Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Deep”

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 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Battery state-of-health diagnostics during fast cycling using physics-informed deep-learning

Rapid, in-situ Li-ion battery state-of-health (SOH) quantification is challenging. Li-ion battery aging can vary significantly with chemistry, operating conditions, cycling demands, electrode design, and operation history. As a cell ages, optimal and safe operating conditions need to be adapted to account for battery degradation by tracking critical aging modes such as loss-of-lithium-inventory (LLI), loss-of-active-material (LAM) in either electrode, and/or impedance rise. This manuscript describes a framework for identifying battery aging modes in-operando using fast-rate voltage charge/discharge responses. The framework uses a physically based Li-ion battery model to produce synthetic high-rate responses at aged states. The aging model is calibrated against experimental data from cells with different electrode loadings and cycled under a variety of fast-charging conditions (1 h, 15 min, 10 min, and 7 min charging). The synthetically generated high-rate responses at aged states are then used to train a deep-learning model to identify real cell state-of-health from fast charge/discharge battery voltage responses. The synthetically trained deep-learning model performance is validated by comparing to standard incremental capacity analysis and half-cell measurements. Finally, the framework demonstrates the benefits of using high-rate physics-based models to generate synthetic data for training deep-learning models.

25 ENERGY STORAGE↗
DOE OSTI2024

Complex multicomponent spectrum analysis with Deep Neural Network

Here, in this paper, we present the use of deep neural networks to estimate physical parameters from complex optical emission spectra of the D β /H β transition. Specifically, we focus on estimating the radio frequency electric field vector of the lower hybrid wave and isotope ratio within the scrape-off-layer plasma of the WEST tokamak. Fitting the spectral data using a traditional non-linear least squares analysis requires many free parameters and is computationally expensive, rendering the data unusable for real-time control. By implementing relatively small neural networks, the physical parameters can be directly extracted from the spectral data with reasonable accuracy in a few milliseconds. The deep neural network prediction can serve as input for a reduced model using least-squares fitting or for real-time control. We show that deep neural networks can be an effective tool for analyzing complex multicomponent spectra, providing a speedup of more than 10 5 times compared to least residual analysis, with an accuracy of 0.5% for the isotope ratio, and 0.09 kV/cm and 0.38 kV/cm for the RF radial and poloidal electric field respectively.

47 OTHER INSTRUMENTATION↗
DOE OSTI2017

The role of deep acceptor centers in the oxidation of acceptor-doped wide-band-gap perovskites ABO{sub 3}

The impact of deep acceptor centers on defect thermodynamics and oxidation of wide-band-gap acceptor-doped perovskites without mixed-valence cations is studied. These deep centers are formed by the acceptor-bound small hole polarons whose stabilization energy can be high enough (significantly higher than the hole-acceptor Coulomb interaction energy). It is shown that the oxidation enthalpy ΔH{sub ox} of oxide is determined by the energy ε{sub A} of acceptor-bound states along with the formation energy E{sub V} of oxygen vacancies. The oxidation reaction is demonstrated to be either endothermic or exothermic, and the regions of ε{sub A} and E{sub V} values corresponding to the positive or negative ΔH{sub ox} are determined. The contribution of acceptor-bound holes to the defect thermodynamics strongly depends on the acceptor states depth ε{sub A}: it becomes negligible at ε{sub A} less than a certain value (at which the acceptor levels are still deep). With increasing ε{sub A}, the concentration of acceptor-bound small hole polarons can reach the values comparable to the dopant content. The results are illustrated with the acceptor-doped BaZrO{sub 3} as an example. It is shown that the experimental data on the bulk hole conductivity of barium zirconate can be described both in the band transport model and in the model of hopping small polarons localized on oxygen ions away from the acceptor centers. Depending on the ε{sub A} magnitude, the oxidation reaction can be either endothermic or exothermic for both mobility mechanisms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Graph interpolating activation improves both natural and robust accuracies in data-efficient deep learning

