolutional Neural Networks

This code is a collection of python code that defines, trains, and tests Log-Additive Convolutional Neural Networks. The model components and training routine are based on the PyTorch python library. The code implements the Log-Additive Convolutional Neural Networks as described in Pagendam et al. 2023. In addition to the Log-Additive Convolutional Neural Networks, this library also defines the Log-Normal Density loss function as described in Pagendam et al. 2023. Code from this paper is not publicly available, so the Pytorch implementation of this type of model is unique to this library.

Callis, Skylar↗

Prediction of laser beam spatial profiles in a high-energy laser facility by use of deep learning

We adapt the significant advances achieved recently in the field of generative artificial intelligence/machine-learning to laser performance modeling in multipass, high-energy laser systems with application to high-shot-rate facilities relevant to inertial fusion energy. Advantages of neural-network architectures include rapid prediction capability, data-driven processing, and the possibility to implement such architectures within future low-latency, low-power consumption photonic networks. Four models were investigated that differed in their generator loss functions and utilized the U-Net encoder/decoder architecture with either a reconstruction loss alone or combined with an adversarial network loss. We achieved inference times of 1.3 ms for a 256 × 256 pixel near-field beam with errors in predicted energy of the order of 1% over most of the energy range. It is shown that prediction errors are significantly reduced by ensemble averaging the models with different weight initializations. These results suggest that including the temporal dimension in such models may provide accurate, real-time spatiotemporal predictions of laser performance in high-shot-rate laser systems.

47 OTHER INSTRUMENTATION↗

Optimal control of the electron temperature profile in DIII-D using machine learning surrogate models

The viability of the tokamak as a potential fusion reactor depends on the ability to keep the plasma in a stable regime while achieving temperatures, densities, and confinement times that are as high as possible. Tokamak scenario development attempts to find plasma regimes that achieve all of these conditions and are accessible with a given set of hardware constraints. This requires the ability to control plasma properties such as the normalized beta, the internal inductance, safety factor, rotation, etc. One property that has received less attention than some of the others, but is no less critical to achieving high performance, is the electron temperature (T e ) profile. In this work, Linear Quadratic Integral (LQI) control is used to develop a controller for the electron temperature profile in DIII-D. The controller is based on a linearized model derived from the transport equation that describes the evolution of the electron temperature, and includes contributions from the neural network surrogate models NubeamNet and MMMnet. Furthermore, the controller is tested in simulation using COTSIM, and is proven capable of tracking a target T e profile.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Utah FORGE Well 16A(78)-32 Stimulation DFN Fracture Plane Evaluation and Data

This dataset includes files used to fit planar fractures through the preliminary earthquake catalogs of the three stages of the April 2022 well 16A(78)-32 stimulation which is linked bellow. These planar features have been used to update the FORGE reference Discrete Fracture Network (DFN) model. The files are provided to encourage other modelers to use additional workflows to find additional/alternative features. To this end, the dataset includes the cleaned earthquake catalog data translated to the FORGE reference model global reference frame, the well trajectory of 16A(78)-32 in those same coordinates, the fit 15 planar features in csv format, and a pdf file with slides illustrating the process used to fit the features. A recorded presentation of this material is available from the October 2022 FORGE Modeling and Simulation Forum which is also linked below.

15 GEOTHERMAL ENERGY↗

Raman spectrum and polarizability of liquid water from deep neural networks

We introduce a scheme based on machine learning and deep neural networks to model the environmental dependence of the electronic polarizability in insulating materials. Application to liquid water shows that training the network with a relatively small number of molecular configurations is sufficient to predict the polarizability of arbitrary liquid configurations in close agreement with ab initio density functional theory calculations. In combination with a neural network representation of the interatomic potential energy surface, the scheme allows us to calculate the Raman spectra along 2-nanosecond classical trajectories at different temperatures for H 2 O and D 2 O. The vast gains in efficiency provided by the machine learning approach enable longer trajectories and larger system sizes relative to ab initio methods, reducing the statistical error and improving the resolution of the low-frequency Raman spectra. Decomposing the spectra into intramolecular and intermolecular contributions elucidates the mechanisms behind the temperature dependence of the low-frequency and stretch modes.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Toward Large-Scale Image Segmentation on Summit

