Search NASA⌕ Search

SEARCH · Search NASA

Results for “Synthetic 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.

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

At least 19 records

Proton Radiography Imager:Generates Synthetic Proton Radiographs

ProRad is a computer program that is used to generate synthetic images of proton (or other charged particles) radiographs. The proton radiographs arc images that arc obtained by sending energetic protons (or electrons or positrons, for example) through 11 plasma where electric and/or magnetic fields alter the particles trajectory, Dnd the variations me imaged on RC film, image plate, or equivalent

Wilks, ScottC.↗

Proton Radiography Imager:Generates Synthetic Proton Radiographs

ProRad is a computer program that is used to generate synthetic images of proton (or other charged particles) radiographs. The proton radiographs arc images that arc obtained by sending energetic protons (or electrons or positrons, for example) through 11 plasma where electric and/or magnetic fields alter the particles trajectory, Dnd the variations me imaged on RC film, image plate, or equivalent

Wilks, Scott C.↗

PIV/BOS synthetic image generation in variable density environments for error analysis and experiment design

In this work, we present an image generation methodology based on ray tracing that can be used to render realistic images of Particle Image Velocimetry (PIV) and Background Oriented Schlieren (BOS) experiments in the presence of density/refractive index gradients. This methodology enables the simulation of aero-thermodynamics experiments for experiment design, error, and uncertainty analysis. Images are generated by emanating light rays from the particles or dot pattern, and propagating them through the density gradient field and the optical elements, up to the camera sensor. The rendered images are realistic, and can replicate the features of a given experimental setup, like optical aberrations and perspective effects, which can be deliberately introduced for error analysis. We demonstrate this methodology by simulating a BOS experiment with a known density field obtained from direct numerical simulations (DNS) of homogeneous buoyancy driven turbulence, and comparing the light ray displacements from ray tracing to results from BOS theory. The light ray displacements show good agreement with the reference data. This methodology provides a framework for further development of simulation tools for use in experiment design and development of image analysis tools for PIV and BOS applications. Finally, an implementation of the proposed methodology in a Python-CUDA program is made available as an open source software for researchers.

47 OTHER INSTRUMENTATION↗

Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model's foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research.

Generative Adversarial Networks↗

Implementation of a Novel Algorithm For Generating Synthetic CT Images From Magnetic Resonance Imaging Data Sets for Prostate Cancer Radiation Therapy

Purpose: To describe and evaluate a method for generating synthetic computed tomography (synCT) images from magnetic resonance simulation (MR-SIM) data for accurate digitally reconstructed radiograph (DRR) generation and dose calculations in prostate cancer radiation therapy. Methods and Materials: A retrospective evaluation was performed in 9 prostate cancer patients who had undergone MR-SIM in addition to CT simulation (CT-SIM). MR-SIM data were used to generate synCT images by using a novel, voxel-based weighted summation approach. A subset of patients was used for weight optimization, and the number of patients to use during optimization was determined. Hounsfield unit (HU) differences between CT-SIM and synCT images were analyzed via mean absolute error (MAE). Original, CT-based treatment plans were mapped onto synCTs. DRRs were generated, and agreement between CT and synCT-generated DRRs was evaluated via Dice similarity coefficient (DSC). Dose was recalculated, and dose-volume metrics and gamma analysis were used to evaluate resulting treatment plans. Results: Full field-of-view synCT MAE across all patients was 74.3 ± 10.9 HU with differences from CTs of 2.0 ± 8.1 HU and 11.9 ± 46.7 HU for soft tissue structures (prostate, bladder, and rectum) and femoral bones, respectively. Calculated DSCs for anterior-posterior and lateral DRRs were 0.90 ± 0.04 and 0.92 ± 0.05, respectively. Differences in D99%, mean dose, and maximum dose to the clinical target volume from CT-SIM dose calculations were 0.75% ± 0.35%, 0.63% ± 0.34%, and 0.54% ± 0.33%, respectively, for synCT-generated plans. Gamma analysis (2%/2 mm dose difference/distance to agreement) revealed pass rates of 99.9% ± 0.1% (range, 99.7%-100%). Conclusion: Generated synCTs enabled accurate DRR generation and dose computation for prostate MR-only simulation. Dose recalculated on synCTs agreed well with original planning distributions. Further validation using a larger patient cohort is warranted.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models

Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone.

