Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Neural Networks (Computer)”

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 865 records · Page 48

Perspectives for computational modeling of cell replacement for neurological disorders

Mathematical modeling of anatomically-constrained neural networks has provided significant insights regarding the response of networks to neurological disorders or injury. A logical extension of these models is to incorporate treatment regimens to investigate network responses to intervention. The addition of nascent neurons from stem cell precursors into damaged or diseased tissue has been used as a successful therapeutic tool in recent decades. Interestingly, models have been developed to examine the incorporation of new neurons into intact adult structures, particularly the dentate granule neurons of the hippocampus. These studies suggest that the unique properties of maturing neurons, can impact circuit behavior in unanticipated ways. In this perspective, we review the current status of models used to examine damaged CNS structures with particular focus on cortical damage due to stroke. Secondly, we suggest that computational modeling of cell replacement therapies can be made feasible by implementing approaches taken by current models of adult neurogenesis. The development of these models is critical for generating hypotheses regarding transplant therapies and improving outcomes by tailoring transplants to desired effects.

60 APPLIED LIFE SCIENCES↗

Enhanced Data Efficiency Using Deep Neural Networks and Gaussian Processes for Aerodynamic Design Optimization

Adjoint-based optimization methods are attractive for aerodynamic shape design primarily due to their computational costs being independent of the dimensionality of the input space and their ability to generate high-fidelity gradients that can then be used in a gradient-based optimizer. This makes them very well suited for high-fidelity simulation based aerodynamic shape optimization of highly parametrized geometries such as aircraft wings. However, the development of adjoint-based solvers involve careful mathematical treatment and their implementation require detailed software development. Furthermore, they can become prohibitively expensive when multiple optimization problems are being solved, each requiring multiple restarts to circumvent local optima. In this work, we propose a machine learning enabled, surrogate-based framework that replaces the expensive adjoint solver, without compromising on predicting predictive accuracy. Specifically, we first train a deep neural network (DNN) from training data generated from evaluating the high-fidelity simulation model on a model-agnostic design of experiments on the geometry shape parameters. The optimum shape may then be computed by using a gradient-based optimizer coupled with the trained DNN. Subsequently, we also perform a gradient-free Bayesian optimization, where the trained DNN is used as the prior mean. We observe that the latter framework (DNN-BO) improves upon the DNN-only based optimization strategy for the same computational cost. Overall, this framework predicts the true optimum with very high accuracy, while requiring far fewer high-fidelity function calls compared to the adjoint-based method. Furthermore, we show that multiple optimization problems can be solved with the same machine learning model with high accuracy, to amortize the offline costs associated with constructing our models. Our methodology finds applications in the early stages of aerospace design. (C) 2021 Published by Elsevier Masson SAS.

Renganathan, S. Ashwin↗

Physics-informed heterogeneous graph neural networks for DC blocker placement

The threat of geomagnetic disturbances (GMDs) to the reliable operation of the bulk energy system has spurred the development of effective strategies for mitigating their impacts. One such approach involves placing transformer neutral blocking devices, which interrupt the path of geomagnetically induced currents (GICs) to limit their impact. The high cost of these devices and the sparsity of transformers that experience high GICs during GMD events, however, calls for a sparse placement strategy that involves high computational cost. To address this challenge, we developed a physics-informed heterogeneous graph neural network (PIHGNN) for solving the graph-based dc-blocker placement problem. Our approach combines a heterogeneous graph neural network (HGNN) with a physics-informed neural network (PINN) to capture the diverse types of nodes and edges in ac/dc networks and incorporates the physical laws of the power grid. We train the PIHGNN model using a surrogate power flow model and validate it using case studies. Results demonstrate that PIHGNN can effectively and efficiently support the deployment of GIC dc-current blockers, ensuring the continued supply of electricity to meet societal demands. Furthermore, our approach has the potential to contribute to the development of more reliable and resilient power grids capable of withstanding the growing threat that GMDs pose.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Fast and accurate learned multiresolution dynamical downscaling for precipitation

