Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “GAN”

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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Super Resolution for Renewable Energy Resource Data With Wind From Reanalysis Data (Sup3rWind) and Application to Ukraine [Slides]

In this work we present a novel deep learning-based downscaling method, using generative adversarial networks (GANs), for generating high-resolution wind resource data from ECMWF Reanalysis v5 data (ERA5). We show that by training a GAN model on ERA5, as opposed to coarsened high-resolution data, we achieve results that are competitive with conventional dynamical downscaling. This GAN-based downscaling method additionally reduces computational costs over dynamical downscaling by two orders of magnitude. All GANs are trained on data sampled from CONUS, selected to provide a diverse sampling of terrain conditions, and validated on observational data along with data held out from training. This cross-validation shows low error and high correlations with observations and excellent agreement with hold out data across physical distributions. Our approach is finally used to downscale 30km hourly ERA5 to 2-km 5-minute wind data, for January 2000 through December 2023, at multiple hub heights, over Ukraine, Moldova, and part of Romania. Comparisons against observational data from Meteorological Assimilation Data Ingest System (MADIS) and multiple wind farms show the same level of performance as for CONUS validation. This 24 year data record is the first member of the "super resolution for renewable energy resource data with wind from reanalysis data" dataset (Sup3rWind).

17 WIND ENERGY↗
NASA NTRS2008

Schottky barrier diode and method thereof

Pt/n.sup.-GaN Schottky barrier diodes are disclosed that are particularly suited to serve as ultra-violet sensors operating at wavelengths below 200 nm. The Pt/n.sup.-GaN Schottky barrier diodes have very large active areas, up to 1 cm.sup.2, which exhibit extremely low leakage current at low reverse biases. Very large area Pt/n.sup.-GaN Schottky diodes of sizes 0.25 cm.sup.2 and 1 cm.sup.2 have been fabricated from n.sup.-/n.sup.+ GaN epitaxial layers grown by vapor phase epitaxy on single crystal c-plane sapphire, which showed leakage currents of 14 pA and 2.7 nA, respectively for the 0.25 cm.sup.2 and 1 cm.sup.2 diodes both configured at a 0.5V reverse bias.

Aslam, Shahid↗
NASA NTRS2021

Semantic Segmentation of High-Resolution Satellite Imagery using Generative Adversarial Networks with Progressive Growing

With increase in urbanization and Earth Sciences research into urban areas, the need to quickly and accurately segment urban rooftop maps has never been greater. Cur-rent machine learning techniques struggle to produce high accuracy maps in dense urban zones where there is high image noise and foot print overlap. In this paper, we evaluate a training methodology for pixel-wise segmentation for high resolution satellite imagery using progressive growing of generative adversarial networks as a solution. We apply our model to segmenting building rooftops and compare these results to conventional methods for rooftop segmentation. We evaluate our approach using the SpaceNet version 2 and xView datasets. Our experiments show that for SpaceNet, progressive Generative Adversarial Network (GAN) training achieved a test accuracy of 93% compared to 89% for traditional GAN training and 87% for U-Net architecture, while for xView, we achieved 71% accuracy using progressive GAN training compared to 69% through traditional GAN training and 65% using U-Net.

Semantic↗
DOE OSTI2020

Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks

Climate models encapsulate our best understanding of the Earth system, allowing research to be conducted on its future under alternative assumptions of how human-driven climate forces are going to evolve. An important application of climate models is to provide metrics of mean and extreme climate changes, particularly under these alternative future scenarios, as these quantities drive the impacts of climate on society and natural systems. Because of the need to explore a wide range of alternative scenarios and other sources of uncertainties in a computationally efficient manner, climate models can only take us so far, as they require significant computational resources, especially when attempting to characterize extreme events, which are rare and thus demand long and numerous simulations in order to accurately represent their changing statistics. Here we use deep learning in a proof of concept that lays the foundation for emulating global climate model output for different scenarios. We train two "loosely conditioned" Generative Adversarial Networks (GANs) that emulate daily precipitation output from a fully coupled Earth system model: one GAN modeling Fall-Winter behavior and the other Spring-Summer. Our GANs are trained to produce spatiotemporal samples: 32 days of precipitation over a 64x128 regular grid discretizing the globe. We evaluate the generator with a set of related performance metrics based upon KL divergence, and find the generated samples to be nearly as well matched to the test data as the validation data is to test. We also find the generated samples to accurately estimate the mean number of dry days and mean longest dry spell in the 32 day samples. Our trained GANs can rapidly generate numerous realizations at a vastly reduced computational expense, compared to large ensembles of climate models, which greatly aids in estimating the statistics of extreme events.