58 GEOSCIENCES↗

Assessing the Dosimetric Accuracy of Magnetic Resonance-Generated Synthetic CT Images for Focal Brain VMAT Radiation Therapy

Purpose: The purpose of this study was to assess the dosimetric accuracy of synthetic CT (MRCT) volumes generated from magnetic resonance imaging (MRI) data for focal brain radiation therapy. Methods and Materials: A study was conducted in 12 patients with gliomas who underwent both MR and CT imaging as part of their simulation for external beam treatment planning. MRCT volumes were generated from MR images. Patients' clinical treatment planning directives were used to create 12 individual volumetric modulated arc therapy (VMAT) plans, which were then optimized 10 times on each of their respective CT and MRCT-derived electron density maps. Dose metrics derived from optimization criteria, as well as monitor units and gamma analyses, were evaluated to quantify differences between the imaging modalities. Results: Mean differences between planning target volume (PTV) doses on MRCT and CT plans across all patients were 0.0% (range: −0.1 to 0.2%) for D{sub 95%}; 0.0% (−0.7 to 0.6%) for D{sub 5%}; and −0.2% (−1.0 to 0.2%) for D{sub max}. MRCT plans showed no significant changes in monitor units (−0.4%) compared to CT plans. Organs at risk (OARs) had average D{sub max} differences of 0.0 Gy (−2.2 to 1.9 Gy) over 85 structures across all 12 patients, with no significant differences when calculated doses approached planning constraints. Conclusions: Focal brain VMAT plans optimized on MRCT images show excellent dosimetric agreement with standard CT-optimized plans. PTVs show equivalent coverage, and OARs do not show any overdose. These results indicate that MRI-derived synthetic CT volumes can be used to support treatment planning of most patients treated for intracranial lesions.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

The LSST DESC data challenge 1: generation and analysis of synthetic images for next-generation surveys

Data Challenge 1 (DC1) is the first synthetic data set produced by the Rubin Observatory Legacy Survey of Space and Time (LSST) Dark Energy Science Collaboration (DESC). DC1 is designed to develop and validate data reduction and analysis and to study the impact of systematic effects that will affect the LSST data set. DC1 is comprised of r -band observations of 40 deg 2 to 10 yr LSST depth. In this paper, we present each stage of the simulation and analysis process: (a) generation, by synthesizing sources from cosmological N -body simulations in individual sensor-visit images with different observing conditions; (b) reduction using a development version of the LSST Science Pipelines; and (c) matching to the input cosmological catalogue for validation and testing. We verify that testable LSST requirements pass within the fidelity of DC1. We establish a selection procedure that produces a sufficiently clean extragalactic sample for clustering analyses and we discuss residual sample contamination, including contributions from inefficiency in star–galaxy separation and imperfect deblending. We compute the galaxy power spectrum on the simulated field and conclude that: (i) survey properties have an impact of 50 per cent of the statistical uncertainty for the scales and models used in DC1; (ii) a selection to eliminate artefacts in the catalogues is necessary to avoid biases in the measured clustering; and (iii) the presence of bright objects has a significant impact (2σ–6σ) in the estimated power spectra at small scales (ℓ > 1200), highlighting the impact of blending in studies at small angular scales in LSST.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Data‐Efficient Generation of Synthetic Microstructures of Polymer‐Bonded Energetic Material With Fine‐Tuned Stable Diffusion

Among current deep learning approaches for synthetic image generation, diffusion-based models stand out in terms of algorithmic stability and ability to retain high-fidelity image features with detailed resolution. Here, in this work, we employ Dreambooth, a method for fine-tuning Stable Diffusion, on X-ray CT images of microstructure of the polymer-bonded form (PBX) of a commonly used high explosive, Pentaerythritol tetranitrate (PETN), which yields generative models for creating synthetic PBX images. The models developed here represent five classes (or ‘lots’) of microstructures and demonstrate successful generation of images of each class with high fidelity, as verified by computed classification accuracy of ∼ 94% or higher. Data augmentation afforded by such image synthesis can be used to more reliably decipher underlying statistics, build processing-structure correlations, recognize off-normal structural anomalies, and identify age-related changes. Ideas related to converting image data into appropriate density mapping and performing mesoscale simulation or surrogate modeling of detonation are also discussed.

