Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Image-based modeling”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Wafer-scale waveguide sidewall roughness scattering loss characterization by image processing

Photonic integrated circuits (PICs) are vital for developing affordable, high-performance optoelectronic devices that can be manufactured at an industrial scale, driving innovation and efficiency in various applications. Optical loss of modes in thin film waveguides and devices is a critical measure of their performance. Thin film growth, lithography, masking, and etching processes are imperfect processes that introduce significant sidewall and top-surface roughness and cause dominating optical losses in waveguides and photonic structures. This roughness, as perturbations couple light from guided to far-field radiation modes, leads to scattering losses that can be estimated from theoretical models. Typically, with UV-based lithography, sidewall roughness is significantly larger than wafer-top surface roughness. Atomic force microscopy (AFM) imaging measurement gives a 3D and high-resolution roughness profile, but the measurement is inconvenient, costly, and unscalable for large-scale PICs and at wafer-scale. Here, we evaluate the sidewall roughness profile based on 2D high-resolution scanning electron microscope (SEM) imaging. We characterized the loss on two homemade nitride and oxide films on 3-inch silicon wafers with 12 waveguide devices on each and correlated the scattering loss estimated from a 2D image-based sidewall profile and theoretical Payne model. The lowest loss of guided fundamental transverse electric (TE 0 ) mode is found at 0.075 dB/cm at 633 nm across 24 devices, a record at visible wavelength. Our work shows 100% success (edge continuity span exceeding 95% of image width/height) in edge detection in image processing of all images to estimate autocorrelation function and optical mode loss. These demonstrations offer valuable insights into waveguide sidewall roughness and a comparison of experimental and 2D SEM image processing based loss estimations with applications in loss characterization at wafer-scale PICs.

Khurana, Mohit (ORCID:0000000207898672)↗
DOE OSTI2023

Quantification of the Impact of Acidified Brine on Fracture-Matrix Transport in a Naturally Fractured Shale Using in Situ Imaging and Modeling

Understanding flow, transport, chemical reactions, and hydromechanical processes in fractured geologic materials is key for optimizing a range of subsurface processes including carbon dioxide and hydrogen storage, unconventional energy resource extraction, and geothermal energy recovery. Flow and transport processes in naturally fractured shale rocks have been challenging to characterize due to experimental complexity and the multiscale nature of quantifying continuum scale descriptions of mass exchange between micrometer-scale fractures and nanometer-scale pores. In this study, we use positron emission tomography (PET) to image the transport of a conservative tracer in a naturally fractured Wolfcamp shale core before and after the core was exposed to low pH brine conditions. Image-based experimental observations are interpreted by fitting an analytical transport model to fracture-containing voxels in the core. Results of this analysis indicate subtle increases in matrix diffusivity and a slightly more uniform fracture velocity distribution following exposure to low pH conditions. These observations are compared with a multicomponent one-dimensional reactive transport model that indicates the capacity for a 10% increase in porosity at the fracture-matrix interface as a result of the low pH brine exposure. This porosity change is the result of the dissolution of carbonate minerals in the shale matrix to low pH conditions. Further, this image-based workflow represents a new approach for quantifying spatially resolved fracture-matrix transport processes and provides a foundation for future work to better understand the role of coupled transport, reaction, and mechanical processes in naturally fractured rocks.

58 GEOSCIENCES↗
DOE OSTI2026

smol_model_benchmark

Machine learning models for protein–small molecule binding prediction using graph (GAT), image-based (ResNet), and transformer-based SMILES approaches (ChemBERTa and MIST). The code includes training pipelines and experiments on the dataset from the BELKA Kaggle competition.

