Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep”

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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Deep learning-driven super-resolution in Raman hyperspectral imaging: Efficient high-resolution reconstruction from low-resolution data

Deep learning (DL) has become an indispensable tool in hyperspectral data analysis, automatically extracting valuable features from complex, high-dimensional datasets. Super-resolution reconstruction, an essential aspect of hyperspectral data, involves enhancing spatial resolution, particularly relevant to low-resolution hyperspectral data. Yet, the pursuit of super-resolution in hyperspectral analysis is fraught with challenges, including acquiring ground truth high-resolution data for training, generalization, and scalability. The pressing issue of extended spectral acquisition times, notably for high-resolution scans, is a significant roadblock in hyperspectral imaging. Super-resolution methods offer a promising solution by providing higher spatial resolution data to expedite data collection and yield more efficient outcomes. This paper delves into a practical application of these concepts using Raman imaging, where spectral acquisition times can be prohibitively long. In this context, DL-based super-resolution models demonstrate their efficacy by predicting and reconstructing high-resolution Raman data from low-resolution input, eliminating the need for resource-intensive high-resolution scans. While previous work often relied on substantial high-resolution datasets, this study showcases the ability to achieve similar outcomes even with limited data, presenting a more practical and cost-effective approach. In conclusion, the results offer a glimpse into the transformative potential of this technology to streamline hyperspectral imaging applications by saving valuable time and resources through the successful generation of high-resolution data from low-resolution inputs.

42 ENGINEERING↗
DOE OSTI2025

Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion

In this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. FusionNet integrates temporal, spectral, and physical experimental conditions to model ultrafast nonlinear phenomena, including parametric nonlinear frequency conversion, self-phase modulation, and cross-phase modulation in homogeneous guided systems such as gas-filled hollow-core fibers. These systems bridge physical models with experimental data, advancing our understanding of light-guiding principles and nonlinear interactions while expediting the design and optimization of on-demand high-power, high-brightness systems. Our results demonstrate a 73% reduction in prediction error and an 83% improvement in computational efficiency compared to conventional neural networks. This work establishes a new paradigm for accelerating parametric simulations and optimizing experimental designs in high-power laser systems, with further implications for high-precision spectroscopy, quantum information science, and distributed entangled interconnects.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Long timescale solvation dynamics and confinement: The case of non-ionic deep eutectic solvents of lauric acid and N-methylacetamide

Microscopic segregation and molecular heterogeneities in complex liquids are the result of the interplay between different intermolecular forces, all of which contribute to the energy landscape of the system. A consequence of the intricate energy landscape is the nontrivial effect on the solvation dynamics. Here, the impact of molecular heterogeneities on the solvation dynamics is studied using infrared spectroscopies and molecular dynamics simulations. In particular, this study focuses on the dynamical effect of nanoscopic heterogeneities present in deep eutectic solvents (DESs) composed of lauric acid (LA) and N-methylacetamide (NMA). To this end, a molecular probe containing a carbon triple bond is used as an infrared reporter. The results show that the vibrational probe is likely to be located in the NMA polar domains. Furthermore, the probe solvation dynamics derived from the 2DIR spectra presents a slowdown of its timescale with increasing LA concentration in the DES. Kubo modeling of the probe solvation dynamics shows a correlation between the amplitude of its long time component and the presence of molecular heterogeneities in the sample. Semiclassical modeling of the vibrational line shape of the triple bond stretch demonstrates that the heterogeneities affect the whole solvation dynamics of the system through the amplitudes of the frequency fluctuations. Molecular dynamics simulations confirm the experimental results and their interpretation by showing a slowdown of the solvation dynamics when the LA heterogeneities are present. Overall, the study presents a molecular framework to explain the effect of confinement created by nanoscopic LA heterogeneities on the solvation dynamics of the system.

