SEARCH · Engineering Papers

Results for “image generation”

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.

SourceResearch connectionFrom yearThrough year

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

At least 271 records · Page 15

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Concept Lens: Visual Comparison and Evaluation of Generative Model Manipulations

Generative models are becoming a transformative technology for the creation and editing of images. However, it remains challenging to harness these models for precise image manipulation. These challenges often manifest as inconsistency in the editing process, where both the type and amount of semantic change, depend on the image being manipulated. Moreover, there exist many methods for computing image manipulations, whose development is hindered by the matter of inconsistency. This paper aims to address these challenges by improving how we evaluate, compare, and explore the space of manipulations offered by a generative model. We present Concept Lens, a visual interface that is designed to aid users in understanding semantic concepts carried in image manipulations, and how these manipulations vary over generated images. Given the large space of possible images produced by a generative model, Concept Lens is designed to support the exploration of both generated images, and their manipulations, at multiple levels of detail. To this end, the layout of Concept Lens is informed by two hierarchies: a hierarchical organization of (1) original images, grouped by their similarities, and (2) image manipulations, where manipulations that induce similar changes are grouped together. This layout allows one to discover the types of images that consistently respond to a group of manipulations, and vice versa, manipulations that consistently respond to a group of codes. We show the benefits of this design across multiple use cases, specifically, studying the quality of manipulations for a single method, and offering a means of comparing different methods.

clustering↗

DOE OSTI2024

Wavefront distortion correction in scanning tunneling microscope image

Here, we report an algorithm to identify and correct distorted wavefronts in atomic resolution scanning tunneling microscope images. This algorithm can be used to correct nonlinear in-plane distortions without prior knowledge of the physical scanning parameters, the characteristics of the piezoelectric actuator, or individual atom positions. The 2D image is first defined as a sum of sinusoidal plane waves, where a nonlinear distortion renders a curve for an otherwise ideal linear wavefront. Using the Fourier transforms of local areas of the image, the algorithm generates a wavefront vector field. The identified wavefronts are subsequently linearized for each plane wave without changing lattice orders, giving rise to distortion corrections. Our algorithm is complementary to conventional post-processing algorithms that require prior detection of real space features, which can also be used to correct nonlinear distortions in 2D images acquired by other microscopy techniques.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Hyperspectral acquisition with ScanImage at the single pixel level: application to time domain coherent Raman imaging

We present a comprehensive strategy and its practical implementation using the commercial ScanImage software platform to perform hyperspectral point scanning microscopy when a fast time-dependent signal varies at each pixel level. In the proposed acquisition scheme, the scan along the X-axis is slowed down while the data acquisition is maintained at a high pace to enable the rapid acquisition of the time-dependent signal at each pixel level. The ScanImage generated raw 2D images have a very asymmetric aspect ratio between X and Y, the X axis encoding both for space and time acquisition. The results are X-axis macro-pixel where the associated time-dependent signal is sampled to provide hyperspectral information. We exemplified the proposed hyperspectral scheme in the context of time-domain coherent Raman imaging, where a pump pulse impulsively excites molecular vibrations that are subsequently probed by a time-delayed probe pulse. In this case, the time-dependent signal is a fast acousto-optics delay line that can scan a delay of 4.5ps in 25 μ s at each pixel level. With this acquisition scheme, we demonstrate ultra-fast hyperspectral vibrational imaging in the low frequency range [10 cm −1 , 150 cm −1 ] over a 500 μm field of view (64 x 64 pixels) in 130ms (∼ 7.5 frames/s). The proposed acquisition scheme can be readily extended to other applications requiring the acquisition of a fast-evolving signal at each pixel level.