Gibson, Kaetlyn [Los Alamos National Lab]↗
DOE OSTI2024

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

Tensor datatypes representing field variables like stress, displacement, velocity, etc., have increasingly become a common occurrence in data-driven modeling and analysis of simulations. Numerous methods [such as convolutional neural networks (CNNs)] exist to address the meta-modeling of field data from simulations. As the complexity of the simulation increases, so does the cost of acquisition, leading to limited data scenarios. Modeling of tensor datatypes under limited data scenarios remains a hindrance for engineering applications. Here, in this article, we introduce a direct image-to-image modeling framework of convolutional autoencoders enhanced by information bottleneck loss function to tackle the tensor data types with limited data. The information bottleneck method penalizes the nuisance information in the latent space while maximizing relevant information making it robust for limited data scenarios. The entire neural network framework is further combined with robust hyperparameter optimization. We perform numerical studies to compare the predictive performance of the proposed method with a dimensionality reduction-based surrogate modeling framework on a representative linear elastic ellipsoidal void problem with uniaxial loading. The data structure focuses on the low-data regime (fewer than 100 data points) and includes the parameterized geometry of the ellipsoidal void as the input and the predicted stress field as the output. The results of the numerical studies show that the information bottleneck approach yields improved overall accuracy and more precise prediction of the extremes of the stress field. Additionally, an in-depth analysis is carried out to elucidate the information compression behavior of the proposed framework.

artificial intelligence↗
DOE OSTI2025

Mesoscale Linear Elastic Modeling and Homogenization of Marine Energy Composites

The design of fiber-reinforced composite (FRC)-based components for marine energy applications necessitates a fundamental understanding of material properties and the resulting geometry to predict long-term performance. In this work, we present a modeling workflow to predict linear elastic and diffusive bulk properties at the mesoscale for an idealized geometry based on knowledge of fiber and resin properties. A parametric study was performed to identify the key model input parameters that influence bulk properties. Furthermore, we demonstrate how bulk properties can be leveraged in high-fidelity image-based simulations, where imperfections in tow geometry and voids captured during X-ray computed tomography imaging are explicitly represented within the simulation. Bulk properties of interest include moduli, Poisson’s ratios, hygroscopic swelling, diffusivity, and moisture uptake, which are key parameters for characterizing FRC performance within marine environments. Modeling predictions agreed well with experimental data, except for estimating swelling coefficients, likely due to crack accumulation as a function of moisture uptake. The mesoscale modeling workflow ultimately highlights a versatile framework for understanding the influence of material and geometric properties, which can be leveraged to rapidly assess new FRC-based components.

computational mechanics↗
DOE OSTI2026

An immersed interface method for microstructure-scale electrochemical battery models: numerical formulation and performance portable implementation

We present the numerical formulation, verification, and performance portable implementation of an immersed interface method for microstructure scale electrochemical modeling of batteries. The innovation in this approach is the resolution of chemical species and electrostatic potential discontinuities at active interfaces without the use of interface conforming unstructured grids. A unified formulation on Cartesian grids for all domains (electrodes and electrolyte) is used with interfacial flux conditions applied using volume fraction or “color” function gradients. We have developed one dimensional and two dimensional test cases with analytic solutions for electrochemical modeling using which we verified the consistency and accuracy of our scheme. Our solver is also validated against solutions from a macroscale model and an unstructured multi-subdomain solver for a full lithium ion cell. We then demonstrated the utility of our solver on an image-based complex battery electrode microstructure at high charging rate. Our technique also exhibits good scalability on distributed memory architectures using central processing units (CPU), with problem sizes up to 1.8 billion degrees of freedom and with 5400 ranks. Initial performance studies of our open-source performance portable solver showed about 70 times speed up using a graphics processing unit (GPU) compared to single compute core for a problem with 4 million cells.

