Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “dl”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Large Spin-Orbit Torque in 𝑎-Plane 𝛼−Fe 2 ⁢O 3 /Pt Bilayers

Realization of efficient spin-orbit torque switching of the Neel vector in insulating antiferromagnets is a challenge, often complicated by spurious effects. Quantifying the spin-orbit torques in antiferromagnet or heavy metal heterostructures is an important first step toward this goal. Here, we employ magneto-optic techniques to study damping-like spin-orbit torque (DL-SOT) in a-plane α-Fe 2 O 3 (hematite) with a Pt spin-orbit overlayer. We find that the DL-SOT efficiency is 2 orders of magnitude larger than reported in c- and r-plane hematite/Pt using harmonic Hall techniques. The large magnitude of DL-SOT is supported by direct imaging of current-induced motion of antiferromagnetic domains that happens at moderate current densities. Furthermore, our study introduces a new method for quantifying spin-orbit torque in antiferromagnets with a small canted moment and identifies a-plane α-Fe 2 O 3 as a promising candidate to realize efficient SOT switching.

Antiferromagnetism↗
DOE OSTI2019

Adversarial Training for Privacy-Preserving Deep Learning Model Distribution

Collaboration among cancer registries is essential to develop accurate, robust, and generalizable deep learning models for automated information extraction from cancer pathology reports. Sharing data presents a serious privacy issue, especially in biomedical research and healthcare delivery domains. Distributing pretrained deep learning (DL) models has been proposed to avoid critical data sharing. However, there is growing recognition that collaboration among clinical institutes through DL model distribution exposes new security and privacy vulnerabilities. These vulnerabilities increase in natural language processing (NLP) applications, in which the dataset vocabulary with word vector representations needs to be associated with the other model parameters. In this paper, we propose a novel privacy-preserving DL model distribution across cancer registries for information extraction from cancer pathology reports with privacy and confidentiality considerations. The proposed approach exploits the adversarial training framework to distinguish private features from shared features among different datasets. It only shares registry-invariant model parameters, without sharing raw data nor registry-specific model parameters among cancer registries. Thus, it protects both the data and the trained model simultaneously. We compare our proposed approach to single-registry models, and a model trained on centrally hosted data from different cancer registries. The results show that the proposed approach significantly outperforms the single-registry models and achieves statistically indistinguishable micro and macro F1-score as compared to the centralized model.

Alawad, Mohammed↗
DOE OSTI2021

Performance Profile of Transformer Fine-Tuning in Multi-GPU Cloud Environments

The study presented here focuses on performance characteristics and trade-offs associated with running machine-learning tasks in multi-GPU environments on both on-site cloud computing resources and commercial cloud services (Azure). Specifically, this study examines these tradeoffs by examining the performance of training and fine-tuning of transformer-based deep-learning (DL) networks on clinical notes and data, a task of critical importance in the medical domain. To this end, we perform DL-related experiments on the widely deployed NVIDIA V100 GPUs and on the newer A100 GPUs connected via NVLink or PCIe. This study analyzes the execution time of major operations to train DL models and investigate popular options to optimize each of them. We examine and present the findings on the impacts that various operations (e.g. data loading into GPUs, training, fine-tuning), optimizations, and system configurations (single vs. multi-GPU, NVLink vs. PCIe) have on the overall training performance.

Begoli, Edmon↗
DOE OSTI2026

FitCache: A Transparent Drop-In Framework for Multi-Tier Caching to Accelerate Distributed Deep Learning Workloads

Training in Deep learning (DL) remains highly compute- and data-intensive, with I/O becoming a critical bottleneck as models and datasets scale. Recent studies report that data loading can dominate training time, especially on large-scale HPC systems with shared parallel file systems (PFS). Existing caching approaches either rely on single-tier designs or require intrusive modifications to training pipelines, limiting their portability and effectiveness. In this work, we present FitCache, a transparent drop-in framework for multi-tier caching to accelerate distributed DL training by coordinating fast local memory (e.g., DRAM, Persistent Memory (PMem)) and NVMe as hierarchical caches atop PFS. Our design adapts to hardware diversity, i.e., if NVMe is missing, memory transparently acts as a caching tier, ensuring stable performance. FitCache transparently intercepts I/O requests and issues concurrent fetches across all tiers, returning data from the fastest responder without centralized metadata or static redirection paths. FitCache adapts to dynamic workloads and heterogeneous clusters while maintaining POSIX compatibility. Experiments on Frontier (2048 GPUs) and smaller research clusters show that FitCache reduces training time by up to 40% and per-batch I/O latency by up to 71.6% compared to Lustre Orion PFS, offering a drop-in solution for scalable DL training.