Dreambooth↗

Benchmark Imagery Project: Report on Generation of Synthetic Images

The “Benchmark Imagery” project is a DOE NA-22-funded effort whose three-year goal is to create a suite of imagery that can be used to test geospatial algorithms used for extracting semantic content from overhead images of industrial facilities (e.g., auto-annotation). The project is a collaborative effort between Los Alamos National Laboratory (LANL) and the Lawrence Livermore National Laboratory (LLNL). Although a variety of image modalities are used to capture overhead photographs of terrestrial facilities, the current focus of the effort of this project is on collecting and annotating conventional visual-band (RGB or RGB/NIR) images. Presently, the set of images consists of 114 airborne images of various US industrial facilities. We have annotated all of the images in the imagery set, using a constrained vocabulary of about a dozen general terms such as “building,” ”tower,” or “electrical substation.” The project plans to include synthetic and composite images in addition to actual photographs. In preparation for using synthetic images, we have built a proof-of-principle synthetic image of a fictitious nuclear power plant. This report describes the key aspects of creating that image.

97 MATHEMATICS AND COMPUTING↗

Statistical characterization of experimental magnetized liner inertial fusion stagnation images using deep-learning-based fuel–background segmentation

Significant variety is observed in spherical crystal x-ray imager (SCXI) data for the stagnated fuel–liner system created in Magnetized Liner Inertial Fusion (MagLIF) experiments conducted at the Sandia National Laboratories Z-facility. As a result, image analysis tasks involving, e.g., region-of-interest selection (i.e. segmentation), background subtraction and image registration have generally required tedious manual treatment leading to increased risk of irreproducibility, lack of uncertainty quantification and smaller-scale studies using only a fraction of available data. We present a convolutional neural network (CNN)-based pipeline to automate much of the image processing workflow. This tool enabled batch preprocessing of an ensemble of N scans = 139 SCXI images across N exp = 67 different experiments for subsequent study. The pipeline begins by segmenting images into the stagnated fuel and background using a CNN trained on synthetic images generated from a geometric model of a physical three-dimensional plasma. The resulting segmentation allows for a rules-based registration. Our approach flexibly handles rarely occurring artifacts through minimal user input and avoids the need for extensive hand labelling and augmentation of our experimental dataset that would be needed to train an end-to-end pipeline. Here we also fit background pixels using low-degree polynomials, and perform a statistical assessment of the background and noise properties over the entire image database. Our results provide a guide for choices made in statistical inference models using stagnation image data and can be applied in the generation of synthetic datasets with realistic choices of noise statistics and background models used for machine learning tasks in MagLIF data analysis. We anticipate that the method may be readily extended to automate other MagLIF stagnation imaging applications.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

STAIR 2.0: A Generic and Automatic Algorithm to Fuse Modis, Landsat, and Sentinel-2 to Generate 10 m, Daily, and Cloud-/Gap-Free Surface Reflectance Product

Remote sensing datasets with both high spatial and high temporal resolution are critical for monitoring and modeling the dynamics of land surfaces. However, no current satellite sensor could simultaneously achieve both high spatial resolution and high revisiting frequency. Therefore, the integration of different sources of satellite data to produce a fusion product has become a popular solution to address this challenge. Many methods have been proposed to generate synthetic images with rich spatial details and high temporal frequency by combining two types of satellite datasets—usually frequent coarse-resolution images (e.g., MODIS) and sparse fine-resolution images (e.g., Landsat). In this paper, we introduce STAIR 2.0, a new fusion method that extends the previous STAIR fusion framework, to fuse three types of satellite datasets, including MODIS, Landsat, and Sentinel-2. In STAIR 2.0, input images are first processed to impute missing-value pixels that are due to clouds or sensor mechanical issues using a gap-filling algorithm. The multiple refined time series are then integrated stepwisely, from coarse- to fine- and high-resolution, ultimately providing a synthetic daily, high-resolution surface reflectance observations. We applied STAIR 2.0 to generate a 10-m, daily, cloud-/gap-free time series that covers the 2017 growing season of Saunders County, Nebraska. Moreover, the framework is generic and can be extended to integrate more types of satellite data sources, further improving the quality of the fusion product. View Full-Text

