Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Convolutional Neural Networks”

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 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers

Deep neural networks (DNNs) have heavily relied on traditional computational units, such as CPUs and GPUs. However, this conventional approach brings significant computational burden, latency issues, and high power consumption, limiting their effectiveness. This has sparked the need for lightweight networks such as ExtremeC3Net. Meanwhile, there have been notable advancements in optical computational units, particularly with metamaterials, offering the exciting prospect of energy-efficient neural networks operating at the speed of light. Yet, the digital design of metamaterial neural networks (MNNs) faces precision, noise, and bandwidth challenges, limiting their application to intuitive tasks and low-resolution images. In this study, we proposed a large kernel lightweight segmentation model, ExtremeMETA. Based on ExtremeC3Net, our proposed model, ExtremeMETA maximized the ability of the first convolution layer by exploring a larger convolution kernel and multiple processing paths. With the large kernel convolution model, we extended the optic neural network application boundary to the segmentation task. To further lighten the computation burden of the digital processing part, a set of model compression methods was applied to improve model efficiency in the inference stage. The experimental results on three publicly available datasets demonstrated that the optimized efficient design improved segmentation performance from 92.45 to 95.97 on mIoU while reducing computational FLOPs from 461.07 MMacs to 166.03 MMacs. The large kernel lightweight model ExtremeMETA showcased the hybrid design’s ability on complex tasks.

large convolution kernel↗
DOE OSTI2020

Genetic Algorithm for Hyperparameter Optimization in Gaussian Process Modeling

A genetic algorithm is developed and applied to optimize hyperparameters of convolutional recursively determined dual neural network-Gaussian process (NNGP) kernels. As a specific application of the combined GPNN-GA algorithm, it is applied to image classification in publicly available data of Hyper Suprime-Cam Subaru Strategic Program. Matthews correlation coefficient is calculated based on results of binary star-galaxy classification and used as a fitting function of the GA module of the algorithm. The simulation results confirm significant improvement of the classification accuracy with optimized hyperparameters.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Improving Subsurface Stress Characterization for Carbon Dioxide Storage Projects by Incorporating Machine Learning Techniques

The overall objective of this project is to develop a framework for reliable characterization and prediction of the state of stress in the overburden and underburden (including the basement) in CO 2 storage reservoirs using machine learning and integrated geomechanics and geophysical methods. Specifically, we propose to develop workflow encompassing of technologies and/or methods to predict stress and pressure changes due to CO 2 injection in an active tertiary recovery site and their impacts on subtle fault activation, fractures and occurrence of microseismic events and compare responses to field observations. In this project, we anticipate using dataset from the Farnsworth field Unit (FWU) which is operated by Purdure Petroleum. A novel elastic-waveform VSP inversion technique will be used to estimate high-resolution spatial and temporal changes of elastic moduli in CO 2 storage reservoirs, which will be combined with velocity-stress relationship derived from laboratory tests to obtain subsurface pressure and stress. Clustered microseismic data will be jointly inverted for improved focal mechanisms. Least-squares reverse-time migration of microseismic waveform data will be performed to directly image fracture/fault zones. Additionally, a deep neural network machine learning technique with convolutional and recurrent layers will be used for learning the spectro-temporal structures in microseismic waveforms. The results of this geotechnical data analysis will be integrated to develop a high-resolution 3D mechanical earth model extending from the overburden sealing formations to the underburden including the basement. Mechanical properties will be derived through integration of mechanical logs, tests, available results from chemo-mechanical laboratory tests, and elastic inversion of seismic data using a combination of Bayesian and stochastic methods as well as machine learning technique. Failure features (faults/fractures) will be represented and/or modeled based on seismic and core data analysis. A transient hydrodynamic-geomechanical model will be developed through coupling with the calibrated FWU reservoir simulation model. The full physics coupled model will be used to train a reduced order proxy model using machine learning algorithm for estimating stress which will then be used with appropriate constitutive relationships and forward seismological models to simulate pressure changes and induced microseismicity. An advanced optimization framework will be developed to perform a history match to minimize error between field observations and simulated. The history matched proxy model will be verified against the full-physics equivalent. The field observations that will be used in the coupled model calibration process include pressure/stress inverted from VSP, moment magnitude from microseismic analysis, real time downhole pressure measurements, production and injection data. Parameter sensitivity and uncertainty analysis will be performed to characterize the impact of model parameter uncertainty on stress estimates. The proposed project will have significant impact on future field implementation of the proposed technology. Because the project field site is an ongoing CO 2 EOR development, the value of the new technology will be demonstrated in an operational context and evaluated as a viable risk mitigation strategy. Cost/benefit will be evaluated together with the various commercial incentives for CO 2 sequestration available to oil and gas operators. The extensive available dataset and ongoing data acquisition under the SWP Phase III work plan provides flexibility for investigation of multiple approaches and reduces technical risk.