Chemical compounds↗
DOE OSTI2025

Dual modulation of the anion-driven thermodynamic properties of aqueous choline halide-based deep eutectic solvents

Deep eutectic solvents (DESs) are considered tunable solvents because their specific properties can be achieved based on the choice of components and their relative concentrations in a mixture. In this article, we investigate the influence of the variation in halide ions (F − , Cl − , Br − , I − ) of choline salts used on the thermodynamic and physicochemical properties of choline halide-based DESs. Our findings show that the density of choline halide-based DESs decreases nonlinearly with an increasing mole fraction of water, following a trend based on the size of the halides, with choline iodide showing the highest density. Temperature-dependent density data reveal that the thermal expansion coefficient decreases slightly with increasing water content, indicating a more stable volume at a higher mole fraction of water. The excess molar volume (V E ) of the DES mixtures exhibits complex behavior depending on the choline halide used, with both negative and positive V E values observed across different water mole fractions. These variations are linked to the hydrogen bonding interactions between the DES components and water molecules. In addition, viscosities decrease with increasing water content, suggesting the disruption of hydrogen bonding networks and enhanced mobility of the ions, which contributes to the observed increase in conductivity. The excess molar Gibbs energies, enthalpies, and entropies of activation have also been determined.

Choline halide↗
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 OSTI2025

Sparse-Data Deep Learning Strategies for Radiographic Non-Destructive Testing

Radiography is an imaging technique used in a variety of applications, such as medical diagnosis, airport security, and nondestructive testing. We present a deep learning system for extracting information from radiographic images. We perform various prediction tasks using our system, including material classification and regression on the dimensions of a given object that is being radiographed. Our system is designed to address the sparse-data issue for radiographic nondestructive testing applications. It uses a radiographic simulation tool for synthetic data augmentation, and it uses transfer learning with a pre-trained convolutional neural network model. Using this system, our preliminary results indicate that the object geometry regression task saw an improvement of 70% in the R-squared value when using a multi-regime model. In addition, we increase the performance of the object material classification tasks by utilizing data from different imaging systems. In particular, using neutron imaging improved the material classification accuracy by 20% when compared to x-ray imaging.

convolutional neural networks↗
DOE OSTI2025

Projecting U.S. coastal storm surge risks and impacts with deep learning

Storm surge is one of the deadliest hazards posed by tropical cyclones (TCs), yet assessing its current and future risk is difficult due to the phenomenon’s rarity and physical complexity. Recent advances in artificial intelligence applications to natural hazard modeling suggest a new avenue for addressing this problem. We develop a deep learning storm surge model to efficiently estimate coastal surge risk in the United States from 900 000 synthetic TC events, accounting for projected changes in TC behavior and sea levels. The derived historical 100 year surge (the event with a 1% yearly exceedance probability) agrees well with historical observations and other modeling techniques. When coupled with an inundation model, we find that heightened TC intensities and sea levels by the end of the century result in a 50% increase in population at risk. Key findings include markedly heightened risk in Florida, and critical thresholds identified in Georgia and South Carolina.

RAFT↗
DOE OSTI2024

Deep learning based event reconstruction for cyclotron radiation emission spectroscopy

The objective of the cyclotron radiation emission spectroscopy (CRES) technology is to build precise particle energy spectra. This is achieved by identifying the start frequencies of charged particle trajectories which, when exposed to an external magnetic field, leave semi-linear profiles (called tracks) in the time–frequency plane. Due to the need for excellent instrumental energy resolution in application, highly efficient and accurate track reconstruction methods are desired. Deep learning convolutional neural networks (CNNs) - particularly suited to deal with information-sparse data and which offer precise foreground localization—may be utilized to extract track properties from measured CRES signals (called events) with relative computational ease. In this work, we develop a novel machine learning based model which operates a CNN and a support vector machine in tandem to perform this reconstruction. A primary application of our method is shown on simulated CRES signals which mimic those of the Project 8 experiment—a novel effort to extract the unknown absolute neutrino mass value from a precise measurement of tritium β - -decay energy spectrum. When compared to a point-clustering based technique used as a baseline, we show a relative gain of 24.1% in event reconstruction efficiency and comparable performance in accuracy of track parameter reconstruction.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Accelerating cavity fault prediction using deep learning at Jefferson Laboratory