47 OTHER INSTRUMENTATION↗

Observational Signatures of a Kink-unstable Coronal Flux Rope Using Hinode /EIS

The signatures of energy release and energy transport for a kink-unstable coronal flux rope are investigated via forward modeling. Synthetic intensity and Doppler maps are generated from a 3D numerical simulation. The CHIANTI database is used to compute intensities for three Hinode /EIS emission lines that cover the thermal range of the loop. The intensities and Doppler velocities at simulation-resolution are spatially degraded to the Hinode /EIS pixel size (1″), convolved using a Gaussian point-spread function (3″), and exposed for a characteristic time of 50 s. The synthetic images generated for rasters (moving slit) and sit-and-stare (stationary slit) are analyzed to find the signatures of the twisted flux and the associated instability. We find that there are several qualities of a kink-unstable coronal flux rope that can be detected observationally using Hinode /EIS, namely the growth of the loop radius, the increase in intensity toward the radial edge of the loop, and the Doppler velocity following an internal twisted magnetic field line. However, EIS cannot resolve the small, transient features present in the simulation, such as sites of small-scale reconnection (e.g., nanoflares).

79 ASTRONOMY AND ASTROPHYSICS↗

How Low Can You Go? Using Synthetic 3D Imagery to Drastically Reduce Real-World Training Data for Object Detection

Deep convolutional neural networks (DCNNs) currently provide state-of-the-art performance on image classification and object detection tasks, and there are many global security mission areas where such models could be extremely useful. Crucially, the success of these models is driven in large part by the widespread availability of high-quality open source data sets such as Image Net, Common Objects in Context (COCO), and KITTI, which contain millions of images with thousands of unique labels. However, global security relevant objects-of-interest can be difficult to obtain: relevant events are low frequency and high consequence; the content of relevant images is sensitive; and adversaries and proliferators seek to obscure their activities. For these cases where exemplar data is hard to come-by, even fine-tuning an existing model with available data can be effectively impossible. Recent work demonstrated that models can be trained using a combination of real-world and synthetic images generated from 3D representations; that such models can exceed the performance of models trained using real-world data alone; and that the generated images need not be perfectly realistic (Tremblay, et al., 2018). However, this approach still required hundreds to thousands of real-world images for training and fine tuning, which for sparse, global security-relevant datasets can be an unrealistic hurdle. In this research, we validate the performance and behavior of DCNN models as we drive the number of real-world images used for training object detection tasks down to a minimal set. We perform multiple experiments to identify the best approach to train DCNNs from an extremely small set of real-world images. In doing so, we: Develop state-of-the-art, parameterized 3D models based on real-world images and sample from their parameters to increase the variance in synthetic image training data; Use machine learning explainability techniques to highlight and correct through targeted training the biases that result from training using completely synthetic images; and Validate our results by comparing the performance of the models trained on synthetic data to one another, and to a control model created by fine-tuning an existing ImageNet-trained model with a limited number (hundreds) of real-world images.

