Search NASA⌕ Search

SEARCH · Search NASA

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Combining Deep Learning and scatterControl for High-Throughput X-ray CT Based Non-Destructive Characterization of Large-Scale Casted Metallic Components

X-ray computed tomography (XCT) is essential for nondestructive evaluation and quality control of large-scale metal components. XCT imaging, however, faces significant challenges from metal artifacts, particularly those caused by Compton scattering, which degrade image quality and obscure critical details. Hardware-based solutions (e.g. scatterControl) offer advancements by intercepting scattered photons and reducing artifacts, but they can be time-consuming and require additional processing. Here, we propose modifying and leveraging a novel deep learning (DL) framework, Simurgh, to enhance and accelerate scatter correction in XCT. By combining scatterControl with DL-based artifact removal, we demonstrate significant reduction in scan time while producing high-quality reconstructions. Through extensive evaluation on industrial XCT data, we show that our methods reduce scan time by up to more than 10 x while preserving flaw detectability. Quantitative analysis across multiple segmentation techniques confirms that Simurgh-based reconstructions consistently outperform traditional Feldkamp-Davis-Kress, model-based iterative reconstruction, and commercial DL models in both pixel-level and task-specific evaluations, enabling scalable, high-throughput XCT workflows for characterization of large scale components in applications such as casting and metal additive manufacturing.

Complex metal parts↗
DOE OSTI2024

A deep learning-based workflow for fast prediction of 3D state variables in geological carbon storage: A dimension reduction approach

Deep learning (DL) models are extensively used as surrogate models for high-fidelity simulations of multiphase fluid flow in porous media at large scales, enabling fast forecasts of the spatial–temporal evolution of three-dimensional (3D) state variables in geological carbon storage (GCS). However, training these models in high-dimensional space remains computationally demanding and prone to overfitting because of limited training data. This paper presents a novel workflow to address these challenges by integrating dimension reduction (DR) methods. Here, the proposed workflow employed pre-trained DR models to extract the latent variables of geological models and state variables and utilized the multi-layer perceptron (MLP) for constructing mapping functions between the input and output variables in latent spaces. Subsequently, the pre-trained reconstruction models converted the MLP-predicted latent state variables to their original high-dimensional form. Furthermore, we proposed a novel strategy for the DR and reconstruction of 3D saturation fields to account for the unique data characteristics of sparsity, nonuniformity, and discontinuity. The proposed strategy applied PCA and inverse PCA for 2D average saturation fields and developed a DL-based 3D reconstruction model, leveraging three 2D average saturation fields as input to produce a 3D saturation field as output. The pre-training of DR and reconstruction models and training of MLP models were conducted on 84 Gulf of Mexico (GoM) simulations and evaluated on 12 testing simulations. Each simulation contained 720 monthly time steps, with the first 360 months as the injection period and the rest as the post-injection period. The proposed workflow, incorporating DR and DL models, accurately predicts the normalized 3D pressure fields, achieving mean square error (MSE) of 2.92 × 10 -7 compared to the ground truth obtained from a full-physics simulator. Furthermore, the proposed strategy outperformed PCA and convolutional autoencoder (CAE) models on 3D saturation fields, resulting in minor workflow prediction errors with an MSE of 2.93 × 10 -5 . The results suggest the proposed workflow provides sufficient predictive fidelity across temporal and spatial scales, and enables a speedup of 160 times compared to the full-physics simulator, facilitating improved decision-making and risk assessment for large-scale GCS management in real-time scenarios.

3D reconstruction model↗
DOE OSTI2026

Deep Learning enabled spectral energy conversion for in situ exposure measurements

A detector-specific deep learning (DL) approach is presented for spectra-to-exposure conversion using large-format sodium iodide (NaI(Tl)) detectors deployed for in situ environmental radiation measurements in emergency response scenarios. Accurate determination of exposure from NaI spectra is challenging due to poor energy resolution, partial energy absorption, and the strong sensitivity of traditionally deployed analytical conversion methods to calibrated source geometry and pre-deployment assumptions. Here, to address these limitations, a multi-layer perceptron model was trained on a hybrid in situ /Monte Carlo dataset constructed to span a broad range of photon energies, spatial extents, and realistic deployment variability, representative of general in situ emergency response conditions. The DL model was evaluated against commonly fielded analytical approaches under matched simulation conditions, including a single-factor method, a G-function method, and a modeled pressurized ion chamber (PIC) baseline. This study was intentionally computational in scope to enable controlled, like-for-like comparisons between conversion techniques while minimizing confounding real-world variability. Comparison to the modeled PIC provides contextual benchmarking and is not intended as a field inter-comparison with deployed instruments. Across the evaluated 20 keV to 3 MeV energy range, the DL approach consistently exhibited higher accuracy and reduced variance relative to the analytical methods against a deterministically calculated exposure. This may indicate improved robustness to spectral complexity without reliance on source-, geometric-, or spectral region-specific optimization. While results do not represent real-world validation, the presented work demonstrates that deep learning may effectively learn the nonlinear detector response-to-exposure relationship for asymmetric NaI(Tl) detectors and offers a promising pathway for improving in situ exposure estimation using spectroscopic systems already integrated into initial real-time emergency response operations.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2020