Hu, Guangxing [ORNL] (ORCID:0009000283203614)↗
DOE OSTI2021

UIR-Net: Object Detection in Infrared Imaging of Thermomechanical Processes in Automotive Manufacturing

Thermomechanical processes (TMPs) such as resistance spot welding (RSW) and hot stamping are widely used in automotive manufacturing. Recent advancement in sensing technology has led to an increasing adoption of thermographic cameras to capture the infrared (IR) radiation of a metal part (or component of a part) during its thermomechanical processing or immediately after the process when the part is still hot. Detecting the object(s) of interest from raw IR images is an essential step in analyzing these data. Deep learning (DL) has been a recent success for object detection (OD), but the application of DL-based OD for industrial IR images in manufacturing is largely lagging behind. The major contribution of this work, which is also the distinction from previous OD studies, is the capability of building the OD model with unlabeled IR images, i.e., imaging data without accurate information indicating the object position. Here, the architecture of Unsupervised IR Image Net (UIR-Net) is designed to accommodate the unique characteristics of IR images from TMPs in manufacturing. This study presents a novel method for OD in unlabeled IR images from TMPs. The proposed method, called UIR-Net, consists of two components: label generation and DL model construction. Two case studies from automotive manufacturing, RSW and hot stamping, are reported to demonstrate the feasibility and effectiveness of the proposed method.

42 ENGINEERING↗
DOE OSTI2025

Data-driven global ocean modeling for seasonal to decadal prediction

Accurate modeling of ocean dynamics is crucial for enhancing our understanding of complex ocean circulation processes, predicting climate variability, and tackling challenges posed by climate change. Although great efforts have been made to improve traditional numerical models, predicting global ocean variability over multiyear scales remains challenging. Here, we propose ORCA-DL (Oceanic Reliable foreCAst via Deep Learning), a data-driven three-dimensional ocean model for seasonal to decadal prediction of global ocean dynamics. ORCA-DL accurately simulates the three-dimensional structure of global ocean dynamics with high physical consistency and outperforms state-of-the-art numerical models in capturing extreme events, including El Niño–Southern Oscillation and upper ocean heat waves. Moreover, ORCA-DL stably emulates ocean dynamics at decadal timescales, demonstrating its potential even for skillful decadal predictions and climate projections. Our results demonstrate the high potential of data-driven models for providing efficient and accurate global ocean modeling and prediction.

Science & Technology - Other Topics↗
DOE OSTI2024

The Case for Co-Designing Model Architectures with Hardware

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL model to be more amenable to the target hardware can significantly improve the runtime performance of DL training and inference. In this paper, we provide a set of guidelines for users to maximize the runtime performance of their transformer models. These guidelines have been created by carefully considering the impact of various model hyperparameters controlling model shape on the efficiency of the underlying computation kernels executed on the GPU. We find the throughput of models with “efficient” model shapes is up to 39% higher while preserving accuracy compared to models with a similar number of parameters but with unoptimized shapes.

