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 1,225 records · Page 68
All sourcesNASA NTRSDOE OSTI
NASA NTRS1994

A feasibility study for long-path multiple detection using a neural network

Least-squares inverse filters have found widespread use in the deconvolution of seismograms and the removal of multiples. The use of least-squares prediction filters with prediction distances greater than unity leads to the method of predictive deconvolution which can be used for the removal of long path multiples. The predictive technique allows one to control the length of the desired output wavelet by control of the predictive distance, and hence to specify the desired degree of resolution. Events which are periodic within given repetition ranges can be attenuated selectively. The method is thus effective in the suppression of rather complex reverberation patterns. A back propagation(BP) neural network is constructed to perform the detection of first arrivals of the multiples and therefore aid in the more accurate determination of the predictive distance of the multiples. The neural detector is applied to synthetic reflection coefficients and synthetic seismic traces. The processing results show that the neural detector is accurate and should lead to an automated fast method for determining predictive distances across vast amounts of data such as seismic field records. The neural network system used in this study was the NASA Software Technology Branch's NETS system.

Feuerbacher, G. A.↗
DOE OSTI2020

Data-Driven Template Discovery Using Graph Convolutional Neural Networks

Modeling adversarial activities is a critical component of developing high-con?dence indicators of efforts to acquire, fabricate, proliferate, and/or deploy weapons of mass terror (WMTs). Current approaches to generating representative patterns of interest (a.k.a templates) from the real-world domains involve a Subject Matter Expert (SME)-guided manual process. The goal of Data-Driven Template Discovery (DDTD) is to use a (potentially small) set of SME generated templates to discover other previously unknown and interesting templates in an attributed graph. A template is an activity pattern describing a set of interactions among a group of nodes in the graph. The motivation behind DDTD is to expand the original set of templates, without having SMEs craft all the templates by hand. DDTD also provides seed templates to SMEs, to help them construct larger, high-?delity, and scenario-oriented templates. In these cases, obtaining a larger set of templates that are related (contain similar signals) to the original set is of great value. In this work, we propose to use Graph Convolutional Neural Networks (GCNs) to discover new templates that are heavily related to the original set. GCNs are a family of Neural Network (NN) architectures especially designed to work directly on graphs. In contrast to the traditional NNs, that require considerable amounts of labeled data, GCNs do not require a big labeled training set because they can directly leverage the graph structure instead. This property makes GCNs the perfect tool for creating activity templates.

Joaristi, Mikel↗
DOE OSTI2020

A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters

A Continuous Filter Convolutional Neural Network (CF-CNN) was trained to predict the potential energy of water cluster networks \ce{(H2O)_{\textit{N}}}, \textit{N}=10--30, corresponding to local minima lying within 5 kcal/mol from the putative minima taken from a newly published database containing over 5 million unique networks. The chemical sampling space of the database was characterized using chemical descriptors derived from graph theory, which led to the identification of important trends in the topology, connectivity, polygon structures associated with the various networks as a function of cluster size. The resulting graphs are available alongside the original database at \url{https://sites.uw.edu/wdbase/}. The CF-CNN trained on a subset of 500,000 networks for (\textit{N}=10, 30) yielded a mean absolute error of 0.002$\pm$0.002 kcal/mol per water molecule, giving the trained CF-CNN the highest accuracy of any neural network-based surrogate model to date. In addition, clusters of sizes not included in the training set exhibited errors of the same magnitude, indicating that the CF-CNN ptotocol is general enough to accurately predict energies of networks for both smaller and larger sizes than those used during training. The graph-theoretical descriptors were developed in order to analyze the properties of the full database and interpret the predictive power of the CF-CNN. Using topology measures, such as the Wiener index and the average shortest path length along with two similarity measures, we showed that all networks from the test set were within the range of the ones from the training set, suggesting that the training set covered the chemical space of interest quite well. Our graph analysis suggests that the mean degree and number of polygons for networks with larger errors tend to lie further from the mean than those with lower errors. The generality of the used CF-CNN was thus demonstrated, while the use of the graph-theoretical descriptors assisted in interpreting the predicted results.

