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 127 records · Page 7

Spectral Synthesis for Geostationary Satellite-to-Satellite Translation

Earth-observing satellites carrying multispectral sensors are widely used to monitor the physical and biological states of the atmosphere, land, and oceans. These satellites have different vantage points above the Earth and different spectral imaging bands resulting in inconsistent imagery from one to another. This presents challenges in building downstream applications. What if we could generate synthetic bands for existing satellites from the union of all domains? We tackle the problem of generating synthetic spectral imagery for multispectral sensors as an unsupervised image-to-image translation problem modeled with a variational autoencoder (VAE) and generative adversarial network (GAN) architecture. Our approach introduces a novel shared spectral reconstruction loss to constrain the high-dimensional feature space of multispectral images. Simulated experiments performed by dropping one or more spectral bands show that cross-domain reconstruction outperforms measurements obtained from a second vantage point. Our proposed approach enables the synchronization of multispectral data and provides a basis for more homogeneous remote sensing datasets.

Geostationary satellites↗

Synthetic Data Generation Using Machine Learning

Robust machine learning techniques for image analysis require a substantial amount of data to yield confident results. In the nuclear domain, data scarcity is a substantial challenge because there are so few facilities worldwide. This research focuses on being able alleviate the data scarcity problem by generating synthetic data to bridge the gap between large and small datasets. This work achieves that goal using a Generative Adversarial Network (GAN) architectural approach, by training a model on real-world data and expands that small dataset through synthetic data amendments. Model performance is impacted by the size of the real-world dataset and the number of training epochs utilized. This means that 1) It is important to develop your GAN to be optimized with the specific data type, and 2) approaches taken when training the GAN should be specialized to encompass important aspects of the dataset that it is generating. By taking a step to improve dataset sizes in this way, the gap between models trained by parties with significant amount of data and those without access to large data, closes, allowing for robust analyses of satellite imagery for nuclear domain applications.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Critical range evaluation using a diagonal flat plate

A novel technique is presented to image stray signals in RCS measurement ranges. In this technique, the scattered fields of a flat plate in the diagonal plane are measured in a range for various frequencies and look angles. The scattered field data is then processed to generate an inverse synthetic aperture radar (ISAR) image of the diagonal flat plate. It is shown that scattering mechanisms associated with various stray signals can be identified by using the ISAR image. This leads to better understanding of the range and possible chamber improvements. Scattering mechanisms as small as 90 dB below the plate broadside scattered field level have been observed in the image domain due to the high directivity and low sidelobe characteristics associated with the diagonal flat plate backscattered fields. The results obtained from evaluating the two compact range facilities at The Ohio State University ElectroScience Laboratory are presented to illustrate the virtues of this new range evaluation technique.

Lee, Teh-Hong↗

Digital enhancement of computerized axial tomograms

A systematic evaluation has been conducted of certain digital image enhancement techniques performed in image space. Three types of images have been used, computer generated phantoms, tomograms of a synthetic phantom, and axial tomograms of human anatomy containing images of lesions, artificially introduced into the tomograms. Several types of smoothing, sharpening, and histogram modification have been explored. It has been concluded that the most useful enhancement techniques are a selective smoothing of singular picture elements, combined with contrast manipulation. The most useful tool in applying these techniques is the gray-scale histogram.

Roberts, E., Jr.↗

TU-AB-BRA-03: Atlas-Based Algorithms with Local Registration-Goodness Weighting for MRI-Driven Electron Density Mapping

Purpose: To develop image-analysis algorithms to synthesize CT with accurate electron densities for MR-only radiotherapy of head & neck (H&N) and pelvis anatomies. Methods: CT and 3T-MRI (Philips, mDixon sequence) scans were randomly selected from a pool of H&N (n=11) and pelvis (n=12) anatomies to form an atlas. All MRIs were pre-processed to eliminate scanner and patient-induced intensity inhomogeneities and standardize their intensity histograms. CT and MRI for each patient were then co-registered to construct CT-MRI atlases. For more accurate CT-MR fusion, bone intensities in CT were suppressed to improve the similarity between CT and MRI. For a new patient, all CT-MRI atlases are deformed onto the new patients’ MRI initially. A newly-developed generalized registration error (GRE) metric was then calculated as a measure of local registration accuracy. The synthetic CT value at each point is a 1/GRE-weighted average of CTs from all CT-MR atlases. For evaluation, the mean absolute error (MAE) between the original and synthetic CT (generated in a leave-one-out scheme) was computed. The planning dose from the original and synthetic CT was also compared. Results: For H&N patients, MAE was 67±9, 114±22, and 116±9 HU over the entire-CT, air and bone regions, respectively. For pelvis anatomy, MAE was 47±5 and 146±14 for the entire and bone regions. In comparison with MIRADA medical, an FDA-approved registration tool, we found that our proposed registration strategy reduces MAE by ∼30% and ∼50% over the entire and bone regions, respectively. GRE-weighted strategy further lowers MAE by ∼15% to ∼40%. Our primary dose calculation also showed highly consistent results between the original and synthetic CT. Conclusion: We’ve developed a novel image-analysis technique to synthesize CT for H&N and pelvis anatomies. Our proposed image fusion strategy and GRE metric help generate more accurate synthetic CT using locally more similar atlases (Support: Philips Healthcare). The research is supported by Philips HealthCare.

