Search NASA⌕ Search

SEARCH · Search NASA

Results for “Shallow 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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Sampling and resolution characteristics in reduced order models of shallow water equations: Intrusive vs nonintrusive

We investigate the sensitivity of reduced order models (ROMs) to training data spatial resolution as well as sampling rate. In particular, we consider proper orthogonal decomposition (POD), coupled with Galerkin projection (POD-GP), as an intrusive reduced order modeling technique. For non-intrusive ROMs, we consider two frameworks. The first is using dynamic mode decomposition (DMD), and the second is based on artificial neural networks (ANNs). For ANN, we utilized a residual deep neural network, and for DMD we have studied two versions of DMD approaches; one with hard thresholding and the other with sorted bases selection. Also, we highlight the differences between mean-subtracting the data (centering) and using the data without mean-subtraction. We tested these ROMs using a system of 2D shallow water equations for four different numerical experiments, adopting combinations of sampling rates and spatial resolutions. For these cases, we found that the DMD basis obtained with hard threshodling is sensitive to sampling rate. The sorted DMD algorithm helps to mitigate this problem and yields more stabilized and converging solution. Furthermore, we demonstrate that both DMD approaches without mean subtraction provide significantly more accurate results than DMD with mean-subtracting the data. On the other hand, POD is relatively insensitive to sampling rate and yields better representation of the flow field. Meanwhile, spatial resolution has little effect on both POD and DMD performances. Here, the numerical results reveal that an ANN on POD subspace (POD-ANN) performs remarkably better than POD-GP and DMD in capturing system dynamics, even with a small number of modes.

42 ENGINEERING↗
DOE OSTI2022

Utah FORGE - Development of a Reservoir Seismic Velocity Model and Seismic Resolution Study

This is data from and a final report on the development of a 3D velocity model for the larger FORGE area and on the seismic resolution in the stimulated fracture volume at the bottom of well 16A-32. The velocity model was developed using RMS velocities of the seismic reflection survey and seismic velocity logs from borehole measurements as an input model. To improve the accuracy of the model in the shallow subsurface, travel times phase arrivals of the direct propagating P-waves were determined from the seismic reflection data, using PhaseNet, a deep-neural-network-based seismic arrival time picking method. The travel times were subsequently inverted using the input velocity model. The seismic resolution study used borehole and surface seismic sensors as well as the seismicity observed during the April 2022 stimulation experiment to estimate the seismic resolution in the activated fracture reservoir. The data contain a 3D P- and S-wave velocity model for the larger FORGE area.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Probabilistic neural networks for fluid flow surrogate modeling and data recovery

We consider the use of probabilistic neural networks for fluid flow surrogate modeling and data recovery. This framework is constructed by assuming that the target variables are sampled from a Gaussian distribution conditioned on the inputs. Consequently, the overall formulation sets up a procedure to predict the hyperparameters of this distribution which are then used to compute an objective function given training data. We demonstrate that this framework has the ability to provide for prediction confidence intervals based on the assumption of a probabilistic posterior, given an appropriate model architecture and adequate training data. The applicability of the present framework to cases with noisy measurements and limited observations is also assessed. To demonstrate the capabilities of this framework, we consider canonical regression problems of fluid dynamics from the viewpoint of reduced-order modeling and spatial data recovery for four canonical data sets. The examples considered in this study arise from (i) the shallow-water equations, (ii) a two-dimensional cylinder flow, (iii) the wake of a NACA0012 airfoil with a Gurney flap, and (iv) the NOAA sea surface temperature data set. Furthermore, the present results indicate that the probabilistic neural network not only produces a machine-learning-based fluid flow surrogate model but also systematically quantifies the uncertainty therein to assist with model interpretability.

42 ENGINEERING↗
DOE OSTI2022

Neural net detection of seismic features related to gas hydrates and free gas accumulations on the northern U.S. Atlantic margin

Bottom-simulating reflections (BSRs) that sometimes mark the base of the gas hydrate stability zone in marine sediments are often identified based on the reverse polarity reflections that cut across stratigraphic layering in seismic amplitude data. On the northern U.S. Atlantic margin (USAM) between Cape Hatteras and Hudson Canyon, legacy seismic data have revealed pronounced BSRs south of the deepwater extension of Hudson Canyon and more subtle ones from offshore Delaware south to Cape Hatteras, where the reflections sometimes follow stratigraphic layering. Using high-resolution seismic data acquired during the 2018 Mid-Atlantic Resource Imaging Experiment and a supervised neural net, we identify seismic features associated with gas hydrates and/or the top of gas between Hudson Canyon and Cape Hatteras. Using seismic attributes especially sensitive to the presence of gas, we train a neural network algorithm on seismic data from an area with strong BSRs and then apply the model to the rest of the data set. The results indicate that gas hydrate and/or shallow free gas are significantly more widespread on the northern part of the USAM than previously known. Seismic indicators of gas extend landward from the 2000 m isobath to the upper continental slope in sectors with (offshore Virginia) and, to a lesser extent, without (offshore New Jersey) pervasive upper slope methane seeps. Higher sand content and intermediate sediment thickness, factors related to the container size and gas charge in a petroleum systems framework, are associated with more robust gas indicators.