Yin, Junqi↗
DOE OSTI2022

Understanding Platinum Ionomer Interface Properties of Polymer Electrolyte Fuel Cells

A well-designed cathode catalyst layer with optimal ionomer distribution is critical to minimizing amount of Platinum (Pt) content in polymer electrolyte fuel cells (PEFCs). The impact of Pt loading, ionomer content and carbon support types on the catalyst/ionomer interface were also investigated at dry and wet conditions. Higher Pt loadings resulted in higher double layer capacity (C dl ) and similar electrochemical surface area (ECSA) due to well dispersed ionic phase material. Higher ionomer content resulted in higher ionic conductivity but also showed similar SO 3 − group coverage. High surface area (HSA) carbon support had larger ECSA and C dl at both dry and wet conditions, as less agglomerated Pt was well dispersed in the meso-pores of the support. Lower SO 3 − group coverages were observed for HSA carbon than for Vulcan carbon due to Pt particles being buried within the porous HSA carbon support. The effect of cell conditioning and voltage recovery on the PEFC cathode catalyst layer was shown to have minimal impact on SO 3 − group coverage despite a decrease in C dl and ECSA due to the size increase of Pt particles. At dry condition, a significant increases in SO 3 − group coverage were observed for all MEAs due to higher adsorptivity of ionomer in dry conditions.

25 ENERGY STORAGE↗
DOE OSTI2024

Simultaneously improving accuracy and computational cost under parametric constraints in materials property prediction tasks

Abstract Modern data mining techniques using machine learning (ML) and deep learning (DL) algorithms have been shown to excel in the regression-based task of materials property prediction using various materials representations. In an attempt to improve the predictive performance of the deep neural network model, researchers have tried to add more layers as well as develop new architectural components to create sophisticated and deep neural network models that can aid in the training process and improve the predictive ability of the final model. However, usually, these modifications require a lot of computational resources, thereby further increasing the already large model training time, which is often not feasible, thereby limiting usage for most researchers. In this paper, we study and propose a deep neural network framework for regression-based problems comprising of fully connected layers that can work with any numerical vector-based materials representations as model input. We present a novel deep regression neural network, iBRNet, with branched skip connections and multiple schedulers, which can reduce the number of parameters used to construct the model, improve the accuracy, and decrease the training time of the predictive model. We perform the model training using composition-based numerical vectors representing the elemental fractions of the respective materials and compare their performance against other traditional ML and several known DL architectures. Using multiple datasets with varying data sizes for training and testing, We show that the proposed iBRNet models outperform the state-of-the-art ML and DL models for all data sizes. We also show that the branched structure and usage of multiple schedulers lead to fewer parameters and faster model training time with better convergence than other neural networks. Scientific contribution: The combination of multiple callback functions in deep neural networks minimizes training time and maximizes accuracy in a controlled computational environment with parametric constraints for the task of materials property prediction.

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

Three-dimensional cooperative inversion of airborne magnetic and gravity gradient data using deep-learning techniques

Using multiple geophysical methods has become a prevailing approach in numerous geophysical applications to investigate subsurface structures and parameters. These multimethod-based exploration strategies have the potential to greatly diminish uncertainties and ambiguities encountered during geophysical data analysis and interpretation. One of the applications is the cooperative inversion of airborne magnetic and gravity gradient data for the interpretation of data obtained in mineral, oil and gas, and geothermal explorations. In this paper, a unified cooperative inversion framework is designed by combining the standard separate inversions with a deep neural network (DNN), which serves as the link between different types of data. A well-trained DNN takes the separately inverted susceptibility and density models as the inputs and provides improved models that will be used as the initial models of deterministic inversions. A two-round iteration strategy is adopted to guarantee the reasonability of the recovered models and overall efficiency of the inversion. In addition, this deep-learning (DL)-based framework demonstrates excellent generalization abilities when tested on models that are entirely distinct from the training data sets. The framework can easily incorporate multiphysics without necessitating any structural changes to the network. Synthetic experiments validate that our DL-based method outperforms conventional separate inversions and cross-gradient-based joint inversion in view of the accuracy of the recovered models and inversion efficiency. Successful application to field data further verifies the effectiveness of our DL-based method.