58 GEOSCIENCES↗
DOE OSTI2024

Nonlinear encoding in diffractive information processing using linear optical materials

Nonlinear encoding of optical information can be achieved using various forms of data representation. Here, we analyze the performances of different nonlinear information encoding strategies that can be employed in diffractive optical processors based on linear materials and shed light on their utility and performance gaps compared to the state-of-the-art digital deep neural networks. For a comprehensive evaluation, we used different datasets to compare the statistical inference performance of simpler-to-implement nonlinear encoding strategies that involve, e.g., phase encoding, against data repetition-based nonlinear encoding strategies. We show that data repetition within a diffractive volume (e.g., through an optical cavity or cascaded introduction of the input data) causes the loss of the universal linear transformation capability of a diffractive optical processor. Therefore, data repetition-based diffractive blocks cannot provide optical analogs to fully connected or convolutional layers commonly employed in digital neural networks. However, they can still be effectively trained for specific inference tasks and achieve enhanced accuracy, benefiting from the nonlinear encoding of the input information. Our results also reveal that phase encoding of input information without data repetition provides a simpler nonlinear encoding strategy with comparable statistical inference accuracy to data repetition-based diffractive processors. Our analyses and conclusions would be of broad interest to explore the push-pull relationship between linear material-based diffractive optical systems and nonlinear encoding strategies in visual information processors.

42 ENGINEERING↗
DOE OSTI2022

Attention-based convolutional capsules for evapotranspiration estimation at scale

Evapotranspiration (ET) measures the amount of water lost from the Earth's surface to the atmosphere and is an integral metric for both agricultural and environmental sciences. Understanding and quantifying ET is critical for achieving effective management of freshwater and irrigation systems. However, current ET estimation models suffer from a trade-off between accuracy and spatial coverage. In this study, we introduce our model Quench, a neural network architecture that achieves highly-accurate ET estimates over large continuous spatial extents. Quench uses our novel Attention-Based Convolutional Capsule for its neural network layers to identify areas of focus and efficiently extract ET information from satellite imagery. Benchmarks that profile our model's performance show substantive improvements in accuracy, with up to 128% increase in accuracy compared to traditional convolutional-based and process-based models. Finally, Quench also demonstrates consistent model performance over high geospatial variability and a diverse array of regions, seasons, climates, and vegetations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media

This paper presents a new deep learning data-driven model for predicting structure dependent pore-fluid velocity fields in rock. The model is based on a Convolutional Auto-Encoder (CAE) artificial neural network capable of learning from image data generated by direct numerical simulations of fluid flow through pore-structures, such as by Lattice Boltzmann or molecular dynamics methods. The main novelty of the model in comparison to previous CAE-based data-driven approaches consists of three parts. The first is a methodology for decomposing the full-domain of the porous media into sub-regions, or “sub-domains”, in order to reduce the overall size of the CAE, batch process the sub-domains in parallel, and enable the CAE to learn local and generalizable nonlinear mappings of pore-fluid velocities. The second consists of embedding the finite difference solutions of the incompressible Navier-Stokes and continuity equations into convolutional layers prior to the CAE in order to provide the CAE with knowledge of fluid dynamics physics (PhyFlow). The third main novelty is that the training of the CAE is regularized with a hierarchical loss function that encourages the learning of fluid flow patterns (in a way similar to ranked modes in principal component analysis), ranking from most to least important. This is shown to increase the stability in learning, reduce over-fitting, and promote interpretability of the CAE neural network layers (HierCAE). The comprehensive new data-driven model, which we call the PhyFlow-HierCAE model, is shown to exhibit improved accuracy and generalizability of flow field predictions over conventional CAE models, attributable to the embedded physical knowledge and the hierarchical regularization, as well as realize orders of magnitude speed-ups in computation times as a surrogate for the direct numerical simulations. Examples of training and forward predictions on unseen pore-structures are provided and evaluated for data from Lattice Boltzmann and molecular dynamics simulations of pore-fluid flow. The model is shown to be a fast and accurate emulator (or “surrogate”) for predicting effective permeability of unseen pore-structures based on learning from relatively small direct numerical simulation datasets.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

