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 811 records · Page 45

NEUROSPF: A Tool For the Symbolic Analysis of Neural Networks

This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks. Given a trained neural network model, the tool extracts the architecture and model parameters and translates them into a Java representation that is amenable for analysis using the Symbolic PathFinder symbolic execution tool. Notably, NEUROSPF encodes specialized peer classes for parsing the model’s parameters, thereby enabling efficient analysis. With NEUROSPF the user has the flexibility to specify either the inputs or the network internal parameters as symbolic, promoting the application of program analysis and testing approaches from software engineering to the field of machine learning. For instance, NEUROSPF can be used for coverage-based testing and test generation, finding adversarial examples and also constraint-based repair of neural networks, thus improving the reliability of neural networks and of the applications that use them.

neural networks↗

Pilot Workload Rating Predictions Using Image Data and Recurrent Neural Networks

In this work, we augmented existing methods for estimating pilot workload ratings with deep neural networks trained using data from simulated flight tests in the Vertical Motion Simulator (VMS). We used an existing method, Spare Capacity Operations Estimator (SCOPE), along with a recurrent neural network and conducted comparison studies between the two methods individually, and when used together. We found that using both methods together can improve the result over using either approach alone. In our first test case, we achieved an improved linear correlation coefficient of 0.409 over that of SCOPE alone at 0.352 on the training dataset. Through cross validation, we also found that the results may be dependent on the split of training vs. validation data, and that further investigation should be conducted to understand what additional inputs to the neural network model should be made.

Image Data↗

Importance of Engineered and Learned Molecular Representations in Predicting Organic Reactivity, Selectivity, and Chemical Properties

Machine-readable chemical structure representations are foundational in all attempts to harness machine learning for the prediction of reactivities, selectivities, and chemical properties directly from molecular structure. The featurization of discrete chemical structures into a continuous vector space is a critical phase undertaken before model selection, and the development of new ways to quantitatively encode molecules is an active area of research. Here, we highlight the application and suitability of different representations, from expert-guided “engineered” descriptors to automatically “learned” features, in different prediction tasks relevant to organic and organometallic chemistry, where differing amounts of training data are available. These tasks include statistical models of stereo- and enantioselectivity, thermochemistry, and kinetics developed using experimental and quantum chemical data. The use of expert-guided molecular descriptors provides an opportunity to incorporate chemical knowledge, domain expertise, and physical constraints into statistical modeling. In applications to stereoselective organic and organometallic catalysis, where data sets may be relatively small and 3D-geometries and conformations play an important role, mechanistically informed features can be used successfully to obtain predictive statistical models that are also chemically interpretable. We provide an overview of several recent applications of this approach to obtain quantitative models for reactivity and selectivity, where topological descriptors, quantum mechanical calculations of electronic and steric properties, along with conformational ensembles, all feature as essential ingredients of the molecular representations used. Alternatively, more flexible, general-purpose molecular representations such as attributed molecular graphs can be used with machine learning approaches to learn the complex relationship between a structure and prediction target. This approach has the potential to out-perform more traditional representation methods such as “hand-crafted” molecular descriptors, particularly as data set sizes grow. One area where this is particularly relevant is in the use of large sets of quantum mechanical data to train quantitative structure–property relationships. A general approach toward curating useful data sets and training highly accurate graph neural network models is discussed in the context of organic bond dissociation enthalpies, where this strategy outperforms regression using precomputed descriptors. Finally, we describe how graph neural network predictions can be incorporated into mechanistically informed statistical models of chemical reactivity and selectivity. Once trained, this approach avoids the expensive computational overhead associated with quantum mechanical calculations, while maintaining chemical interpretability. We illustrate examples for which fast predictions of bond dissociation enthalpy and of the identities of radicals formed through cleavage of a molecule’s weakest bond are used in simple physical models of site-selectivity and reactivity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Study of Complex Deep Learning Networks on High-Performance, Neuromorphic, and Quantum Computers

Current deep learning approaches have been very successful using convolutional neural networks trained on large graphical-processing-unit-based computers. Three limitations of this approach are that (1) they are based on a simple layered network topology, i.e., highly connected layers, without intra-layer connections; (2) the networks are manually configured to achieve optimal results, and (3) the implementation of the network model is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing to automatically determine network topology, and neuromorphic computing for a low-power hardware implementation. We use the MNIST dataset for our experiment, due to input size limitations of current quantum computers. Our results show the feasibility of using the three architectures in tandem to address the above deep learning limitations. Finally, we show that a quantum computer can find high quality values of intra-layer connection weights in a tractable time as the complexity of the network increases, a high performance computer can find optimal layer-based topologies, and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware.