25 ENERGY STORAGE↗
DOE OSTI2023

AutoSourceID-Classifier: Star-galaxy classification using a convolutional neural network with spatial information

Aims.Traditional star-galaxy classification techniques often rely on feature estimation from catalogs, a process susceptible to introducing inaccuracies, thereby potentially jeopardizing the classification’s reliability. Certain galaxies, especially those not manifesting as extended sources, can be misclassified when their shape parameters and flux solely drive the inference. We aim to create a robust and accurate classification network for identifying stars and galaxies directly from astronomical images. Methods.The AutoSourceID-Classifier (ASID-C) algorithm developed for this work uses 32x32 pixel single filter band source cutouts generated by the previously developed AutoSourceID-Light (ASID-L) code. By leveraging convolutional neural networks (CNN) and additional information about the source position within the full-field image, ASID-C aims to accurately classify all stars and galaxies within a survey. Subsequently, we employed a modified Platt scaling calibration for the output of the CNN, ensuring that the derived probabilities were effectively calibrated, delivering precise and reliable results. Results.We show that ASID-C, trained on MeerLICHT telescope images and using the Dark Energy Camera Legacy Survey (DECaLS) morphological classification, is a robust classifier and outperforms similar codes such as SourceExtractor. To facilitate a rigorous comparison, we also trained an eXtreme Gradient Boosting (XGBoost) model on tabular features extracted by SourceExtractor. While this XGBoost model approaches ASID-C in performance metrics, it does not offer the computational efficiency and reduced error propagation inherent in ASID-C’s direct image-based classification approach. ASID-C excels in low signal-to-noise ratio and crowded scenarios, potentially aiding in transient host identification and advancing deep-sky astronomy.

Astronomy & Astrophysics↗
DOE OSTI2023

Discovering a reaction–diffusion model for Alzheimer’s disease by combining PINNs with symbolic regression

Misfolded tau proteins play a critical role in the progression and pathology of Alzheimer's disease. Recent studies suggest that the spatio-temporal pattern of misfolded tau follows a reaction-diffusion type equation. However, the precise mathematical model and parameters that characterize the progression of misfolded protein across the brain remain incompletely understood. Here, we use deep learning and artificial intelligence to discover a mathematical model for the progression of Alzheimer's disease using longitudinal tau positron emission tomography from the Alzheimer's Disease Neuroimaging Initiative database. Specifically, we integrate physics informed neural networks (PINNs) and symbolic regression to discover a reaction-diffusion type partial differential equation for tau protein misfolding and spreading. First, we demonstrate the potential of our model and parameter discovery on synthetic data. Then, we apply our method to discover the best model and parameters to explain tau imaging data from 46 individuals who are likely to develop Alzheimer's disease and 30 healthy controls. Our symbolic regression discovers different misfolding models f(c) for two groups, with a faster misfolding for the Alzheimer's group, f(c) = 0.23c 3 – 1.34c 2 + 1.11c, than for the healthy control group, f(c) = –c 3 + 0.62c 2 + 0.39c. Our results suggest that PINNs, supplemented by symbolic regression, can discover a reaction-diffusion type model to explain misfolded tau protein concentrations in Alzheimer's disease. Furthermore, we expect our study to be the starting point for a more holistic analysis to provide image-based technologies for early diagnosis, and ideally early treatment of neurodegeneration in Alzheimer's disease and possibly other misfolding-protein based neurodegenerative disorders.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Deep Learning Scene Classification Experiments in Automatic Detection of Slums on Planetscope Imagery

Population growth is increasingly happening in slum settlements of the large urban centers in the Global South. The term "slum" encompasses a wide range of communities, located mostly in underserved areas, and often exhibiting distinct structural and functional informalities with a relatively high concentration of marginalized populations. To address the issues confronting slums for effective planning and development, including the realistic estimation of the resident population, identifying them accurately is fundamental. Given the disagreements over a universal definition, diverse characteristic features, and socio-political limitations, global detection of slums is a veritable challenge. In this paper, we present experiments in slum detection using a scene classification algorithm and 3-meter spatial resolution satellite imagery. We train and evaluate the model for slum detection in Mumbai, India for the year 2023 and test the temporal generalization of the trained model on Mumbai in 2020 and 2018. In addition, we explore the pathways toward geographic generalization to Kolkata and Delhi (India). We discuss several limitations in the workflow and model, situate our findings in the existing literature, and suggest improvements and alternatives. With this, we establish baseline methods and experiments as a first step towards developing an image-based global slum detection framework and algorithm. This work adds to the community discussion on methods, data challenges, and open questions related to the detection of slums globally. With this research, we hope to improve our understanding of human settlements, especially in critical areas, improve population estimates, and help measure progress towards the sustainable development goals.