Semantic segmentation of images is an important computer vision task that emerges in a variety of application domains such as medical imaging, robotic vision and autonomous vehicles to name a few. While these domain-specific image analysis tasks involve relatively small image sizes (~ 10 2 × 10 2 ), there are many applications that need to train machine learning models on image data with extents that are orders of magnitude larger (~10 4 × 10 4 ). Training deep neural network (DNN) models on large extent images is extremely memory-intensive and often exceeds the memory limitations of a single graphical processing unit, a hardware accelerator of choice for computer vision workloads. Here, an efficient, sample parallel approach to train U-Net models on large extent image data sets is presented. Its advantages and limitations are analyzed and near-linear strong-scaling speedup demonstrated on 256 nodes (1536 GPUs) of the Summit supercomputer. Using a single node of the Summit supercomputer, an early evaluation of a recently released model parallel framework called GPipe is demonstrated to deliver ~ 2X speedup in executing a U-Net model with an order of magnitude larger number of trainable parameters than reported before. Performance bottlenecks for pipelined training of U-Net models are identified and mitigation strategies to improve the speedups are discussed. Together, these results open up the possibility of combining both approaches into a unified scalable pipelined and data parallel algorithm to efficiently train U-Net models with very large receptive fields on data sets of ultra-large extent images.

Seal, Sudip↗

Model Exploration of an Information-Based Healthcare Intervention Using Parallelization and Active Learning

This paper describes the application of a large-scale active learning method to characterize the parameter space of a computational agent-based model developed to investigate the impact of CommunityRx, a clinical information-based health intervention that provides patients with personalized information about local community resources to meet basic and self-care needs. Additionally, the diffusion of information about community resources and their use is modeled via networked interactions and their subsequent effect on agents' use of community resources across an urban population. A random forest model is iteratively fitted to model evaluations to characterize the model parameter space with respect to observed empirical data. We demonstrate the feasibility of using high-performance computing and active learning model exploration techniques to characterize large parameter spaces; by partitioning the parameter space into potentially viable and non-viable regions, we rule out regions of space where simulation output is implausible to observed empirical data. We argue that such methods are necessary to enable model exploration in complex computational models that incorporate increasingly available micro-level behavior data. We provide public access to the model and high-performance computing experimentation code.

97 MATHEMATICS AND COMPUTING↗

Evaluating System Parameters on a Dragonfly using Simulation and Visualization

The dragon y topology is becoming a popular choice for build- ing high-radix, low-diameter networks with high-bandwidth links. Even with a powerful network, preliminary experi- ments on Edison at NERSC have shown that for communica- tion heavy applications, job interference and thus presumably job placement remains an important factor. In this paper, we explore the e ects of job placement, job sizes, parallel workloads and network con gurations on network through- put to better understand inter-job interference. We use a simulation tool called Damsel y to model the network be- havior of Edison and study the impact of various system parameters on network throughput. Parallel workloads based on ve representative communication patters are used and the simulation studies on up to 131,072 cores are aided by a new visualization of the dragon y network.

97 MATHEMATICS AND COMPUTING↗

Estimating Surface Solar Irradiance Using Meteosat-8 Satellite for India and Surrounding Regions (2017-2019)

Using the Physical Solar Model, Version 3 (PSM V3), the National Renewable Energy Laboratory—in collaboration with the University of Wisconsin, the National Oceanic and Atmospheric Administration, and Solar Consulting Services—produced modeled surface solar irradiance based on Meteosat-8 satellite cloud information. PSM V3 implements a physics-based radiative transfer approach to model surface solar irradiance using cloud properties processed from raw satellite data and ancillary data such as aerosol optical depth and precipitable water vapor from the Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2). Further, the modeled surface solar irradiance was validated using 10 high-quality ground measurement data from the Baseline Surface Radiation Network. The modeled data showed good correlation with the ground measurement, and the overall uncertainty is less than 35% for all validation locations. Because of the satellite viewing geometry, the Indian and European locations demonstrated higher uncertainties than the African locations, where the Meteosat-8 satellite has a more nadir viewing geometry. Further, instruction on how to access the data is provided.