Effects of Anisotropic Strain on Spin–Orbit Torque Produced by the Dirac Nodal Line Semimetal IrO 2

We report spin-torque ferromagnetic resonance studies of the efficiency of the damping-like (ξ DL ) spin–orbit torque exerted on an adjacent ferromagnet film by current flowing in epitaxial (001) and (110) IrO 2 thin films. IrO 2 possesses Dirac nodal lines (DNLs) in the band structure that are gapped by spin–orbit coupling, which could enable a very high spin Hall conductivity, σ SH . We find that the (001) films do exhibit exceptionally high ξ DL ranging from 0.45 at 293 K to 0.65 at 30 K, which sets the lower bounds of σ SH to be 1.9 × 10 5 and 3.75 × 10 5 Ω –1 m –1 , respectively, 10 times higher and of opposite sign than the theoretical prediction. Furthermore, ξ DL and σ SH are substantially reduced in anisotropically strained (110) films. Here, we suggest that this high sensitivity to anisotropic strain is because of changes in contributions to σ SH near the DNLs.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2022

A Multiscale Deep Learning Model for Soil Moisture Integrating Satellite and In Situ Data

Deep learning (DL) models trained on hydrologic observations can perform extraordinarily well, but they can inherit deficiencies of the training data, such as limited coverage of in situ data or low resolution/accuracy of satellite data. In this work, we propose a novel multiscale DL scheme learning simultaneously from satellite and in situ data to predict 9 km daily soil moisture (5 cm depth). Based on spatial cross-validation over sites in the conterminous United States, the multiscale scheme obtained a median correlation of 0.901 and root-mean-square error of 0.034 m 3 /m 3 . It outperformed the Soil Moisture Active Passive satellite mission's 9 km product, DL models trained on in situ data alone, and land surface models. Our 9 km product showed better accuracy than previous 1 km satellite downscaling products, highlighting limited impacts of improving resolution. Not only is our product useful for planning against floods, droughts, and pests, our scheme is generically applicable to geoscientific domains with data on multiple scales, breaking the confines of individual data sets.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Short‐Term Hourly Weather Forecasting Using PredRNN With Image Preprocessing

Global weather forecast models are vital tools with numerous applications, including public safety, agriculture, and transportation. Recent advancements in artificial intelligence (AI) and deep learning (DL) have shown the potential to enhance weather forecasting accuracy and speed. In this study, we developed a short-term hourly weather forecast framework with a wavelet transform function for data preprocessing and a spatiotemporal DL model, PredRNN, for predicting five surface atmospheric variables, including wind speed and direction, mean sea level pressure (MSLP), temperature, and precipitation. The framework demonstrated promising results. It produces global forecasts at 0.25° (∼25 km) with a 1-day lead time RMSE of 1.8 m/s for wind components, 180 Pa for MSLP, and 1.8 K for temperature. Although our model does not surpass state-of-the-art AI weather forecast models across all metrics, it outperforms these models in precipitation forecasting and wind prediction at short lead times and achieves comparable accuracy for MSLP. Its native hourly forecasting capability, together with training on widely accessible GPU hardware, contributes meaningfully to the advancement of accessible DL weather forecasting methods. Our work highlights the importance of integrating temporal components and data transformation techniques to improve the predictability and accuracy of weather forecasts.

Tran, Hoang [Pacific Northwest National Laboratory↗
DOE OSTI2022

AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging

Abstract The problem of phase retrieval underlies various imaging methods from astronomy to nanoscale imaging. Traditional phase retrieval methods are iterative and are therefore computationally expensive. Deep learning (DL) models have been developed to either provide learned priors or completely replace phase retrieval. However, such models require vast amounts of labeled data, which can only be obtained through simulation or performing computationally prohibitive phase retrieval on experimental datasets. Using 3D X-ray Bragg coherent diffraction imaging (BCDI) as a representative technique, we demonstrate AutoPhaseNN, a DL-based approach which learns to solve the phase problem without labeled data. By incorporating the imaging physics into the DL model during training, AutoPhaseNN learns to invert 3D BCDI data in a single shot without ever being shown real space images. Once trained, AutoPhaseNN can be effectively used in the 3D BCDI data inversion about 100× faster than iterative phase retrieval methods while providing comparable image quality.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs

Applications of deep learning (DL) to design nanomaterials are hampered by a lack of suitable data representations and training data. Here, in this study, we report efforts to overcome these limitations and leverage DL to optimize the nonlinear optical properties of core–shell upconverting nanoparticles (UCNPs). UCNPs, which have applications in fields such as biosensing, super-resolution microscopy and three-dimensional printing, can emit visible and ultraviolet light from near-infrared excitations. We report a large-scale dataset of UCNP emission spectra based on accurate but expensive kinetic Monte Carlo simulations (N > 6,000) and use these data to train a heterogeneous graph neural network using a physically motivated representation of UCNP nanostructure. Applying gradient-based optimization on the trained graph neural network, we identify structures with 6.5× higher predicted emission under 800-nm illumination than any UCNP in our training set. Our work reveals design principles for UCNP heterostructures and presents a roadmap for DL-based inverse design of nanomaterials.