Bilbrey, Jenna A.↗
DOE OSTI2022

Regularizing Invertible Neural Networks for Airfoil Design Through Dimension Reduction

This work examines how dimension reduction can improve the performance of invertible neural networks (INN) for airfoil design. Design workflows are typically expensive, relying on many evaluations of high fidelity computational fluid dynamics (CFD) models. Furthermore, the inverse design problem is typically ill-posed. That is, multiple valid solutions exist that satisfy the design criteria. Regularization can reduce this inverse design space and simplify the problem. We study the use of subspace-based input dimension reduction to act as a regularizer for the INN model and improve the recovery of new airfoil shapes with desired performance characteristics. We find that the dimension reduction identifies two dominant modes, relating to airfoil thickness and camber, that optimally determine the airfoil's aerodynamics. We demonstrate the capability of the proposed INN model to generate 100 airfoils that satisfy the specific aerodynamic and structural characteristics.

airfoil design↗
DOE OSTI2022

A Self-learning Neural Network Approach for Radio Frequency Interference Detection and Removal in Radio Astronomy

In this work, we present a novel neural network (NN) method for the detection and removal of radio frequency interference (RFI) from the raw digitized signal in the signal processing chain of a typical radio astronomy experiment. The main advantage of our method is that it does not require a training set. Instead, our method relies on the fact that the true signal of interest coming from astronomical sources is thermal and therefore described as a Gaussian random process, which cannot be compressed. We employ a variational encoder/decoder network to find the compressible information in the data stream that can explain the most variance with the fewest degrees of freedom. We demonstrate it on a set of toy problems and stored ring buffers from the Baryon Mapping eXperiment prototype. We find that the RFI subtraction is effective at cleaning simulated time streams: While we find that the power spectra of the RFI-cleaned time streams output by the NN suffer from extra signal consistent with additive noise, we find that it is generally around percent level across the band and sub 10% in contaminated spectral channels even when RFI power is an order of magnitude larger than the signal. We discuss the advantages and limitations of this method and possible implementation in the front end of future radio experiments.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Compute in‐Memory with Non‐Volatile Elements for Neural Networks: A Review from a Co‐Design Perspective

Abstract Deep learning has become ubiquitous, touching daily lives across the globe. Today, traditional computer architectures are stressed to their limits in efficiently executing the growing complexity of data and models. Compute‐in‐memory (CIM) can potentially play an important role in developing efficient hardware solutions that reduce data movement from compute‐unit to memory, known as the von Neumann bottleneck. At its heart is a cross‐bar architecture with nodal non‐volatile‐memory elements that performs an analog multiply‐and‐accumulate operation, enabling the matrix‐vector‐multiplications repeatedly used in all neural network workloads. The memory materials can significantly influence final system‐level characteristics and chip performance, including speed, power, and classification accuracy. With an over‐arching co‐design viewpoint, this review assesses the use of cross‐bar based CIM for neural networks, connecting the material properties and the associated design constraints and demands to application, architecture, and performance. Both digital and analog memory are considered, assessing the status for training and inference, and providing metrics for the collective set of properties non‐volatile memory materials will need to demonstrate for a successful CIM technology.

36 MATERIALS SCIENCE↗
NASA NTRS1997

Neural Network Based Sensory Fusion for Landmark Detection

NASA is planning to send numerous unmanned planetary missions to explore the space. This requires autonomous robotic vehicles which can navigate in an unstructured, unknown, and uncertain environment. Landmark based navigation is a new area of research which differs from the traditional goal-oriented navigation, where a mobile robot starts from an initial point and reaches a destination in accordance with a pre-planned path. The landmark based navigation has the advantage of allowing the robot to find its way without communication with the mission control station and without exact knowledge of its coordinates. Current algorithms based on landmark navigation however pose several constraints. First, they require large memories to store the images. Second, the task of comparing the images using traditional methods is computationally intensive and consequently real-time implementation is difficult. The method proposed here consists of three stages, First stage utilizes a heuristic-based algorithm to identify significant objects. The second stage utilizes a neural network (NN) to efficiently classify images of the identified objects. The third stage combines distance information with the classification results of neural networks for efficient and intelligent navigation.

