Variational Autoencoder for EL Image Analysis for Cell Crack Power Loss Prediction
Explore the source record for details and available documents.
Jost, Norman Robin [Sandia National Laboratories (↗
SEARCH · Engineering Papers
Results for “image analysis”
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.
Leveraging unlabeled SEM datasets with self-supervised learning for enhanced particle segmentation
Scanning Electron Microscopes (SEMs) are widely used in experimental science laboratories, often requiring cumbersome and repetitive user analysis. Automating SEM image analysis processes is highly desirable to address this challenge. In particle sample analysis, Machine Learning (ML) has emerged as the most effective approach for particle segmentation. However, the time-intensive process of manually annotating thousands of SEM images limits the applicability of supervised learning approaches. Self-Supervised Learning (SSL) offers a promising alternative by enabling knowledge extraction from raw, unlabeled data. This study presents a framework for evaluating SSL techniques in SEM image analysis, focusing on novel methods leveraging the ConvNeXtV2 architecture for particle detection. A dataset comprising 25,000 SEM images is curated to benchmark these proposed SSL methods. The results demonstrate that ConvNeXtV2 models, with varying parameter counts, consistently outperform other techniques in particle detection across different length scales, achieving up to a 34% reduction in relative error compared to established SSL methods. Furthermore, an ablation study explores the relationship between dataset size and SSL performance, providing actionable insights for practitioners regarding model selection and resource efficiency. This research advances the integration of SSL into autonomous analysis pipelines and supports its application in accelerating materials science discovery.
Rettenberger, Luca↗
Imaging and analysis data of short-term co-culture in soilchip
Fluorescently tagged bacterial soil isolates were cultured with N-acetylglucosamine, chitopentose, or chitin in porous SoilChip devices designed to mimic the structural habitats found in soil. Imaging analysis was used to examine how microbial traits, nutrient substrate solubility and degree of polymerization, and time affected microbial growth and species’ spatial assembly.
Feng, Song [Pacific Northwest National Laboratory ↗
Statistical analysis of HAADF-STEM images to determine the surface coverage and distribution of immobilized molecular complexes
The surface immobilization of molecular catalysts is attractive because it combines the benefits of homogeneous and heterogeneous catalysis. However, determining the surface coverage and distribution of a molecular catalyst on a solid support is often challenging, inhibiting our ability to design improved catalytic systems. Here, in this work, we demonstrate that the combination of scanning transmission electron microscopy (STEM) and image analysis of the individual positions of heavy atoms in transition metal complexes via a convolutional neural network (CNN) allows statistically robust determination of the surface coverage and distribution of immobilized molecular catalysts. These observations provide information about how changes in the functionalization conditions, attachment group, and structure of the molecular catalyst affect the surface coverage and distribution, providing insight into the chemical mechanism of surface immobilization. The method could be generally valuable for correlating the surface coverage and distribution to the activity, selectivity, and stability of a catalytic system.
HAADF-STEM↗
Evaluating User Errors and Temporal Trends in Marine Fish Communities Using 360-Degree Underwater Photography
The use of environmental DNA (eDNA) sampling has been proposed as a complementary method to monitor fish species in marine environments, offering a non-invasive and potentially more efficient approach to marine species observations. eDNA monitoring could be especially useful in and around sites targeted for marine energy generation as these regions need regular monitoring that would be impractical with traditional techniques. Before we can fully rely upon eDNA, we must first verify its accuracy against other proven methods, such as the use of underwater photography. In this study, I deployed a 360-degree camera in the tidal channel of Sequim Bay once a month during several hours overlapping slack tide. I investigated how having multiple people identify and count fish on underwater images could affect the overall results. Using chi square tests in R, I compared my fish identifications and counts to those made by another intern on the same images recorded in August. I found significant differences in the number of species identified and the total individual counts between the two different datasets. I also tested the statistical differences in both Shannon diversity and Pielou evenness indices between the August, September, and November camera deployments using a Hutcheson t-test. Only one significant difference was found in the Shannon index comparisons, and none were found between the Pielou evenness comparisons. These findings show that if multiple identifiers are used to process underwater images, quality control checks must be made to reduce the potential for error. This also points toward the possibility to leverage more advanced image analysis processes, such as automated image analysis software. The findings from this study also show that the dynamics of marine fish communities can vary over a few months; however, further analysis is needed to determine the extent of the seasonal changes in Sequim Bay.