Metais, Samuel↗

DOE OSTI2022

Specifications of EBR-II Neutron Radiography Method Description and Digitization Approach

All neutron radiography (NRAD) images of fuel pins in Argonne’s collection were originally generated using the NRAD imaging facility established in the Hot Fuel Examination Facility (HFEF) at Idaho National Laboratory (INL). The NRAD reactor facility was built in 1977 and has been operating since. The reactor is a TRIGA-type reactor operating at a power level of 250 kWth to provide a neutron source for radiography imaging. The reactor is equipped with two beam tubes (i.e., east beam tube and north beam tube) to guide the neutron beams to two radiography stations. The east radiography station is directly under the HFEF main cell and is dedicated for specimens already in the HFEF hot cell. The north radiography station is outside of the main HFEF hot cell and allows NRAD imaging of non-irradiated items. The NRAD images of EBR-II irradiated metallic fuel pins were taken in the east radiography station. Thermal neutrons have the capability to transmit through most materials and are ideal for NRAD imaging. However, because of their high thermal neutron absorption cross-section, fissile materials (e.g., highly-enriched nuclear fuels) may not be as transmissible to thermal neutrons. This is also the case for oversize specimens with extraneous thickness. Epithermal neutron imaging is therefore used as a complement to thermal neutron NRAD imaging. At HFEF’s NRAD facility, both thermal and epithermal neutrons can be used for NRAD imaging. Irradiated nuclear fuels emit high levels of γ radiation that can easily darken X-ray films, so direct exposure NRAD cannot be used to image them. Instead, an indirect NRAD imaging method was developed at HFEF’s NRAD facility. In this method, foils made of materials that can be activated by neutrons (i.e., with large neutron absorption cross section) are used to collect transmitted neutron signals. Then the activated foils are then placed against X-ray films and enclosed in a vacuum cassette so that the γ decay from the activated foils can produce images on the X-ray films. Then, general X-ray film processing procedures are used to digitize and store the images. By using different foil materials, different energy neutrons can be used for NRAD imaging. At the HFEF NRAD station, two types of films are commonly used: dysprosium (Dy) foils with thickness of 130 microns are used to capture thermal neutron signal, while indium (In) foils with thickness of 130 microns are used to capture epithermal neutron signal. A cadmium or gadolinium foil is put before the indium foil to work as a thermal neutron filter. The thermal and epithermal NRAD images can be taken simultaneously by using a Dy/Cd/In sandwiched foil combination. The typical NRAD exposure time is approximately 20 minutes. Then the exposed foils are transferred to film vacuum cassettes. The vacuum ensures that there is no gap between the foil and the film. The foil-to-film exposure time is at least three half-lives of the corresponding radioisotopes, which are 3 hours for In and 7.5 hours for Dy, respectively. Exposed films are processed using an automatic film processor to produce completed NRAD images.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2021

The role of chalcogen vacancies for atomic defect emission in MoS 2

For two-dimensional (2D) layered semiconductors, control over atomic defects and understanding of their electronic and optical functionality represent major challenges towards developing a mature semiconductor technology using such materials. Here, we correlate generation, optical spectroscopy, atomic resolution imaging, and ab initio theory of chalcogen vacancies in monolayer MoS 2 . Chalcogen vacancies are selectively generated by in-vacuo annealing, but also focused ion beam exposure. The defect generation rate, atomic imaging and the optical signatures support this claim. We discriminate the narrow linewidth photoluminescence signatures of vacancies, resulting predominantly from localized defect orbitals, from broad luminescence features in the same spectral range, resulting from adsorbates. Vacancies can be patterned with a precision below 10 nm by ion beams, show single photon emission, and open the possibility for advanced defect engineering of 2D semiconductors at the ultimate scale.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Lamb wave imaging with actuator network for damage quantification in aluminum plate structures

Lamb waves have been widely used for damage detection on plate-like structures. However, there are still considerable interests on quantifying damage with complex profile. In this article, quantification of complex damage in plate-like structures using a network of actuators and time-space Lamb wavefield is investigated. The actuator network inspection system is implemented with multiple PZT transducers for Lamb wave actuation in round robin pattern and scanning laser Doppler vibrometer for wavefield sensing. The PZT network is arranged in a way that the target area is fully enclosed and Lamb waves come to the damage from all directions. Waves induced by the damage are subsequently obtained through frequency-wavenumber filtering, using the experimentally acquired dispersion curves presented in the paper. The filtered waves from all wave actuators are then used to generate a synthetic image of the damage being inspected. Two cases of complex damage are evaluated on aluminum plates, mass loss with triangular profile and mass addition with a three-letter cluster profile. Our results show that the damages are not only detected but also their profiles are clearly outlined in the images. We believe the subject methods provide improved evaluation of damage profile for Lamb wavefield based damage quantification.

