Image Similarity Search Poster
Empowering Nuclear Energy Research with Advanced Image Similarity Search
97 - MATHEMATICS AND COMPUTING↗
SEARCH · Engineering Papers
Results for “Computational imaging”
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.
Ultra-compact Imaging Technology (CRADA Final Report)
As part of the Cyclotron Road program, Synopic (formerly FlatCam LLC) sought to investigate the benefits of its depth-sensitive imaging techniques. The basic principle involved using a thin mask specially designed to encode light reaching a sensor, in conjunction with optimized computational algorithms, in such a manner that allowed for both miniaturization of imaging systems and improved computation toward high resolution, three-dimensional imaging. By thoroughly exploring the resolution, mask/optical design, and algorithmic capabilities of our depth sensitive technology, we expand the potential applications for (but not limited to) medical, consumer and industrial purposes. The project aimed to develop new imaging systems by building on previous work and using 1) materials capable of modulating and 2) sensors capable of measuring visible and longer wavelengths. Preliminary research was conducted to design, fabricate and characterize imaging systems with the goal of improving resolution, enhancing single capture, three-dimensional imaging, and extending depth of field of captured images. The primary goal was to determine whether adapting the depth-sensitive imaging system is feasible, and early results are promising.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Reinforcement Learning as a Parsimonious Alternative to Prediction Cascades: A Case Study on Image Segmentation
Deep learning architectures have achieved state-of-the-art (SOTA) performance on computer vision tasks such as object detection and image segmentation. This may be attributed to the use of over-parameterized, monolithic deep learning architectures executed on large datasets. Although such large architectures lead to increased accuracy, this is usually accompanied by a larger increase in computation and memory requirements during inference. While this is a non-issue in traditional machine learning (ML) pipelines, the recent confluence of machine learning and fields like the Internet of Things (IoT) has rendered such large architectures infeasible for execution in low-resource settings. For some datasets, large monolithic pipelines may be overkill for simpler inputs. To address this problem, previous efforts have proposed decision cascades where inputs are passed through models of increasing complexity until the desired performance is achieved. However, we argue that cascaded prediction leads to sub-optimal throughput and increased computational cost due to wasteful intermediate computations. To address this, we propose PaSeR (Parsimonious Segmentation with Reinforcement Learning) a non-cascading, cost-aware learning pipeline as an efficient alternative to cascaded decision architectures. Through experimental evaluation on both real-world and standard datasets, we demonstrate that PaSeR achieves better accuracy while minimizing computational cost relative to cascaded models. Further, we introduce a new metric IoU/GigaFlop to evaluate the balance between cost and performance. On the real-world task of battery material phase segmentation, PaSeR yields 179% improvement over SOTA MatPhase model and a 196% improvement over IDK Cascades under the IoU/GigaFlop metric. We also demonstrate PaSeR’s adaptability to complementary models trained on a noisy MNIST dataset, where it outperforms all baselines on IoU/GigaFlop by an average of 44%.
Srikshan, Bharat↗
Non-contact rapid reader system for reflective particle tags
A reflective particle tag reader system includes a read head assembly having a camera, illuminators, and a rigid frame portion for supporting the camera and the illuminators. The illuminators illuminate a focal point located opposite the camera where a reflective particle tag is placed. A computer in data communication with the camera receives and store images of the reflective particle tag that are acquired by the camera. The computer is programmed to process video images and to quantify a positional alignment parameter and an angular alignment parameter of the reader with respect to the reflective particle tag. A rapid burst of image frames is obtained in response to the positional alignment and the angular alignment parameters being within a predetermined tolerance and identity of the reflective tag is established between a first image set and a second image set.