59 BASIC BIOLOGICAL SCIENCES↗
Quantitative approaches for multiscale structural analysis with atomic resolution electron microscopy
Atomic-resolution imaging with scanning transmission electron microscopy is a powerful tool for characterizing the nanoscale structure of materials, in particular features such as defects, local strains, and symmetry-breaking distortions. In addition to advanced instrumentation, the effectiveness of the technique depends on computational image analysis to extract meaningful features from complex datasets recorded in experiments, which can be complicated by the presence of noise and artifacts, small or overlapping features, and the need to scale analysis over large representative areas. Here, we present image analysis approaches which synergize real and reciprocal space information to efficiently and reliably obtain meaningful structural information with picometer scale precision across hundreds of nanometers of material from atomic-resolution electron microscope images. Damping superstructure peaks in reciprocal space allows symmetry-breaking structural distortions to be disentangled from other sources of inhomogeneity and measured with high precision. Real-space fitting of the wavelike signals resulting from Fourier filtering enables absolute quantification of lattice parameter variations and strain, as well as the uncertainty associated with these measurements. Implementations of these algorithms are made available as an open source python package.
36 MATERIALS SCIENCE↗
Improving microstructures segmentation via pretraining with synthetic data
Image analysis of material microstructures through microscopy is an integral capability in the field of materials science. The topological and chemical information obtained through microscopy allow us to draw vital connections between material microstructures, properties, and processing. While scanning electron microscopy (SEM) is able to yield a considerable wealth of information interpretable by the intuition of experts, there has been considerable interest in using machine learning, convolutional neural networks (CNNs) in particular, for such image analysis task. Training CNNs for an image analysis task requires a large annotated dataset. However, in many materials science applications, obtaining a large annotated dataset is cost and labor intensive. In this work, we study the use of synthetic data to enlarge the available annotated experimental data of uranium oxide. We utilize a modified Potts model to simulate uranium oxide particles with morphologies similar to those observed experimentally. We then leverage an image-to-image translation model to synthesize the simulated particles as if they are acquired with SEM. Through this process, we obtain pairs of particle images and their corresponding SEM representations, which corresponds to pairs of annotations and images. Unlike previous works, we leverage synthetic data for pretraining a CNN model prior, and finetune that model further with experimental data. We experimentally demonstrate that using synthetic data as incremental learning process benefits the overall performance compared to training a model on combined synthetic and experimental data.
36 MATERIALS SCIENCE↗
Image Distinguishability Analysis Testing Through Principal Components and Its Application to Hot Spot Scale Invariance
Hot spots are spatial regions of intense energy localization that govern initiation of secondary high explosives. Studies that characterize or compare simulated hot spots are frequently either qualitatively descriptive or resort to quantitative distribution functions that neglect stochastic variations and spatial correlations—effects that are also neglected in common comparison tests like the Kolmogorov–Smirnov test. To this end, we develop an image distinguishability analysis (IDA) test based on principal component (PC) analysis that makes pixel-by-pixel comparisons between small, for example, O(<10), image data sets. The IDA test makes comparisons through a generalized distance metric in the PC space and a test statistic that is derived to calculate mathematical equation-values. Here, we derive a statistical distribution and criticality criterion to determine whether images are distinguishable from established baselines. We apply the IDA test on images generated from molecular dynamics simulations of hot spots from pore collapse in TATB to assess scale invariance in the complex patterns of hot spots that form in a representative high explosive crystal. The IDA test shows that TATB hot spot spatial temperature fields and their derived temperature histograms exhibit scale-invariant features over specific intervals of shock orientation, strength, and initial pore diameter. However, the IDA test also shows that qualitatively different conclusions regarding invariance can be reached depending on whether the hot spot is treated as a spatially correlated field as opposed to a distribution function that lacks spatial information.