Arndt, Jacob↗
DOE OSTI2024

Plasma Bubble Column Reactor: A High Throughput Reactor Design for Water Treatment

Plasma-based water treatment (PWT) is a promising technology that can degrade various emerging contaminants. However, PWT application on an industrially viable scale is hindered by the lack of an efficient reactor design that combines enhanced plasma-liquid contact with high liquid throughput. This work investigates the applicability of a bubble column gas-liquid contactor to PWT. A pulsed plasma bubble column reactor (PBCR) with a concentric rod-cylinder electrode configuration was used to correlate contaminant removal performance with the gas-liquid contact parameters of the bubble column. A surfactant, rhodamine B dye, and a nonsurfactant, caffeine, were used as model contaminants at µM concentration levels. The bubble column characteristics, i.e., gas holdup, bubble size distribution, and gas-liquid area, were measured as a function of superficial gas velocity using image-based methods. Degradation rates of both contaminants increased with gas flowrate. For caffeine, the increase was attributed to intensified bulk liquid mixing, while dye degradation increased due to the increased gas-liquid area. Ultimately, we show that bubble column contactors significantly improve the utilization of plasma-generated reactive species toward contaminant degradation by distributing them over a large contact area. As a result, a better match between the plasma species interfacial flux and the interfacial contaminant concentration leads to improved treatment energy efficiency. Furthermore, typical degradation energy efficiencies were ~10 g/kWh for caffeine and ~60 g/kWh for rhodamine B.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Image-Based Fracture Surface Defect Characterization Methods for Additively Manufactured Ti-6Al-4V Tested in Fatigue

Abstract Fatigue initiation in additively manufactured samples/parts often occurs at processed-induced defects such as lack-of-fusion (LoF), keyhole, or other morphological/microstructural defects that have unique characteristics and measurable qualities. Attempts at identifying and minimizing such defects have utilized optimized processing conditions along with in situ and ex situ characterization that includes metallography and/or X-ray computed tomography (XCT). This paper highlights the benefits of using fracture surface analyses to detect and quantify defects that may not be detected by metallography/XCT due to sectioning and resolution limits. In addition to using manual quantification of fatigue initiating LoF and keyhole defects on fracture surfaces, image-based machine learning using convolutional neural networks such as U-Net were also used to automate the process. Statistical analyses were used to identify the extreme cases of defects that initiated and accelerated fatigue and to model the distribution of defect size and shape characteristics to distinguish the type of defect. Initial results show agreement between trained machine learning models and ground truth data in defect segmentation, and the distributions of defect characteristics are distinguishable to particular process-induced defect types.

Materials Science↗
DOE OSTI2026

PIE-Enabled Study of Aqueous Corrosion & Zr Hydriding in Cr-Coated Cladding: M3GV-23PN0101132