Abstract Accelerating cavities are an integral part of the continuous electron beam accelerator facility (CEBAF) at Jefferson Laboratory. When any of the over 400 cavities in CEBAF experiences a fault, it disrupts beam delivery to experimental user halls. In this study, we propose the use of a deep learning model to predict slowly developing cavity faults. By utilizing pre-fault signals, we train a long short-term memory-convolutional neural network binary classifier to distinguish between radio-frequency (RF) signals during normal operation and RF signals indicative of impending faults. We optimize the model by adjusting the fault confidence threshold and implementing a multiple consecutive window criterion to identify fault events, ensuring a low false positive rate. Results obtained from analysis of a real dataset collected from the accelerating cavities simulating a deployed scenario demonstrate the model’s ability to identify normal signals with 99.99% accuracy and correctly predict 80% of slowly developing faults. Notably, these achievements were achieved in the context of a highly imbalanced dataset, and fault predictions were made several hundred milliseconds before the onset of the fault. Anticipating faults enables preemptive measures to improve operational efficiency by preventing or mitigating their occurrence.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Machine-learned closure of URANS for stably stratified turbulence: connecting physical timescales & data hyperparameters of deep time-series models

Stably stratified turbulence (SST), a model that is representative of the turbulence found in the oceans and atmosphere, is strongly affected by fine balances between forces and becomes more anisotropic in time for decaying scenarios. Moreover, there is a limited understanding of the physical phenomena described by some of the terms in the Unsteady Reynolds-Averaged Navier–Stokes (URANS) equations—used to numerically simulate approximate solutions for such turbulent flows. Rather than attempting to model each term in URANS separately, it is attractive to explore the capability of machine learning (ML) to model groups of terms, i.e. to directly model the force balances. We develop deep time-series ML for closure modeling of the URANS equations applied to SST. We consider decaying SST which are homogeneous and stably stratified by a uniform density gradient, enabling dimensionality reduction. We consider two time-series ML models: long short-term memory and neural ordinary differential equation. Both models perform accurately and are numerically stable in a posteriori (online) tests. Furthermore, we explore the data requirements of the time-series ML models by extracting physically relevant timescales of the complex system. We find that the ratio of the timescales of the minimum information required by the ML models to accurately capture the dynamics of the SST corresponds to the Reynolds number of the flow. The current framework provides the backbone to explore the capability of such models to capture the dynamics of high-dimensional complex dynamical system like SST flows.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Machine learning and deep learning tools for the automated capture of cancer surveillance data

The National Cancer Institute and the Department of Energy strategic partnership applies advanced computing and predictive machine learning and deep learning models to automate the capture of information from unstructured clinical text for inclusion in cancer registries. Applications include extraction of key data elements from pathology reports, determination of whether a pathology or radiology report is related to cancer, extraction of relevant biomarker information, and identification of recurrence. With the growing complexity of cancer diagnosis and treatment, capturing essential information with purely manual methods is increasingly difficult. These new methods for applying advanced computational capabilities to automate data extraction represent an opportunity to close critical information gaps and create a nimble, flexible platform on which new information sources, such as genomics, can be added. This will ultimately provide a deeper understanding of the drivers of cancer and outcomes in the population and increase the timeliness of reporting. These advances will enable better understanding of how real-world patients are treated and the outcomes associated with those treatments in the context of our complex medical and social environment.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Longitudinal spin transfer to Λ hyperons in semi-inclusive deep inelastic scattering with the CLAS12 spectrometer

The polarization of Λ hyperons is preserved in the angular distribution of their decay products. This property allows one to study the spin structure of the Λ. In semi-inclusive deep inelastic scattering where a high energy lepton interacts with a nucleon target and one or more hadrons and the scattered lepton are detected in the final state, the probability for a struck quark to impart the polarization of the lepton to the Λ may be measured. In particular, in electron-proton scattering this quantity may be related to the longitudinal light quark polarization of the Λ. Currently, limited experimental data cannot discriminate between different models of Λ spin structure. This work reports on the measurement of the longitudinal spin transfer 𝐷$^{Λ}_{𝐿⁢𝐿′}$ to the Λ using data taken by the CLAS12 spectrometer at Jefferson Lab with a 10.6 GeV longitudinally polarized electron beam and an unpolarized hydrogen target. This measurement is the most precise to date, and, in comparison with theory predictions, it offers valuable insight into the relative dominance of current and target fragmentation in Λ production.