Geochemistry & Geophysics↗
DOE OSTI2022

Delineating Variabilities of Groundwater Level Prediction Across the Agriculturally Intensive Transboundary Aquifers of South Asia

We report the groundwater depletion in South Asia’s Himalayan, transboundary Indus-Ganges-Brahmaputra-Meghna (IGBM) rivers basin is among the highest globally. Given the high irrigation demand and population, groundwater sustainability requires an improved understanding of groundwater systems for the accurate prediction of groundwater levels (GWLs). However, the prediction of groundwater system behaviors is a significant challenge since it is dominated by spatiotemporal and subsurface depth-dependent drivers. Earlier studies that address the challenges are mainly based on the short spatial and temporal extent and/or do not separate the renewable (i.e., shallow) vs nonrenewable (i.e., deeper) groundwater signals. Here, we first identified the variable importance of spatial and depth-dependent drivers on GWL in the IGBM basin. Our results indicate a greater influence of anthropogenic factors (i.e., widespread pumping and increased population) in most parts of the IGBM basin, except in the precipitation-dominated basin of the Brahmaputra. Our next purpose was to delineate a multifactorial approach for GWL prediction using the two most used machine learning models (i.e., support vector machine and feed-forward neural network) in the literature. In general, the machine learning model outputs show a good match in comparison to the GWL from the observation wells (n = 2303 distributed across India and Bangladesh) with some limitations in areas with increased groundwater irrigation. We separately compared the results from shallow (<35 m) and deep (>35 m) observation wells, emphasizing the significance of deep groundwater pumping. Our approach highlights the importance of spatiotemporal to multidepth factors in GWL prediction and can be adopted in other parts of the globe to predict GWLs.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture

This work presents a two-stage adaptive framework for progressively developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We impose desirable structures on the DNN by employing manifold regularization, sparsity regularization, and physics-informed terms. We introduce a ε – δ – stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a ε – δ stability-promoting algorithm. Further, we also derive the necessary conditions for the trainability of a newly added layer and investigate the training saturation problem. In the second stage of the algorithm (post-processing), a sequence of shallow networks is employed to extract information from the residual produced in the first stage, thereby improving the prediction accuracy. Numerical investigations on prototype regression and classification problems demonstrate that the proposed approach can outperform fully connected DNNs of the same size. Moreover, by equipping the physics-informed neural network (PINN) with the proposed adaptive architecture strategy to solve partial differential equations, we numerically show that adaptive PINNs not only are superior to standard PINNs but also produce interpretable hidden layers with provable stability. As a result, we also apply our architecture design strategy to solve inverse problems governed by elliptic partial differential equations.

42 ENGINEERING↗
DOE OSTI2025

Geospatial modeling of near subsurface temperatures of the contiguous United States for assessment of materials degradation

Abstract Understanding subsurface temperature variations is crucial for assessing material degradation in underground structures. This study maps subsurface temperatures across the contiguous United States for depths from 50 to 3500 m, comparing linear interpolation, gradient boosting (LightGBM), neural networks, and a novel hybrid approach combining linear interpolation with LightGBM. Results reveal heterogeneous temperature patterns both horizontally and vertically. The hybrid model performed best achieving a root mean square error of 2.61 °C at shallow depths (50–350 m). Model performance generally decreased with depth, highlighting challenges in deep temperature prediction. State-level analyses emphasized the importance of considering local geological factors. This study provides valuable insights for designing efficient underground facilities and infrastructure, underscoring the need for depth-specific and region-specific modeling approaches in subsurface temperature assessment.