14 SOLAR ENERGY↗

Optimizing squeezing in a coherent quantum feedback network of optical parametric oscillators

Advances in the emerging field of coherent quantum feedback control (CQFC) have led to the development of new capabilities in the areas of quantum control and quantum engineering, with a particular impact on the theory and applications of quantum optical networks. For this study, we consider a CQFC network consisting of two coupled optical parametric oscillators (OPOs) and study the squeezing spectrum of its output field. The performance of this network as a squeezed-light source with desired spectral characteristics is optimized by searching over the space of model parameters with experimentally motivated bounds. We use the QNET package to model the network’s dynamics and the PyGMO package of global optimization algorithms to maximize the degree of squeezing at a selected sideband frequency or the average degree of squeezing over a selected bandwidth. The use of global search methods is critical for identifying the best possible performance of the CQFC network, especially for squeezing at higher-frequency sidebands and higher bandwidths. The results demonstrate that the CQFC network of two coupled OPOs makes it possible to vary the squeezing spectrum, effectively utilize the available pump power, and overall significantly outperform a single OPO. Additionally, the Hessian eigenvalue analysis shows that the squeezing generation performance of the optimally operated CQFC network is robust to small variations of phase parameters.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Identifying stochastic dynamics via finite expression methods

Modeling stochastic differential equations (SDEs) is crucial for understanding complex dynamical systems in various scientific fields. Recent methods often employ neural network-based models, which typically represent SDEs through a combination of deterministic and stochastic terms. However, these models usually lack interpretability and have difficulty in generalizing beyond their training domain. Here, this paper introduces the Finite Expression Method (FEX), a symbolic learning approach designed to derive interpretable mathematical representations of the deterministic component of SDEs. For the stochastic component, we integrate FEX with advanced generative modeling techniques to provide a comprehensive representation of SDEs. The numerical experiments on linear, nonlinear, and multidimensional SDEs demonstrate that FEX generalizes well beyond the training domain and delivers more accurate long-term predictions compared to neural network-based methods. The symbolic expressions identified by FEX not only improve prediction accuracy but also offer valuable scientific insights into the underlying dynamics of the systems.

Complex dynamical systems↗

Discrimination Analysis of Earthquakes and Man-Made Events Using ARMA Coefficients Determination by Artificial Neural Networks

A Quadratic Neural Networks (QNNs) model has been developed for identifying seismic source classification problem at regional distances using ARMA coefficients determination by Artificial Neural Networks (ANNs). We have devised a supervised neural system to discriminate between earthquakes and chemical explosions with filter coefficients obtained by windowed P-wave phase spectra (15 s). First, we preprocess the recording's signals to cancel out instrumental and attenuation site effects and obtain a compact representation of seismic records. Second, we use a QNNs system to obtain ARMA coefficients for feature extraction in the discrimination problem. The derived coefficients are then applied to the neural system to train and classification. In this study, we explore the possibility of using single station three-component (3C) covariance matrix traces from a priori-known explosion sites (learning) for automatically recognizing subsequent explosions from the same site. The results have shown that this feature extraction gives the best classifier for seismic signals and performs significantly better than other classification methods. The events have been tested, which include 36 chemical explosions at the Semipalatinsk test site in Kazakhstan and 61 earthquakes (mb = 5.0-6.5) recorded by the Iranian National Seismic Network (INSN). The 100% correct decisions were obtained between site explosions and some of non-site events. The above approach to event discrimination is very flexible as we can combine several 3C stations.

58 GEOSCIENCES↗

Nonlinear Elasticity: From Single Chain to Networks and Gels

Biological and polymeric networks show highly nonlinear stress–strain behavior manifested in materials that stiffen with increasing deformation. Using a combination of the theoretical analysis and molecular dynamics simulations, we develop a model of network deformation that describes nonlinear mechanical properties of networks and gels by relating their macroscopic strain-hardening behavior to molecular parameters of the network strands. The starting point of our approach is a nonlinear force/elongation relation for discrete chains with varying bending rigidity. The derived expression for the network free energy is a universal function of the first deformation invariant and chain elongation ratio that depends on a ratio of the unperturbed chain size to chain dimension in a fully extended conformation. The model predictions for the nonlinear shear modulus and differential shear modulus for uniaxial and shear deformations are in very good agreement with both the results of molecular dynamics simulations of networks and with experimental data for biopolymer networks of actin, collagen, fibrin, vimentin, neurofilaments, and pectin.