60 APPLIED LIFE SCIENCES↗

Denoising diffusion probabilistic models for generative alloy design

Inverse material design is an extremely challenging optimization task made difficult by, in part, the highly nonlinear relationship linking performance with composition. Quantitative approaches have improved significantly owing to advances in high throughput experimentation and computational thermodynamics. However, existing physics-based tools are mostly forward models; input a chemistry and obtain a prediction. More recently the materials community has leveraged advances in the machine learning community to establish novel inverse design frameworks. Very recently denoising diffusion probabilistic models have been shown to be extremely powerful generators producing synthetic data of various modalities e.g. images, text, audio, tables, etc.. In this work a novel framework for alloy design and optimization is proposed leveraging these class of models. Five key generative tasks are demonstrated (1) unconditional generation (2) composition conditioned generation (3) property conditioned generation (4) multi-feedstock conditioned generation and (5) generative optimization. These methods were tested on three case studies: high entropy alloy design, superalloy binder jet additive manufacturing, and in-situ dual-feedstock wire-arc additive manufacturing. Results indicate that the established models are extremely flexible, expressive, and robust. The architecture’s flexibility and training procedure empower the model to learn complex intra-compositional and composition-property relationships. Furthermore, the probabilistic nature of these models makes them well suited for addressing solution non-uniqueness and tackling uncertainty quantification tasks. While the fidelity and quantity of the underlying training data is paramount, we envision that future alloy design frameworks will make extensive use of these kinds of machine learning models as “search” tools bolstering the utility of experimental and computational approaches.

36 MATERIALS SCIENCE↗

Virtual Sensing with Unsupervised Image-to-Image Translation

Earth observing satellites carrying multi-spectral sensors are widely used to monitor the physical and biological states of the atmosphere, land, and oceans. These satellites have different vantage points above the earth and different spectral imaging bands resulting in inconsistent imagery from one to another. This presents challenges in building downstream applications. What if we could generate synthetic bands for existing satellites from the union of all domains? We tackle the problem of generating synthetic spectral imagery for multispectral sensors as an unsupervised image-to-image translation problem with partial labels and introduce a novel shared spectral reconstruction loss. Simulated experiments performed by dropping one or more spectral bands show that cross-domain reconstruction outperforms measurements obtained from a second vantage point. On a downstream cloud detection task, we show that generating synthetic bands with our model improves segmentation performance beyond our baseline. Our proposed approach enables synchronization of multispectral data and provides a basis for more homogeneous remote sensing datasets.

Geostationary satellites↗

Quantification of MagLIF Morphology using the Mallat Scattering Transformation

The morphology of the stagnated plasma resulting from Magnetized Liner Inertial Fusion (MagLIF) is measured by imaging the self-emission x-rays coming from the multi-keV plasma, and the evolution of the imploding liner is measured by radiographs. Equivalent diagnostic response can be derived from integrated rad-MHD simulations from programs such as Hydra and Gorgon. There have been only limited quantitative ways to compare the image morphology, that is the texture, of simulations and experiments. We have developed a metric of image morphology based on the Mallat Scattering Transformation (MST), a transformation that has proved to be effective at distinguishing textures, sounds, and written characters. This metric has demonstrated excellent performance in classifying ensembles of synthetic stagnation images. We use this metric to quantitatively compare simulations to experimental images, cross experimental images, and to estimate the parameters of the images with uncertainty via a linear regression of the synthetic images to the parameter used to generate them. This coordinate space has proved very adept at doing a sophisticated relative back-ground subtraction in the MST space. This was needed to compare the experimental self emission images to the rad-MHD simulation images. We have also developed theory that connects the transformation to the causal dynamics of physical systems. This has been done from the classical kinetic perspective and from the field theory perspective, where the MST is the generalized Green's function, or S-matrix of the field theory in the scale basis. From both perspectives the first order MST is the current state of the system, and the second order MST are the transition rates from one state to another. An efficient, GPU accelerated, Python implementation of the MST was developed. Future applications are discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Analysis of coseismic surface displacement gradients using radar interferometry: New insights into the Landers earthquake

