Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep Neural Network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,585 records · Page 88
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Probabilistic Deep Learning Approach to Automate the Interpretation of Multi-phase Diffraction Spectra

Autonomous synthesis and characterization of inorganic materials requires the automatic and accurate analysis of X-ray diffraction spectra. For this task, we designed a probabilistic deep learning algorithm to identify complex multi-phase mixtures. At the core of this algorithm lies an ensemble convolutional neural network trained on simulated diffraction spectra, which are systematically augmented with physics-informed perturbations to account for artifacts that can arise during experimental sample preparation and synthesis. In this work, larger perturbations associated with off-stoichiometry are also captured by supplementing the training set with hypothetical solid solutions. Spectra containing mixtures of materials are analyzed with a newly developed branching algorithm that utilizes the probabilistic nature of the neural network to explore suspected mixtures and identify the set of phases that maximize confidence in the prediction. Our model is benchmarked on simulated and experimentally measured diffraction spectra, showing exceptional performance with accuracies exceeding those given by previously reported methods based on profile matching and deep learning. We envision that the algorithm presented here may be integrated in experimental workflows to facilitate the high-throughput and autonomous discovery of inorganic materials.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Deep learning for time series forecasting: a survey of recent advances

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Geometry-complete diffusion for 3D molecule generation and optimization

Abstract Generative deep learning methods have recently been proposed for generating 3D molecules using equivariant graph neural networks (GNNs) within a denoising diffusion framework. However, such methods are unable to learn important geometric properties of 3D molecules, as they adopt molecule-agnostic and non-geometric GNNs as their 3D graph denoising networks, which notably hinders their ability to generate valid large 3D molecules. In this work, we address these gaps by introducing the Geometry-Complete Diffusion Model (GCDM) for 3D molecule generation, which outperforms existing 3D molecular diffusion models by significant margins across conditional and unconditional settings for the QM9 dataset and the larger GEOM-Drugs dataset, respectively. Importantly, we demonstrate that GCDM’s generative denoising process enables the model to generate a significant proportion of valid and energetically-stable large molecules at the scale of GEOM-Drugs, whereas previous methods fail to do so with the features they learn. Additionally, we show that extensions of GCDM can not only effectively design 3D molecules for specific protein pockets but can be repurposed to consistently optimize the geometry and chemical composition of existing 3D molecules for molecular stability and property specificity, demonstrating new versatility of molecular diffusion models. Code and data are freely available on GitHub .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Solving Seismic Wave Equations on Variable Velocity Models With Fourier Neural Operator

Here, in the study of subsurface seismic imaging, solving the acoustic wave equation is a pivotal component in existing models. The advancement of deep learning (DL) enables solving partial differential equations (PDEs), including wave equations, by applying neural networks to identify the mapping between the inputs and the solution. This approach can be faster than traditional numerical methods when numerous instances are to be solved. Previous works that concentrate on solving the wave equation by neural networks consider either a single velocity model or multiple simple velocity models, which is restricted in practice. Instead, inspired by the idea of operator learning, this work leverages the Fourier neural operator (FNO) to effectively learn the frequency domain seismic wavefields under the context of variable velocity models. We also propose a new framework paralleled FNO (PFNO) for efficiently training the FNO-based solver given multiple source locations and frequencies. Numerical experiments demonstrate the high accuracy of both FNO and PFNO with complicated velocity models in the OpenFWI datasets. Furthermore, the cross-dataset generalization test verifies that PFNO adapts to out-of-distribution velocity models. Finally, PFNO admits higher computational efficiency on large-scale testing datasets than the traditional finite-difference method. The aforementioned advantages endow the FNO-based solver with the potential to build powerful models for research on seismic waves.