Polymer Science↗

Baseflow Identification via Explainable AI With Kolmogorov‐Arnold Networks

Abstract Hydrological models often involve constitutive laws that may not be optimal in every application. We propose to replace such laws with the Kolmogorov‐Arnold networks (KANs), a class of neural networks designed to identify symbolic expressions. We demonstrate KAN's potential on the problem of baseflow identification, a notoriously challenging task plagued by significant uncertainty. KAN‐derived functional dependencies of the baseflow components on the aridity index outperform their original counterparts; they demonstrate that water availability, rather than potential evapotranspiration, drives baseflow by constraining actual evapotranspiration under arid conditions. On a test set, they increase the Nash‐Sutcliffe efficiency (NSE) by 65%, decrease the root mean squared error by 29%, and increase the Kling‐Gupta efficiency by 34%. This superior performance is achieved while reducing the number of fitting parameters from three to two. Next, we use data from 378 catchments across the continental United States to refine the water‐balance equation at the mean‐annual scale. The KAN‐derived equations based on the refined water balance outperform both the current aridity index model, with up to a 105% increase in NSE, and the KAN‐derived equations based on the original water balance. While the performance of our model and tree‐based machine learning methods is similar, KANs offer the advantage of simplicity and transparency and require no specific software or computational tools. This case study focuses on the aridity index formulation, but the approach is flexible and transferable to other hydrological processes. Plain Language Summary Equations used in hydrologic model are often suboptimal, resulting in reduced prediction accuracy and efficiency. We implemented Kolmogorov‐Arnold networks (KAN), a machine learning algorithm for deriving symbolic formulations, to estimate groundwater recharge and showed that it outperforms an existing state‐of‐the‐art semi‐empirical formulation. In hydrology, Nash‐Sutcliffe efficiency (NSE), root mean squared error (RMSE), and Kling‐Gupta efficiency (KGE) are commonly used to evaluate model performance. Higher NSE and KGE values indicate better performance, while lower RMSE values are preferable. Our results show that NSE increased by 71%, RMSE decreased by 32%, and KGE improved by 25%. In addition, KAN identifies an optimal functional form and can be used to derive new analytical formulas using the prior knowledge. The KAN‐inspired equation outperformed the original formulation and reduced the fitting parameters. Furthermore, we refined the water‐balance equation at the mean‐annual scale and showed that, based on the new water‐balance equation, KAN can derive new formulations that are superior to the original aridity index formulations (up to 105% increase in NSE) and KAN‐derived equations based on the original water balance. These findings highlight the significant potential of KAN to advance the scientific understanding of a wide range of hydrologic processes. Key Points Kolmogorov‐Arnold networks (KANs) enhance interpretability of machine‐learned hydrological models KAN‐derived symbolic formulations outperform state‐of‐the‐art semi‐empirical aridity indices KAN‐identified functional form yields an analytical index with fewer fitting parameters and improved performance

baseflow↗

Flow-Driven Stretch Fluctuations Govern the Nonlinear Viscoelasticity of Elongating Associative Polymer Networks

We use nonequilibrium molecular dynamics simulations to verify recent tube-model predictions that associative polymer networks exhibit broad stretch fluctuations during elongational flow. Simulations further show that these fluctuating dynamics give rise to the rate-dependent extensional viscosity 𝜂 𝐸 measured in filament stretching experiments on H-bonding networks. Simulations model bivalent associative networks with a reactive bead-spring model for varying association strength and extensional strain rate. We observe that stretch fluctuations are driven by a new form of chain tumbling, where chains continually collapse and elongate as their associations break and reform within the advecting network. This produces a broad, nearly uniform distribution of chain stretch over a wide range of strain rates, manifesting as a rate-independent plateau in the extensional stress. Our results show that the nonlinear viscoelasticity of associative networks is dominated by large fluctuations in molecular response, which cannot be captured by current mean-field models.

biomimetic & bio-inspired materials↗

Final Report for Industrial Base Cybersecurity Initiative (IBCI) Project (FY2019)