climate emulation, extreme climate, impacts, machi↗
DOE OSTI2021

All-MOCVD-grown gallium nitride diodes with ultra-low resistance tunnel junctions

In this work, we carefully investigate three important effects including postgrowth activation annealing, delta (δ) dose and magnesium (Mg) buildup delay as well as experimentally demonstrate their influence on the electrical properties of GaN homojunction p–n diodes with a tunnel junction (TJ). The diodes were monolithically grown by metalorganic chemical vapor deposition (MOCVD) in a single growth step. By optimizing the annealing parameters for Mg activation, δ-dose for both donors and acceptors at TJ interfaces, and p + -GaN layer thickness, a significant improvement in tunneling properties is achieved. For the TJs embedded within the continuously-grown, all-MOCVD GaN diode structures, ultra-low voltage penalties of 158 mV and 490 mV are obtained at current densities of 20 A cm –2 and 100 A cm –2 , respectively. The diodes with the engineered TJs show a record-low differential resistivity of 1.6 × 10 –4 Ω cm 2 at 5 kA cm –2 .

42 ENGINEERING↗
DOE OSTI2023

20 kV Gallium Nitride pn Diode Electro-Magnetic Pulse Arrestor for Grid Reliability (Final Scientific/Technical Report)

This project developed vertical Gallium Nitride (GaN) pn diodes under two main thrusts: (1) A focus on relatively higher-voltage devices for use as fast EMP arrestors to protect the electric grid; and (2) A focus on a Foundry effort to establish the manufacturability of relatively lower voltage devices. For the first thrust, the aim was to develop devices that go into avalanche breakdown to clamp the voltage across sensitive grid equipment subject to voltage transients induced by electromagnetic pulses (EMPs). Devices with breakdown voltages exceeding 6.5 kV were achieved, and breakdown times shorter than 1 ns were demonstrated, which is sufficiently fast to protect against the fast component of an EMP-induced signal. Key challenges included the epitaxial growth of thick (50 µm or more), low-doped (low 10 15 cm -3 range) GaN layers comprising the drift regions of the diodes, as well as the design and fabrication of edge termination structures (step-etched junction termination extensions) to prevent premature breakdown. Midway through the project, an additional emphasis was put on large-area, high-current devices, and forward currents of approximately 400 A were achieved in composite devices towards the end of the project. Experimental and theoretical studies of impact ionization and avalanche ruggedness were also conducted. For the second thrust (the Foundry), the focus was primarily on 1.2-kV-class devices, although towards the end of the project outstanding results on 3.3-kV class devices were also achieved. The aim of the Foundry was to develop a high-yield, reliable, and economic vertical GaN pn diode process. The Foundry conducted characterization of incoming epitaxial material and correlated this information with the yield and performance of fully processed devices. Wafer maps of diode characteristics such as forward and reverse current as well as capacitance-voltage curves were measured using auto-probing. Several mask sets comprising different-area devices as well as multiple edge termination designs (implanted junction termination extensions, guard rings, and combinations thereof) were studied, and machine-learning-based approaches were utilized to analyze the data. Packaging and reliability efforts were also undertaken for the Foundry diodes, which are necessary for a viable commercial process.

20KV↗
NASA NTRS1994

(abstract) Transmission Electron Microscopy of Al(sub x)Ga(sub 1-x)N/SiC Multilayer Structures Grown on Sapphire Substrates

The potential of wide-band-gap III-V nitrides as ultraviolet sensors and light emitters has prompted an increasing amount of work recently, including the fabrication of the first UV sensors from as-deposited single crystal GaN. We have used high resolution transmission electron microscopy (TEM) to study the microstructure of two novel developments of wide-band-gap III-V nitrides: the growth of ultra-short period GaN/AlN superlattices; and the incorporation of SiC layers into Al(sub x)Ga(sub 1-x)N structures. By varying the relative periods in a GaN/AlN superlattice, the band gap of the composite can be tailored to lie between the elemental values of 365 nm for GaN and 200 nm for AlN. The group IV semiconductor, SiC, has a wide band-gap and has a close lattice match (less than 3 %) to Al(sub x)Ga(sub 1-x)N for growth on the basal plane. Demonstration of epitaxial growth for Al(sub x)Ga(sub 1-x)N/SiC multilayers would introduce a wide band-gap analog to the already existing family of III-V and Si(sub 1-x)Ge(sub x) heteroepitaxial growth systems. Although good quality growth of GaN on SiC substrates has been demonstrated, Al(sub x)Ga(sub 1-x)N/SiC multilayer structures have never been grown and the interfacial structure is unknown.