58 GEOSCIENCES↗
DOE OSTI2021

Automating Discovery of Physics-Informed Neural State Space Models via Learning and Evolution

Recent works exploring deep learning application to dynamical systems modeling have demonstrated that embedding physical priors into neural networks can yield more effective, physically-realistic, and data-efficient models. However, in the absence of complete prior knowledge of a dynamical system's physical characteristics, determining the optimal structure and optimization strategy for these models can be difficult. In this work, we explore methods for discovering neural state space dynamics models for system identification. Starting with a design space of block-oriented state space models and structured linear maps with strong physical priors, we encode these components into a model genome alongside network structure, penalty constraints, and optimization hyperparameters. Demonstrating the overall utility of the design space, we employ an asynchronous genetic search algorithm that alternates between model selection and optimization and obtains accurate physically consistent models of three physical systems: an aerodynamics body, a continuous stirred tank reactor, and a two tank interacting system.

genetic algorithms, neural architecture search, ne↗
DOE OSTI2024

Utilization of Synthetic Near-Infrared Spectra via Generative Adversarial Network to Improve Wood Stiffness Prediction

Near-infrared (NIR) spectroscopy is widely used as a nondestructive evaluation (NDE) tool for predicting wood properties. When deploying NIR models, one faces challenges in ensuring representative training data, which large datasets can mitigate but often at a significant cost. Machine learning and deep learning NIR models are at an even greater disadvantage because they typically require higher sample sizes for training. In this study, NIR spectra were collected to predict the modulus of elasticity (MOE) of southern pine lumber (training set = 573 samples, testing set = 145 samples). To account for the limited size of the training data, this study employed a generative adversarial network (GAN) to generate synthetic NIR spectra. The training dataset was fed into a GAN to generate 313, 573, and 1000 synthetic spectra. The original and enhanced datasets were used to train artificial neural networks (ANNs), convolutional neural networks (CNNs), and light gradient boosting machines (LGBMs) for MOE prediction. Overall, results showed that data augmentation using GAN improved the coefficient of determination (R 2 ) by up to 7.02% and reduced the error of predictions by up to 4.29%. ANNs and CNNs benefited more from synthetic spectra than LGBMs, which only yielded slight improvement. All models showed optimal performance when 313 synthetic spectra were added to the original training data; further additions did not improve model performance because the quality of the datapoints generated by GAN beyond a certain threshold is poor, and one of the main reasons for this can be the size of the initial training data fed into the GAN. LGBMs showed superior performances than ANNs and CNNs on both the original and enhanced training datasets, which highlights the significance of selecting an appropriate machine learning or deep learning model for NIR spectral-data analysis. The results highlighted the positive impact of GAN on the predictive performance of models utilizing NIR spectroscopy as an NDE technique and monitoring tool for wood mechanical-property evaluation. Further studies should investigate the impact of the initial size of training data, the optimal number of generated synthetic spectra, and machine learning or deep learning models that could benefit more from data augmentation using GANs.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2022

A Deep Learning Approach to Fast Radiative Transfer

Due to the sheer volume of data, leveraging satellite instrument observations effectively in a data assimilation context for numerical weather prediction or for remote sensing requires a radiative transfer model as an observation operator that is both fast and accurate at the same time. Physics-based line-by-line radiative transfer (RT) models fulfil the requirement for accuracy, but are too slow and too costly in computational terms for operational applications. Therefore, fast methods were developed to be able to perform fast RT calculations using techniques such as spectral sampling or pre-computed look-up tables. The operational fast models currently calculate the absorption and scattering coefficients from the pre-computed regression coefficients and atmospheric state and cloud profiles. As a novel solution to this problem, this work investigates a deep learning approach to replace the regression coefficients in the fast RT models. A selection of hidden-layer neural network configurations is trained against atmospheric transmittance profile data computed by an accurate line-by-line model and their performance is evaluated and their advantages and disadvantages are discussed.

Machine learning↗
DOE OSTI2019

Development of a deep machine learning interatomic potential for metalloid-containing Pd-Si compounds

Interatomic potentials based on neural-network machine learning (ML) approach to address the long-standing challenge of accuracy versus efficiency in molecular-dynamics simulations have recently attracted a great deal of interest. In this work, utilizing Pd-Si system as a prototype, we extend the development of neural-network ML potentials to compounds exhibiting various types of bonding characteristics. The ML potential is trained by fitting to the energies and forces of both liquid and crystal structures first-principles calculations based on density-functional theory (DFT). We show that the generated ML potential captures the structural features and motifs in Pd 82 Si 18 and Pd 75 Si 25 liquids more accurately than the existing interatomic potential based on embedded-atom method (EAM). The ML potential also describes the solid-liquid interface of these systems very well. Moreover, while the existing EAM potential fails to describe the relative energies of various crystalline structures and predict wrong ground-state structures at Pd 3 Si and Pd 9 Si 2 composition, the developed ML potential predicts correctly the ground-state structures from genetic algorithm search. The efficient ML potential with DFT accuracy from our study will provide a promising scheme for accurate atomistic simulations of structures and dynamics of complex Pd-Si system.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
NASA NTRS2019