The map of the coseismic displacement field generated by interferometric processing of synthetic aperture radar (SAR) images taken before and after the June 28, 1992, Landers earthquake sequence brings new insights into the nature of deformation caused by these earthquakes. We use the interferometric map generated by Massonnet et al. (1993) to analyze the surface displacement field in the vicinity of the fault trace. Complexities in the fringe pattern near the fault reflect short-wavelength variations of the surface rupture and slip distribution, and attest to large displacement gradients. Along two sections of the fault, characteristic fringe patterns can be recognized, contrasting in density and direction with patterns observed away from the rupture. In order to understand the observed fringe patterns, we compute synthetic interferograms in three simple cases: (1) rigid-body rotations about a vertical axis, (2) about a horizontal axis (tilt), and (3) distributed, simple shear. The orientation and spatial separation of interferometric fringes predicted by these models help constrain near-field deformation and rupture parameters. Where the Kickapoo fault connects with the Homestead Valley fault, the interferogram shows a clear pattern of parallel N20 deg W fringes separated by about 160 m. This pattern and vertical offsets measured along the Kickapoo fault suggest that the block between this fault and the Johnson Valley fault may have been tilted, down to the west. A 5-km block lifted by 1 m on one side would be tilted by an angle of 0.01 deg (190 microrad), producing fringes separated by about 160 m, parallel to the tilt axis. Such a tilt, parallel to a N20 deg W direction, would account for the gradual, northward increase of the vertical slip component observed along the Kickapoo fault. This tilt may also explain the 1 m of reverse slip observed along the 'slip gap' section of the Homestead Valley break. Between the southern end of the Johnson Valley fault and the Eureka Peak fault, where no surface rupture has been mapped, the dense pattern of fringes implies distributed shear, probably resulting from fault slip at depth. The density and direction of the fringes in the gap are consistent with a right-lateral slip of 1.2-3.8 m on a blind fault locked above the depth of 1.5-2 km. Such observations of small wavelength features in the SAR interferogram bring new insights into the near-field displacement gradient and thus on response of the uppermost crust to seismic rupture.

Peltzer, Gilles↗

Generation of random geological models using multi-randomization for machine learning

Generating high-fidelity geological models is essential for advancing machine learning (ML) methods in automated seismic interpretation. For instance, seismic images paired with corresponding fault labels are foundational for ML-based fault detection from seismic migration sections. While several open-access datasets of random geological models exist, open-source tools specifically designed to produce large volumes of such models for ML applications remain scarce. To address this gap, we present RGM (Random Geological Model), an open-source software package for efficiently generating 2D and 3D synthetic geological models tailored for ML workflows. RGM supports the creation of diverse model components, including medium property distributions (P-/S-wave velocities and density), seismic reflectivity images (i.e., synthetic migration sections), relative geological time, and discrete fault attributes such as probability, dip, strike, rake, and displacement. It also accommodates the creation of complex geological features such as salt bodies and unconformities. The model generation algorithm employs a multi-randomization strategy, yielding an effectively infinite-dimensional model space that encompasses a wide range of geological scenarios and associated seismic features. Furthermore, RGM incorporates a method to generate synthetic elastic migration images using analytical elastic reflection coefficients combined with frequency-dependent scaling. This functionality enables the creation of training datasets for ML models that leverage elastic seismic images. RGM is implemented in modern object-oriented Fortran, allowing users to flexibly control statistical parameters governing model variability. We demonstrate the capability, performance, and geological realism of the package through comprehensive 2D and 3D examples.

58 GEOSCIENCES↗

Co-notch and independent windowing to mitigate interference in SAR-based imagery

Various technologies for mitigating distortion in coherent image products generated from SAR data are described herein. Synthetic aperture radar (SAR) datasets generated based upon SAR returns from first and second passes of a SAR platform over a scene are received. The SAR datasets can be co-notched at matching sample indices to improve coherence of SAR images generated from the datasets. Windowed SAR data is generated by applying independent windows to subsets of each of the datasets to reduce sidelobe levels of their image impulse responses. Coherent image products are generated based upon the windowed SAR data, wherein an image quality of the coherent image products is improved as compared to coherent image products generated based upon the SAR datasets.