GaN AlN GaN/AlN↗
DOE OSTI2022

Utilization of the Critic Subnetwork of a Generative Adversarial Network as Detector of Morphological Material Change in Image Data

The resolution of computed tomography (CT) has become high enough to monitor morphological changes due to aging in materials in long-term applications. For this work, we explored the utility of the critic of a generative adversarial network (GAN) to automatically detect such changes. The GAN was trained with images of pristine Pharmatose, which is used as a surrogate energetic material. It is important to note that images of the material with altered morphology were only used during the test phase. The GAN-generated images reproduced the microstructure of Pharmatose well, although some unrealistic particle fusion was seen. Calculated morphological metrics (volume fraction, interfacial line length, and local thickness) for the synthetic images also showed good agreement with the training data, albeit with signs of mode collapse in the interfacial line length. While the critic exposed changes in particle size, it showed limited ability to distinguish images by particle shape. The detection of shape differences was also a more challenging task for the selected morphological metrics that related to energetic material performance. We further tested the critic with images of aged Pharmatose. Subtle changes due to aging are difficult for the human analyst to detect; but both critic and morphological metrics analysis showed image differentiation.

36 MATERIALS SCIENCE↗
DOE OSTI2020

MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking

In the past few years, Generative Adversarial Networks (GANs) have dramatically advanced our ability to represent and parameterize high-dimensional, non-linear image manifolds. As a result, they have been widely adopted across a variety of applications, ranging from challenging inverse problems like image completion, to problems such as anomaly detection and adversarial defense. A recurring theme in many of these applications is the notion of projecting an image observation onto the manifold that is inferred by the generator. In this context, Projected Gradient Descent (PGD) has been the most popular approach, which essentially optimizes for a latent vector that minimizes the discrepancy between a generated image and the given observation. However, PGD is a brittle optimization technique that fails to identify the right projection (or latent vector) when the observation is corrupted, or perturbed even by a small amount. Such corruptions are common in the real world, for example images in the wild come with unknown crops, rotations, missing pixels, or other kinds of non-linear distributional shifts which break current encoding methods, rendering downstream applications unusable. To address this, we propose corruption mimicking—a new robust projection technique, that utilizes a surrogate network to approximate the unknown corruption directly at test time, without the need for additional supervision or data augmentation. The proposed method is significantly more robust than PGD and other competing methods under a wide variety of corruptions, thereby enabling a more effective use of GANs in real-world applications. Finally, more importantly, we show that our approach produces state-of-the-art performance in several GAN-based applications—anomaly detection, domain adaptation, and adversarial defense, that benefit from an accurate projection.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Distinctive features of structural evolution and thermodynamic response in wide-bandgap semiconductors driven by intense electronic excitation

Radiation-tolerant material selection requires balancing lattice rigidity, defect dynamics, and electronic stability, as shown by covalent SiC outperforming ionic Ga 2 O 3 and GaN under extreme environments. Responding to intense electronic excitation, irradiation-driven phase segregation (β → δ/κ in Ga 2 O 3 ) and core–shell track (disordered structure in GaN), accompanied by elemental redistribution, contrastingly, exceptional radiation tolerance manifested by comparatively minimal lattice distortion (0.17 % strain variation) was demonstrated in SiC. These differential responses are primarily attributed to two fundamental mechanisms: (i) thermodynamic driving forces governing defect migration and phase separation, and (ii) the synergistic effects of robust covalent bonding composition coupled with efficient defect recombination processes. Here, the stronger electron–phonon (e-ph) coupling in Ga 2 O 3 (4.34 × 1018 W m −3 K −1 ) and GaN (3.55 × 10 18 W m −3 K −1 ) enhances lattice energy deposition, triggering thermal spikes (ΔT ≫ T m ) and structural transition behaviors, whereas weaker e-ph coupling in SiC (3.69 × 10 18 W m −3 K −1 ), relatively high thermodynamic parameters and efficient energy dissipation suppress thermal spikes to maintaining lattice integrity. The photoresponse degradation driven by enhanced radiative recombination is dominant in N-doped SiC, while V-doped systems achieve defect-mediated photoconduction optimization characterized by abrupt current transitions, matching fluorescence yield evolutions, and directly connecting defect engineering to optoelectronic performance.