deep inelastic scattering↗
DOE OSTI2025

Defect Complexes in CrSBr Revealed Through Electron Microscopy and Deep Learning

Atomic defects underpin the properties of van der Waals materials, and their understanding is essential for advancing quantum and energy technologies. Scanning transmission electron microscopy is a powerful tool for defect identification in atomically thin materials, and extending it to multilayer and beam-sensitive materials would accelerate their exploration. Here, we establish a comprehensive defect library in a bilayer of the magnetic quasi-1D semiconductor CrSBr by combining atomic-resolution imaging, deep learning, and calculations. We apply a custom-developed machine learning work flow to detect, classify, and average point vacancy defects. This classification enables us to uncover several distinct Cr interstitial defect complexes, combined Cr and Br vacancy defect complexes, and lines of vacancy defects that extend over many unit cells. We show that their occurrence is in agreement with our computed structures and binding energy densities, reflecting the intriguing layer interlocked crystal structure of CrSBr. Our ab initio calculations show that the interstitial defect complexes give rise to highly localized electronic states. These states are of particular interest due to the reduced electronic dimensionality and magnetic properties of CrSBr and are, furthermore, predicted to be optically active. Our results broaden the scope of defect studies in challenging materials and reveal new defect types in bilayer CrSBr that can be extrapolated to the bulk and to over 20 materials belonging to the same FeOCl structural family.

deep learning↗
DOE OSTI2025

Single-valued representation of unpolarized and polarized semi-inclusive deep inelastic scattering at next-to-next-to-leading order

We revisit the recently published analytic results for unpolarized and polarized semi-inclusive deep inelastic scattering (SIDIS) at next-to-next-to-leading order (NNLO) in quantum chromodynamics (QCD). These expressions for the hard scattering coefficients contain case distinctions in the kinematic (𝑥,𝑧)-plane, splitting the analytic result into four regions. By reexpressing the coefficient functions in terms of single-valued polylogarithms, we remove these case distinctions and can present a unified result valid across the entire kinematic range of SIDIS. This reduces the length of the overall expressions by 30% to 60%.

Deep inelastic scattering↗
DOE OSTI2026

Flavor, transverse momentum, and azimuthal dependence of charged pion multiplicities in semi-inclusive deep-inelastic scattering with 10.6 GeV electrons

Measurements of semi-inclusive deep-inelastic scattering multiplicities for 𝜋 + and 𝜋 − from proton and deuteron targets are reported on a grid of hadron kinematic variables 𝑧, 𝑃 𝑇 , and 𝜙* for leptonic kinematic variables in the range 0.3<𝑥<0.6 and 3<𝑄 2 <5GeV 2 . Data were acquired in 2018 and 2019 at Jefferson Lab Hall C with a 10.6 GeV electron beam impinging on 10-cm-long liquid hydrogen and deuterium targets. Scattered electrons and charged pions were detected in the High Momentum Spectrometer and Super High Momentum Spectrometer, respectively. The multiplicities were fitted for each bin in (𝑥,𝑄 2 ,𝑧,𝑃𝑡) to extract the 𝜙*—independent 𝑀 0 and the azimuthal modulations ⟨cos⁡(𝜙*)⟩ and ⟨cos⁡(2⁢𝜙*)⟩. The 𝑃𝑡 dependence of the 𝑀 0 results was found to be remarkably consistent for the four cases studied: 𝑒⁢𝑝→𝑒⁢𝜋 + ⁢𝑋, 𝑒⁢𝑝→𝑒⁢𝜋 − ⁢𝑋, 𝑒⁢𝑑→𝑒⁢𝜋 + ⁢𝑋, 𝑒⁢𝑑→𝑒⁢𝜋 − ⁢𝑋 over the range 0GeV<𝑃 𝑡 <0.4GeV, as were the multiplicities evaluated near 𝜙*=180∘ over the extended range 0GeV<𝑃 𝑡 <0.7GeV. The Gaussian widths of the 𝑃 𝑡 dependence exhibit a quadratic increase with 𝑧. The cos⁡(𝜙*) modulations were found to be consistent with zero for 𝜋 + , in agreement with previous world data, while the 𝜋 − moments were, in many cases, significantly greater than zero. The cos⁡(2⁢𝜙*) modulations were found to be consistent with zero. The higher statistical precision of this dataset of about 20 000 individual multiplicity values, compared with previously published data, should allow improved determinations of quark transverse momentum distributions and higher twist contributions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