FALCON: Framework for Anomaly Detection in Industrial Control Systems

Industrial Control Systems (ICS) are used to control physical processes in critical infrastructure. These systems are used in a wide variety of operations such as water treatment, power generation and distribution, and manufacturing. While the safety and security of these systems are of serious concern, recent reports have shown an increase in targeted attacks aimed at manipulating physical processes to cause catastrophic consequences. This trend emphasizes the need for algorithms and tools that provide resilient and smart attack detection mechanisms to protect ICS. In this paper, we propose an anomaly detection framework for ICS based on a deep neural network. The proposed methodology uses dilated convolution and long short-term memory (LSTM) layers to learn temporal as well as long term dependencies within sensor and actuator data in an ICS. The sensor/actuator data are passed through a unique feature engineering pipeline where wavelet transformation is applied to the sensor signals to extract features that are fed into the model. Additionally, this paper explores four variations of supervised deep learning models, as well as an unsupervised support vector machine (SVM) model for this problem. The proposed framework is validated on Secure Water Treatment testbed results. This framework detects more attacks in a shorter period of time than previously published methods.

97 - MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
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↗
DOE OSTI2021

Binary Complex Neural Network Acceleration on FPGA

Being able to learn from complex data with phase information is imperative for many signal processing applications. Today’s real-valued deep neural networks (DNNs) have shown efficiency in latent information analysis but fall short when applied to the complex domain. Deep complex networks (DCN) , in contrast, can learn from complex data, but have high computational costs; therefore, they cannot satisfy the instant decision making requirements of many deployable systems dealing with short observations or short signal bursts. Recent, Binarized Complex Neural Network (BCNN), which integrates DCNs with binarized neural networks (BNN), shows great potential in classifying complex data in real-time. In this paper, we propose a structural pruning based accelerator of BCNN, which is able to provide more than 5000 frames/s inference throughput on edge devices. The high performance comes from both the algorithm and hardware sides. On the algorithm side, we conduct structural pruning to the original BCNN models and obtain 20 × pruning rates with negligible accuracy loss; on the hardware side, we propose a novel 2D convolution operation accelerator for the binary complex neural network. Experimental results show that the proposed design works with over 90% utilization and is able to achieve the inference throughput of 5882 frames/s and 4938 frames/s for complex NIN-Net and ResNet-18 using CIFAR-10 dataset and Alveo U280 Board.

Peng, Hongwu↗
DOE OSTI2023

Protein model quality assessment using rotation–equivariant transformations on point clouds

Machine learning research concerning protein structure has seen a surge in popularity over the last years with promising advances for basic science and drug discovery. Working with macromolecular structure in a machine learning context requires an adequate numerical representation, and researchers have extensively studied representations such as graphs, discretized 3D grids, and distance maps. As part of CASP14, we explored a new and conceptually simple representation in a blind experiment: atoms as points in 3D, each with associated features. These features—initially just the basic element type of each atom—are updated through a series of neural network layers featuring rotation-equivariant convolutions. Starting from all atoms, we further aggregate information at the level of alpha carbons before making a prediction at the level of the entire protein structure. We find that this approach yields competitive results in protein model quality assessment despite its simplicity and despite the fact that it incorporates minimal prior information and is trained on relatively little data. As a result, its performance and generality are particularly noteworthy in an era where highly complex, customized machine learning methods such as AlphaFold 2 have come to dominate protein structure prediction.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Explore Spatio‐Temporal Learning of Large Sample Hydrology Using Graph Neural Networks