Improving the accuracy and robustness of deep neural nets (DNNs) and adapting them to small training data are primary tasks in deep learning (DL) research. In this paper, we replace the output activation function of DNNs, typically the data-agnostic softmax function, with a graph Laplacian-based high-dimensional interpolating function which, in the continuum limit, converges to the solution of a Laplace–Beltrami equation on a high-dimensional manifold. Furthermore, we propose end-to-end training and testing algorithms for this new architecture. The proposed DNN with graph interpolating activation integrates the advantages of both deep learning and manifold learning. Compared to the conventional DNNs with the softmax function as output activation, the new framework demonstrates the following major advantages: First, it is better applicable to data-efficient learning in which we train high capacity DNNs without using a large number of training data. Second, it remarkably improves both natural accuracy on the clean images and robust accuracy on the adversarial images crafted by both white-box and black-box adversarial attacks. Third, it is a natural choice for semi-supervised learning. This paper is a significant extension of our earlier work published in NeurIPS, 2018. For reproducibility, the code is available at https://github.com/BaoWangMath/DNN-DataDependentActivation .

Mathematics↗
DOE OSTI2021

Deep Learning Segmentation of Complex Features in Atomic-Resolution Phase-Contrast Transmission Electron Microscopy Images

Phase-contrast transmission electron microscopy (TEM) is a powerful tool for imaging the local atomic structure of materials. TEM has been used heavily in studies of defect structures of two-dimensional materials such as monolayer graphene due to its high dose efficiency. However, phase-contrast imaging can produce complex nonlinear contrast, even for weakly scattering samples. It is, therefore, difficult to develop fully automated analysis routines for phase-contrast TEM studies using conventional image processing tools. For automated analysis of large sample regions of graphene, one of the key problems is segmentation between the structure of interest and unwanted structures such as surface contaminant layers. In this study, we compare the performance of a conventional Bragg filtering method with a deep learning routine based on the U-Net architecture. We show that the deep learning method is more general, simpler to apply in practice, and produces more accurate and robust results than the conventional algorithm. We provide easily adaptable source code for all results in this paper and discuss potential applications for deep learning in fully automated TEM image analysis.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Modeling Liquid Water by Climbing up Jacob’s Ladder in Density Functional Theory Facilitated by Using Deep Neural Network Potentials

Within the framework of Kohn–Sham density functional theory (DFT), the ability to provide good predictions of water properties by employing a strongly constrained and appropriately normed (SCAN) functional has been extensively demonstrated in recent years. Here, we further advance the modeling of water by building a more accurate model on the fourth rung of Jacob’s ladder with the hybrid functional, SCAN0. In particular, we carry out both classical and Feynman path-integral molecular dynamics calculations of water with the SCAN0 functional and the isobaric–isothermal ensemble. To generate the equilibrated structure of water, a deep neural network potential is trained from the atomic potential energy surface based on ab initio data obtained from SCAN0 DFT calculations. For the electronic properties of water, a separate deep neural network potential is trained by using the Deep Wannier method based on the maximally localized Wannier functions of the equilibrated trajectory at the SCAN0 level. The structural, dynamic, and electric properties of water were analyzed. The hydrogen-bond structures, density, infrared spectra, diffusion coefficients, and dielectric constants of water, in the electronic ground state, are computed by using a large simulation box and long simulation time. For the properties involving electronic excitations, we apply the GW approximation within many-body perturbation theory to calculate the quasiparticle density of states and bandgap of water. Compared to the SCAN functional, mixing exact exchange mitigates the self-interaction error in the meta-generalized-gradient approximation and further softens liquid water toward the experimental direction. For most of the water properties, the SCAN0 functional shows a systematic improvement over the SCAN functional. However, some important discrepancies remain. The H-bond network predicted by the SCAN0 functional is still slightly overstructured compared to the experimental results.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2017

Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations

Recent advances in scanning transmission electron and scanning probe microscopies have opened unprecedented opportunities in probing the materials structural parameters and various functional properties in real space with an angstrom-level precision. This progress has been accompanied by exponential increase in the size and quality of datasets produced by microscopic and spectroscopic experimental techniques. These developments necessitate adequate methods for extracting relevant physical and chemical information from the large datasets, for which a priori information on the structures of various atomic configurations and lattice defects is limited or absent. Here we demonstrate an application of deep neural networks to extracting information from atomically resolved images including location of the atomic species and type of defects. We develop a “weakly-supervised” approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set. We further apply our approach to interpret complex atomic and defect transformation, including switching between different coordination of silicon dopants in graphene as a function of time, formation of peculiar silicon dimer with mixed 3-fold and 4-fold coordination, and the motion of molecular “rotor”. In conclusion, this deep learning based approach resembles logic of a human operator, but can be scaled leading to significant shift in the way of extracting and analyzing information from raw experimental data.