organic↗
Review: Recent advances of ToF-SIMS for environmental analysis and imaging
Background: Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is a powerful surface analysis technique, initially developed and applied in inorganic materials and semiconductors. In past decades, ToF-SIMS has attracted more attention in its analysis capabilities of organic materials, with increased applications in biology, medical, and health development. It has also become a versatile and effective tool in environmental analysis due to its high mass resolution, mass accuracy, and depth profiling. Results: In this review, we first give an overview of the principle of ToF-SIMS and follow with recent ToF-SIMS applications in exemplary environmental study cases, including atmospheric aerosol, soil, water, plant, and organic solvent analysis. Moreover, sample preparation techniques are summarized in relation to corresponding environmental applications. Specifically, we call attention to ToF-SIMS investigations showcasing studies in surface chemical compositions, images, and depth profile analysis. These findings emphasize the important role of interfacial chemistry in environmental processes and provide valuable insights into dynamic processes, such as chemical transformation, particle formation, plant biology, and microbial inspired biotechnology development. The mass spectral imaging results acquired by ToF-SIMS offer a deeper understanding of intermediate stages and transient phases for environmental specimens. Significance: In situ and operando imaging offer new possibilities in studying phenomena in real time with high spatial resolution. Furthermore, it is anticipated that more research groups will use ToF-SIMS in environmental research given recent advances in measurement capabilities and surging needs in chemical mapping of complex analytes and systems.
Aerosol↗
Enhancing the Range and Reliability of the Spacer Layer Imaging Method
The spacer layer imaging method (SLIM) is widely used to measure the thickness of additive and lubricant films, in lubricant development and evaluation, and for fundamental research into elastohydrodynamic lubrication and tribofilm formation mechanisms. The film thickness measurement, as implemented on several popular tribometers, provides powerful, non-destructive in-situ mapping of film topography with nanometre-scale height sensitivity. However, the results can be highly sensitive to experimental procedure, machine condition, and image analysis, in some cases reporting unphysical film thickness trends. The prevailing image analysis techniques make it challenging to interrogate these errors, often hiding their multivariate nonlinear behaviour from the user by spatial averaging. Herein, several common ‘silent errors’ in the SLIM measurement, including colour matching to incorrect fringe orders, and colour drift due to the optical properties of the system or film itself, are discussed, with examples. A robust suite of novel a priori and a posteriori methods to address these issues, and to improve the accuracy and reliability of the measurement, are also presented, including a novel, computationally inexpensive circle-finding algorithm for automated image processing. In combination, these methods allow reliable mapping of films up to at least 800 nm in thickness, representing a significant milestone for the utility of SLIM applied to elastohydrodynamic contact.
EHL film geometry↗
Exploring Capability of Multimodal Foundation Model for Image-based Fault Detection of Photovoltaic Modules
Multimodal Foundation Model (MFM), like ChatGPT and Gemini, have emerged as powerful tools for their exceptional natural language processing capabilities and their emerging potential in image analysis. This paper investigates the application of MFMs for photovoltaic (PV) fault detection through image analysis, focusing on ChatGPT 4.0 and Gemini 1.5 Pro. Three types of PV images and the corresponding common PV faults are detected: bird droppings using visible images, cell cracks via electroluminescence (EL) images, and hotspots using infrared (IR) images. Among the two models, Gemini 1.5 Pro demonstrated superior performance, achieving near-perfect results with an average F1 score of 0.97, consistently outperforming ChatGPT 4.0 in accuracy and reliability. Unlike traditional machine learning (ML) models, MFMs can operate in a zero shot manner that does not require additional training by the user, and the input images are not limited by size, angle, scope, or PV technology. The strong adaptability and user-friendliness make MFM a promising tool for analyzing PV images and advancing health monitoring for PV modules.
Li, Baojie↗
ToF-SIMS Imaging and Analysis of Light Isotopes in Irradiated Materials
Explore the source record for details and available documents.
Yu, Xiao-Ying [ORNL] (ORCID:0000000298613109)↗
Statistical Analysis of Imaging Laser Scan Data of an Exhaust Tunnel at the SRS
• The SRS H-Canyon Building is a critical facility under the responsibility of DOE-EM. • It includes an Air Exhaust Tunnel (HCAEX) that allows for ventilation of the process airflow. • Inspections are performed remotely because of hazards, e.g. radioactivity, debris, high airflow, and nitric acid vapors.