Kumbla, Kishan -K.↗
DOE OSTI2019

Pairwise Association of Seismic Arrivals with Convolutional Neural Networks

Correctly determining the association of seismic phases across a network is crucial for developing accurate earthquake catalogs. Nearly all established methods use travel time information as the main criterion for determining associations, and in problems in which earthquake rates are high and many false arrivals are present, many standard techniques may fail to resolve the problem accurately. As an alternative approach, in this work we apply convolutional neural networks (CNNs) to the problem of associations; we train CNNs to read earthquake waveform arrival pairs between two stations and predict the binary classification of whether the two waveforms are from a common source or different sources. Applying the method to a large training dataset of previously cataloged earthquakes in Chile, we obtain >80% true positive prediction rates for high-frequency data (>2 Hz) and stations separated in excess of 100 km. As a secondary benefit, the output of the neural network can also be used to infer predicted phase types of arrivals. Here, the method is ideally applied in conjunction with standard travel-time-based association routines and can be adapted for arbitrary network geometries and applications, so long as sufficient training data are available.

58 GEOSCIENCES↗
DOE OSTI2023

Quantum Neural Networks: Issues, Training, and Applications

Our work in the field aims at explaining the limitations and expressive power of Quantum Machine Learning models, as well as finding feasible training algorithms that could be implemented in near-term Quantum Computers. The promise of Quantum Machine Learning is that by incorporating quantum effects, such as entanglement, into machine learning models researchers can improve model performance and understand more complex datasets. This pledge is particularly pronounced in the design of Quantum neural networks (QNNs), a promising framework for creating quantum algorithms, that promise to outperform classical models by combining the speedups of quantum computation with the widespread successes of deep learning. We show that applying this approach alone to quantum deep learning is problematic given that an excess of entanglement between the hidden and visible layers can destroy the predictive power of our QNN models. We address the barren plateau problem by suggesting the use of a generative, unbounded, nonlinear loss function with simple gradients. The loss function quantifies how much the quantum states generated by the QNNs differ from the data and the goal during training is to minimize it. Finally, we showcase how to use generative training to construct a "classical-quantum" neural network to accurately interpolate between the ground states of a Molecular Hamiltonian, a central question in Quantum Chemistry.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2016

Muon Neutrino Disappearance in NOvA with a Deep Convolutional Neural Network Classifier

The NuMI Off-axis Neutrino Appearance Experiment (NOvA) is designed to study neutrino oscillation in the NuMI (Neutrinos at the Main Injector) beam. NOvA observes neutrino oscillation using two detectors separated by a baseline of 810 km; a 14 kt Far Detector in Ash River, MN and a functionally identical 0.3 kt Near Detector at Fermilab. The experiment aims to provide new measurements of Δm 2 and θ23 and has potential to determine the neutrino mass hierarchy as well as observe CP violation in the neutrino sector. Essential to these analyses is the classification of neutrino interaction events in NOvA detectors. Raw detector output from NOvA is interpretable as a pair of images which provide orthogonal views of particle interactions. A recent advance in the field of computer vision is the advent of convolutional neural networks, which have delivered top results in the latest image recognition contests. This work presents an approach novel to particle physics analysis in which a convolutional neural network is used for classification of particle interactions. The approach has been demonstrated to improve the signal efficiency and purity of the event selection, and thus physics sensitivity. Early NOvA data has been analyzed (2.74×10 20 POT, 14 kt equivalent) to provide new best- fit measurements of sin 2 (θ23) = 0.43 (with a statistically-degenerate compliment near 0.60) and |Δm2 | = 2.48 × 10 -3 eV 2 .