97 MATHEMATICS AND COMPUTING↗

FORMATION AND EVOLUTION OF A MULTI-THREADED SOLAR PROMINENCE

We investigate the process of formation and subsequent evolution of prominence plasma in a filament channel and its overlying arcade. We construct a three-dimensional time-dependent model of an intermediate quiescent prominence suitable to be compared with observations. We combine the magnetic field structure of a three-dimensional sheared double arcade with one-dimensional independent simulations of many selected flux tubes, in which the thermal nonequilibrium process governs the plasma evolution. We have found that the condensations in the corona can be divided into two populations: threads and blobs. Threads are massive condensations that linger in the flux tube dips. Blobs are ubiquitous small condensations that are produced throughout the filament and overlying arcade magnetic structure, and rapidly fall to the chromosphere. The threads are the principal contributors to the total mass, whereas the blob contribution is small. The total prominence mass is in agreement with observations, assuming reasonable filling factors of order 0.001 and a fixed number of threads. The motion of the threads is basically horizontal, while blobs move in all directions along the field. We have generated synthetic images of the whole structure in an H{alpha} proxy and in two EUV channels of the Atmospheric Imaging Assembly instrument on board Solar Dynamics Observatory, thus showing the plasma at cool, warm, and hot temperatures. The predicted differential emission measure of our system agrees very well with observations in the temperature range log T = 4.6-5.7. We conclude that the sheared-arcade magnetic structure and plasma behavior driven by thermal nonequilibrium fit the abundant observational evidence well for typical intermediate prominences.

79 ASTRONOMY AND ASTROPHYSICS↗

Dust trapping by vortices in transitional disks: evidence for non-ideal magnetohydrodynamic effects in protoplanetary disks

We study particle trapping at the edge of a gap opened by a planet in a protoplanetary disk. In particular, we explore the effects of turbulence driven by the magnetorotational instability on particle trapping, using global three-dimensional magnetohydrodynamic (MHD) simulations including Lagrangian dust particles. We study disks either in the ideal MHD limit or dominated by ambipolar diffusion (AD) which plays an essential role at the outer regions of a protoplanetary disk. With ideal MHD, strong turbulence (the equivalent viscosity parameter α ∼ 10{sup –2}) in disks prevents vortex formation at the edge of the gap opened by a 9 M{sub J} planet, and most particles (except the particles that drift fastest) pile up at the outer gap edge almost axisymmetrically. When AD is considered, turbulence is significantly suppressed (α ≲ 10{sup –3}), and a large vortex forms at the edge of the planet induced gap, which survives ∼1000 orbits. The vortex can efficiently trap dust particles that span 3 orders of magnitude in size within 100 planetary orbits. We have also carried out two-dimensional hydrodynamical (HD) simulations using viscosity as an approximation to MHD turbulence. These HD simulations can reproduce vortex generation at the gap edge as seen in MHD simulations. Finally, we use our simulation results to generate synthetic images for ALMA dust continuum observations on Oph IRS 48 and HD 142527, which show good agreement with existing observations. Predictions for future ALMA cycle 2 observations have been made. We conclude that the asymmetry in ALMA observations can be explained by dust trapping vortices and the existence of vortices could be the evidence that the outer protoplanetary disks are dominated by AD with α < 10{sup –3} at the disk midplane.

79 ASTRONOMY AND ASTROPHYSICS↗

IMAGING THE TIME EVOLUTION OF ETA CARINAE'S COLLIDING WINDS WITH HST

We report new Hubble Space Telescope/Space Telescope Imaging Spectrograph observations that map the high-ionization forbidden line emission in the inner arcsecond of Eta Car, the first that fully image the extended wind-wind interaction region of the massive colliding wind binary. These observations were obtained after the 2009.0 periastron at orbital phases 0.084, 0.163, and 0.323 of the 5.54 year spectroscopic cycle. We analyze the variations in brightness and morphology of the emission, and find that blueshifted emission (-400 to -200 km s{sup -1}) is symmetric and elongated along the northeast-southwest axis, while the redshifted emission (+100 to +200 km s{sup -1}) is asymmetric and extends to the north-northwest. Comparison with synthetic images generated from a three-dimensional (3D) dynamical model strengthens the 3D orbital orientation found by Madura et al., with an inclination of i Almost-Equal-To 138 Degree-Sign , an argument of periapsis of {omega} Almost-Equal-To 270 Degree-Sign , and an orbital axis that is aligned at the same position angle on the sky as the symmetry axis of the Homunculus, 312 Degree-Sign . We discuss the potential that these and future mappings have for constraining the stellar parameters of the companion star and the long-term variability of the system.

79 ASTRONOMY AND ASTROPHYSICS↗