97 MATHEMATICS AND COMPUTING↗

The effect of inhibition of PP1 and TNFα signaling on pathogenesis of SARS coronavirus

The complex interplay between viral replication and host immune response during infection remains poorly understood. While many viruses are known to employ antiimmune strategies to facilitate their replication, highly pathogenic virus infections can also cause an excessive immune response that exacerbates, rather than reduces pathogenicity. To investigate this dichotomy in severe acute respiratory syndrome coronavirus (SARS-CoV), we developed a transcriptional network model of SARS-CoV infection in mice and used the model to prioritize candidate regulatory targets for further investigation. We validated our predictions in 18 different knockout (KO) mouse strains, showing that network topology provides significant predictive power to identify genes that are important for viral infection. We identified a novel player in the immune response to virus infection, Kepi, an inhibitory subunit of the protein phosphatase 1 (PP1) complex, which protects against SARS-CoV pathogenesis. We also found that receptors for the proinflammatory cytokine, tumor necrosis factor alpha (TNFα), promote pathogenesis through a parallel feed-forward circuit that promotes inflammation. These results are consistent with previous studies showing the role of over-stimulation of the inflammatory response to SARS-CoV in pathogenesis. We conclude that the critical balance between immune response and inflammation can be manipulated to improve the outcome of the infection. Further, our study provides two potential therapeutic strategies for mitigating the effects of SARS-CoV infection, and may provide insight into treatment strategies for Middle East Respiratory Syndrome Coronavirus (MERS-CoV).

network inference↗

Structural Studies of Amorphous Materials by Fluctuation Electron Microscopy

Fluctuation Electron Microscopy (FEM) is a technique that examines the fluctuations in electron scattering across a uniformly thin amorphous sample. The statistics of the intensity fluctuations, mean and variance, reveal any underlying medium-range order present in the structure. The goals of this project were: (1) To determine the fundamentals of the scattering physics that gives rise to the variance signal in fluctuation electron microscopy (FEM); (2) To use these discoveries to find ways to quantify FEM; (3) To apply the FEM method to interesting and technologically important families of amorphous materials, particularly those with important applications in energy-related processes. Excellent progress was made in items (1) and (2). In stage (3) we did not examine the metamict zircons, as proposed. Instead, we examined films of polycrystalline and amorphous semi-conducting diamond. Significant accomplishments are: (1) A Reverse Monte Carlo procedure was successfully implemented to invert FEM data into a structural model. This is computer-intensive, but it demonstrated that diffraction and FEM data from amorphous silicon are most consistent with a paracrystallite model. This means that there is more diamond-like topology present in amorphous silicon than is predicted by the continuous random network model. (2) There is significant displacement decoherence arising in diffraction from amorphous silicon and carbon. The samples are being bombarded by the electron beam and atoms do not stay still while being irradiated – much more than was formerly understood. The atom motions cause the destructive and constructive interferences in the diffraction pattern to fluctuate with time, and it is the time-averaged speckle that is being measured. The variance is reduced by a factor m, 4 ≤ m ≤ 1000, relative to that predicted by kinematical scattering theory. (3) Speckle intensity obeys a gamma distribution, where the mean intensity $ \overline{I}\ $ and m are the two parameters governing the shape of the gamma distribution profile. m is determined by the illumination spatial coherence, which is normally very high, and mostly by the displacement decoherence within the sample. (4) Amorphous materials are more affected by the electron beam than are crystalline materials. Different samples exhibit different disruptibility, as measured by the effective values of m that fit the data. (5) Understanding the origin of the displacement decoherence better should lead to efficient methods for computing the observed variance from amorphous materials.

36 MATERIALS SCIENCE↗

Water Network Tool for Resilience (WNTR). User Manual, Version 0.2.3

The Water Network Tool for Resilience (WNTR, pronounced winter) is a Python package designed to simulate and analyze resilience of water distribution networks. Here, a network refers to the collection of pipes, pumps, valves, junctions, tanks, and reservoirs that make up a water distribution system. WNTR has an application programming interface (API) that is flexible and allows for changes to the network structure and operations, along with simulation of disruptive incidents and recovery actions. WNTR is based upon EPANET, which is a tool to simulate the movement and fate of drinking water constituents within distribution systems. Users are encouraged to be familiar with the use of EPANET and/or should have background knowledge in hydraulics and pressurized pipe network modeling before using WNTR. EPANET has a graphical user interface that might be a useful tool to facilitate the visualization of the network and the associated analysis results. Information on EPANET can be found at https://www.epa.gov/water-research/epanet. WNTR is compatible with EPANET 2.00.12 [Ross00]. In addition, users should have experience using Python, including the installation of additional Python packages. General information on Python can be found at https://www.python.org/.