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Neural-network quantum states for ultra-cold Fermi gases

Abstract Ultra-cold Fermi gases exhibit a rich array of quantum mechanical properties, including the transition from a fermionic superfluid Bardeen-Cooper-Schrieffer (BCS) state to a bosonic superfluid Bose-Einstein condensate (BEC). While these properties can be precisely probed experimentally, accurately describing them poses significant theoretical challenges due to strong pairing correlations and the non-perturbative nature of particle interactions. In this work, we introduce a Pfaffian-Jastrow neural-network quantum state featuring a message-passing architecture to efficiently capture pairing and backflow correlations. We benchmark our approach on existing Slater-Jastrow frameworks and state-of-the-art diffusion Monte Carlo methods, demonstrating a performance advantage and the scalability of our scheme. We show that transfer learning stabilizes the training process in the presence of strong, short-ranged interactions, and allows for an effective exploration of the BCS-BEC crossover region. Our findings highlight the potential of neural-network quantum states as a promising strategy for investigating ultra-cold Fermi gases.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
NASA NTRS2004

Neural Network for Image-to-Image Control of Optical Tweezers

A method is discussed for using neural networks to control optical tweezers. Neural-net outputs are combined with scaling and tiling to generate 480 by 480-pixel control patterns for a spatial light modulator (SLM). The SLM can be combined in various ways with a microscope to create movable tweezers traps with controllable profiles. The neural nets are intended to respond to scattered light from carbon and silicon carbide nanotube sensors. The nanotube sensors are to be held by the traps for manipulation and calibration. Scaling and tiling allow the 100 by 100-pixel maximum resolution of the neural-net software to be applied in stages to exploit the full 480 by 480-pixel resolution of the SLM. One of these stages is intended to create sensitive null detectors for detecting variations in the scattered light from the nanotube sensors.

Decker, Arthur J.↗
DOE OSTI2021

Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations

Advection-dispersion equations (ADEs) are commonly used to describe transport phenomena in porous media. Even though mature discretization-based numerical methods for ADEs exist, some challenges still remain, especially when it comes to solving advection-dominated forward ADEs and diffusion-dominated backward ADEs. The latter problem usually arises in the source identification context and leads to numerically unstable grid-based solutions that require a form of regularization or should be treated as an inverse problem that is computationally more expensive because it requires solving the forward problem multiple times. In this study, we propose a discretization-free approach based on the physics-informed neural network (PINN) method for solving coupled ADE and Darcy flow equations with space-dependent hydraulic conductivity. In this approach, the hydraulic conductivity, hydraulic head, and concentration fields are approximated with deep neural networks (DNNs). We assume that the conductivity field is given by its values on a grid, and we use these values to train the conductivity DNN. The head and concentration DNNs are trained by minimizing the residuals of the flow equation and ADE and using the initial and boundary conditions as additional constraints. The PINN method is applied to one- and two-dimensional forward ADE problems, where its performance for various P\'{e}clet numbers ($Pe$) is compared with the analytical and numerical solutions. We find that the PINN method is accurate with errors of less than 1\% and outperforms some conventional discretization-based methods for $Pe$ larger that 100. Next, we demonstrate that the PINN method remains accurate for the backward ADEs, with the relative errors in most cases staying under 5\% compared to the reference concentration field. Finally, we show that when available, the concentration measurements can be easily incorporated in the PINN method and significantly improve (by more than 50\% in the considered cases) the accuracy of the PINN solution of the backward ADE.