Sivonxay, Eric [Lawrence Berkeley National Laborat↗
DOE OSTI2020

Deep learning surrogate model for kinetic Landau-fluid closure with collision

In this work, the kinetic Landau-fluid (LF) closure with collision and periodic boundary condition is used in the development of the deep learning (DL) surrogate model. A classical neural network, namely, feedforward neural network or sometimes termed multilayer perceptron, is constructed and trained to learn the kinetic LF closure in the static limit and arbitrary mean free path in configuration space. The preliminary relation between best hyperparameters and critical parameters for data generation is found. Compared with the numerical approach (non-Fourier method) of the LF closure, the deep learning surrogate model shows an order of magnitude of improvement in terms of accuracy. Perhaps most importantly, the surrogate model closure has been integrated for the first time with fluid simulations. Our DL-enabled fluid simulations, for the first time, give the correct Landau damping rate for a wide range of wave vectors, while the Hammett–Perkins closure cannot produce the correct damping rate. We correctly connect the collisionless Hammett–Perkins closure and collisional Braginskii closure to reproduce the intrinsic nonlocal feature of the heat flux with DL techniques. We address the most concerning error accumulation problem and find that simulations with the deep learning surrogate model are as good as, if not better than, simulations with the analytic closure in terms of long-term numerical stability in the linear Landau damping test.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Deep learning-based quasi-continuum theory for structure of confined fluids

Predicting the structural properties of water and simple fluids confined in nanometer scale pores and channels is essential in, for example, energy storage and biomolecular systems. Classical continuum theories fail to accurately capture the interfacial structure of fluids. In this work, we develop a deep learning-based quasi-continuum theory (DL-QT) to predict the concentration and potential profiles of a Lennard-Jones (LJ) fluid and water confined in a nanochannel. The deep learning model is built based on a convolutional encoder–decoder network (CED) and is applied for high-dimensional surrogate modeling to relate the fluid properties to the fluid–fluid potential. The CED model is then combined with the interatomic potential-based continuum theory to determine the concentration profiles of a confined LJ fluid and confined water. Further, we show that the DL-QT model exhibits robust predictive performance for a confined LJ fluid under various thermodynamic states and for water confined in a nanochannel of different widths. The DL-QT model seamlessly connects molecular physics at the nanoscale with continuum theory by using a deep learning model.

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

Learning dynamical systems from data: An introduction to physics-guided deep learning

Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expensive numerical integration, requiring significant computational resources and domain expertise. While deep learning (DL) provides efficient alternatives for modeling complex dynamics, they require a large amount of labeled training data. Furthermore, its predictions may disobey the governing physical laws and are difficult to interpret. Physics-guided DL aims to integrate first-principled physical knowledge into data-driven methods. It has the best of both worlds and is well equipped to better solve scientific problems. Recently, this field has gained great progress and has drawn considerable interest across discipline Here, we introduce the framework of physics-guided DL with a special emphasis on learning dynamical systems. We describe the learning pipeline and categorize state-of-the-art methods under this framework. We also offer our perspectives on the open challenges and emerging opportunities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Integrated deep learning framework for unstable event identification and disruption prediction of tokamak plasmas

Abstract The ability to identify underlying disruption precursors is key to disruption avoidance. In this paper, we present an integrated deep learning (DL) based model that combines disruption prediction with the identification of several disruption precursors like rotating modes, locked modes, H-to-L back transitions and radiative collapses. The first part of our study demonstrates that the DL-based unstable event identifier trained on 160 manually labeled DIII-D shots can achieve, on average, 84% event identification rate of various frequent unstable events (like H-L back transition, locked mode, radiative collapse, rotating MHD mode, large sawtooth crash), and the trained identifier can be adapted to label unseen discharges, thus expanding the original manually labeled database. Based on these results, the integrated DL-based framework is developed using a combined database of manually labeled and automatically labeled DIII-D data, and it shows state-of-the-art (AUC = 0.940) disruption prediction and event identification abilities on DIII-D. Through cross-machine numerical disruption prediction studies using this new integrated model and leveraging the C-Mod, DIII-D, and EAST disruption warning databases, we demonstrate the improved cross-machine disruption prediction ability and extended warning time of the new model compared with a baseline predictor. In addition, the trained integrated model shows qualitatively good cross-machine event identification ability. Given a labeled dataset, the strategy presented in this paper, i.e. one that combines a disruption predictor with an event identifier module, can be applied to upgrade any neural network based disruption predictor. The results presented here inform possible development strategies of machine learning based disruption avoidance algorithms for future tokamaks and highlight the importance of building comprehensive databases with unstable event information on current machines.

plasma instabilities↗
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 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↗