Information security issues impact all manufacturing sectors and are particularly troublesome when designs for advanced weapons systems are lost via attacks that propagate through the relatively unprotected lower tiers of the nation's supply chains. The US Manufacturing Industrial Base (MIB) consists of suppliers and distributors that range in size from large prime contractors with extensive cybersecurity resources to small shops with little or no in-house information technology capabilities. The acquisition and maintenance of the technologies, systems, and financial resources needed to assure secure collaborations can be an overwhelming challenge for many manufacturers yet the cost of poor cybersecurity practices can lead to the compromise of national security information worth hundreds of millions of dollars. The Department of Defense Manufacturing Industrial Base Policy organization and the Department of Energy, Energy Efficiency and Renewable Energy Advanced Manufacturing Office have chartered the Los Alamos National Laboratory (LANL) and the Oak Ridge Y-12 National Security Complex (Y-12) to design, develop, and demonstrate a Manufacturing Threat Evaluation Wargaming System (MTEWS). The MTEWS concept is based on the use of a virtual model of the computer networks and cybersecurity protocols used across the MIB that will be continuously updated to reflect the dynamic threat environment. The MTEWS cyber-physical test range will demonstrate a prototype wargaming system that analyzes the impact of new and existing cybersecurity threats while also providing the information needed to sustain the integrity of the MIB supply chains. A long-term goal is the establishment of an enduring national manufacturing operations center that proactively responds to the continuously changing attacks that threaten the MIB and US national security. LANL and Y-12 have formed an Industrial Base Cybersecurity Initiative Team (IBCI), consisting of partners from the public, private and academic sectors, that is developing the MTEWS. To date, most of the project tasks have been centered on the technologies required to create a representative model of the MIB because this is a foundational element for the entire project. Modeling activities at the University of North Carolina at Charlotte (UNC Charlotte) have demonstrated a VMware-based prototype system that can accommodate a network model with up to 350 nodes and includes features such as the option to incorporate network scanning information when building the model and the ability to down select the elements of duplicative networks to a statistically significant subset that avoids redundantly duplicating network configurations. Broad Ordering Agreements have been established with UNC Charlotte and the University of West Florida (UWF) that support a variety of cybersecurity for manufacturing tasks and wide-spread endorsement has been received from government, industry and academia sectors concerning the IBCI goals and technical direction.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Development of neural network convection parameterizations for climate and NWP models using Cloud Resolving Model simulations

A novel approach based on the neural network (NN) technique is formulated and used for development of a NN ensemble stochastic convection parameterization for climate models. This fast parameterization is built based on data from Cloud Resolving Model (CRM) simulations initialized with and driven by the TOGA-COARE data available for the 4-month winter season from November 1992 to February 1993. CRM simulated data were averaged and projected onto the GCM space of atmospheric states to implicitly define a stochastic convection parameterization. This parameterization is emulated using an ensemble of neural networks (NNs). The developed NNs are trained and tested. The inherent uncertainty of the stochastic convection parameterization derived following this approach is estimated. The newly developed NN convection parameterization has been tested in a diagnostic mode of NCAR CAM. It produced reasonable and promising climate simulations for the TOGA-COARE winter. This paper is devoted to discussion of the concept, methodology, initial results,and the major challenges of development of NN convection parameterizations for climate and numerical weather prediction (NWR) models.

97 MATHEMATICS AND COMPUTING↗

MFNets: data efficient all-at-once learning of multifidelity surrogates as directed networks of information sources

We present an approach for constructing a surrogate from ensembles of information sources of varying cost and accuracy. The multifidelity surrogate encodes connections between information sources as a directed acyclic graph, and is trained via gradient-based minimization of a nonlinear least squares objective. While the vast majority of state-of-the-art assumes hierarchical connections between information sources, our approach works with flexibly structured information sources that may not admit a strict hierarchy. The formulation has two advantages: (1) increased data efficiency due to parsimonious multifidelity networks that can be tailored to the application; and (2) no constraints on the training data—we can combine noisy, non-nested evaluations of the information sources. Finally, numerical examples ranging from synthetic to physics-based computational mechanics simulations indicate the error in our approach can be orders-of-magnitude smaller, particularly in the low-data regime, than single-fidelity and hierarchical multifidelity approaches.

97 MATHEMATICS AND COMPUTING↗