DLSIA: Deep Learning for Scientific Image Analysis

DLSIA (Deep Learning for Scientific Image Analysis) is a Python-based machine learning library that empowers scientists and researchers across diverse scientific domains with a range of customizable convolutional neural network (CNN) architectures for a wide variety of tasks in image analysis to be used in downstream data processing. DLSIA features easy-to-use architectures, such as autoencoders, tunable U-Nets and parameter-lean mixed-scale dense networks (MSDNets). Additionally, this article introduces sparse mixed-scale networks (SMSNets), generated using random graphs, sparse connections and dilated convolutions connecting different length scales. For verification, several DLSIA-instantiated networks and training scripts are employed in multiple applications, including inpainting for X-ray scattering data using U-Nets and MSDNets, segmenting 3D fibers in X-ray tomographic reconstructions of concrete using an ensemble of SMSNets, and leveraging autoencoder latent spaces for data compression and clustering. As experimental data continue to grow in scale and complexity, DLSIA provides accessible CNN construction and abstracts CNN complexities, allowing scientists to tailor their machine learning approaches, accelerate discoveries, foster interdisciplinary collaboration and advance research in scientific image analysis.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A Predictive Deep-Reinforcement-Learning-Based Connected Automated Vehicle Anticipatory Longitudinal Control in a Mixed Traffic Lane Change Condition

Maintaining safety and efficiency for mixed traffic consisting of connected automated vehicles (CAVs) and human-driven vehicles (HDVs) is an arduous task due to the inherent HDVs’ stochasticity. Especially for longitudinal control, which is the basic function of vehicle automation, prevailing research primarily considers CAV’s car-following control merely the acceleration and deceleration of leading vehicles. However, this approach overlooks the potential disruptions caused by surrounding vehicles executing lane changes, which can significantly impact the control vehicle’s stability and overall safety. Hence, our study introduces a predictive deep reinforcement learning (DRL) longitudinal CAV controller. This innovative approach leverages prediction from a physics-informed neural network as well as the control capability of DRL to better anticipate and mitigate issues arising from lane-changing, enhancing the safety and efficiency of CAVs in such scenarios. Finally, validated by the numerical simulations embedded with the real-world data, the results indicate that the proposed controller significantly enhances the safety and efficiency of CAVs in situations involving lane changes by other vehicles, showcasing its potential as a valuable tool in advancing CAV technology in mixed traffic.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

Here, the rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for system operators. The large-scale integration of distributed energy resources (DERs) and the rapid exchange of measurement data via communication networks present major opportunities for advancing grid operations but also introduce greater uncertainty, higher data dimensionality, more complex network and device models, and challenging control and optimization problems. Deep reinforcement learning (DRL) algorithms are promising in addressing these challenges. However, they have not been effectively adapted for power systems applications, requiring extensive customization for implementation and evaluation. This has resulted in reproducibility challenges and a steep learning curve for researchers new to applying DRL algorithms to the power systems domain. To bridge these gaps, this tutorial aims to serve as a valuable resource for researchers interested in exploring learning-based algorithms to operate active power distribution networks. Specifically, this work presents a generalized process for translating sequential decision-making problems in power distribution systems into Markov decision process (MDP) formulations, illustrated through concrete grid service examples. Additionally, we introduce a simple environment design strategy to develop and evaluate example DRL algorithms for distribution system applications, complete with an included code repository to guide users through environment construction.

24 POWER TRANSMISSION AND DISTRIBUTION↗