Wells, William Willie [Savannah River National Lab↗
3013 Baseline Inner Container Report: Description, Imaging, and Analysis
This report presents consolidated findings from three microscopy studies of baseline Bagless Transfer Containers (BTCs), which are the inner containers used in DOE Standard 3013-compliant plutonium storage packages. The studies were conducted by Los Alamos National Laboratory (LANL), Savannah River National Laboratory (SRNL), and DNV, a subcontractor specializing in corrosion science. The baseline BTCs examined had not been exposed to corrosive environments, serving as control samples for comparison with destructively examined (DE) containers. Additionally, the Background section provides an overview of the BTC design, including manufacturing methods, material properties, and container configurations that may influence corrosion behavior. The primary objective of the LANL and SRNL studies was to establish reference characteristics of BTCs to distinguish manufacturing artifacts from corrosion-induced features observed in DE containers. Both laboratories used advanced microscopy techniques, including Wide Area Microscopy (WAMS), Laser Confocal Microscopy (LCM), Scanning Electron Microscopy (SEM), and Focused Ion Beam (FIB), to reveal that most surface anomalies were shallow and attributable to flow-forming processes, not corrosion. Subsurface impurities, identified as non-metallic inclusions, were also observed. DNV’s investigation focused on characterizing the mechanical and chemical properties of the BTC material to support crack growth modeling. Their findings indicate higher hardness and strength but reduced ductility—consistent with flow-formed 304L stainless steel and a higher-than-expected martensite content, in contrast to manufacturer claims. Ongoing and future studies, including Electron Backscatter Diffraction (EBSD), aim to further understand the microstructural factors influencing crack initiation and propagation. The combined studies provide a crucial baseline for distinguishing corrosion effects in DE containers, contributing to the safe and reliable long-term storage of plutonium-bearing materials.
36 MATERIALS SCIENCE↗
Laboratory Hail Damage of Photovoltaic Modules: Electroluminescence and High-speed Digital Image Correlation Analysis
This work experimentally investigates hail-related failures in Glass/Backsheet and Glass/Glass PV modules with varying ice ball diameters and velocities.
DiGregorio, Steven John↗
Imaging and Analysis of Insoluble Electrorefiner Material
Throughout pyroprocessing efforts at the Hot Fuel Examination Facility (HFEF), insoluble material has accumulated in the Electrorefiner (ER) vessel. The objective of this effort was to analyze the accumulated material to determine its origin. Material was removed from the ER salt bath and distilled to remove excess salt prior to performing analysis. Three samples were sent for chemical and isotopic analysis and underwent an ethyl acetate-bromine dissolution to segregate the oxide fraction from the metal fraction. Actinide concentrations were determined using a quadrupole–inductively coupled plasma–mass spectrometer (Q-ICP-MS). Three additional samples were sent for morphologic and elemental analysis by scanning electron microscopy (SEM) with Energy Dispersive X-ray (EDX) analysis at the Irradiated Materials Characterization Laboratory (IMCL). Analyses suggest that the material is primarily composed of UO2. with a small fraction of metal. This study draws no single conclusion as to the origin of the insoluble material in the ER. The particle sizes and morphologies observed in SEM micrographs indicate that the larger particles observed may be a result of introducing material to the ER that has not been completely reduced in Oxide Reduction (OR) operations, which precede electrorefining. Smaller particles may be due to reactions with oxygen and moisture present in HFEF. This research suggests that microscopic analysis of fuel particles before and after OR operations (including after distillation) as well as the uranium product collected on the cathode in the ER would increase understanding about particle morphology within the pyrochemical process.
11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
Laboratory Hail Damage of Photovoltaic Modules: Electroluminescence and High-speed Digital Image Correlation Analysis
Explore the source record for details and available documents.
DiGregorio, Steven John↗
FY25 Progress Report: SRNL Analysis of ICCWR LCM and WAMS data for Corrosion and Cracking
Algorithms for Machine Learning (ML) and image analysis for the 3013 Surveillance Program have been developed in an ongoing collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). The objective of the algorithms is to automate the identification of corrosion and cracks in the Inner Container Closure Weld Region (ICCWR) of the canister system used to store Pu-bearing material. Data for corrosion and cracking is collected from large binary files generated by a Laser Confocal Microscope (LCM), the Wide Area 3D Measurement System (WAMS), or, in a recent proposal, by a Scanning Electron Microscope (SEM). The ML software uses the physical attributes in the data files (e.g., one or more of: height, color, and 16-bit grayscale values as functions of position in a plane projection) to detect signs of surface corrosion and cracking after being trained on similar data with the features to be detected. Although the initial scope included screening for broader indicators of corrosion, e.g., pitting, the identification of potential cracks was prioritized for the past several years at the request of program leadership.
12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