42 ENGINEERING↗
Rapid neutron and gamma-ray source localization using machine learning
Rapid localization of radiation sources is critical for applications including nuclear emergency response, safeguards, and security. However, conventional imaging systems such as neutron scatter cameras and Compton cameras depend on rare coincidence events, which often result in long acquisition times. In this work, we address the challenge of rapid source localization by developing a machine learning approach to predict the direction of a single radiation source using only count rates from an array of neutron and gamma-ray detectors. The proposed model is a fully connected neural network (FCNN) trained using Monte Carlo simulation data from a 252 Cf source. The model hyperparameters are optimized with a small set of routine 252 Cf measurements. We benchmarked the performance of the trained and optimized machine learning model using additional 252 Cf , 137 Cs , and PuBe measurements under laboratory conditions with varying source-detector configurations. For these measurements, the machine learning model achieved a mean localization error smaller than 30° with 3 x 10 3 system counts, corresponding to 8 s measurement time for the imaging system used in this work. In this low-statistics regime, the method outperformed traditional scatter-based imaging by more than 75% in localization accuracy for the evaluated measurement configurations. These results demonstrate that a machine learning-based approach can significantly reduce the time required for accurate single-source localization, providing a robust and computationally efficient alternative to traditional imaging systems in time-critical nuclear security and emergency response scenarios.
Gamma-ray imaging↗
Grain size estimation in fluvial gravel bars using uncrewed aerial vehicles: A comparison between methods based on imagery and topography
Abstract Grain size assessments are necessary for understanding the various geomorphological, hydrological and ecological processes that occur within rivers. Recent research has shown that the application of Structure‐from‐Motion (SfM) photogrammetry to imagery from uncrewed aerial vehicles (UAVs) shows promise for rapidly characterising grain sizes along rivers in comparison to traditional field‐based methods. Here, we evaluated the applicability of different methods for estimating grain sizes in gravel bars along a study reach in the Olentangy River in Columbus, Ohio. We collected imagery of these gravel bars with a UAV and processed those images with SfM photogrammetry software to produce three‐dimensional point clouds and orthomosaics. Our evaluation compared statistical models calibrated on topographic roughness, which was computed from the point clouds, and to those based on image texture, which was computed from the orthomosaics. Our results showed that statistical models calibrated on image texture were more accurate than those based on topographic roughness. This might be because of site‐specific patterns of grain size, shape and imbrication. Such patterns would have complicated the detection of topographic signatures associated with individual grains. Our work illustrates that UAV‐SfM approaches show potential to be used as an accessible method for characterising surface grain sizes along rivers at higher spatial and temporal resolutions than those provided by traditional methods.
Wong, Tyler↗
Numerical Investigation of the Spark Discharge Process in a Crossflow
The present study numerically investigates the spark discharge process under crossflow conditions using a thermal equilibrium plasma solver that fully couples the electromagnetic physics and fluid dynamics in a computational framework. Numerical results are validated by the comparison with experimental data. Here, the spark discharge experiment is performed in a constant volume vessel using an inductive coil ignition system for automotive applications, and the evolution of the spark channel is measured using high-speed imaging. The crossflow in the gap between the spark-plug electrodes is generated by a rotating fan with two different fan speeds, and the flow velocity across the gap is characterized by particle image velocimetry (PIV) measurement. A computational fluid dynamics (CFD) solver is employed to simulate the crossflow and provide the flow field variables (velocity, pressure, temperature) to the plasma solver. The crossflow velocity predicted in the flow simulation agrees well with the PIV data in that the non-uniform velocity profiles at monitoring points are reproduced by the CFD code. With the crossflow initialization in the plasma solver, the simulated spark discharge process from the breakdown to spark discharge matches the experimental data, including the voltage and circuit waveforms and the high-speed images of the spark channel evolution. The stretch of spark channel captured by plasma simulations agrees with the measured data. The plasma simulation reveals that the mean temperature of the spark channel is maintained at 5000 K during the discharge phase, and the temperature varies along the spark channel so that the highest value is obtained at the spark root on the center electrode. Overall, the results presented in this paper are meant to provide valuable information about the properties of the plasma generated by the spark discharge.