54 ENVIRONMENTAL SCIENCES↗

Supervised Learning for Distribution Secondary Systems Modeling: Improving Solar Interconnection Processes

The current interconnection process and hosting capacity analysis for distributed energy resources (DERs), such as photovoltaics (PV) and battery energy storage systems, are based on analyzing grid network constraints (voltage and thermal) using only medium-voltage distribution network models. This is because most utilities do not have secondary low-voltage system models that connect service transformers and residential customers. This is important because in many cases the main impact of interconnecting DERs could occur on the low-voltage distribution systems. This paper proposes a supervised learning method to approximate local secondary models to improve the interconnection process. The proposed supervised learning method includes a decision tree model that predicts the secondary topology and a logistic regression model that predicts conductor types. The case studies demonstrate the benefits of including secondary low-voltage circuits in the interconnection process. We report the proposed modeling methodology is readily scalable and thus can reduce the cost and effort of PV interconnection for the industry and stakeholders.

14 SOLAR ENERGY↗

Power flow for spacecraft power systems

A method for constructing the generalized system-level admittance matrix for use with a Newton-Raphson power flow is presented. The network modeling technique presented does not use the standard pi-equivalent models, which assume a lossless return path, for the transmission line and transformer. If the return path cannot be assumed lossless, then the standard algorithms for constructing the system admittance matrix cannot be used. The method presented here uses concepts from linear graph theory to combine network modules to form the system-level admittance matrix. The modeling technique is presented, and the resulting matrix is used with a standard Newton-Raphson power flow to calculate all system voltages and current (power) flows.

Halpin, S. M.↗

SCEDS: protein fragments for molecular replacement in Phaser

Protein fragments suitable for use in molecular replacement can be generated by normal-mode perturbation, analysis of the difference distance matrix of the original versus normal-mode perturbed structures, and SCEDS, a score that measures the sphericity, continuity, equality and density of the resulting fragments. A method is described for generating protein fragments suitable for use as molecular-replacement (MR) template models. The template model for a protein suspected to undergo a conformational change is perturbed along combinations of low-frequency normal modes of the elastic network model. The unperturbed structure is then compared with each perturbed structure in turn and the structurally invariant regions are identified by analysing the difference distance matrix. These fragments are scored with SCEDS, which is a combined measure of the sphericity of the fragments, the continuity of the fragments with respect to the polypeptide chain, the equality in number of atoms in the fragments and the density of C{sup α} atoms in the triaxial ellipsoid of the fragment extents. The fragment divisions with the highest SCEDS are then used as separate template models for MR. Test cases show that where the protein contains fragments that undergo a change in juxtaposition between template model and target, SCEDS can identify fragments that lead to a lower R factor after ten cycles of all-atom refinement with REFMAC5 than the original template structure. The method has been implemented in the software Phaser.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Multilevel Training of Neural Networks

MTNN is a software library for applying multilevel algorithms on training neural networks. Based on PyTorch, it is designed to be an extensible framework to enable researchers to implement multilevel training algorithms on a variety of neural network models. This release includes a culmination of preliminary work in applying the multilevel Full Approximation Scheme technique on fully connected and convolutional neural networks to solve PDE problems (pending publication submission).

Li, Ruipeng↗

Model-form Error Correction using Universal Differential Equations for an Agent-Based Model of Infectious Disease

This report demonstrates universal differential equations (UDEs) as an approach to bridge the gap between ordinary differential equations (ODE) models and agent-based models (ABMs). Using UDE models as surrogates for ABMs allows us to preserve the foundational ODE that represents global disease dynamics while coupling it with a neural network model to approximate functions for the local behaviors of the ABM.

59 BASIC BIOLOGICAL SCIENCES↗

Higher-order neural network software for distortion invariant object recognition

The state-of-the-art in pattern recognition for such applications as automatic target recognition and industrial robotic vision relies on digital image processing. We present a higher-order neural network model and software which performs the complete feature extraction-pattern classification paradigm required for automatic pattern recognition. Using a third-order neural network, we demonstrate complete, 100 percent accurate invariance to distortions of scale, position, and in-plate rotation. In a higher-order neural network, feature extraction is built into the network, and does not have to be learned. Only the relatively simple classification step must be learned. This is key to achieving very rapid training. The training set is much smaller than with standard neural network software because the higher-order network only has to be shown one view of each object to be learned, not every possible view. The software and graphical user interface run on any Sun workstation. Results of the use of the neural software in autonomous robotic vision systems are presented. Such a system could have extensive application in robotic manufacturing.