Intense electronic excitation↗
DOE OSTI2024

Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms

This study examines the effectiveness of generative models in drug discovery, material science, and polymer science, aiming to overcome constraints associated with traditional inverse design methods relying on heuristic rules. Generative models generate synthetic data resembling real data, enabling deep learning model training without extensive labeled datasets. They prove valuable in creating virtual libraries of molecules for material science and facilitating drug discovery by generating molecules with specific properties. While generative adversarial networks (GANs) are explored for these purposes, mode collapse restricts their efficacy, limiting novel structure variability. To address this, we introduce a masked language model (LM) inspired by natural language processing. Although LMs alone can have inherent limitations, we propose a hybrid architecture combining LMs and GANs to efficiently generate new molecules, demonstrating superior performance over standalone masked LMs, particularly for smaller population sizes. This hybrid LM-GAN architecture enhances efficiency in optimizing properties and generating novel samples.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Facet-selective morphology-controlled remote epitaxy of ZnO microcrystals via wet chemical synthesis

We report on morphology-controlled remote epitaxy via hydrothermal growth of ZnO micro- and nanostructure crystals on graphene-coated GaN substrate. The morphology control is achieved to grow diverse morphologies of ZnO from nanowire to microdisk by changing additives of wet chemical solution at a fixed nutrient concentration. Although the growth of ZnO is carried out on poly-domain graphene-coated GaN substrate, the direction of hexagonal sidewall facet of ZnO is homogeneous over the whole ZnO-grown area on graphene/GaN because of strong remote epitaxial relation between ZnO and GaN across graphene. Atomic-resolution transmission electron microscopy corroborates the remote epitaxial relation. The non-covalent interface is applied to mechanically lift off the overlayer of ZnO crystals via a thermal release tape. The mechanism of facet-selective morphology control of ZnO is discussed in terms of electrostatic interaction between nutrient solution and facet surface passivated with functional groups derived from the chemical additives.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Structural differences between human and mouse neurons and their implementation in generative AIs

Mouse and human brains have different functions that depend on their neuronal networks. We analyzed nanometer-scale three-dimensional structures of brain tissues of the mouse medial prefrontal cortex and compared them with structures of the human anterior cingulate cortex. The obtained results indicated that mouse neuronal somata are smaller and neurites are thinner than those of human neurons. We implemented these characteristics of mouse neurons in convolutional layers of a generative adversarial network (GAN) and a denoising diffusion implicit model (DDIM), which were then subjected to image generation tasks using photo datasets of cat faces, cheese, human faces, birds, and automobiles. The mouse-mimetic GAN outperformed a standard GAN in the image generation task using the cat faces and cheese photo datasets, but underperformed for human faces and birds. The mouse-mimetic DDIM gave similar results, suggesting that the nature of the datasets affected the results. Analyses of the five datasets indicated differences in their image entropy, which should influence the number of parameters required for image generation. The preferences of the mouse-mimetic AIs coincided with the impressions commonly associated with mice. The relationship between the neuronal network and brain function should be investigated by implementing other biological findings in artificial neural networks.

generative AI↗
DOE OSTI2022

Surmounting the interband threshold limit by the hot electron excitation of multi-metallic plasmonic AgAuCu NPs for UV photodetector application

We report multi-metallic alloy NPs composed of various elemental compositions can surmount the interband threshold limit of mono-metallic NPs and thus can offer a promising route to boost up the performance limit of conventional ultraviolet photodetectors (PDs). In this work, a hybrid UV-PD configuration has been demonstrated by combining the multi-metallic plasmonic alloy NPs of AgCu, AuCu, and AgAuCu on a GaN photoactive layer in order to exploit the improved photo carrier injection by the strong hot electrons and LSPR. Among various devices, the tri-metallic AgAuCu NP PD demonstrates the highest performance with a remarkably high photocurrent of 1.47 x 10 -2 A at 1 V with fast rise (T r ) and fall (T f ) times of 170 and 700 ms with a very stable current. This leads to the superior figure-of-merit parameters of the PD with a photoresponsivity of 4.3 x 10 6 mA W-1, detectivity of 3.52 x 10 12 Jones and EQE of 1.39 x 10 6 %, which is ~16 times higher than the bare GaN PD. This ranks the AgAuCu PD as one of the best GaN based UV photodetectors. The photocurrent enhancement and excellent figure-of-merit can be attributed to the significantly increased photo carrier injection by the efficient hot electron generation via the LSPR and improved interfacial barrier characteristics by the tri-metallic elemental synergy.