Science & Technology - Other Topics↗
DOE OSTI2022

Nonconvex regularization for sparse neural networks

Convex ℓ 1 regularization using an infinite dictionary of neurons has been suggested for constructing neural networks with desired approximation guarantees, but can be affected by an arbitrary amount of over-parametrization. This can lead to a loss of sparsity and result in networks with too many active neurons for the given data, in particular if the number of data samples is large. As a remedy, in this paper, a nonconvex regularization method is investigated in the context of shallow ReLU networks: We prove that in contrast to the convex approach, any resulting (locally optimal) network is finite even in the presence of infinite data (i.e., if the data distribution is known and the limiting case of infinite samples is considered). Moreover, here we show that approximation guarantees and existing bounds on the network size for finite data are maintained.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

First Impressions: Early-time Classification of Supernovae Using Host-galaxy Information and Shallow Learning

Substantial effort has been devoted to the characterization of transient phenomena from photometric information. Automated approaches to this problem have taken advantage of complete phase coverage of an event, limiting their use for triggering rapid follow-up of ongoing phenomena. In this work, we introduce a neural network with a single recurrent layer designed explicitly for early photometric classification of supernovae (SNe). Our algorithm leverages transfer learning to account for model misspecification, host-galaxy photometry to solve the data-scarcity problem soon after discovery, and a custom weighted loss to prioritize accurate early classification. We first train our algorithm using state-of-the-art transient and host-galaxy simulations, then adapt its weights and validate it on the spectroscopically confirmed SNe Ia, SNe II, and SNe Ib/c from the Zwicky Transient Facility Bright Transient Survey. On observed data, our method achieves an overall accuracy of 82% ± 2% within 3 days of an event’s discovery, and an accuracy of 87% ± 5% within 30 days of discovery. At both early and late phases, our method achieves comparable or superior results to the leading classification algorithms with a simpler network architecture. These results help pave the way for rapid photometric and spectroscopic follow-up of scientifically valuable transients discovered in massive synoptic surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Detecting and Characterizing Fracture Zones Using a Convolutional Neural Network

This project directly supports the Geothermal Technologies Office (GTO) objectives outlined in the Multi-Year Program Plan (MYPP) by advancing two key research areas: “Exploration and Characterization” and “Data, Modeling, and Analysis.” This project has successfully demonstrated a pre-drilling ability to image and characterize the distribution and connectivity of subsurface faults and fractures, key parameters for identifying permeable pathways that enable geothermal fluids to circulate and produce energy. Specifically, we developed and implemented innovative machine learning methodologies to enhance geothermal exploration. Large-scale faults were detected using a Convolutional Neural Network (CNN), while small-scale fractures were characterized using a novel Double-Beam Neural Network (DBNN). These tools have proven both technically effective and cost-efficient by reducing reliance on expensive exploratory drilling. Through collaboration with our geothermal industry partner, this research has significantly advanced techniques for identifying hidden geothermal systems and extending the productive lifespan of existing geothermal fields. We applied our methods to two geothermal fields—Soda Lake (Nevada) and Lightning Dock (New Mexico)—to identify shallow steam-charged fracture zones and characterize deep faults at depths of 1.5-2 km. The steam zone identified at the Soda Lake geothermal field showed excellent agreement with prior drilling data, validating the effectiveness of our approaches. In addition, the analysis revealed three new prospective drilling targets for further development and verification. The outcomes of this project improve our scientific understanding of geothermal reservoir behavior, enhance exploration efficiency, extend the economic life of existing geothermal plants. Ultimately, these advancements contribute to GTO’s goal of achieving more sustainable, affordable, and data-driven geothermal energy development across the United States.

15 GEOTHERMAL ENERGY↗
DOE OSTI2026

Recurrent convolutional neural networks for modeling nonadiabatic dynamics of quantum-classical systems

Recurrent neural networks (RNNs) have recently been extensively applied to model the time evolution in fluid dynamics, weather predictions, and even chaotic systems due to their ability to capture temporal dependencies and sequential patterns in data. Here we present an RNN model based on convolutional neural networks for modeling the nonlinear nonadiabatic dynamics of hybrid quantum-classical systems. The dynamical evolution of the hybrid systems is governed by equations of motion for classical degrees of freedom and von Neumann equation for electrons. The Physics-Aware Recurrent Convolution (PARC) neural network structure incorporates a differentiator-integrator architecture that inductively models the spatiotemporal dynamics of generic physical systems. Here, we apply our RNN approach to learn the space-time evolution of a one-dimensional semiclassical Holstein model after an interaction quench. For shallow quenches (small changes in electron-lattice coupling), the deterministic dynamics can be accurately captured using a single-CNN-based recurrent network. In contrast, deep quenches induce chaotic evolution, making long-term trajectory prediction significantly more challenging. Nonetheless, we demonstrate that the PARC-CNN architecture can effectively learn the statistical climate of the Holstein model under deep-quench conditions.