He, Qizhi↗
DOE OSTI2022

Electron energy loss spectroscopy database synthesis and automation of core-loss edge recognition by deep-learning neural networks

Abstract The ionization edges encoded in the electron energy loss spectroscopy (EELS) spectra enable advanced material analysis including composition analyses and elemental quantifications. The development of the parallel EELS instrument and fast, sensitive detectors have greatly improved the acquisition speed of EELS spectra. However, the traditional way of core-loss edge recognition is experience based and human labor dependent, which limits the processing speed. So far, the low signal–noise ratio and the low jump ratio of the core-loss edges on the raw EELS spectra have been challenging for the automation of edge recognition. In this work, a convolutional-bidirectional long short-term memory neural network (CNN-BiLSTM) is proposed to automate the detection and elemental identification of core-loss edges from raw spectra. An EELS spectral database is synthesized by using our forward model to assist in the training and validation of the neural network. To make the synthesized spectra resemble the real spectra, we collected a large library of experimentally acquired EELS core edges. In synthesize the training library, the edges are modeled by fitting the multi-Gaussian model to the real edges from experiments, and the noise and instrumental imperfectness are simulated and added. The well-trained CNN-BiLSTM network is tested against both the simulated spectra and real spectra collected from experiments. The high accuracy of the network, 94.9%, proves that, without complicated preprocessing of the raw spectra, the proposed CNN-BiLSTM network achieves the automation of core-loss edge recognition for EELS spectra with high accuracy.

36 MATERIALS SCIENCE↗
NASA NTRS2008

Neural Networks as a Tool for Constructing Continuous NDVI Time Series from AVHRR and MODIS

The long term Advanced Very High Resolution Radiometer-Normalized Difference Vegetation Index (AVHRR-NDVI) record provides a critical historical perspective on vegetation dynamics necessary for global change research. Despite the proliferation of new sources of global, moderate resolution vegetation datasets, the remote sensing community is still struggling to create datasets derived from multiple sensors that allow the simultaneous use of spectral vegetation for time series analysis. To overcome the non-stationary aspect of NDVI, we use an artificial neural network (ANN) to map the NDVI indices from AVHRR to those from MODIS using atmospheric, surface type and sensor-specific inputs to account for the differences between the sensors. The NDVI dynamics and range of MODIS NDVI data at one degree is matched and extended through the AVHRR record. Four years of overlap between the two sensors is used to train a neural network to remove atmospheric and sensor specific effects on the AVHRR NDVI. In this paper, we present the resulting continuous dataset, its relationship to MODIS data, and a validation of the product.

Brown, Molly E.↗
DOE OSTI2023

GRAPH CONVOLUTIONAL NEURAL NETWORK (GCNN)FOR POLYMER PROPERTY PREDICTION

SF-22-121 Graph convolutional neural networks (GCNN) are powerful machine learning models that apply a message-passing algorithm on adjacent nodes in a graph. Due to the natural representation of molecules via discrete graphs (where nodes encode atoms and edges encode bonds), GCNNs are an intuitive machine learning model chemical space informatics, including the prediction of polymer properties. Here, molecules are represented in feature and adjacency matrices where they are directly used as inputs to a GCNN.

FEINSTEIN, JEREMY↗
DOE OSTI2023

Quantum-inspired tempering for ground state approximation using artificial neural networks

A large body of work has demonstrated that parameterized artificial neural networks (ANNs) can efficiently describe ground states of numerous interesting quantum many-body Hamiltonians. However, the standard variational algorithms used to update or train the ANN parameters can get trapped in local minima, especially for frustrated systems and even if the representation is sufficiently expressive. We propose a parallel tempering method that facilitates escape from such local minima. This methods involves training multiple ANNs independently, with each simulation governed by a Hamiltonian with a different "driver" strength, in analogy to quantum parallel tempering, and it incorporates an update step into the training that allows for the exchange of neighboring ANN configurations. We study instances from two classes of Hamiltonians to demonstrate the utility of our approach using Restricted Boltzmann Machines as our parameterized ANN. The first instance is based on a permutation-invariant Hamiltonian whose landscape stymies the standard training algorithm by drawing it increasingly to a false local minimum. The second instance is four hydrogen atoms arranged in a rectangle, which is an instance of the second quantized electronic structure Hamiltonian discretized using Gaussian basis functions. We study this problem in a minimal basis set, which exhibits false minima that can trap the standard variational algorithm despite the problem’s small size. We show that augmenting the training with quantum parallel tempering becomes useful to finding good approximations to the ground states of these problem instances.

Albash, Tameem↗