71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
Cryo-electron tomography related radiation-damage parameters for individual-molecule 3D structure determination
To understand the dynamic structure–function relationship of soft- and biomolecules, the determination of the three-dimensional (3D) structure of each individual molecule (nonaveraged structure) in its native state is sought-after. Cryo-electron tomography (cryo-ET) is a unique tool for imaging an individual object from a series of tilted views. However, due to radiation damage from the incident electron beam, the tolerable electron dose limits image contrast and the signal-to-noise ratio (SNR) of the data, preventing the 3D structure determination of individual molecules, especially at high-resolution. Although recently developed technologies and techniques, such as the direct electron detector, phase plate, and computational algorithms, can partially improve image contrast/SNR at the same electron dose, the high-resolution structure, such as tertiary structure of individual molecules, has not yet been resolved. Here, we review the cryo-electron microscopy (cryo-EM) and cryo-ET experimental parameters to discuss how these parameters affect the extent of radiation damage. This discussion can guide us in optimizing the experimental strategy to increase the imaging dose or improve image SNR without increasing the radiation damage. With a higher dose, a higher image contrast/SNR can be achieved, which is crucial for individual-molecule 3D structure. With 3D structures determined from an ensemble of individual molecules in different conformations, the molecular mechanism through their biochemical reactions, such as self-folding or synthesis, can be elucidated in a straightforward manner.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Advances in Image-Domain Multi-Resolution and Super-Resolution Algorithms for Industrial X-Ray Computed Tomography: A Literature Survey and New Insights
Industrial X-ray Computed Tomography (XCT) is a nondestructive method for inspection and character ization of materials and parts. XCT captures images of a part from various angles, and these images are then used to construct Three-Dimensional (3D) representations of that part. This method enables assessing the quality of the parts, identifying defects and understanding their physical properties without damaging them.
36 MATERIALS SCIENCE↗
Hydra: An AI-Based Framework for Interpretable and Portable Data Quality Monitoring
Hydra is an advanced framework designed for training and managing AI models for near real time data quality monitoring at Jefferson Lab. Deployed in all four experimental halls, Hydra has analyzed over 2 million images and has extended its capabilities to offline monitoring and validation. Hydra utilizes computer vision to continually analyze sets of images of monitoring plots generated 24/7 during experiments. Generally, these sets of images are produced at a rate and quantity that is exceedingly difficult for shift crews to effectively monitor. Significant effort has been devoted to enhancing Hydra’s user interface, to ensure that it provides clear, actionable insights for shift workers and other users. Gradient Weighted Class Activation Maps (GradCAM) provide added interpretability, allowing users to visualize important regions of the image for classification. Hydra has been containerized to enable the creation of portable demos and seamless integration with container-based technologies such as Kubernetes and Docker. With the user interface enhancements and containerization, Hydra can be rapidly deployed for new use cases and experiments. This talk will describe the Hydra framework, its user interface and experience, and the challenges inherent in its design and deployment.
Britton, Thomas [Thomas Jefferson National Acceler↗
Stochastic generation of electrolyzer anode catalyst layers
Here, we introduce a stochastic methodology to reproduce the complex pore structure observed in commercial iridium catalyst layers. This method preserves the α pore (pores smaller than 250 nm) and β pore (pores greater than or equal to 250 nm) regions of the catalyst layer. The morphology of the generated materials was validated by comparing the pore size distributions of generated materials against those obtained from commercial materials imaged using x-ray nano computed tomography. We further demonstrate that the pore size distributions of the generated materials are statistically indistinguishable from the imaged catalyst layers, indicating that the stochastic methodology is capable of accurately reproducing catalyst layer morphology. Pore network modelling was conducted on the generated catalyst materials to simulate single-phase permeability, electrical conductivity, and ionic conductivity, and these properties were found to be within experimentally measured ranges for electrolyzer catalyst layers. Additionally, simulations were performed on the generated materials with varying ionomer and iridium catalyst loadings. As the ionomer loading is added, proton conductivity increases exponentially, which demonstrates the importance of optimizing ionomer loading, considering that these effects will be exacerbated in the hydration and temperature conditions of operating electrolyzers. The stochastic material generation method presented in this work is a powerful tool for the development of novel low loading catalyst layers, where the effect of various structural parameters on electrolyzer performance characteristics can be explored.