Using Deep Learning to Automate Inference of Meteoroid Pre-Entry Properties

Properly assessing the asteroid threat depends on the knowledge of asteroid pre-entry parameters, such as size, velocity, mass, density, and strength. Although a vast number of possible bodies to study exist, such characterization of asteroid populations is currently limited by substantial costs associated with space rendezvous missions and rare meteorite findings. As asteroids fragment, ablate, and decelerate in the atmosphere, they emit light detectable by ground-based and space-borne instruments. Earth’s atmosphere, thus, becomes an accessible laboratory that enables impactor risk assessments by facilitating inference of the pre-entry parameters. These asteroid pre-entry conditions are typically deduced by modeling the entry and breakup physics that best reproduce the observed light or energy deposition curve. However, this process requires extensive manual trial-and-error of uncertain modeling parameters. Automating meteor modeling and inference would improve property distributions used in risk assessments and enable population characterization as more light curves become more readily available through the presence of space assets and ground-based camera networks. We previously developed a genetic algorithm to automate meteor modeling by using the fragment-cloud model (FCM) to search for the values of the FCM input parameters (e.g., diameter) that generate energy deposition profiles that match the observed one. Now, we apply deep learning to infer asteroid diameter, velocity, and density from observed energy deposition curves. We trained and tested our neural network models with synthetic energy deposition curves modeled using the FCM rubble pile implementation. We present an application of a 1D convolutional neural network and compare its performance to other attempted regressors and machine learning techniques, such as a fully connected neural network and Random Forest regression, to demonstrate its capabilities. We validate our model weights and approach using the Chelyabinsk, Tagish Lake, Benešov, Košice, and Lost City meteors.

Tarano, Ana Maria↗
DOE OSTI2022

Classification of Cloud Particle Imagery from Aircraft Platforms Using Convolutional Neural Networks

Abstract A vast amount of ice crystal imagery exists from a variety of field campaign initiatives that can be utilized for cloud microphysical research. Here, nine convolutional neural networks are used to classify particles into nine regimes on over 10 million images from the Cloud Particle Imager probe, including liquid and frozen states and particles with evidence of riming. A transfer learning approach proves that the Visual Geometry Group (VGG-16) network best classifies imagery with respect to multiple performance metrics. Classification accuracies on a validation dataset reach 97% and surpass traditional automated classification. Furthermore, after initial model training and preprocessing, 10 000 images can be classified in approximately 35 s using 20 central processing unit cores and two graphics processing units, which reaches real-time classification capabilities. Statistical analysis of the classified images indicates that a large portion (57%) of the dataset is unusable, meaning the images are too blurry or represent indistinguishable small fragments. In addition, 19% of the dataset is classified as liquid drops. After removal of fragments, blurry images, and cloud drops, 38% of the remaining ice particles are largely intersecting the image border (≥10% cutoff) and therefore are considered unusable because of the inability to properly classify and dimensionalize. After this filtering, an unprecedented database of 1 560 364 images across all campaigns is available for parameter extraction and bulk statistics on specific particle types in a wide variety of storm systems, which can act to improve the current state of microphysical parameterizations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Statistically-informed deep learning for gravitational wave parameter estimation