Materials Science↗

DOE OSTI2023

De novo design of protein structure and function with RFdiffusion

Abstract There has been considerable recent progress in designing new proteins using deep-learning methods 1–9 . Despite this progress, a general deep-learning framework for protein design that enables solution of a wide range of design challenges, including de novo binder design and design of higher-order symmetric architectures, has yet to be described. Diffusion models 10,11 have had considerable success in image and language generative modelling but limited success when applied to protein modelling, probably due to the complexity of protein backbone geometry and sequence–structure relationships. Here we show that by fine-tuning the RoseTTAFold structure prediction network on protein structure denoising tasks, we obtain a generative model of protein backbones that achieves outstanding performance on unconditional and topology-constrained protein monomer design, protein binder design, symmetric oligomer design, enzyme active site scaffolding and symmetric motif scaffolding for therapeutic and metal-binding protein design. We demonstrate the power and generality of the method, called RoseTTAFold diffusion (RFdiffusion), by experimentally characterizing the structures and functions of hundreds of designed symmetric assemblies, metal-binding proteins and protein binders. The accuracy of RFdiffusion is confirmed by the cryogenic electron microscopy structure of a designed binder in complex with influenza haemagglutinin that is nearly identical to the design model. In a manner analogous to networks that produce images from user-specified inputs, RFdiffusion enables the design of diverse functional proteins from simple molecular specifications.

Science & Technology - Other Topics↗

DOE OSTI2020

Laser-driven x-ray and proton micro-source and application to simultaneous single-shot bi-modal radiographic imaging

Radiographic imaging with x-rays and protons is an omnipresent tool in basic research and applications in industry, material science and medical diagnostics. The information contained in both modalities can often be valuable in principle, but difficult to access simultaneously. Laser-driven solid-density plasma-sources deliver both kinds of radiation, but mostly single modalities have been explored for applications. Their potential for bi-modal radiographic imaging has never been fully realized, due to problems in generating appropriate sources and separating image modalities. Here, we report on the generation of proton and x-ray micro-sources in laser-plasma interactions of the focused Texas Petawatt laser with solid-density, micrometer-sized tungsten needles. We apply them for bi-modal radiographic imaging of biological and technological objects in a single laser shot. Thereby, advantages of laser-driven sources could be enriched beyond their small footprint by embracing their additional unique properties, including the spectral bandwidth, small source size and multi-mode emission.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2021

Reconstructing porous media using generative flow networks

One area of intense scientific interest for the study of sandstones, carbonates, and shale at the pore scale is the use of limited image and petrophysical data to generate multiple realizations of a rock’s pore structure. Such images aid efforts to quantify uncertainty in petrophysical properties, including porosity–permeability transforms. We develop and evaluate a deep learning-based method to synthesize porous media volumes using a so-called generative flow model trained on x-ray microscope images of rock texture and pore structure. These models are optimized on a log-likelihood objective and they synthesize large and realistic three-dimensional images. Further, we demonstrate the rapid generation of sandstone image volumes that display realism as gauged by quantitative comparison of topological features using Minkowski functionals of porosity, specific surface area, and the Euler–Poincaré characteristic (i.e., pore connectivity). We also evaluate the single-phase permeability using Navier–Stokes and lattice Boltzmann methods and show that transport properties of the generated samples match measured trends.

58 GEOSCIENCES↗

DOE OSTI2024

Resolving the Electron Plume within a Scanning Electron Microscope

Scanning electron microscopy (SEM), a century-old technique, is today a ubiquitous method of imaging the surface of nanostructures. However, most SEM detectors simply count the number of secondary electrons from a material of interest, and thereby overlook the rich material information contained within them. Here, by simple modifications to a standard SEM tool, we resolve the momentum and energy information on secondary electrons by directly imaging the electron plume generated by the electron beam of the SEM. Leveraging these spectroscopic imaging capabilities, our technique is able to image lateral electric fields across a prototypical silicon p–n junctions and to distinguish differently doped regions, even when buried beyond depths typically accessible by SEM. Intriguingly, the subsurface sensitivity of this technique reveals unexpectedly strong surface band bending within nominally passivated semiconductor structures, providing useful insights for complex layered component designs, in which interfacial dynamics dictate device operation. Further, these capabilities for noninvasive, multimodal probing of complicated electronic components are crucial in today’s electronic manufacturing but is largely inaccessible even with sophisticated techniques. These results show that seemingly simple SEM can be extended to probe complex and useful material properties.