36 MATERIALS SCIENCE↗
Three-dimensional electron temperature measurement of inertial confinement fusion hotspots using x-ray emission tomography
Here we present a novel approach to reconstruct three-dimensional (3D) electron temperature distributions of inertially confined fusion plasma hotspots at the National Ignition Facility. Using very limited number of two-dimensional (2D) x-ray imaging lines of sight, we perform 3D reconstructions of x-ray emission distributions from different x-ray energy channels ranging from 20 to 30 keV. 2D time-integrated x-ray images are processed using the algebraic reconstruction technique to reconstruct a 3D hotspot x-ray emission distribution that is self-consistent with the input images. 3D electron temperatures are computed using the energy channel ratios. We demonstrate the high accuracy and applicability of this method with different complex hotspot geometries in both synthetic and experimental results.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Automated defect identification in electroluminescence images of solar modules
Solar photovoltaic (PV) modules are susceptible to manufacturing defects, mishandling problems or extreme weather events that can limit energy production or cause early device failure. Trained professionals use electroluminescence (EL) images to identify defects in modules, however, field surveys or inline image acquisition can generate millions of EL images, which are infeasible to analyze by rote inspection. Here, we develop a rapid automatic computer vision pipeline (~0.5 seconds/module) to analyze EL images and identify defects including cracks, intra-cell defects, oxygen-induced defects, and solder disconnections. Defect identification is achieved with a machine learning model (Random Forest, ResNet models and YOLO) trained on 762 manually-labeled EL images of PV modules. We compare model performance on an imbalanced real-world validation set containing 134 EL images and determine that ResNet18 and YOLO are the optimal models; we next evaluated these models on a dedicated testing set (129 module images) with resulting macro F1 scores of 0.83 (ResNet18) and 0.78 (YOLO). Using a field EL survey of a PV power plant damaged in a vegetation fire, we analyze 18,954 EL images (2.4 million cells) and inspect the spatial distribution of defects on the solar modules. The results find increased frequency of ‘crack’, ‘solder’ and ‘intra-cell’ defects on the edges of the solar module closest to the ground after fire. We also find an abnormal increase of striation rings on cells which were assumed to be caused mainly in fabrication process. Our methods are published as open-source software. It can also be used to identify other kinds of defects or process different types of solar cells with minor modification on models by transfer learning.
14 SOLAR ENERGY↗
First-In-Human Validation of CT-Based Proton Range Prediction Using Prompt Gamma Imaging in Prostate Cancer Treatments
Uncertainty in computed tomography (CT)-based range prediction substantially impairs the accuracy of proton therapy. Direct determination of the stopping-power ratio (SPR) from dual-energy CT (DECT) has been proposed (DirectSPR), and initial validation studies in phantoms and biological tissues have proven a high accuracy. However, a thorough validation of range prediction in patients has not yet been achieved by any means. Here, we present the first systematic validation of CT-based proton range prediction in patients using prompt gamma imaging (PGI).
62 RADIOLOGY AND NUCLEAR MEDICINE↗
Introduction to Special Section: Machine Learning for Image-based Geologic Interpretation
Image-based geological interpretation has been a labor-intensive and time-consuming process because it requires well-trained geoscientists to identify geological structures, features, and textures from various types of images. These images include scanning electron microscopic images, optical microscopic images, optical photos, resistivity images, seismic volumes, remote-sensing images, etc. With fast-evolving machine learning (ML) technology and computing power in recent decades, computers can achieve nearhuman-level to super-human-level performance with scalable high efficiency in the computer vision field. These technological revolutions facilitated image-based geological interpretation in petroleum exploration and production. For example, a fault picking method applied to 3-D seismic volume data using deep learning can achieve superior performance in comparison to conventional auto-picking methods. In addition, under the new normal of low oil prices, the petroleum industry seeks cost-effective strategies such as automating traditionally labor-intensive processes. Nevertheless, the potential of applying ML to geological image interpretation is still facing a few key challenges including data scarcity, data distribution, poor data and/or label quality, data leakage, learning algorithms, model architecture, training methodologies, testing and evaluation metrics, hyper-parameters optimization, model drift, production deployment, and the like.