47 OTHER INSTRUMENTATION↗

Deep generative learning of magnetic frustration in artificial spin ice from magnetic force microscopy images

Increasingly large datasets of microscopic images with nanoscale resolution facilitate the development of machine learning methods to identify and analyze subtle physical phenomena embedded within the images. In this work, microscopic images of honeycomb lattice spin-ice samples serve as datasets from which we automate the calculation of net magnetic moments and directional orientations of spin-ice configurations. In the first stage of our workflow, machine learning models are trained to accurately predict magnetic moments and directions within spin-ice structures. Variational Autoencoders (VAEs), an emergent unsupervised deep learning technique, are employed to generate high-quality synthetic magnetic force microscopy (MFM) images and extract latent feature representations, thereby reducing experimental and segmentation errors. The second stage of proposed methodology enables precise identification and prediction of frustrated vertices and nanomagnetic segments, effectively correlating structural and functional aspects of microscopic images. This facilitates the design of optimized spin-ice configurations with controlled frustration patterns, enabling potential on-demand synthesis.

36 MATERIALS SCIENCE↗

TIA: A forward model and analyzer for Talbot interferometry experiments of dense plasmas

Interferometry is one of the most sensitive and successful diagnostic methods for plasmas. However, owing to the design of most common interferometric systems, the wavelengths of operation and, therefore, the range of densities and temperatures that can be probed are severely limited. Talbot–Lau interferometry offers the possibility of extending interferometry measurements to x-ray wavelengths by means of the Talbot effect. While there have been several proof-of-concept experiments showing the efficacy of this method, it is only recently that experiments to probe High Energy Density (HED) plasmas using Talbot–Lau interferometry are starting to take place. To improve these experimental designs, we present here the Talbot-Interferometry Analyzer (TIA) tool, a forward model for generating and postprocessing synthetic x-ray interferometry images from a Talbot–Lau interferometer. Although TIA can work with any two-dimensional hydrodynamic code to study plasma conditions as close to reality as possible, this software has been designed to work by default with output files from the hydrodynamic code FLASH, making the tool user-friendly and accessible to the general plasma physics community. Here, the model has been built into a standalone app, which can be installed by anyone with access to the MATLAB runtime installer and is available upon request to the authors.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

ADVANCED WAVEFORM SIMULATION FOR SEISMIC MONITORING EVENTS

Abstract We conduct a detailed test of a recently developed technique, CAPloc, in recovering source parameters from a few stations against results from a large broadband network in Southern California. The method uses a library of 1D Green’s functions which are broken into segments and matched to waveform observations with adjustable timing shifts. These shifts can be established by calibration against a distribution of well-located earthquakes and assembled in tomographic images for predicting various phase-delays. Synthetics generated from 2D cross-sections through these models indicates that 1D synthetic waveforms are sufficient in modeling but simply shifted in time for most hard-rock sites. This simplification allows the source inversion for both mechanism and location to easily obtain by grid search. We test one-station mechanisms for 160 events against the array for both PAS and GSC which have data since 1960. While individual solutions work well (about 90%), joint solutions produce more reliable and defensible results. Inverting for both mechanism and location also works well except for certain complex paths across deep basins and along mountain ridges.

58 GEOSCIENCES↗

Radar system description

A brief overview is given of the hardware and software utilized to generate the CV-990 synthetic aperture radar's image products. The on-board hardware is described, then the operational processing software, and finally the image products that are routinely available.

Held, D. N.↗

Tree Canopy Characterization for EO-1 Reflective and Thermal Infrared Validation Studies: Rochester, New York

The tree canopy characterization presented herein provided ground and tree canopy data for different types of tree canopies in support of EO-1 reflective and thermal infrared validation studies. These characterization efforts during August and September of 2001 included stem and trunk location surveys, tree structure geometry measurements, meteorology, and leaf area index (LAI) measurements. Measurements were also collected on thermal and reflective spectral properties of leaves, tree bark, leaf litter, soil, and grass. The data presented in this report were used to generate synthetic reflective and thermal infrared scenes and images that were used for the EO-1 Validation Program. The data also were used to evaluate whether the EO-1 ALI reflective channels can be combined with the Landsat-7 ETM+ thermal infrared channel to estimate canopy temperature, and also test the effects of separating the thermal and reflective measurements in time resulting from satellite formation flying.

