Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural 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 1,387 records · Page 77

Vibrational energies for HFCO using a neural network sum of exponentials potential energy surface

A six-dimensional potential energy surface (PES) for formyl fluoride (HFCO) is fit in a sum-of-products form using neural network exponential fitting functions. The ab initio data upon which the fit is based were computed at the explicitly correlated coupled cluster with single, double, and perturbative triple excitations [CCSD(T)-F12]/cc-pVTZ-F12 level of theory. The PES fit is accurate (RMSE = 10 cm{sup −1}) up to 10 000 cm{sup −1} above the zero point energy and covers most of the experimentally measured IR data. The PES is validated by computing vibrational energies for both HFCO and deuterated formyl fluoride (DFCO) using block improved relaxation with the multi-configuration time dependent Hartree approach. The frequencies of the fundamental modes, and all other vibrational states up to 5000 cm{sup −1} above the zero-point energy, are more accurate than those obtained from the previous MP2-based PES. The vibrational frequencies obtained on the PES are compared to anharmonic frequencies at the MP2/aug-cc-pVTZ and CCSD(T)/aug-cc-pVTZ levels of theory obtained using second-order vibrational perturbation theory. The new PES will be useful for quantum dynamics simulations for both HFCO and DFCO, e.g., studies of intramolecular vibrational redistribution leading to unimolecular dissociation and its laser control.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Self-consistent core-pedestal transport simulations with neural network accelerated models

Fusion whole device modeling simulations require comprehensive models that are simultaneously physically accurate, fast, robust, and predictive. In this paper we describe the development of two neural-network (NN) based models as a means to perform a snon-linear multivariate regression of theory-based models for the core turbulent transport fluxes, and the pedestal structure. Specifically, we find that a NN-based approach can be used to consistently reproduce the results of the TGLF and EPED1 theory-based models over a broad range of plasma regimes, and with a computational speedup of several orders of magnitudes. These models are then integrated into a predictive workflow that allows prediction with self-consistent core-pedestal coupling of the kinetic profiles within the last closed flux surface of the plasma. Finally, the NN paradigm is capable of breaking the speed-accuracy trade-off that is expected of traditional numerical physics models, and can provide the missing link towards self-consistent coupled core-pedestal whole device modeling simulations that are physically accurate and yet take only seconds to run.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Fishing for Clickbaits in Social Images and Texts with Linguistically-Infused Neural Network Models

This paper presents the results and conclusions of our participation in the Clickbait Challenge 2017 on automatic clickbait detection in social media. We first describe linguistically-infused neural network models and identify informative representations to predict the level of clickbaiting present in Twitter posts. Our models allow to answer the question not only whether a post is a clickbait or not, but to what extent it is a clickbait post e.g., not at all, slightly, considerably, or heavily clickbaity using a score ranging from 0 to 1. We evaluate the predictive power of models trained on varied text and image representations extracted from tweets. Our best performing model that relies on the tweet text and linguistic markers of biased language extracted from the tweet and the corresponding page yields mean squared error (MSE) of 0.04, mean absolute error (MAE) of 0.16 and R2 of 0.43 on the held-out test data. For the binary classification setup (clickbait vs. non-clickbait), our model achieved F1 score of 0.69. We have not found that image representations combined with text yield significant performance improvement yet. Nevertheless, this work is the first to present preliminary analysis of objects extracted using Google Tensorflow object detection API from images in clickbait vs. non-clickbait Twitter posts. Finally, we outline several steps to improve model performance as a part of the future work.

dlickbait challenge, Twitter, neural networks, mac↗

Quantum Perturbation Theory Using Tensor Cores and a Deep Neural Network

In this work, time-independent quantum response calculations are performed using Tensor cores. This is achieved by mapping density matrix perturbation theory onto the computational structure of a deep neural network. The main computational cost of each deep layer is dominated by tensor contractions, i.e., dense matrix–matrix multiplications, in mixed-precision arithmetics, which achieves close to peak performance. Quantum response calculations are demonstrated and analyzed using self-consistent charge density-functional tight-binding theory as well as coupled-perturbed Hartree–Fock theory. For linear response calculations, a novel parameter-free convergence criterion is presented that is well-suited for numerically noisy low-precision floating point operations and we demonstrate a peak performance of almost 200 Tflops using the Tensor cores of two Nvidia A100 GPUs.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

CEGANN: Crystal Edge Graph Attention Neural Network for multiscale classification of materials environment

Abstract We introduce Crystal Edge Graph Attention Neural Network (CEGANN) workflow that uses graph attention-based architecture to learn unique feature representations and perform classification of materials across multiple scales (from atomic to mesoscale) and diverse classes ranging from metals, oxides, non-metals to hierarchical materials such as zeolites and semi-ordered mesophases. CEGANN can classify based on a global, structure-level representation such as space group and dimensionality (e.g., bulk, 2D, clusters, etc.). Using representative materials such as polycrystals and zeolites, we demonstrate its transferability in performing local atom-level classification tasks, such as grain boundary identification and other heterointerfaces. CEGANN classifies in (thermal) noisy dynamical environments as demonstrated for representative zeolite nucleation and growth from an amorphous mixture. Finally, we use CEGANN to classify multicomponent systems with thermal noise and compositional diversity. Overall, our approach is material agnostic and allows for multiscale feature classification ranging from atomic-scale crystals to heterointerfaces to microscale grain boundaries.