58 GEOSCIENCES↗
Identifying Neutrino Final States and Energies in MicroBooNE with New Deep-Learning Based LArTPC Reconstruction Frameworks
MicroBooNE, a Liquid Argon Time Projection Chamber (LArTPC) located in the $\nu_{\mu}$-dominated Booster Neutrino Beam at Fermilab, has been studying $\nu_{e}$ charged-current (CC) interaction rates to shed light on the MiniBooNE low energy excess. The LArTPC technology employed by MicroBooNE provides the capability to image neutrino interactions with mm-scale precision. Computer vision and other machine learning techniques are promising tools for image processing that could boost efficiencies for selecting $\nu_{e}$-CC and other rare signals, reduce cosmic and beam-induced backgrounds, and improve the reconstruction of neutrino energies. The MicroBooNE experiment has been at the forefront of developing and testing such techniques for use in physics analyses. In this poster we overview deep-learning based reconstruction methods. We will showcase the use of a recurrent neural network to estimate neutrino energies and present a new reconstruction framework that uses convolutional neural networks to locate neutrino interaction vertices, tag pixels with track and shower labels, and perform particle identification on reconstructed clusters. We will present studies characterizing the performance of these new tools and demonstrate their effectiveness through their use in an inclusive $\nu_{e}$-CC event selection.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Identifying Neutrino Final States and Energies in MicroBooNE with New Deep-Learning Based LArTPC Reconstruction Frameworks
MicroBooNE, a Liquid Argon Time Projection Chamber (LArTPC) located in the $\nu_{\mu}$-dominated Booster Neutrino Beam at Fermilab, has been studying $\nu_{e}$ charged-current (CC) interaction rates to shed light on the MiniBooNE low energy excess. The LArTPC technology employed by MicroBooNE provides the capability to image neutrino interactions with mm-scale precision. Computer vision and other machine learning techniques are promising tools for image processing that could boost efficiencies for selecting $\nu_{e}$-CC and other rare signals, reduce cosmic and beam-induced backgrounds, and improve the reconstruction of neutrino energies. The MicroBooNE experiment has been at the forefront of developing and testing such techniques for use in physics analyses. In this poster we overview deep-learning based reconstruction methods. We will showcase the use of a recurrent neural network to estimate neutrino energies and present a new reconstruction framework that uses convolutional neural networks to locate neutrino interaction vertices, tag pixels with track and shower labels, and perform particle identification on reconstructed clusters. We will present studies characterizing the performance of these new tools and demonstrate their effectiveness through their use in an inclusive $\nu_{e}$-CC event selection.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Nanotomography for Quantitative 3D Particle Reconstruction
Particulates are ubiquitous across fuel cycle operations and carry critical information about particle formation, processing, and potential proliferation-related activities. Traditional analytical techniques, including micro-Raman spectroscopy and standard electron microscopy, are often limited in spatial resolution or dimensionality, particularly when used to examine metallic or submicron-scale features. Understanding particle morphology, phase distribution, and internal porosity is essential for constraining formation conditions, thermodynamic environments, and material transport behavior. In this report, we demonstrate the application of plasma focused ion beam nanotomography to reconstruct micron-scale particulates at nanoscale resolution. Using high-resolution backscattered electron imaging and Avizo software, we obtained 3D reconstructions that enabled quantitative analysis of particle morphology, phase composition, and internal voids. Representative examples include a Ta particle with a large central void and a composite particle with embedded tetrahedral crystalline structures. These reconstructions reveal structural and compositional details that are inaccessible through conventional 2D imaging. The results demonstrate that nanotomography provides both qualitative and quantitative insights into particle formation and behavior. Using nanotomography, porosity and phase distributions can be quantified to inform models of particle density, transport, and solidification conditions. Beyond technical insights, the workflow developed here establishes a transferable capability for analyzing heterogeneous particles and has potential applications in bulk materials studies via x-ray computed tomography or other volumetric imaging modalities. Ongoing efforts are focused on optimizing the workflow to process multiple particles simultaneously, increasing throughput and statistical robustness. Overall, this work illustrates the power of nanotomography as a tool for connecting particulate morphology to formation mechanisms, composition, and transport, thereby strengthening analytical capabilities for nuclear forensics, fuel cycle analysis, and related scientific investigations.
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