36 MATERIALS SCIENCE↗
DOE OSTI2018

Argo Observations of the Deep Mixing Band in the Southern Ocean: A Salinity Modeling Challenge

The Southern Ocean plays an important role in mediating oceanic uptake of CO 2 and heat due to a strong meridional overturning circulation. Gridded Argo float data for 2004–2017 were used to evaluate subsurface processes at the mixed layer depth (MLD) that occur in a narrow deep mixing band. Shifts in the value of the Turner Angle at the MLD indicate that early in the season the MLD deepens slowly as it encounters and is stabilized by a subsurface salt maximum. By September mixing has penetrated this salinity feature and the rate of deepening is faster once the MLD is deeper than the depth where the maximum salinity occurs (~150–200 m). This distinctive salinity layer is the result of surface Ekman transport of fresh water from the south and subsurface advection of high-salinity water from the north. Two configurations of the Community Earth System Model (CESM) ocean-ice forced hindcast experiments—one with 1° and the other with 0.1° horizontal resolution (Parallel Ocean Program low and high resolutions [POP-LR and POP-HR], respectively)—are compared with the Argo data for 2005–2009. POP-LR has a shallow MLD bias common to many Fifth Coupled Models Intercomparison Project (CMIP5) models, while POP-HR has a mix of deep and shallow MLD biases. While both models were able to replicate the large-scale processes leading to formation of a high-salinity layer, the salinity feature in POP-HR is too strong and deep. Neither model was able to replicate the vertical mixing processes leading to penetration of the subsurface salt maximum.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Deep Learning Emulation of Subgrid-Scale Processes in Turbulent Shear Flows

Deep neural networks (DNNs) are developed from a data set obtained from the dynamic Smagorinsky model to emulate the subgrid-scale (SGS) viscosity (ν sgs ) and diffusivity (κ sgs ) for turbulent stratified shear flows encountered in the oceans and the atmosphere. These DNNs predict ν sgs and κ sgs from velocities, strain rates, and density gradients such that the evolution of the kinetic energy budget and density variance budget terms is similar to the corresponding values obtained from the original dynamic Smagorinsky model. These DNNs also compute ν sgs and κ sgs ~2–4 times quicker than the dynamic Smagorinsky model resulting in a ~2–2.5 times acceleration of the entire simulation. This study demonstrates the feasibility of deep learning in emulating the subgrid-scale (SGS) phenomenon in geophysical flows accurately in a cost-effective manner. In a broader perspective, deep learning-based surrogate models can present a promising alternative to the traditional parameterizations of the subgrid-scale processes in climate models.

58 GEOSCIENCES↗
DOE OSTI2021

Upscaling Reactive Transport and Clogging in Shale Microcracks by Deep Learning

Fracture networks in shales exhibit multiscale features. A rock system may contain a few main fractures and thousands of microcracks, whose length and aperture are orders of magnitude smaller than the former. It is computationally prohibitive to resolve all the fractures explicitly for such multiscale fracture networks. One traditional approach is to model the small-scale features (e.g., microcracks in shales) as an effective medium. Although this fracture-matrix conceptualization significantly reduces the problem complexity, there are classes of physical processes that cannot be accurately upscaled by effective medium approximations, e.g., microcrack clogging during mineral reactions. Here, we employ deep learning in place of effective medium theory to upscale physical processes in small-scale features. Specifically, we consider reactive transport in a fracture-microcrack network where microcracks can be clogged by precipitation. A deep learning multiscale algorithm is developed, in which the microcracks are upscaled as a wall boundary condition of the main fractures. The wall boundary condition is constructed by recurrent neural networks, which take concentration histories as input and predict the solute transport from main fractures to microcracks. The deep learning multiscale algorithm is firstly employed in specific scenarios, then a general model is developed which can work under various conditions. The new approach is validated against fully resolved simulations and an analytical solution, providing a reliable and efficient solution for problems that cannot be upscaled by effective medium models.