Abstract. This study develops a neural-network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combination of low- and high-resolution simulations (that differ not only in spatial resolution but also in geospatial patterns) to train a neural network to map from the former to the latter. Specifically, we define two types of CNNs, one that stacks variables directly and one that encodes each variable before stacking, and we train each CNN type both with a conventional loss function, such as mean square error (MSE), and with a conditional generative adversarial network (CGAN), for a total of four CNN variants. We compare the four new CNN-derived high-resolution precipitation results with precipitation generated from original high-resolution simulations, a bilinear interpolater and the state-of-the-art CNN-based super-resolution (SR) technique. Results show that the SR technique produces results similar to those of the bilinear interpolator with smoother spatial and temporal distributions and smaller data variabilities and extremes than the original high-resolution simulations. While the new CNNs trained by MSE generate better results over some regions than the interpolator and SR technique do, their predictions are still biased from the original high-resolution simulations. The CNNs trained by CGAN generate more realistic and physically reasonable results, better capturing not only data variability in time and space but also extremes such as intense and long-lasting storms. The new proposed CNN-based downscaling approach can downscale precipitation from 50 to 12 km in 14 min for 30 years once the network is trained (training takes 4 h using 1 GPU), while the conventional dynamical downscaling would take 1 month using 600 CPU cores to generate simulations at the resolution of 12 km over the contiguous United States.

54 ENVIRONMENTAL SCIENCES↗

Distributed Stochastic Optimization of a Neural Representation Network for Time-Space Tomography Reconstruction

4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. Conventional back-projection based reconstruction methods assume that the object remains static for the duration of several tens or hundreds of X-ray projection measurement images (reconstruction of consecutive limited-angle CT scans). However, this is an unrealistic assumption for many in-situ experiments that causes spurious artifacts and inaccurate morphological reconstructions of the object. To solve this problem, we propose to perform a 4D time-space reconstruction using a distributed implicit neural representation (DINR) network that is trained using a novel distributed stochastic training algorithm. Our DINR network learns to reconstruct the object at its output by iterative optimization of its network parameters such that the measured projection images best match the output of the CT forward measurement model. Here, we use a forward measurement model that is a function of the DINR outputs at a sparsely sampled set of continuous valued 4D object coordinates. Unlike previous neural representation architectures that forward and back propagate through dense voxel grids that sample the object's entire time-space coordinates, we only propagate through the DINR at a small subset of object coordinates in each iteration resulting in an order-of-magnitude reduction in memory and compute for training. DINR leverages distributed computation across several compute nodes and GPUs to produce high-fidelity 4D time-space reconstructions. We use both simulated parallel-beam and experimental cone-beam X-ray CT datasets to demonstrate the superior performance of our approach.

36 MATERIALS SCIENCE↗

Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

We study the applicability of spiking neural networks and neuromorphic hardware for solving general optimization problems without the use of adaptive training or learning algorithms. We leverage the dynamics of Hopfield networks and spin-glass systems to construct a fully connected spiking neural system to generate synchronous spike responses indicative of the underlying community structure in an undirected, unweighted graph. Mapping this fully connected system to current generation neuromorphic hardware is done by embedding sparse tree graphs to generate only the leading-order spiking dynamics. Here, we demonstrate that for a chosen set of benchmark graphs, the spike responses generated on a current generation neuromorphic processor can improve the stability of graph partitions and non-overlapping communities can be identified even with the loss of higher-order spiking behavior if the graphs are sufficiently dense. For sparse graphs, the loss of higher-order spiking behavior improves the stability of certain graph partitions but does not retrieve the known community memberships.