We introduce deep learning models to estimate the masses of the binary components of black hole mergers, $(m_1,m_2)$, and three astrophysical properties of the post-merger compact remnant, namely, the final spin, $a_\mathrm f$, and the frequency and damping time of the ringdown oscillations of the fundamental $\ell = m = 2$ bar mode, $(\omega_\mathrm R, \omega_\mathrm I)$. Our neural networks combine a modified WaveNet architecture with contrastive learning and normalizing flow. We validate these models against a Gaussian conjugate prior family whose posterior distribution is described by a closed analytical expression. Upon confirming that our models produce statistically consistent results, we used them to estimate the astrophysical parameters $(m_1,m_2, a_\mathrm f, \omega_\mathrm R, \omega_\mathrm I)$ of five binary black holes: GW150914, GW170104, GW170814, GW190521 and GW190630. We use PyCBC Inference to directly compare traditional Bayesian methodologies for parameter estimation with our deep learning based posterior distributions. Our results show that our neural network models predict posterior distributions that encode physical correlations, and that our data-driven median results and 90% confidence intervals are similar to those produced with gravitational wave Bayesian analyses. This methodology requires a single V100 NVIDIA GPU to produce median values and posterior distributions within two milliseconds for each event. Furthermore, this neural network, and a tutorial for its use, are available at the Data and Learning Hub for Science.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

General-Purpose Bayesian Tensor Learning With Automatic Rank Determination and Uncertainty Quantification

A major challenge in many machine learning tasks is that the model expressive power depends on model size. Low-rank tensor methods are an efficient tool for handling the curse of dimensionality in many large-scale machine learning models. The major challenges in training a tensor learning model include how to process the high-volume data, how to determine the tensor rank automatically, and how to estimate the uncertainty of the results. While existing tensor learning focuses on a specific task, this paper proposes a generic Bayesian framework that can be employed to solve a broad class of tensor learning problems such as tensor completion, tensor regression, and tensorized neural networks. We develop a low-rank tensor prior for automatic rank determination in nonlinear problems. Our method is implemented with both stochastic gradient Hamiltonian Monte Carlo (SGHMC) and Stein Variational Gradient Descent (SVGD). We compare the automatic rank determination and uncertainty quantification of these two solvers. We demonstrate that our proposed method can determine the tensor rank automatically and can quantify the uncertainty of the obtained results. We validate our framework on tensor completion tasks and tensorized neural network training tasks.

Bayesian inference↗
DOE OSTI2024

Bayesian Neural Network Variational Autoencoder Inverse Mapper (BNN-VAIM) and its application in Compton Form Factors extraction

Abstract We extend the Variational Autoencoder Inverse Mapper (VAIM) framework for the inverse problem of extracting Compton Form Factors (CFFs) from deeply virtual exclusive reactions, such as the unpolarized Deeply virtual exclusive scattering (DVCS) cross section. VAIM is an end-to-end deep learning framework to address the solution ambiguity issue in ill-posed inverse problems, which comprises of a forward mapper and a backward mapper to simulate the forward and inverse processes, respectively. In particular, we incorporate Bayesian Neural Network (BNN) into the VAIM architecture (BNN-VAIM) for uncertainty quantification. By sampling the weights and biases distributions of the BNN in the backward mapper of the VAIM, BNN-VAIM is able to estimate prediction uncertainty associated with each individual solution obtained for an ill-posed inverse problem. We first demonstrate the uncertainty quantification capability of BNN-VAIM in a toy inverse problem. Then, we apply BNN-VAIM to the inverse problem of extracting 8 CFFs from the unpolarized DVCS cross section.

Instruments & Instrumentation↗
DOE OSTI2022

Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5

Abstract. There is growing interest in data-driven weather prediction (DDWP), e.g., using convolutional neural networks such as U-NET that are trained on data from models or reanalysis. Here, we propose three components, inspired by physics, to integrate with commonly used DDWP models in order to improve their forecast accuracy. These components are (1) a deep spatial transformer added to the latent space of U-NET to capture rotation and scaling transformation in the latent space for spatiotemporal data, (2) a data-assimilation (DA) algorithm to ingest noisy observations and improve the initial conditions for next forecasts, and (3) a multi-time-step algorithm, which combines forecasts from DDWP models with different time steps through DA, improving the accuracy of forecasts at short intervals. To show the benefit and feasibility of each component, we use geopotential height at 500 hPa (Z500) from ERA5 reanalysis and examine the short-term forecast accuracy of specific setups of the DDWP framework. Results show that the spatial-transformer-based U-NET (U-STN) clearly outperforms the U-NET, e.g., improving the forecast skill by 45 %. Using a sigma-point ensemble Kalman (SPEnKF) algorithm for DA and U-STN as the forward model, we show that stable, accurate DA cycles are achieved even with high observation noise. This DDWP+DA framework substantially benefits from large (O(1000)) ensembles that are inexpensively generated with the data-driven forward model in each DA cycle. The multi-time-step DDWP+DA framework also shows promise; for example, it reduces the average error by factors of 2–3. These results show the benefits and feasibility of these three components, which are flexible and can be used in a variety of DDWP setups. Furthermore, while here we focus on weather forecasting, the three components can be readily adopted for other parts of the Earth system, such as ocean and land, for which there is a rapid growth of data and need for forecast and assimilation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2019