Holstein model↗
DOE OSTI2020

Multiobjective and categorical global optimization of photonic structures based on ResNet generative neural networks

Abstract We show that deep generative neural networks, based on global optimization networks (GLOnets), can be configured to perform the multiobjective and categorical global optimization of photonic devices. A residual network scheme enables GLOnets to evolve from a deep architecture, which is required to properly search the full design space early in the optimization process, to a shallow network that generates a narrow distribution of globally optimal devices. As a proof-of-concept demonstration, we adapt our method to design thin-film stacks consisting of multiple material types. Benchmarks with known globally optimized antireflection structures indicate that GLOnets can find the global optimum with orders of magnitude faster speeds compared to conventional algorithms. We also demonstrate the utility of our method in complex design tasks with its application to incandescent light filters. These results indicate that advanced concepts in deep learning can push the capabilities of inverse design algorithms for photonics.

Jiang, Jiaqi↗
DOE OSTI2024

Variation-Resilient FeFET-Based In-Memory Computing Leveraging Probabilistic Deep Learning

Reliability issues stemming from device level nonidealities of nonvolatile emerging technologies like ferroelectric field-effect transistors (FeFETs), especially at scaled dimensions, cause substantial degradation in the accuracy of in-memory crossbar-based AI systems. Here, in this work, we present a variation-aware design technique to characterize the device level variations and to mitigate their impact on hardware accuracy employing a Bayesian neural network (BNN) approach. An effective conductance variation model is derived from the experimental measurements of cycle-to-cycle (C2C) and device-to-device (D2D) variations performed on FeFET devices fabricated using 28 nm high-k metal gate technology. The variations were found to be a function of different conductance states within the given programming range, which sharply contrasts earlier efforts where a fixed variation dispersion was considered for all conductance values. Such variation characteristics formulated for three different device sizes at different read voltages were provided as prior variation information to the BNN to yield a more exact and reliable inference. Near-ideal accuracy for shallow networks (MLP5 and LeNet models) on the MNIST dataset and limited accuracy decline by ~3.8%–16.1% for deeper AlexNet models on CIFAR10 dataset under a wide range of variations corresponding to different device sizes and read voltages, demonstrates the efficacy of our proposed device-algorithm co-design technique.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2019

Next-Generation Optical Sensing Technologies for Exploring Ocean Worlds - NASA FluidCam, MiDAR, and NeMO-Net

We highlight three emerging NASA optical technologies that enhance our ability to remotely sense, analyze, and explore ocean worlds–FluidCam and fluid lensing, MiDAR, and NeMO-Net. Fluid lensing is the first remote sensing technology capable of imaging through ocean waves without distortions in 3D at sub-cm resolutions. Fluid lensing and the purpose-built FluidCam CubeSat instruments have been used to provide refraction-corrected 3D multispectral imagery of shallow marine systems from unmanned aerial vehicles (UAVs). Results from repeat 2013 and 2016 airborne fluid lensing campaigns over coral reefs in American Samoa present a promising new tool for monitoring fine-scale ecological dynamics in shallow aquatic systems tens of square kilometers in area. MiDAR is a recently-patented active multispectral remote sensing and optical communications instrument which evolved from FluidCam. MiDAR is being tested on UAVs and autonomous underwater vehicles (AUVs) to remotely sense living and non-living structures in light-limited and analog planetary science environments. MiDAR illuminates targets with high-intensity narrowband structured optical radiation to measure an object’s spectral reflectance while simultaneously transmitting data. MiDAR is capable of remotely sensing reflectance at fine spatial and temporal scales, with a signal-to-noise ratio 10-10(exp 3) times higher than passive airborne and spaceborne remote sensing systems, enabling high-framerate multispectral sensing across the ultraviolet, visible, and near-infrared spectrum. Preliminary results from a 2018 mission to Guam show encouraging applications of MiDAR to imaging coral from airborne and underwater platforms whilst transmitting data across the air-water interface. Finally, we share NeMO-Net, the Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment. NeMO-Net is a machine learning technology under development that exploits high-resolution data from FluidCam and MiDAR for augmentation of low-resolution airborne and satellite remote sensing. NeMO-Net is intended to harmonize the growing diversity of 2D and 3D remote sensing with in situ data into a single open-source platform for assessing shallow marine ecosystems globally using active learning for citizen-science based training. Preliminary results from four-class Q17 coral classification have an accuracy of 94.4%. Together, these maturing technologies present promising scalable, practical, and cost-efficient innovations that address current observational and technological challenges in optical sensing of marine systems.