97 MATHEMATICS AND COMPUTING↗

Make the Fastest Faster: Importance Mask Synthesis for Interactive Volume Visualization using Reconstruction Neural Networks

Visualizing a large-scale volumetric dataset with high resolution is challenging due to the substantial computational time and space complexity. Recent deep learning-based image inpainting methods significantly improve rendering latency by reconstructing a high-resolution image for visualization in constant time on GPU from a partially rendered image where only a portion of pixels go through the expensive rendering pipeline. However, existing solutions need to render every pixel of either a predefined regular sampling pattern or an irregular sample pattern predicted from a low-resolution image rendering. Both methods require a significant amount of expensive pixel-level rendering. In this work, we provide Importance Mask Learning (IML) and Synthesis (IMS) networks, which are the first attempts to directly synthesize important regions of the regular sampling pattern from the user’s view parameters, to further minimize the number of pixels to render by jointly considering the dataset, user behavior, and the downstream reconstruction neural network. Our solution is a unified framework to handle various types of inpainting methods through the proposed differentiable compaction/decompaction layers. Experiments show our method can further improve the overall rendering latency of state-of-the-art volume visualization methods using reconstruction neural network for free when rendering scientific volumetric datasets. Our method can also directly optimize the off-the-shelf pre-trained reconstruction neural networks without elongated retraining.

Large-scale data↗

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?

In the last few years, we have seen the rise of deep learning applications in a broad range of computational chemistry research problems. Using human-engineered chemical features, such as molecular descriptors and fingerprints, deep learning models have shown similar, if not better performance that most traditional machine learning algorithms. Recently, we reported on the development of Chemception, a deep convolutional neural network (CNN) architecture for general-purpose small molecule property prediction. On average, Chemception matched the performance of expert-developed QSAR/QSPR models trained on chemical features (molecular fingerprints), despite that it was trained on just 2D images of molecular drawings with minimal chemical information. Here, we investigate the effects of systematically removing and adding basic chemical information to the image channels of the 2D images used to train Chemception. By augmenting our images with only 3 additional basic chemical information, we demonstrate the improvement of Chemception performance – that it is now more accurate than contemporary deep learning models trained on ECFP fingerprints for the prediction of toxicity, activity and solvation free energy, as well as physics-based free energy simulation methods for computing solvation properties. By altering the chemical information content in the image channels, and examining the resulting performance of Chemception, we also identify to two different “learning patterns” in toxicity/activity as compared to solvation free energy, and it parallels the fundamental differences in contemporary chemistry research for predicting toxicity/activity and solvation free energy.

Artificial Intelligence, Cheminformatics, Computat↗

Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials

Quantum machine-learning algorithms have emerged to be a promising alternative to their classical counterparts as they leverage the power of quantum computers. Such algorithms have been developed to solve problems like electronic structure calculations of molecular systems and spin models in magnetic systems. However, the discussion in all these recipes focuses specifically on targeting the ground state. Herein we demonstrate a quantum algorithm that can filter any energy eigenstate of the system based on either symmetry properties or a predefined choice of the user. The workhorse of our technique is a shallow neural network encoding the desired state of the system with the amplitude computed by sampling the Gibbs–Boltzmann distribution using a quantum circuit and the phase information obtained classically from the nonlinear activation of a separate set of neurons. We show that the resource requirements of our algorithm are strictly quadratic. To demonstrate its efficacy, we use state filtration in monolayer transition metal dichalcogenides which are hitherto unexplored in any flavor of quantum simulations. We implement our algorithm not only on quantum simulators but also on actual IBM-Q quantum devices and show good agreement with the results procured from conventional electronic structure calculations. We thus expect our protocol to provide a new alternative in exploring the band structures of exquisite materials to usual electronic structure methods or machine-learning techniques that are implementable solely on a classical computer.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Three Artificial Spintronic Leaky Integrate-and-Fire Neurons

We report that due to their non-volatility and intrinsic current integration capabilities, spintronic devices that rely on domain wall (DW) motion through a free ferromagnetic track have garnered significant interest in the field of neuromorphic computing. Although a number of such devices have already been proposed, they require the use of external circuitry to implement several important neuronal behaviors. As such, they are likely to result in either a decrease in energy efficiency, an increase in fabrication complexity, or even both. To resolve this issue, we have proposed three individual neurons that are capable of performing these functionalities without the use of an external circuitry. To implement leaking, the first neuron uses a dipolar coupling field, the second uses an anisotropy gradient, and the third uses shape variations of the DW track.

