Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep potential”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Federated learning for 2D synchrotron x-ray diffractometry: a cross-institutional approach for phase quantification of Ti–6Al–4V alloy

High-energy Two dimensional (2D) synchrotron x-ray diffractometry provides important insights into the atomistic structure and phase evolution of materials, yet traditional analysis methods remain complex, knowledge-intensive, and computationally demanding. Deep-learning models offer a powerful alternative for automating their analysis. Institutions that hold these datasets may be unwilling to share their data due to privacy and security policies, as well as the challenges associated with large-scale data transfer. As a result, models trained on local datasets often perform well only on their own data but exhibit bias and poor generalization across different instruments or facilities. To overcome these limitations, we explore federated learning (FL) for 2D synchrotron diffractograms, enabling collaborative model training without exchanging raw data. In this study, 2D synchrotron diffractograms of Ti–6Al–4V alloy collected from two independent facilities are used to train convolutional neural networks for predicting the β-phase volume fraction. Experimental results show that federated global models significantly outperform locally trained models in terms of generalization and achieve accuracy comparable to centralized trained models. These findings demonstrate the potential of FL to enable secure, cross-institutional collaboration and enhance the scalability of deep-learning-based materials characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Warming Response of Deep Soil Carbon (LDRD Final Report)

The overarching objective of this LDRD project was to determine the vulnerability of deep soil organic carbon (SOC) to warming in the Sierra Nevada region. Deep soils (>30 cm) store more than 70% of global SOC, and increased SOC decomposition and CO 2 emissions caused by warming are potentially large climate change feedbacks. According to the Intergovernmental Panel on Climate Change, temperatures are expected to increase by 4°C by the year 2100, warming the land and underlying soil, and making understanding of how warming will influence deep SOC storage and persistence critical to projecting the land carbon sink. However, uncertainty remains in our process-level understanding and ability to quantify how projected warming will impact the stability of carbon in deep soils. We investigated warming effects on deep (up to 16 m) SOC stability across climate, vegetation, and soil mineralogy gradients in California. We sampled soils from the surface to bedrock (down to 16 meters) at four sites representing vastly different ecosystems across the Northern and Southern Sierra Nevada mountains. This study quantified the response of SOC concentration, distribution, and vulnerability to warming using a soil incubation experiment to warm the whole soil profile and radiocarbon and stable isotopes to assess which pools are vulnerable to loss under warming. Our results refine our understanding of the terrestrial carbon cycle by revealing the vulnerability of deep SOC to future changes in climate and how minerology may influence that vulnerability.

58 GEOSCIENCES↗
DOE OSTI2024

Super Resolving Unrolled Neural Networks for Remote Sensing

In remote sensing systems, the capabilities of the system are constrained by the complex interactions between size, weight, and power (SWAP) of potential designs. In electro-optical (EO) systems, examples of these critical parameters include the system’s sensitivity and resolution. Those parameters can be increased by ever larger optical apertures and focal planes but at the cost of more SWAP. Multi-image super resolution (MISR) techniques allow resolution to be enhanced via computation rather than more sophisticated optical hardware. These algorithms combine multiple images together into a single, higher resolution image, trading temporal resolution and computation for spatial resolution. Fielded MISR techniques, such as Drizzle, can require several hundred images to create a single super resolved image, implying reduced temporal resolution, increased data acquisition load, and limiting mission applications. Iterative techniques, such as model-based image reconstruction and compressive sensing, have been shown to create super resolved images using fewer images than Drizzle. They do this by posing an optimization problem that balances accuracy between a highly accurate physical model and an image model. In the case of super resolution, the physical model is defined by the relation between low resolution input images and the desired high resolution output image. The image model encodes some assumptions about the super resolved image. These assumptions are meant to suppress reconstruction artifacts that arise due to deterministic physical model error, stochastic measurement noise, and potential undersampling. In practice, the performance of iterative methods are limited by imaging models compatible with optimization. Deep learning-based methods can effectively learn image models of arbitrary complexity, but lack the theoretical explainability and robustness of iterative techniques. Consensus equilibrium (CE) generalizes the iterative techniques beyond optimization, enabling blackbox algorithms such as traditional and neural image denoisers to be used as the image model. CE-based approaches retain much of the explainability and robustness of iterative techniques while allowing the expressiveness of machine learning image models to be used. Additionally, by unrolling iterations of CE with an embedded image denoiser, the image denoiser can be further trained and specialized to the specific application with potentially higher quality reconstructions. Under this project, we demonstrated the feasibility of training an unrolled neural network based upon CE. While we didn’t train one, we showed that the CE process is differentiable and its gradient can be tractably computed. We also explored the usage of a variants of CE akin to generative neural works. Most importantly, we applied the CE framework to a number of problems including non-blind deconvolution, upsampling, single-image super resolution, MISR, event-based sensing, and saturated deconvolution. Our MISR prototype creates high quality reconstructions with an order of magnitude fewer images than previous approaches and, critically, produces these reconstructions fast enough for practical usage.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