Chromium-coated zirconium alloy cladding is under investigation as an accident-tolerant fuel (ATF) concept to extend performance to higher burnups via improved oxidation resistance and reduced hydrogen pickup. However, hydrothermal corrosion behavior and hydrogen transport mechanisms governing in-service hydriding of these coatings remain poorly understood. In a collaborative study between Pacific Northwest National Laboratory (PNNL), Idaho National Laboratory (INL), and the University of Huddersfield, cold spray (CS) and physical vapor deposition (PVD) Cr-coated Optimized ZIRLO™ cladding samples were characterized after exposure to PWR-simulated water chemistry under both in-core (neutron irradiation) and out-of-core (aqueous-only) conditions at the MIT Research Reactor. Multi-scale characterization was performed independently at PNNL and INL to evaluate coating integrity, microstructural evolution, Cr/Zr interface chemistry, and hydride formation. Both laboratories observed a consistent divergence in hydriding behavior: out-of-core CS Cr-coated cladding exhibited elevated hydride concentrations exceeding those of uncoated cladding, whereas in-core CS samples showed substantially suppressed hydriding. In-core specimens also displayed irradiation-specific features, including nanoscale voids within the Cr coating and radiation-induced segregation clusters in the Zr substrate. CS coatings retained an interdiffusion-free Cr/Zr bond with no intermetallic layer, whereas PVD coatings exhibited inferior quality with visible cracks and pores. An automated image-based hydride quantification method systematically overestimated bulk hydrogen content relative to inert gas fusion measurements, underscoring the need for standardized sample preparation and reference standards. Interpretation of hydride nucleation and growth is complicated by the open inner-diameter of the specimens, which provides additional hydrogen pathways. The results motivate further foundational studies to support predictive models of hydrothermal corrosion and hydrogen transport in unirradiated and irradiated Cr-coated cladding.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Securing Federated Learning Against Active Reconstruction Attacks

Federated Learning (FL) has amassed notable attention for its ability to preserve user privacy while emphasizing the retainment of model training efficiency. Due to this potential, FL has been integrated in many domains, such as healthcare, finance, law, and industrial engineering, where data cannot be easily exchanged due to sensitive information and strict privacy laws. However, current research has indicated that FL protocols are easily compromised by active data reconstruction attacks employed by actively dishonest servers. The malicious modification of global model parameters allows an actively dishonest server to obtain a direct copy of users’ private data via gradient inversion. Here, this class of attacks is highly underexplored and continues to be a major challenge due to the intense threat model. In this paper, we propose OASIS as a scalable and modality-agnostic defense based on data augmentation that counteracts active data reconstruction attacks while preserving model performance. To generalize our defense, we uncover the intuition behind gradient inversion that enables these attacks and theoretically establish the conditions by which the defense can be considered robust regardless of attack design. From this, we formulate our defense with data augmentation that illustrates its ability to undermine the attack principle. We evaluate OASIS on five real-world datasets–two image-based (ImageNet and CIFAR100) and three text-based (Wikitext, Stack Overflow, and Shakespeare)–which span diverse uses cases such as vision tasks and language modeling. Comprehensive evaluations on these datasets exhibit the efficacy of OASIS and highlight its feasibility as a solution.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Advancing SiC clad fuel performance model: bridging micro- and macro-scale models and experimental validation

This report presents a workflow for advancing fuel performance modeling of SiC composite cladding for light-water reactors by linking microscale, experimental data-informed finite element analysis with rod-scale fuel performance codes such as BISON. The workflow uses X-ray computed tomography (XCT) to capture the actual geometry and processing-induced defects of as-fabricated SiC composite tube specimens, particularly porosity and wall-thickness variations, and converts the segmented XCT volumes into image-based finite element meshes for high fidelity structural analysis.

Koyanagi, Takaaki [Oak Ridge National Laboratory (↗
DOE OSTI2023

NeRVI: Compressive neural representation of visualization images for communicating volume visualization results

We present NeRVI, a new deep-learning approach that compresses a large collection of visualization images generated from time-varying data for communicating volume visualization results. Based on an image-based implicit neural representation, our approach represents tens of thousands of high-resolution rendering images parametrized by different parameters via a hybrid model of multilayer perceptrons and convolutional neural networks. Here, our model predicts images and corresponding masks, and the masks are utilized for loss computation and network training to capture fine structural details and small components. In conjunction with model quantization and weight encoding, NeRVI yields highly compact compressive neural representations while preserving the image fidelity well. We demonstrate the effectiveness of NeRVI with isosurface rendering and direct volume rendering images generated from multiple data sets and compare NeRVI with other state-of-the-art deep learning-based (InSituNet, SIREN, NeRF, and NeRV) methods. Quantitative and qualitative results show that NeRVI provides an alternative solution that augments domain scientists' ability to manage, represent, and communicate scientific visualization output.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Seismicity-constrained fault detection and characterization with a multitask machine learning model