neural network crossbar↗

Mapping of Benthic Habitats at Marine Renewable Energy Sites Using Multibeam Echosounder and Sediment Profile Imaging Technologies

Objectives/Scope: The goal of this work was to develop a consistent and semi-automated seafloor survey method for generating high-resolution, benthic habitat maps for environmental assessments and monitoring of marine renewable energy sites. Sediment profile and plan view imaging (SPI/PV) technology was combined with multibeam bathymetry and acoustic backscatter methods to demonstrate a rapid, cost-effective benthic mapping protocol. A key technical innovation of this project was the development of an image processing platform that automatically measures key features from the images. Methods: Multibeam echosounder (MBES) acoustic and SPI/PV surveys were conducted at three coastal areas off the U.S. west coast, including the PacWave South energy test site off of Newport, Oregon. Point data on physical and biological sediment conditions obtained from the SPI/PV imagery were used to efficiently ground-truth the high-resolution MBES bathymetry and backscatter mosaics. The SPI camera is an optical corer that obtains an undisturbed 21 by 15 cm, high-resolution, cross-sectional image of the sediment–water interface and upper sediment column. The plan view camera attached to the SPI camera frame captures a downward looking view of the seabed immediately before the SPI image is obtained. As part of this project, we developed a computer vision image processing platform (iSPI) that uses deep convolutional neural networks and other approaches to automatically identify and measure key features in the images, such as grain size and surface relief. Results: Detailed benthic habitat maps were generated using this mapping approach for three different marine settings. The sites mapped included a silt-dominated embayment; a sloping, nearshore, transitional very fine to coarse sand bottom; and a medium, sand-dominated continental shelf marine energy test site. In each case, acoustic and imaging surveys were completed in less than week, and detailed benthic habitat maps were generated within 60 days. The results were placed within the Coastal and Marine Ecological Classification Standard (CMECS) habitat mapping framework, and various combinations of the bathymetry, backscatter, and SPI and PV data were used to generate CMECS component maps. Novel Information: This project developed and demonstrated a repeatable and cost-effective approach for efficiently mapping benthic habitat conditions over broad areas of the seafloor by combining state-of-the-art acoustic and imaging techniques. The primary survey tools used in this project have been used previously in both the offshore renewable (wind) and oil and gas sectors to map and monitor benthic environments. This project’s innovations include 1) the focused use of high-resolution SPI/PV imagery to ground-truth acoustic mosaics, and 2) the development of a computer automated image analysis processing tool that both streamlines and standardizes the generation of data from the imagery and makes the data extraction process more cost-effective and repeatable.

13 HYDRO ENERGY↗

Regularization via f -Divergence: An Application to Multi-Oxide Spectroscopic Analysis

In this paper, we explore the application of convolutional neural networks (CNNs) for predicting the chemical composition of complex geologic samples in a simulated Martian atmospheric environment. Specifically, we aim to characterize oxide weight percentages (wt.%) of rock samples analyzed by remote Laser-Induced Breakdown Spectroscopy (LIBS), framing the problem as a multi-target regression task . Neural networks trained on LIBS spectra are prone to overfitting due to high spectral complexity, limited labeled data, and measurement noise. While regularization is critical for improving generalization, common methods (e.g., ℓ 2 regularization) impose constraints not directly tied to data distribution properties. We propose a novel regularization method based on a specific ƒ-divergence induced by a graph-based estimator, designed to constrain the distributional discrepancy between predictions and targets. This regularizer serves a dual purpose: (a) mitigating overfitting by enforcing a constraint on the distributional difference between predictions and noisy targets, and (b) acting as an auxiliary loss that penalizes large divergences. To enable backpropagation, we develop a differentiable approximation of this particular ƒ-divergence, making the method feasible for neural networks. Experiments on ChemCam and SuperCam LIBS calibration spectra show that mathematical equation-divergence regularization outperforms or matches standard regularization methods (ℓ 1 , ℓ 2 , dropout) and the classical baseline, partial least squares (PLS). Combining ƒ-divergence regularization with standard regularization yields further performance gains, indicating that distributional regularization is useful in this context giving a promising direction for robust model training in planetary science applications. Source code is publicly available at Klein and Li (2025), https://doi.org/10.11578/dc.20250530.7.