36 MATERIALS SCIENCE↗

Artificial neural network prediction of self-diffusion in pure compounds over multiple phase regimes

Artificial neural networks (ANNs) were developed to accurately predict the self-diffusion constants for pure components in liquid, gas and super critical phases. The ANNs were tested on an experimental database of 6625 self-diffusion constants for 118 different chemical compounds. The presence of multiple phases results in a heavy skew in the distribution of diffusion constants and multiple approaches were used to address this challenge. First, an ANN was developed with the raw diffusion values to assess what the main drawbacks of this direct method were. The first approach for improving the predictions involved taking the log 10 of diffusion to provide a more uniform distribution and reduce the range of target output values used to develop the ANN. The second approach involved developing individual ANNs for each phase using the raw diffusion values. Results show that the log transformation leads to a model with the best self-diffusion constant predictions and an overall average absolute deviation (AAD) of 6.56%. The resultant ANN is a generalized model that can be used to predict diffusion across all three phases and over a diverse group of compounds. The importance of each input feature was ranked using a feature addition method revealing that the density of the compound has the largest impact on the ANN prediction of self-diffusion constants in pure compounds.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Deep neural network for the dielectric response of insulators

In this work, we introduce a deep neural network to model in a symmetry preserving way the environmental dependence of the centers of the electronic charge. The model learns from ab initio density functional theory, wherein the electronic centers are uniquely assigned by the maximally localized Wannier functions. When combined with the deep potential model of the atomic potential energy surface, the scheme predicts the dielectric response of insulators for trajectories inaccessible to direct ab initio simulation. The scheme is nonperturbative and can capture the response of a mutating chemical environment. We demonstrate the approach by calculating the infrared spectra of liquid water at standard conditions, and of ice under extreme pressure, when it transforms from a molecular to an ionic crystal.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

SNNPG: Using Spiking Neural Networks to Detect Attacks in the Power Grid

We explore the potential of Spiking Neural Networks (SNN) to enhance the security of power grid operations by detecting False Data Injection (FDI) attacks. These attacks manipulate PMU readings, leading to erroneous control decisions and grid disruptions. We develop a method to convert Phase Measurement Unit (PMU) data into spike trains, capturing both temporal and spatial dimensions. Using an SNN model, we conduct evaluations with simulated power grid data, showcasing accuracy in detecting FDI attacks. SNN models rapidly identify anomalies in real-time PMU data, safeguarding grid operations by alerting operators to irregular readings and preventing incorrect decisions.

artificial intelligence↗

DistGANS- Distributed Generative Adversarial Neural Networks

DistGANs is a Python package to perform distributed training of conditional generative adversarial neural networks for multi-class labeled image data. DistGANs partitionins the training data according to data labels, and enhances scalability by performing a parallel training where multiple generators are concurrently trained, each one of them focusing on a single data label.

Lupo Pasini, Massimiliano [Oak Ridge National Lab.↗

Reconstructing Richtmyer–Meshkov instabilities from noisy radiographs using low dimensional features and attention-based neural networks

We develop an ML-based approach for density reconstruction based on transformer neural networks. This approach is demonstrated in the setting of ICF-like double shell hydrodynamic simulations wherein the parameters related to material properties and initial conditions are varied. The new method can robustly recover the complex topologies given by the Richtmyer-Meshkoff instability (RMI) from a sequence of hydrodynamic features derived from radiographic images corrupted with blur, scatter, and noise. A noise model is developed to characterize errors in extracting features from synthetic radiographs of the simulated density field. The key component of the network is a transformer encoder that acts on a sequence of features extracted from noisy radiographs. This encoder includes numerous self-attention layers that act to learn temporal dependencies in the input sequences and increase the expressiveness of the model. This approach is shown to exhibit an excellent ability to accurately recover the RMI growth rates, despite the gas-metal interface being greatly obscured by radiographic noise. Our approach can be applied in a broad array of fields involving shock physics and material science.

47 OTHER INSTRUMENTATION↗

User Manual - HydraGNN v5.0: Distributed Implementation of Multi-Tasking Graph Neural Networks

This document serves as the user manual for HydraGNN v5.0, a scalable graph neural network (GNN) architecture for simultaneous prediction of multiple target properties using multi-task learning (MTL). This version of HydraGNN has been developed primarily to support the development, training, and deployment of predictive graph-based deep learning (DL) models for atomistic materials modeling. HydraGNN is templated over 13 message-passing policies, including invariant models (GIN, PNA, PNAPlus, GAT, MFC, CGCNN, SAGE, SchNet, DimeNet) and equivariant models (EGNN, PNAEq, PAINN, MACE), and supports distributed training via distributed data parallelism (DDP), DeepSpeed, and Fully Sharded Data Parallelism (FSDP) on leadership-class supercomputers. Although HydraGNN can be applied to problems beyond atomistic materials modeling, its current use is confined to homogeneous graphs. Additional capabilities include machine-learned interatomic potentials with energy-conserving forces, General, Powerful, and Scalable Graph Transformer (GraphGPS) global attention, periodic boundary conditions, hyperparameter optimization, mixed-precision training, and uncertainty quantification.

97 MATHEMATICS AND COMPUTING↗

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Neural networks in communication

An overview is given of eight papers on communication applications of neural networks (NNs), published in the November 1989 special issue of the IEEE Communications Magazine.

Posner, Edward C.↗