58 GEOSCIENCES↗
DOE OSTI2025

Environmental Influences on Deep Convective Upscale Growth Rate in Central Argentina From a Convection‐Permitting Simulation

This study uses a convection‐permitting model simulation to describe the environmental conditions under which convective upscale growth occurs in central Argentina, particularly examining environmental parameters when deep convection initially forms that could differentiate the rate of initial upscale growth. Simulated mesoscale convective systems (MCSs) are separated into slow and rapid growth by the rate of spatial growth from convection initiation until reaching the MCS scale. A low‐level jet (LLJ) is found more frequently near the deep convection that experiences rapid growth to an MCS, but its presence alone is not predictive of rapid growth. Using spatially‐averaged parameters, we find that rapid growth to MCSs also occurs in environments that are significantly more thermodynamically favorable with greater low‐level moisture and instability. Fewer significant differences are found in the kinematic environment with only the 0–2 km vertical wind shear magnitude being significantly larger for rapid growth MCSs compared to slow growth MCSs, potentially related to LLJs often peaking near this height. When focusing only on MCSs with the slowest and fastest growth rates, elevated‐layer shear is significantly smaller for very rapid growth MCSs, suggesting elevated‐layer shear may help discriminate between the upper and lower bounds of growth rate. Finally, when upscale growth occurs near the Sierras de Córdoba (SDC) with a LLJ present, rapid growth is also supported by favorable wind shear orientation. However, this does not hold for upscale growth occurring away from the SDC, highlighting the importance of interpreting shear direction relative to the orientation of features initiating deep convection.

Sasaki, Clayton R. S. [Univ. of Washington, Seattl↗
DOE OSTI2016

Microbial metabolisms in a 2.5-km-deep ecosystem created by hydraulic fracturing in shales

Hydraulic fracturing is the industry standard for extracting hydrocarbons from shale formations. Attention has been paid to the economic benefits and environmental impacts of this process, yet the biogeochemical changes induced in the deep subsurface are poorly understood. Recent single-gene investigations revealed that halotolerant microbial communities were enriched after hydraulic fracturing. Here the reconstruction of 31 unique genomes coupled to metabolite data from the Marcellus and Utica shales revealed that methylamine cycling supports methanogenesis in the deep biosphere. Fermentation of injected chemical additives also sustains long-term microbial persistence, while sulfide generation from thiosulfate represents a poorly recognized corrosion mechanism in shales. Extensive links between viruses and microbial hosts demonstrate active viral predation, which may contribute to the release of labile cellular constituents into the extracellular environment. Our analyses show that hydraulic fracturing provides the organismal and chemical inputs for colonization and persistence in the deep terrestrial subsurface.

Environmental Molecular Sciences Laboratory↗
DOE OSTI2019

An archaeal symbiont-host association from the deep terrestrial subsurface

DPANN archaea have reduced metabolic capacities and are diverse and abundant in deep aquifer ecosystems, but little is known about their interactions with other microorganisms that reside there. In this work, we offer evidence for an archaeal host-symbiont association from a deep aquifer system at the Colorado Plateau (Utah, USA). The symbiont, Candidatus Huberiarchaeum crystalense , and its host, Ca. Altiarchaeum hamiconexum , show a highly significant co-occurrence pattern over 65 metagenome samples collected over six years. The physical association of the two organisms was confirmed with genome-informed fluorescence in situ hybridization depicting small cocci of Ca. H. crystalense attached to Ca. A. hamiconexum cells. Based on genomic information, Ca. H. crystalense potentially scavenges vitamins, sugars, nucleotides, and reduced redox-equivalents from its host and thus has a similar metabolism as Nanoarchaeum equitans . These findings give insight into host-symbiont interactions among members of two uncultivated archaeal phyla that thrive in a deep subsurface aquifer.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Active sulfur cycling in the terrestrial deep subsurface