Abstract Streamflow forecasting over gauged and ungauged basins play a vital role in water resources planning, especially under the changing climate. Increased availability of large sample hydrology data sets, together with recent advances in deep learning techniques, has presented new opportunities to explore temporal and spatial patterns in hydrological signatures for improving streamflow forecasting. The purpose of this study is to adapt and benchmark several state‐of‐the‐art graph neural network (GNN) architectures, including ChebNet, Graph Convolutional Network (GCN), and GraphWaveNet, for end‐to‐end graph learning. We explicitly represent river basins as nodes in a graph, learn the spatiotemporal nodal dependencies, and then use the learned relations to predict streamflow simultaneously across all nodes in the graph. The efficacy of the developed GNN models is investigated using the Catchment Attributes and MEteorology for Large‐sample Studies (CAMELS) data set under two settings, fixed graph topology (transductive learning), and variable graph topology (inductive learning), with the latter applicable to prediction in ungauged basins (PUB). Results indicate that GNNs are generally robust and computationally efficient, achieving similar or better performance than a baseline model trained using the long short‐term memory (LSTM) network. Further analyses are conducted to interpret the graph learning process at the edge and node levels and to investigate the effect of different model configurations. We conclude that graph learning constitutes a viable machine learning‐based method for aggregating spatiotemporal information from a multitude of sources for streamflow forecasting

Sun, Alexander Y.↗
DOE OSTI2023

Investigating permafrost carbon dynamics in Alaska with artificial intelligence

Abstract Positive feedbacks between permafrost degradation and the release of soil carbon into the atmosphere impact land–atmosphere interactions, disrupt the global carbon cycle, and accelerate climate change. The widespread distribution of thawing permafrost is causing a cascade of geophysical and biochemical disturbances with global impacts. Currently, few earth system models account for permafrost carbon feedback (PCF) mechanisms. This research study integrates artificial intelligence (AI) tools and information derived from field-scale surveys across the tundra and boreal landscapes in Alaska. We identify and interpret the permafrost carbon cycling links and feedback sensitivities with GeoCryoAI, a hybridized multimodal deep learning (DL) architecture of stacked convolutionally layered, memory-encoded recurrent neural networks (NN). This framework integratesin-situmeasurements and flux tower observations for teacher forcing and model training. Preliminary experiments to quantify, validate, and forecast permafrost degradation and carbon efflux across Alaska demonstrate the fidelity of this data-driven architecture. More specifically, GeoCryoAI logs the ecological memory and effectively learns covariate dynamics while demonstrating an aptitude to simulate and forecast PCF dynamics—active layer thickness (ALT), carbon dioxide flux (CO 2 ), and methane flux (CH 4 )—with high precision and minimal loss (i.e. ALT RMSE : 1.327 cm [1969–2022]; CO 2 RMSE : 0.697µmolCO 2 m −2 s −1 [2003–2021]; CH 4 RMSE : 0.715 nmolCH 4 m −2 s −1 [2011–2022]). ALT variability is a sensitive harbinger of change, a unique signal characterizing the PCF, and our model is the first characterization of these dynamics across space and time.

Environmental Sciences & Ecology↗
DOE OSTI2021

Short-term apartment-level load forecasting using a modified neural network with selected auto-regressive features

Residential electricity load profiles and their diversity have become increasingly important to realize the benefits of Smart or Transactive Energy Networks (TENs). An important element of TENs will be practical, accurate, and implementable residential load forecasting techniques. While there have been many approaches to short-term load forecasting, few have included forecasting for individual households, partly because the high volatility and idiosyncrasies present in individual household load data can pose significant challenges. In this study, we develop a Convolutional Long Short-Term Memory-based neural network with Selected Autoregressive Features (termed a CLSAF model) to improve short-term household electricity load forecasting accuracy by employing three strategies: autoregressive features selection, exogenous features selection, and a “default” state to avoid overfitting at times of high load volatility. We include aggregations of apartments to floor and building level, because utilities may favor transactive approaches that rely on aggregator models, e.g., a cluster of consumers as opposed to an individual. We demonstrate that the CLSAF model, by virtue of its enhanced feature representation and modest computational resources, can accomplish load forecasting in a multi-family residential building across three spatial granularities (individual apartment/household, floor, and building levels), with an accuracy improvement of up to 25% compared to a persistence model. We propose a data screening technique to characterize time-series electricity-load data. This technique is suitable for integration into a TEN ecosystem and allows one to estimate confidence levels of the load forecasts to optimize computational resources and the risks associated with uncertain forecasts.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Digital Modeling on Large Kernel Metamaterial Neural Network