36 MATERIALS SCIENCE↗

DOE OSTI2021

Universal image representation based on a multimodal graph

A system for classifying a target image with segments having attributes is provided. The system generates a graph for the target image that includes vertices representing segments of the image and edges representing relationships between the connected vertices. For each vertex, the system generates a subgraph that includes the vertex as a home vertex and neighboring vertices representing segments of the target image within a neighborhood of the segment represented by the home vertex. The system applies an autoencoder to each subgraph to generate latent variables to represent the subgraph. The system applies a machine learning algorithm to a feature vector comprising a universal image representation of the target image that is derived from the generated latent variables of the subgraphs to generate a classification for the target image.

Bremer, Peer-Timo↗

DOE OSTI2023

Universal image representation based on a multimodal graph

Bremer, Peer-Timo↗

DOE OSTI2024

A Generative Model for Realistic Galaxy Cluster X-Ray Morphologies

Abstract The X-ray morphologies of clusters of galaxies display significant variations, reflecting their dynamical histories and the nonlinear dependence of X-ray emissivity on the density of the intracluster gas. Qualitative and quantitative assessments of X-ray morphology have long been considered a proxy for determining whether clusters are dynamically active or “relaxed.” Conversely, the use of circularly or elliptically symmetric models for cluster emission can be complicated by the variety of complex features realized in nature, spanning scales from megaparsecs down to the resolution limit of current X-ray observatories. In this work, we use mock X-ray images from simulated clusters from The Three Hundred project to define a basis set of cluster image features. We take advantage of the clusters’ approximate self-similarity to minimize the differences between images before encoding the remaining diversity through a distribution of high-order polynomial coefficients. Principal component analysis then provides an orthogonal basis for this distribution, corresponding to natural perturbations from an average model. This representation allows novel, realistically complex X-ray cluster images to be easily generated, and we provide code to do so. The approach provides a simple way to generate training data for cluster image analysis algorithms and could be straightforwardly adapted to generate clusters displaying specific types of features or selected by physical characteristics available in the original simulations.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

Connectivity-informed drainage network generation using deep convolution generative adversarial networks

Abstract Stochastic network modeling is often limited by high computational costs to generate a large number of networks enough for meaningful statistical evaluation. In this study, Deep Convolutional Generative Adversarial Networks (DCGANs) were applied to quickly reproduce drainage networks from the already generated network samples without repetitive long modeling of the stochastic network model, Gibb’s model. In particular, we developed a novel connectivity-informed method that converts the drainage network images to the directional information of flow on each node of the drainage network, and then transforms it into multiple binary layers where the connectivity constraints between nodes in the drainage network are stored. DCGANs trained with three different types of training samples were compared; (1) original drainage network images, (2) their corresponding directional information only, and (3) the connectivity-informed directional information. A comparison of generated images demonstrated that the novel connectivity-informed method outperformed the other two methods by training DCGANs more effectively and better reproducing accurate drainage networks due to its compact representation of the network complexity and connectivity. This work highlights that DCGANs can be applicable for high contrast images common in earth and material sciences where the network, fractures, and other high contrast features are important.

42 ENGINEERING↗

DOE OSTI2022

Integrating very-high-resolution UAS data and airborne imaging spectroscopy to map the fractional composition of Arctic plant functional types in Western Alaska