Reid, Max B.↗

Efficient hierarchical interconnection for multiprocessor systems

The authors present a novel approach to the design of a class of hierarchical interconnection networks for multiprocessor systems. This approach, based on an architecture providing separate networks for each level, gives a general and flexible way to construct efficient hierarchical networks. The performance and cost-effectiveness of the resulting networks are analyzed and compared in detail, using both unbuffered and buffered network models. It is shown that, if the design parameters are determined based on the degree of locality, the cost-effectiveness of a hierarchical network can be significantly improved. In addition, the authors investigate how to construct a cost-effectiveness hierarchical network by determining appropriate design parameters. Two associated algorithms are developed for this purpose.

Wei, Sizheng↗

Comparison of Analytical and Numerical Performance Predictions for a Regenerative Heat Exchanger in the International Space Station Node 3 Internal Active Thermal Control System

The complexity of International Space Station (ISS) systems modeling often necessitates the concurrence of various dissimilar, parallel analysis techniques to validate modeling. This was the case with a feasibility and performance study of the ISS Node 3 Regenerative Heat Exchanger (RHX). A thermo-hydraulic network model was created and analyzed in SINDA/FLUINT. A less complex, closed form solution of the system dynamics was created using Excel. The purpose of this paper is to provide a brief description of the modeling processes utilized, the results and benefits of each to the ISS Node 3 RHX study.

Wise, Stephen A.↗

Comparison of Analytical and Numerical Performance Predictions for an International Space Station Node 3 Internal Active Thermal Control System Regenerative Heat Exchanger

The complexity of International Space Station (ISS) systems modeling often necessitates the concurrence of various dissimilar, parallel analysis techniques to validate modeling. This was the case with a feasibility and performance study of the ISS Node 3 Regenerative Heat Exchanger (RHX). A thermo-hydraulic network model was created and analyzed in SINDA/FLUINT. A less complex, closed form solution of the systems dynamics was created using an Excel Spreadsheet. The purpose of this paper is to provide a brief description of the modeling processes utilized, the results and benefits of each to the ISS Node 3 RHX study.

Wise, Stephen A.↗

Physics-informed State-space Neural Networks for transport phenomena

This work introduces Physics -informed State -space neural network Models (PSMs), a novel solution to achieving real-time optimization, flexibility, and fault tolerance in autonomous systems, particularly in transportdominated systems such as chemical, biomedical, and power plants. Traditional data -driven methods fall short due to a lack of physical constraints like mass conservation; PSMs address this issue by training deep neural networks with sensor data and physics -informing using components' Partial Differential Equations (PDEs), resulting in a physics -constrained, end -to -end differentiable forward dynamics model. Further, through two in silico experiments - a heated channel and a cooling system loop - we demonstrate that PSMs offer a more accurate approach than a purely data -driven model. In the former experiment, PSMs demonstrated significantly lower average root -mean -square errors across test datasets compared to a purely data -driven neural network, with reductions of 44 %, 48 %, and 94 % in predicting pressure, velocity, and temperature, respectively. Beyond accuracy, PSMs demonstrate a compelling multitask capability, making them highly versatile. In this work, we showcase two: supervisory control of a nonlinear system through a sequentially updated state -space representation and the proposal of a diagnostic algorithm using residuals from each of the PDEs. The former demonstrates PSMs' ability to handle constant and time -dependent constraints, while the latter illustrates their value in system diagnostics and fault detection.

42 ENGINEERING↗

Generalized multifractality at spin quantum Hall transition

Generalized multifractality characterizes scaling of eigenstate observables at Anderson-localization critical points. We explore generalized multifractality in 2D systems, with the main focus on the spin quantum Hall (SQH) transition in superconductors of symmetry class C. Relations and differences with the conventional integer quantum Hall (IQH) transition are also studied. Using the field-theoretical formalism of non-linear sigma-model, we derive the pure-scaling operators representing generalizing multifractality and then “translate” them to the language of eigenstate observables. Performing numerical simulations on network models for SQH and IQH transitions, we confirm the analytical predictions for scaling observables and determine the corresponding exponents. Remarkably, the generalized-multifractality exponents at the SQH critical point strongly violate the generalized parabolicity of the spectrum, which implies violation of the local conformal invariance at this critical point.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