Deep neural networks (DNNs) utilized recently are physically deployed with computational units (e.g., CPUs and GPUs). Such a design might lead to a heavy computational burden, significant latency, and intensive power consumption, which are critical limitations in applications such as Internet of Things (IoT), edge computing, and usage of drones. Recent advances in optical computational units (e.g., metamaterial) have shed light on energy-free and light-speed neural networks. However, the digital design of the metamaterial neural network (MNN) is fundamentally limited by its physical limitations, such as precision, noise, and bandwidth during fabrication. Moreover, the unique advantages of MNN’s (e.g., light-speed computation) are not fully explored via standard 3×3 convolution kernels. In this paper, we propose a novel large kernel metamaterial neural network (LMNN) that maximizes the digital capacity of the state-of-the-art (SOTA) MNN with model re-parametrization and network compression, while also considering the optical limitation explicitly. The new digital learning scheme can maximize the learning capacity of MNN while modeling the physical restrictions of meta-optics. With the proposed LMNN, the computation cost of the convolutional front-end can be offloaded to fabricated optical hardware. The experimental results on two publicly available datasets demonstrate that the optimized hybrid design improved classification accuracy while reducing computational latency. In conclusion, the development of the proposed LMNN is a promising step towards the ultimate goal of energy-free and light-speed AI.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Federated Quantum Machine Learning

Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is located. One of the potential schemes to achieve this property is the federated learning (FL), which consists of several clients or local nodes learning on their own data and a central node to aggregate the models collected from those local nodes. However, to the best of our knowledge, no work has been done in quantum machine learning (QML) in federation setting yet. In this work, we present the federated training on hybrid quantum-classical machine learning models although our framework could be generalized to pure quantum machine learning model. Specifically, we consider the quantum neural network (QNN) coupled with classical pre-trained convolutional model. Our distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training. It demonstrates a promising future research direction for scaling and privacy aspects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Unifying Combinatorial and Graphical Methods in Artificial Intelligence

Recently, a new graph Laplacian, called the inner product Laplacian, was introduced which generalizes many existing Laplacians, including the normalized and combinatorial Laplacian and their weighted variants. The key observation behind the inner product Laplacian is that by defining appropriate inner product spaces on the vertices and edges, the standard Laplacians can be recovered as Hodge Laplacians over the simplicial complex formed by the edges and vertices. These inner product spaces form a natural way to incorporate non-combinatorial information into the definition of a domain-specific Laplacian. In particular, in contrast to current domain-specific weighting schemes which rely solely on edge weights, information regarding the similarity of non-adjacent vertices and arbitrary pairs of edges can be effectively incorporated into the Laplacian. In order to illustrate this approach we consider the problem of calculating the potential energy of an atomistic configuration using Graph Neural Networks. In comparison with start-of-the-art approaches, such as SchNet, our approach replaces a learned (via auto-encoder) representation of the atom types with an inner product space on atoms based on scientific knowledge (e.g., electronegativity). We will illustrate how this approach captures key chemical properties of the molecules and compare the energy calculations with state-of-the-art neural network approaches. However, to compute the resulting Laplacian involves a mixture of sparse and dense matrix computation and yields a dense matrix as the basis for the graph convolution. This dense convolutional kernel necessitates moving away from the standard message passing framework for graph neural networks and increases the computational cost of applying the kernel. In order to mitigate these costs we investigate means of leveraging the mixed sparse and dense computations to reduce the overall computational cost and how these approaches can be automatically transferred to energy efficient hardware (e.g., field programmable gate arrays (FPGAs)).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Point spread function deconvolution using a convolutional autoencoder

A major issue in optical astronomical image analysis is the combined effect of the instrument’s point spread function (PSF) and the atmospheric seeing that blurs images and changes their shape in a way that is band and time-of-observation dependent. In this work we present a very simple neural network based approach to nonblind image deconvolution that relies on feeding a convolutional autoencoder (CAE) input images that have been preprocessed by convolution with the corresponding PSF and its regularized inverse, a method which is both conceptually simple and computationally less intensive. We also present here, a new approach for dealing with limited input dynamic range of neural networks compared to the dynamic range present in astronomical images.

79 ASTRONOMY AND ASTROPHYSICS↗