Widespread changes in vegetation cover and composition are driving strong impacts on Arctic ecosystem functioning and global climate feedbacks. An accurate characterization of tundra vegetation composition is required to understand how the Arctic will respond to future climate change. However, quantifying tundra vegetation composition over large areas is challenging as commonly-used satellite observations are too coarse, spatially and spectrally, to differentiate low-lying tundra vegetation types. Recent airborne and spaceborne imaging spectroscopy platforms provide better data to characterize vegetation composition. Yet, our ability to characterize vegetation composition with imaging spectroscopy remains largely unexplored in the Arctic, particularly due to a lack of ground observations needed to train and test classification models. To address this problem, we collected very-high-resolution (VHR, ~5 cm) unoccupied aerial system (UAS) imagery at three low-Arctic tundra sites located on the Seward Peninsula, western Alaska. In this paper, we examine the feasibility of integrating imagery from the UAS and the hyperspectral Airborne Visible/Infrared Imaging Spectrometer, Next Generation (AVIRIS-NG) airborne instrument to map the fractional composition of 12 key Arctic plant functional types (PFTs). To this end, we first mapped the 12 PFTs from our VHR UAS imagery using random forest classification. We then used these UAS-derived PFT maps as ground truth to develop partial least squares regression (PLSR) models to predict the fractional cover (FCover) of each PFT from AVIRIS-NG imagery. Further, we evaluated the performance of our PLSR models using reserved UAS samples, as well as by mapping PFT FCover and dominant PFT for large tundra landscapes. Our results show that 1) Arctic PFTs can be effectively mapped using VHR UAS imagery, with overall accuracy between 86% and 92%, 2) when the UAS mapped PFTs were used to inform PLSR scaling models, the FCover of the 12 PFTs could be effectively estimated from AVIRIS-NG imagery with a mean absolute error (MAE) <0.13, and 3) our PLSR models outperformed traditional, fully constrained least-squares (FCLS) linear mixture analysis and produced high-quality, spatially contiguous PFT FCover and PFT maps that captured vegetation spatial patterns with similar accuracy to those developed from UAS imagery. The developed PLSR models have the potential to be broadly applied for quantifying vegetation composition with AVIRIS-NG images to help monitor tundra vegetation dynamics and improve process-based modeling of tundra ecosystems.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Deep-learning based artificial intelligence tool for melt pools and defect segmentation

Accelerating fabrication of additively manufactured components with precise microstructures is important for quality and qualification of built parts, as well as for a fundamental understanding of process improvement. Accomplishing this requires fast and robust characterization of melt pool geometries and structural defects in images. This paper proposes a pragmatic approach based on implementation of deep learning models and self-consistent workflow that enable systematic segmentation of defects and melt pools in optical images. Deep learning is based on an image-to-image translation–conditional generative adversarial neural network architecture. An artificial intelligence (AI) tool based on this deep learning model enables fast and incrementally more accurate predictions of the prevalent geometric features, including melt pool boundaries and printing-induced structural defects. We present statistical analysis of geometric features that is enabled by the AI tool, showing strong spatial correlation of defects and the melt pool boundaries. The correlations of widths and heights of melt pools with dataset processing parameters show the highest sensitivity to thermal influences resulting from laser passes in adjacent and subsequent layer passes. The presented models and tools are demonstrated on the aluminum alloy and datasets produced with different sets of processing parameters. However, they have universal quality and could easily be adapted to different material compositions. The method can be easily generalized to microstructural characterizations other than optical microscopy.

additive manufacturing↗

DOE OSTI2024

Point containment algorithms for constructive solid geometry with unbounded primitives

Here, we present several algorithms for evaluating point containment in constructive solid geometry (CSG) trees with unbounded primitives. Three algorithms are presented based on postfix, prefix, and infix notations of the CSG binary expression tree. We show that prefix and infix notations enable short-circuiting logic, which reduces the number of primitives that must be checked during point containment. To evaluate the performance of the algorithms, each algorithm was implemented in the OpenMC Monte Carlo particle transport code, which relies on CSG to represent solid bodies through which subatomic particles travel. Two sets of tests were carried out. First, the execution time to generate a rasterized image of a 2D slice of three CSG models of varying complexity was measured. Use of both prefix and infix notations offered significant speedup over the postfix notation that has traditionally been used in particle transport codes, with infix resulting in a 6 x reduction in execution time relative to postfix for a model of a tokamak fusion device. We then measured the execution time of neutron transport simulations of the same three models using each of the algorithms. The results and performance improvements reveal the same trends as for the rasterization test, with a 5.52 x overall speedup using the infix notation relative to the original postfix notation in OpenMC for the tokamak model.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

Neural-based time series forecasting of loss of coolant accidents in nuclear power plants

During the last few years, deep learning in neural networks has demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.

42 ENGINEERING↗