58 GEOSCIENCES↗

Reinforcement learning based automated history matching for improved hydrocarbon production forecast

History matching aims to find a numerical reservoir model that can be used to predict the reservoir performance. An engineer and model calibration (data inversion) method are required to adjust various parameters/properties of the numerical model in order to match the reservoir production history. In this study, we develop deep neural networks within the reinforcement learning framework to achieve automated history matching that will reduce engineers’ efforts, human bias, automatically and intelligently explore the parameter space, and remove the need of large set of labeled training data. To that end, a fast-marching-based reservoir simulator is encapsulated as an environment for the proposed reinforcement learning. The deep neural-network-based learning agent interacts with the reservoir simulator within reinforcement learning framework to achieve the automated history matching. Reinforcement learning techniques, such as discrete Deep Q Network and continuous Deep Deterministic Policy Gradients, are used toth, used to train the learning agents. The continuous actions enable the Deep Deterministic Policy Gradients to explore more states at each iteration in a a learning episode; consequently, a better history matching is achieved using this algorithm as compared to Deep Q Network. For simplified dual-target composite reservoir models, the best history-matching performances of the discrete and continuous learning methods in terms of normalized root mean square errors are 0.0447 and 0.0038, respectively. Furthermore, our study shows that continuous action space achieved by the deep deterministic policy gradient drastically outperforms deep Q network.

42 ENGINEERING↗

Development of Ensemble Neural Network Convection Parametrizations for Climate Models Using ARM Data

The novel neural network (NN) approach has been formulated and used for development of a NN ensemble stochastic convection parametrization for climate models. This fast parametrization is built based on data from Cloud Resolving Model (CRM) simulations initialized with and forced by TOGA-COARE data. The SAM (System for Atmospheric Modeling), developed by D. Randall, M. Khairoutdinov, and their collaborators, has been used for CRM simulations. The observational data are also used for validation of model simulations. The SAM-simulated data have been averaged and projected onto the GCM space of atmospheric states to implicitly define a stochastic convection parametrization. This parametrization is emulated using an ensemble of NNs. An ensemble of NNs with different NN parameters has been trained and tested. The inherent uncertainty of the stochastic convection parametrization derived in such a way is estimated. Due to these inherent uncertainties, NN ensemble is used to constitute a stochastic NN convection parametrization. The developed NN convection parametrization have been validated in a diagnostic CAM (CAM-NN) run vs. the control CAM run. Actually, CAM inputs have been used, at every time step of the control/original CAM integration, for parallel calculations of the NN convection parametrization (CAM-NN) to produce its outputs as a diagnostic byproduct. Total precipitation (P) and cloudiness (CLD) time series, diurnal cycles, and P and CLD distributions for the large Tropical Pacific Ocean for the parallel CAM-NN and CAM runs show similarity and consistency with the NCEP reanalysis. The P and CLD distributions for the tropical area for the parallel runs have been analyzed first for the TOGA-COARE boreal winter season (November 1992 through February 1993) and then for the winter seasons of the follow-up parallel decadal simulations. The obtained results are encouraging and practically meaningful. They show the validity of the NN approach. This constitutes an important practical conclusion of the study: the obtained results on NN ensembles as a stochastic physics parametrization show a realistic possibility of development of NN convection parametrization for climate (and NWP) models based on learning cloud physics from CRM/SAM simulated data.