The deep terrestrial subsurface remains an environment where there is limited understanding of the extant microbial metabolisms. At Olkiluoto, Finland, a deep geological repository is under construction for the final storage of spent nuclear fuel. It is therefore critical to evaluate the potential impact microbial metabolism, including sulfide generation, could have upon the safety of the repository. As such, we investigated a deep groundwater where sulfate is present, but groundwater geochemistry suggests limited microbial sulfate-reducing activity. Examination of the microbial community at the genome-level revealed microorganisms with the metabolic capacity for both oxidative and reductive sulfur transformations. Deltaproteobacteria are shown to have the genetic capacity for sulfate reduction and possibly sulfur disproportionation, while Rhizobiaceae, Rhodocyclaceae, Sideroxydans, and Sulfurimonas oxidize reduced sulfur compounds. Further examination of the proteome confirmed an active sulfur cycle, serving for microbial energy generation and growth. Our results reveal that this sulfide-poor groundwater harbors an active microbial community of sulfate-reducing and sulfide-oxidizing bacteria, together mediating a sulfur cycle that remained undetected by geochemical monitoring alone. The ability of sulfide-oxidizing bacteria to limit the accumulation of sulfide was further demonstrated in groundwater incubations and highlights a potential sink for sulfide that could be beneficial for geological repository safety.

58 GEOSCIENCES↗
DOE OSTI2020

A deep learning approach to programmable RNA switches

Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these synthetic biology components remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Here, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesize and characterize in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperform (R 2 = 0.43–0.70) previous state-of-the-art thermodynamic and kinetic models (R 2 = 0.04–0.15) and allow for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This work shows that deep learning approaches can be used for functionality predictions and insight generation in RNA synthetic biology.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Chemical trends of deep levels in van der Waals semiconductors

Abstract Properties of semiconductors are largely defined by crystal imperfections including native defects. Van der Waals (vdW) semiconductors, a newly emerged class of materials, are no exception: defects exist even in the purest materials and strongly affect their electrical, optical, magnetic, catalytic and sensing properties. However, unlike conventional semiconductors where energy levels of defects are well documented, they are experimentally unknown in even the best studied vdW semiconductors, impeding the understanding and utilization of these materials. Here, we directly evaluate deep levels and their chemical trends in the bandgap of MoS 2 , WS 2 and their alloys by transient spectroscopic study. One of the deep levels is found to follow the conduction band minimum of each host, attributed to the native sulfur vacancy. A switchable, DX center - like deep level has also been identified, whose energy lines up instead on a fixed level across different hosts, explaining a persistent photoconductivity above 400 K.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Energy efficiency and biological interactions define the core microbiome of deep oligotrophic groundwater

While oligotrophic deep groundwaters host active microbes attuned to the low-end of the bioenergetics spectrum, the ecological constraints on microbial niches in these ecosystems and their consequences for microbiome convergence are unknown. Here, we provide a genome-resolved, integrated omics analysis comparing archaeal and bacterial communities in disconnected fracture fluids of the Fennoscandian Shield in Europe. Leveraging a dataset that combines metagenomes, single cell genomes, and metatranscriptomes, we show that groundwaters flowing in similar lithologies offer fixed niches that are occupied by a common core microbiome. Functional expression analysis highlights that these deep groundwater ecosystems foster diverse, yet cooperative communities adapted to this setting. We suggest that these communities stimulate cooperation by expression of functions related to ecological traits, such as aggregate or biofilm formation, while alleviating the burden on microorganisms producing compounds or functions that provide a collective benefit by facilitating reciprocal promiscuous metabolic partnerships with other members of the community. We hypothesize that an episodic lifestyle enabled by reversible bacteriostatic functions ensures the subsistence of the oligotrophic deep groundwater microbiome.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Understanding important features of deep learning models for segmentation of high-resolution transmission electron microscopy images

Cutting edge deep learning techniques allow for image segmentation with great speed and accuracy. However, application to problems in materials science is often difficult since these complex models may have difficultly learning meaningful image features that would enable extension to new datasets. In situ electron microscopy provides a clear platform for utilizing automated image analysis. In this work, we consider the case of studying coarsening dynamics in supported nanoparticles, which is important for understanding, for example, the degradation of industrial catalysts. By systematically studying dataset preparation, neural network architecture, and accuracy evaluation, we describe important considerations in applying deep learning to physical applications, where generalizable and convincing models are required. With a focus on unique challenges that arise in high-resolution images, we propose methods for optimizing performance of image segmentation using convolutional neural networks, critically examining the application of complex deep learning models in favor of motivating intentional process design.

36 MATERIALS SCIENCE↗