36 MATERIALS SCIENCE↗
DOE OSTI2024

SPIDARman: System-Level Physics-Informed Detection of Anomalies in Reactor Collected Data Considering Human Errors

In nuclear power plants (NPPs), anomalies arising from sensors or human errors (HEs) can undermine the performance and reliability of plant operations. Anomaly detection models can be employed to detect sensor errors and HEs. Additionally, physics-informed machine learning models can utilize the known physics of the system, as described by mathematical equations, to ensure that sensor values are consistent with physical laws. Hence, we propose SPIDARman: System-level Physics-Informed Detection of Anomalies in Reactor Collected Data Considering Human Errors, a holistic physics-informed anomaly detection approach based on generative adversarial networks (GANs) to detect anomalies in both automatically collected sensor data and manually collected surveillance data. Here we test our approach on data collected from a flow loop testbed, showcasing its potential to detect anomalies. Results demonstrate that the proposed model performs better than the baseline GAN-based models in detecting sensor and surveillance anomalies, suggesting the potential of physics-informed anomaly detection GAN models in NPPs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Influence of electrical field on the susceptibility of gallium nitride transistors to proton irradiation

Radiation susceptibility of electronic devices is commonly studied as a function of radiation energetics and device physics. Often overlooked is the presence or magnitude of the electrical field, which we hypothesize to play an influential role in low energy radiation. Accordingly, we present a comprehensive study of low-energy proton irradiation on gallium nitride high electron mobility transistors (HEMTs), turning the transistor ON or OFF during irradiation. Commercially available GaN HEMTs were exposed to 300 keV proton irradiation at fluences varying from 3.76 × 10 12 to 3.76 × 10 14 cm 2 , and the electrical performance was evaluated in terms of forward saturation current, transconductance, and threshold voltage. The results demonstrate that the presence of an electrical field makes it more susceptible to proton irradiation. The decrease of 12.4% in forward saturation and 19% in transconductance at the lowest fluence in ON mode suggests that both carrier density and mobility are reduced after irradiation. Additionally, a positive shift in threshold voltage (0.32 V and 0.09 V in ON and OFF mode, respectively) indicates the generation of acceptor-like traps due to proton bombardment. high-resolution transmission electron microscopy and energy dispersive x-ray spectroscopy analysis reveal significant defects introduction and atom intermixing near AlGaN/GaN interfaces and within the GaN layer after the highest irradiation dose employed in this study. According to in-situ Raman spectroscopy, defects caused by irradiation can lead to a rise in self-heating and a considerable increase in (∼750 times) thermoelastic stress in the GaN layer during device operation. The findings indicate device engineering or electrical biasing protocol must be employed to compensate for radiation-induced defects formed during proton irradiation to improve device durability and reliability.

gallium nitride↗
DOE OSTI2020

DCTRGAN: improving the precision of generative models with reweighting

Significant advances in deep learning have led to more widely used and precise neural network-based generative models such as Generative Adversarial Networks (Gans). We introduce a post-hoc correction to deep generative models to further improve their fidelity, based on the Deep neural networks using the Classification for Tuning and Reweighting (Dctr) protocol. The correction takes the form of a reweighting function that can be applied to generated examples when making predictions from the simulation. We illustrate this approach using Gans trained on standard multimodal probability densities as well as calorimeter simulations from high energy physics. We show that the weighted Gan examples significantly improve the accuracy of the generated samples without a large loss in statistical power. This approach could be applied to any generative model and is a promising refinement method for high energy physics applications and beyond.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Geometrical-Based Generative Adversarial Network to Enhance Digital Rock Image Quality

X-ray microcomputed tomography (micro-CT) is a common tool for the study of porous media structures and properties. High-quality micro-CT data are required to accurately capture pore structures. Acquiring high-quality micro-CT data, however, is not always possible, owing to application limitations and experimental constraints. Therefore, we propose a geometrical-based generative adversarial network (GAN) to rapidly restore noisy micro-CT images to their clean counterparts. The training data and related ground-truth (GT) data are scanned for 7 min and 9.5 h, respectively. To evaluate the performance of the geometrical-based GAN, a 6003 voxel image that has never been used for training is reconstructed and compared with the corresponding GT image. Histogram matching and linear normalization are implemented to adjust the histogram of the reconstructed image to that of the GT image. A watershed-based segmentation method is then applied to delineate pore and solid phases. Lastly, we measure the Minkowski functionals and petrophysical properties, including absolute permeability, pore size distribution, drainage capillary pressure-saturation curve, and imbibition relative permeability, to estimate the physical accuracy of the denoised image. The results show that the proposed geometrical-based GAN can accurately restore noisy micro-CT data. By reducing the scanning time from 9.5 h to 7 min, the expenditure of collecting micro-CT can be decreased significantly. This is particularly important for applications where time-lapse images of a dynamic process are required, high-throughput imaging is necessary for real-time data analysis, or where the quantification of large sample volumes is required.

58 GEOSCIENCES↗