97 MATHEMATICS AND COMPUTING↗

ASCENDS: Advanced data SCiENce toolkit for Non-Data Scientists

Recently, advances in machine learning and artificial intelligence have been playing more and more critical roles in a wide range of areas. For the last several years, industries have shown that how learning from data, identifying patterns and making decisions with minimal human intervention can be extremely useful to their business (e.g., image classification, recommending a product to a customer, finding friends in a social network, predicting customers actions, etc.). These success stories have been motivating scientists who study physics, chemistry, materials, medicine, and many other subjects, to explore a new pathway of utilizing machine learning techniques like regression and classification for their scientific activities. However, most existing machine learning tools, systems, and methodologies have been developed for programming experts but not for scientists (or any users) who have no or little knowledge of programming. ASCENDS is a toolkit that is developed to assist scientists (or any persons) who want to use their data for machine learning tasks, more specifically, correlation analysis, regression, and classification. ASCENDS does not require programming skills. Instead, it provides a set of simple but powerful CLI (Command Line Interface) and GUI (Graphic User Interface) tools for non-data scientists to be able to intuitively perform advanced data analysis and machine learning techniques. ASCENDS has been implemented by wrapping around opensource software including Keras, TensorFlow, and scikit-learn.

97 MATHEMATICS AND COMPUTING↗

Energy metric prediction for double insertion mutants via the RoseNet deep learning framework

Studying the structural and functional implications of protein mutations is an important task in computational biology and bioinformatics. We leverage our previously proposed RoseNet neural network architecture to predict energy metrics of proteins with double amino acid insertions or deletions (InDels). We train models on previously generated benchmark datasets containing the exhaustive double InDel mutations for three proteins, as well as an additional three proteins for which ∼145k random mutants, each with two InDels, have been generated. We expand on our previous work by evaluating three additional proteins and analyzing domain features that impact the prediction capabilities of RoseNet. These features include InDels into secondary structures and the solvent accessible surface area (SASA) scores of the residues. We uncover further evidence to support that RoseNet has a higher proficiency of generalizing to unseen residue combinations than unseen insertion positions. We also observe that RoseNet produces higher-quality predictions when inserting into a β-sheet over an α-helix. Additionally, when the insertions fall in an area of high SASA, RoseNet often displays better performance than inserting into areas of low SASA.

59 BASIC BIOLOGICAL SCIENCES↗

Two-Scale Neural Networks for Partial Differential Equations with Small Parameters

We propose a two-scale neural network method for solving partial differential equations (PDEs) with small parameters using physics-informed neural networks (PINNs). We directly incorporate the small parameters into the architecture of neural networks. The proposed method enables solving PDEs with small parameters in a simple fashion, without adding Fourier features or other computationally taxing searches of truncation parameters. Various numerical examples demonstrate reasonable accuracy in capturing features of large derivatives in the solutions caused by small parameters.

97 MATHEMATICS AND COMPUTING↗

BayesCLUMPY: BAYESIAN INFERENCE WITH CLUMPY DUSTY TORUS MODELS

Our aim is to present a fast and general Bayesian inference framework based on the synergy between machine learning techniques and standard sampling methods and apply it to infer the physical properties of clumpy dusty torus using infrared photometric high spatial resolution observations of active galactic nuclei. We make use of the Metropolis-Hastings Markov Chain Monte Carlo algorithm for sampling the posterior distribution function. Such distribution results from combining all a priori knowledge about the parameters of the model and the information introduced by the observations. The main difficulty resides in the fact that the model used to explain the observations is computationally demanding and the sampling is very time consuming. For this reason, we apply a set of artificial neural networks that are used to approximate and interpolate a database of models. As a consequence, models not present in the original database can be computed ensuring continuity. We focus on the application of this solution scheme to the recently developed public database of clumpy dusty torus models. The machine learning scheme used in this paper allows us to generate any model from the database using only a factor of 10{sup -4} of the original size of the database and a factor of 10{sup -3} in computing time. The posterior distribution obtained for each model parameter allows us to investigate how the observations constrain the parameters and which ones remain partially or completely undetermined, providing statistically relevant confidence intervals. As an example, the application to the nuclear region of Centaurus A shows that the optical depth of the clouds, the total number of clouds, and the radial extent of the cloud distribution zone are well constrained using only six filters. The code is freely available from the authors.

79 ASTRONOMY AND ASTROPHYSICS↗