Robust, automated sleep scoring by a compact neural network with distributional shift correction

Studying the biology of sleep requires the accurate assessment of the state of experimental subjects, and manual analysis of relevant data is a major bottleneck. Recently, deep learning applied to electroencephalogram and electromyogram data has shown great promise as a sleep scoring method, approaching the limits of inter-rater reliability. As with any machine learning algorithm, the inputs to a sleep scoring classifier are typically standardized in order to remove distributional shift caused by variability in the signal collection process. However, in scientific data, experimental manipulations introduce variability that should not be removed. For example, in sleep scoring, the fraction of time spent in each arousal state can vary between control and experimental subjects. We introduce a standardization method, mixture z-scoring, that preserves this crucial form of distributional shift. Using both a simulated experiment and mouse in vivo data, we demonstrate that a common standardization method used by state-of-the-art sleep scoring algorithms introduces systematic bias, but that mixture z-scoring does not. We present a free, open-source user interface that uses a compact neural network and mixture z-scoring to allow for rapid sleep scoring with accuracy that compares well to contemporary methods. This work provides a set of computational tools for the robust automation of sleep scoring.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Femtosecond pulse parameter estimation from photoelectron momenta using machine learning

Abstract Deep learning models have provided huge interpretation power for image-like data. Specifically, convolutional neural networks (CNNs) have demonstrated incredible acuity for tasks such as feature extraction or parameter estimation. Here we test CNNs on strong-field ionization photoelectron spectra, training on theoretical data sets to ‘invert’ experimental data. Pulse characterization is used as a ‘testing ground’, specifically we retrieve the laser intensity, where ‘traditional’ measurements typically lead to 20% uncertainty. We report on crucial data augmentation techniques required to successfully train on theoretical data and return consistent results from experiments, including accounting for detector saturation. The same procedure can be repeated to apply CNNs in a range of scenarios for strong-field ionization. Using a predictive uncertainty estimation, reliable laser intensity uncertainties of a few percent can be extracted, which are consistently lower than those given by traditional techniques. Using interpretability methods can reveal parts of the distribution that are most sensitive to laser intensity, which can be directly associated with holographic interferences. The CNNs employed provide an accurate and convenient ways to extract parameters, and represent a novel interpretational tool for strong-field ionization spectra.

Szołdra, Tomasz (ORCID:0000000228970506)↗
DOE OSTI2019

Deep Symbolic Regression

Symbolic regression is the task of finding tractable mathematical expressions that best fit an input dataset. Deep symbolic regression (DSR) searches the space of tractable mathematical expressions by using a recurrent neural network that generates mathematical expressions. The network is trained using reinforcement learning.

Petersen, BrendenK↗
DOE OSTI2024

Inverse Design of Photonic Surfaces via High throughput Femtosecond Laser Processing and Tandem Neural Networks

Abstract This work demonstrates a method to design photonic surfaces by combining femtosecond laser processing with the inverse design capabilities of tandem neural networks that directly link laser fabrication parameters to their resulting textured substrate optical properties. High throughput fabrication and characterization platforms are developed that generate a dataset comprising 35280 unique microtextured surfaces on stainless steel with corresponding measured spectral emissivities. The trained model utilizes the nonlinear one‐to‐many mapping between spectral emissivity and laser parameters. Consequently, it generates predominantly novel designs, which reproduce the full range of spectral emissivities (average root‐mean‐squared‐error < 2.5%) using only a compact region of laser parameter space 25 times smaller than what is represented in the training data. Finally, the inverse design model is experimentally validated on a thermophotovoltaic emitter design application. By synergizing laser‐matter interactions with neural network capabilities, the approach offers insights into accelerating the discovery of photonic surfaces, advancing energy harvesting technologies.

36 MATERIALS SCIENCE↗