Ved Chirayath↗
DOE OSTI2024

Facial Named Entity Recognition by Attention-Based Graph Convolutional Neural Network

In the realm of facial recognition and analysis, the ability to accurately cluster large datasets of facial images stands as a cornerstone for various applications, ranging from security surveillance to user biometric identification. This project evolves a novel approach to facial data clustering by embedding facial images into a high-dimensional vector space using an advanced embedding model trained on separate data and assumes a graph-like structure on the high-dimensional vectors. We find our method works significantly better than common shallow methods.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Some research topics belonging to classification problems in the nuclear industry, such as fault diagnosis and accident identification, can be solved by feature extraction and subsequent application of statistical machine learning classifiers. Recently, deep neural network-based methods with automatic feature extraction and high accuracy have gained wide attention. They usually require large-scale training data, however, plant fault or accident data are scarce or difficult to obtain. Here this paper proposes a convolutional network (CNN)-based transfer learning method to solve this problem. The network's shallow layer is derived from a pre-trained CNN based on the ImageNet database to automatically extract features, and the deep layer is customized to match the classification problem. Data in non-image formats are converted to image formats and subsequently used to train the network. Case studies of rotating machines fault diagnosis show that the proposed method requires only limited training data to achieve high accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Modeling Multi-View Impedance-Based Cross-Geometry SOH Estimator for Li-ion Batteries

Abstract: Accurately estimating battery’s State of Health (SOH) remains challenging when models must generalize across cell designs and operating conditions. Most Electrochemical Impedance Spectroscopy (EIS)-based approaches either (i) hand-engineer a few Nyquist-plot features for shallow models—fast but does not generalize across geometries—or (ii) learn directly from Nyquist plots with deep networks, which removes manual feature extraction, yet still limited to a single plot type. As a result, cross-geometry robustness and deployability on constrained Internet of Things (IoT) devices remain open problems. We propose a compact Convolutional Neural Network (CNN) (∼ 10k parameters) that takes multi-representation EIS inputs—Nyquist (real/imaginary) and phase–magnitude (|Z|/ϕ) stacked as four channels, so the model can learn complementary degradation signatures while remaining small enough for fast inference. We build a dataset from cyclic aging of two geometries (LG INR18650MJ1 cylindrical cells and LIR2032 coin cells), acquire EIS every ten cycles from 10 kHz to 10 mHz (10 points/decade), and evaluate with leave-one-cell-out testing strategy. We further study fusion vs. single-representation inputs and assess feasibility for on-device deployment (e.g., NVIDIA Jetson device). The results show that training on multiple EIS representations improves SOH estimation accuracy and cross-geometry generalization compared to single-representation models, which uses only Nyquist or phase–magnitude plots. This design targets accurate, generalizable SOH prediction without manual feature engineering while enabling practical real-time use.

Bakr, Ahmed [The University of Alabama (UA)]↗
DOE OSTI2025

Triangle Method for Dense ReLU Layers [SWR-25-72]

This software is an implementation of the methods for initializing and training neural networks to be more efficient per parameter, described more fully below and in the related publication: In theory, depth should make a ReLU network EXPONENTIALLY more efficient by enabling it to produce an exponential number of piecewise linear sections in its output. This reasoning is largely based on the work of mathematicians that have hand-constructed networks that make good use of depth. In practice however, even very deep ReLU networks that have been randomly initialized will behave identically to their shallow counterparts - missing an entire exponential dimension of efficiency. The triangle method is a first attempt at realizing the exponential potential of deep networks. Instead of randomly setting weights, we force pairs of neurons in each layer learn to build triangles (i.e. functions from [0,1] -> [0,1] that look like triangles). This is a very efficient pattern for generating lots of linear pieces because composing two triangular functions doubles the number of pieces with each composition. The triangle method is more than just a different initialization, it is a new paradigm of training. Instead of making direct updates to the matrix weights, we do an extra step of backpropagation to collect the derivatives of the loss function with respect to the shapes of the triangles, training them to tilt left or right. This process essentially holds the networks hand throughout the loss landscape and forces it to always use depth effectively by producing triangular shapes internally. This can produce several orders of magnitude of improvement on convex one-dimensional regression problems. Much more theoretical work is needed to realize its full potential beyond this context, but the implementation in this repository will still work in arbitrary numbers of dimensions. The file Triangle_Method.py is a generalized form of the method that will build each neuron its own custom 1-d convex activation function (with exponential efficiency). Example usage on one dimensional problems can be found in Example_Usage.ipynb and an example of using this in a real neural network can be found in Example_VGG16_CIFAR10.ipynb.

Milkert, Max [National Renewable Energy Laboratory↗