Geochemistry & Geophysics↗
DOE OSTI2021

PhaseGAN: a deep-learning phase-retrieval approach for unpaired datasets

Phase retrieval approaches based on deep learning (DL) provide a framework to obtain phase information from an intensity hologram or diffraction pattern in a robust manner and in real-time. However, current DL architectures applied to the phase problem rely on i) paired datasets, i. e., they arc only applicable when a satisfactory solution of the phase problem has been found, and ii) the fact that most of them ignore the physics of the imaging process. Here, we present PhaseGAN, a new DL approach based on Generative Adversarial Networks, which allows the use of unpaired datasets and includes the physics of image formation. The performance of our approach is enhanced by including the image formation physics and a novel Fourier loss function, providing phase reconstructions when conventional phase retrieval algorithms fail, such as ultra-fast experiments. Thus, PhaseGAN offers the opportunity to address the phase problem in real-time when no phase reconstructions but good simulations or data from other experiments are available.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Design of a Transport System for the PIP-II HB650 Cryomodule

The PIP-II Project at FNAL requires the assembly of 3 high-beta 650MHz cryomodules at STFC Daresbury (DL) in the UK. These modules must be safely transported from DL to FNAL in the USA. Previous experience with cryomodule transport was leveraged at both labs to design a transport system to protect the cryomodules during transit. Requirements for the system included mitigation of shocks, drops, and vibrations, and acting as a lifting fixture. It is comprised of a tessellated steel frame which encompasses the module with a wire rope isolator arrangement which the module mounts to. The frame was designed to withstand the weight of the 12.5 tonne cryomodule in various load cases. Details of shock and vibration profiles were obtained from MIL-STD-810H and were used to guide the sizing of the isolators. The frame and the isolation system were analysed via FEA using the shock and vibration profiles as an input. The transport system was found to be suitable for the given isolation, frame stiffness, and lifting code requirements. The frame has been fabricated and successfully load tested at FNAL. It will now be road tested with a dummy cryomodule before undergoing a trial run to DL.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Comparative Assessment of U-Net-Based Deep Learning Models for Segmenting Microfractures and Pore Spaces in Digital Rocks

Segmentation of high-resolution X-ray microcomputed tomography (µCT) images is crucial in digital rock physics (DRP), affecting the characterization and analysis of microscale phenomena in the porous media. The complexity of geological structures and nonideal scanning conditions pose significant challenges to conventional image segmentation approaches. Motivated by the recent increasing popularity of deep learning (DL) techniques in image processing, this work undertakes a comparative study of DL models, specifically U-Net and its variants, for segmenting multiple targets with distinguished features in digital rocks, including discrete fracture networks (DFNs), pore spaces, and solid rock. Particularly, DFNs have a smaller volumetric fraction over others, bringing in a substantial challenge of imbalanced segmentation. The primary focus is to evaluate the architecture and feature enhancement strategies of various DL models, including U-Net, attention U-Net, residual U-Net, U-Net++, and residual U-Net++. The models were designed as 2.5D, utilizing a central 2D image and its two adjacent upper and lower 2D images as input to provide a pseudo-3D context. In addition, because the ground truth of segmentation was unknown for real-world digital rocks, we created a benchmark data set following the inverse operations of segmentation. The data synthesis started from the label images (i.e., solid rock, pore spaces, and DFNs), followed by simulating partial volume blurring, adding random background noise, and introducing ring artifacts to mimic real raw X-ray µCT images. The data set, which included various rock types (i.e., sandstone and artificial data), scanning resolution, and magnitudes of noise and artifacts, was divided into training and testing data sets with a 90% and 10% ratio, respectively. Moreover, in addition to the conventional pixel-wise evaluation metrics, the physics-based metric of the lattice-Boltzmann method (LBM) simulated permeability provided more comprehensive assessments. The results demonstrated that the residual connections, nested architectures, and redesigned skip connections contribute to the model performance and give the residual U-Net++ the highest accuracy. The improvements were mainly on the boundaries and small targets, especially the DFNs, which dominate the interconnectivity and therefore affect the permeability greatly. This study also rigorously evaluated the efficiency and generalization of each model, demonstrating that the sophisticated architectures achieved excellent practicability and maintained robust performance on completely unseen data, ensuring their suitability for diverse and challenging DRP applications.