Geological fault detection and characterization are crucial for understanding subsurface dynamics across scales. While methods for fault delineation based on either seismicity location analysis or seismic image reflector discontinuity are well-established, a systematic approach that integrates both data types remains absent. We develop a novel machine learning model that unifies seismic reflector images and seismicity location information to automatically identify geological faults and characterize their geometrical properties. The model encodes a seismic image and a seismicity location image separately, and fuses the encoded features with a spatial-channel attention fusion module to improve the learning of important features in both inputs. We design an automated strategy to generate high-quality synthetic training data and labels. To improve the realism of the seismicity location image, we include random seismicity noise and missing seismicity location associated with some of the faults. We validate the model’s efficacy and accuracy using synthetic data examples and two field data examples. Moreover, we show that fine-tuning the trained model with a small, domain-specific dataset enhances its fidelity for field data applications. The results demonstrate that integrating seismicity location and seismic images into a unified framework allows the end-to-end neural network to achieve higher fidelity and accuracy in delineating subsurface faults and their geometrical properties compared with image-only fault detection methods. Our approach offers an adaptive data-driven tool for geological fault characterization and seismic hazard mitigation, bridging the gap between seismicity location and image-based fault detection methods.

58 GEOSCIENCES↗
DOE OSTI2023

Identifying common stored product insects using automated deep learning methods

Monitoring stored product insect pests is a common practice for post-harvest management of stored grain and grain-based commodities, which helps ensure product quality from harvest to final consumer. Current methods of sampling and monitoring can be time-consuming, labor-intensive, expensive and require expertise in insect identification. Therefore, this study aims to develop an image-based automated identification system for common stored product insect species using deep-learning methods. Top-down images of the common stored product adult insect species of Rhyzopertha dominica, Cryptolestes ferrugineus, Tribolium castaneum, Sitophilus oryzae, and Oryzaephilus surinamensis were acquired and analyzed. Deep learning-based, state-of-the-art Convolutional Neural Networks (CNN) models (ResNet-50, MobileNet-v2, DarkNet-53, and EfficientNet-b0) were fine-tuned with a transfer learning approach to classify the insect species. All models were able to correctly identify the insect species with at least 96% accuracy and with few misclassifications. One issue with trained CNNs is that they do not explain the reasoning for the classification and are often called a “black box”. Therefore, visualization methods called Gradient-weighted Class Activation Mapping (Grad-CAM) were implemented to explore the black box network. The Grad-CAM uses heat maps to highlight the major image features that the network focused on to make insect species predictions. The Grad-CAM verifies the network's prediction and also helps improve network performance. This study contributes to the overall goal of developing a camera-based system for monitoring stored grain insects. As a result, the developed system would empower warehouse, flour mills, and other food facilities with a tool to quickly and accurately identify insect species in stored product environments and could be implemented as part of a close to real-time monitoring system.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Image-based novel fault detection with deep learning classifiers using hierarchical labels

One important characteristic of modern fault classification systems is the ability to flag the system when faced with previously unseen fault types. This work considers the unknown fault detection capabilities of deep neural network-based fault classifiers. Specifically, we propose a methodology on how, when available, labels regarding the fault taxonomy can be used to increase unknown fault detection performance without sacrificing model performance. To achieve this, we propose to utilize soft label techniques to improve the state-of-the-art deep novel fault detection techniques during the training process and novel hierarchically consistent detection statistics for online novel fault detection. Lastly, we demonstrated increased detection performance on novel fault detection in inspection images from the hot steel rolling process, with results well replicated across multiple scenarios and baseline detection methods.

42 ENGINEERING↗