Ballard, Jerrell R., Jr.↗

Earth as an Extrasolar Planet: Earth Model Validation Using EPOXI Earth Observations

The EPOXI Discovery Mission of Opportunity reused the Deep Impact flyby spacecraft to obtain spatially and temporally resolved visible photometric and moderate resolution near-infrared (NIR) spectroscopic observations of Earth. These remote observations provide a rigorous validation of whole disk Earth model simulations used to better under- stand remotely detectable extrasolar planet characteristics. We have used these data to upgrade, correct, and validate the NASA Astrobiology Institute s Virtual Planetary Laboratory three-dimensional line-by-line, multiple-scattering spectral Earth model (Tinetti et al., 2006a,b). This comprehensive model now includes specular reflectance from the ocean and explicitly includes atmospheric effects such as Rayleigh scattering, gas absorption, and temperature structure. We have used this model to generate spatially and temporally resolved synthetic spectra and images of Earth for the dates of EPOXI observation. Model parameters were varied to yield an optimum fit to the data. We found that a minimum spatial resolution of approx.100 pixels on the visible disk, and four categories of water clouds, which were defined using observed cloud positions and optical thicknesses, were needed to yield acceptable fits. The validated model provides a simultaneous fit to the Earth s lightcurve, absolute brightness, and spectral data, with a root-mean-square error of typically less than 3% for the multiwavelength lightcurves, and residuals of approx.10% for the absolute brightness throughout the visible and NIR spectral range. We extend our validation into the mid-infrared by comparing the model to high spectral resolution observations of Earth from the Atmospheric Infrared Sounder, obtaining a fit with residuals of approx.7%, and temperature errors of less than 1K in the atmospheric window. For the purpose of understanding the observable characteristics of the distant Earth at arbitrary viewing geometry and observing cadence, our validated forward model can be used to simulate Earth s time dependent brightness and spectral properties for wavelengths from the far ultraviolet to the far infrared.brightness

Robinson, Tyler D.↗

Magnetic Resonance–Based Automatic Air Segmentation for Generation of Synthetic Computed Tomography Scans in the Head Region

Purpose: To incorporate a novel imaging sequence for robust air and tissue segmentation using ultrashort echo time (UTE) phase images and to implement an innovative synthetic CT (synCT) solution as a first step toward MR-only radiation therapy treatment planning for brain cancer. Methods and Materials: Ten brain cancer patients were scanned with a UTE/Dixon sequence and other clinical sequences on a 1.0 T open magnet with simulation capabilities. Bone-enhanced images were generated from a weighted combination of water/fat maps derived from Dixon images and inverted UTE images. Automated air segmentation was performed using unwrapped UTE phase maps. Segmentation accuracy was assessed by calculating segmentation errors (true-positive rate, false-positive rate, and Dice similarity indices using CT simulation (CT-SIM) as ground truth. The synCTs were generated using a voxel-based, weighted summation method incorporating T2, fluid attenuated inversion recovery (FLAIR), UTE1, and bone-enhanced images. Mean absolute error (MAE) characterized Hounsfield unit (HU) differences between synCT and CT-SIM. A dosimetry study was conducted, and differences were quantified using γ-analysis and dose-volume histogram analysis. Results: On average, true-positive rate and false-positive rate for the CT and MR-derived air masks were 80.8% ± 5.5% and 25.7% ± 6.9%, respectively. Dice similarity indices values were 0.78 ± 0.04 (range, 0.70-0.83). Full field of view MAE between synCT and CT-SIM was 147.5 ± 8.3 HU (range, 138.3-166.2 HU), with the largest errors occurring at bone–air interfaces (MAE 422.5 ± 33.4 HU for bone and 294.53 ± 90.56 HU for air). Gamma analysis revealed pass rates of 99.4% ± 0.04%, with acceptable treatment plan quality for the cohort. Conclusions: A hybrid MRI phase/magnitude UTE image processing technique was introduced that significantly improved bone and air contrast in MRI. Segmented air masks and bone-enhanced images were integrated into our synCT pipeline for brain, and results agreed well with clinical CTs, thereby supporting MR-only radiation therapy treatment planning in the brain.

62 RADIOLOGY AND NUCLEAR MEDICINE↗