58 GEOSCIENCES↗
DOE OSTI2023

Deep Learning Model Segmentations on Computed Tomography 3D Reconstructions of Coffee Beans to Determine Void Ratio (U-Net) and Roast Level (LinkNet)

This project will evaluate the functionality of Object Research Dragonfly software’s user produced deep learning (DL) models on Computed Tomography (CT) scanned coffee beans from green (unroasted) through a dark roast. DL models will be expected to identify voids within the coffee beans, and identify the level of roast of the bean from the CT reconstruction. The scope of this project is intended to meet the Capstone Project requirements of University of California San Diego (UCSD) Structural Engineering master’s degree and offer useful insight on Dragonfly’s DL capability for LANL’s Non-Destructive Evaluation (NDE) CT team. The results of this project will be presented to the E-6 NDE group within LANL. Data acquisition was completed with a North Star Imaging (NSI) X-25 CT Cabinet.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Efficient Dimension Reduction of Complex Three-dimensional CO2 Saturation using Deep Learning Models

In the domain of deep learning (DL), dimension reduction is crucial for enhancing training efficiency and mitigating overfitting, particularly when managing complex data such as three-dimensional (3D) saturation data. The 3D saturation data in the context of geological carbon storage (GCS) presents unique challenges due to its inherent sparsity and the abrupt transitions at plume boundaries, known as shock fronts. To address the challenges, we proposed a novel DL framework that integrates dimension reduction with advanced 3D reconstruction techniques. Our model leveraged latent variables derived from 2D average saturation data, offering a robust and efficient solution tailored to the intricate dynamics of 3D saturation fields. The proposed framework can extract the critical features of the high-dimensional data while reducing the variable numbers, which is more tractable for DL models and enhances the model robustness and accuracy. Therefore, it provides a novel approach for modeling and analyses in complex geological scenarios, which finds great potential applications in environmental monitoring and energy storage.

Wang, Hongsheng↗
DOE OSTI2024

Deep Learning-based Parameterization of Complex 3D CO2 Saturation Data in Large-scale Geological Carbon Storage

In deep learning (DL), dimension reduction plays a pivotal role in improving training efficiency and minimizing overfitting, especially when working with complex datasets like three-dimensional (3D) saturation data. In the context of geological carbon storage (GCS), 3D saturation data introduces unique challenges due to its sparse nature and sharp transitions at plume boundaries, known as shock fronts. To tackle these challenges, we developed a novel DL framework that combines dimension reduction with advanced 3D reconstruction techniques. Our approach utilizes latent variables derived from 2D average saturation fields to efficiently capture the essential features of high-dimensional data while reducing the number of variables. This enhances both the robustness and accuracy of DL models, making the framework more practical for real-world applications. By offering a tailored solution for modeling complex 3D saturation dynamics, this framework holds significant potential for environmental monitoring, energy storage, and other geological applications.

Wang, Hongsheng [University of Texas at Austin]↗
DOE OSTI2022

A Comparison of Infectious Disease Forecasting Methods across Locations, Diseases, and Time

Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Deep Learning Classification of Cheatgrass Invasion in the Western United States Using Biophysical and Remote Sensing Data

Cheatgrass (Bromus tectorum) invasion is driving an emerging cycle of increased fire frequency and irreversible loss of wildlife habitat in the western US. Yet, detailed spatial information about its occurrence is still lacking for much of its presumably invaded range. Deep learning (DL) has demonstrated success for remote sensing applications but is less tested on more challenging tasks like identifying biological invasions using sub-pixel phenomena. We compare two DL architectures and the more conventional Random Forest and Logistic Regression methods to improve upon a previous effort to map cheatgrass occurrence at >2% canopy cover. High-dimensional sets of biophysical, MODIS, and Landsat-7 ETM+ predictor variables are also compared to evaluate different multi-modal data strategies. All model configurations improved results relative to the case study and accuracy generally improved by combining data from both sensors with biophysical data. Cheatgrass occurrence is mapped at 30 m ground sample distance (GSD) with an estimated 78.1% accuracy, compared to 250-m GSD and 71% map accuracy in the case study. Furthermore, DL is shown to be competitive with well-established machine learning methods in a limited data regime, suggesting it can be an effective tool for mapping biological invasions and more broadly for multi-modal remote sensing applications.

54 ENVIRONMENTAL SCIENCES↗