A Study of Intermittent Turbulence in Stable Arctic Boundary Layers

Abstract Polar boundary layers are difficult to model due to the existence of intermittent turbulence within stable layers. Here we present a case study evaluation of coherent structures in a stable boundary layer observed during a series of flights with an uncrewed aircraft system (DataHawk2) on 19 October 2016 at Oliktok Point, Alaska as part of the ERASMUS (Evaluation of Routine Atmospheric Sounding Measurements using Unmanned Systems) field campaign. During a sequence of five flights over a nine-hour period, 57 profiles of atmospheric properties (0–400 m a.g.l) were collected. Turbulence was identified using derived Richardson Number, temperature structure function parameter, and turbulence kinetic energy dissipation. Throughout all flights on this strongly stable day, intermittent turbulence was observed. These turbulent layers showed well-mixed potential temperature profiles embedded within otherwise stable potential temperature profiles; often resulting in a characteristic staircase pattern. Turbulent layers ranged from 1 to 30 m deep, with most individual layers being 1–2 m deep. Vertical propagation velocities of layers in the lower atmosphere were on the order of a few cm s −1 , typical of non-convective environments. In different regions of the profile, turbulence was driven by a different balance of buoyancy and shear forces, with turbulence in the near surface environment driven by strong shear forces overcoming strong resistance to buoyancy, while turbulence in elevated layers characterized by weaker shear forces overcoming weaker resistance to buoyancy. We discuss the potential of such datasets for improving subgrid parameterizations of small-scale turbulence embedded within stable boundary layers.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Physics-Informed Deep Learning-Based Proof-of-Concept Study of a Novel Elastohydrodynamic Seal for Supercritical CO 2 Turbomachinery

Supercritical carbon dioxide (sCO 2 ) power cycles show promising potential of higher plant efficiencies and power densities for a wide range of power generation applications such as fossil fuel power plants, nuclear power production, solar power, and geothermal power generation. sCO 2 leakage through the turbomachinery has been one of the main concerns in such applications. To offer a potential solution, we propose an elastohydrodynamic (EHD) seal that can work at elevated pressures and temperatures with low leakage and minimal wear. The EHD seal has a very simple, sleeve-like structure, wrapping on the rotor with minimal initial clearance at micron levels. Here, in this work, a proof-of-concept study for the proposed EHD seal was presented by using the simplified Reynolds equation and Lame’s formula for the fluid flow in the clearance and for seal deformation, respectively. The set of nonlinear equations was solved by using both the conventional Prediction–Correction (PC) method and modern Physics-Informed Neural Network (PINN). It was shown that the physics-informed deep learning method provided good computational efficiency in resolving the steep pressure gradient in the clearance with good accuracy. The results showed that the leakage rates increased quadratically with working pressures and reached a steady-state at high-pressure values of 15~20 MPa, where Q = 300 g/s at 20 MPa for an initial seal clearance of 255 μm. This indicates that the EHD seal could be tailored to become a potential solution to minimize the sCO 2 discharge in power plants.

30 DIRECT ENERGY CONVERSION↗
DOE OSTI2022

Deep learning to estimate permeability using geophysical data

Time-lapse electrical resistivity tomography (ERT) is a popular geophysical method to estimate three-dimensional (3D) permeability fields from electrical potential difference measurements. Traditional inversion and data assimilation methods are used to ingest this ERT data into hydrogeophysical models to estimate permeability. Due to ill-posedness and the curse of dimensionality, existing inversion strategies provide poor estimates and low resolution of the 3D permeability field. Recent advances in deep learning provide us with powerful algorithms to overcome this challenge. This paper presents a deep learning (DL) framework to estimate the 3D subsurface permeability from time-lapse ERT data. To test the feasibility of the proposed framework, we train DL-enabled inverse models on simulation data. Each measurement in both synthetic and field data is standardized by removing the mean and scaling the time-series to unit variance. This pre-processing step is necessary to bring simulation data closer to field observations. Subsurface process models based on hydrogeophysics are used to generate this synthetic data. Training performed on limited simulation data resulted in the DL model over-fitting. An advanced data augmentation based on mixup is implemented to generate additional training samples to overcome this issue. This mixup technique creates weakly labeled (low-fidelity) samples from strongly labeled (high-fidelity) data. The weakly labeled training data is then used to develop DL-enabled inverse models and reduce over-fitting. As both time-lapse ERT (1133048 features/realization) and 3D permeability (585453 features/realization) data samples are from a high-dimensional space, principal component analysis (PCA) is employed to reduce dimensionality. Encoded ERT and encoded permeability are generated using the trained PCA estimators. A deep neural network is then trained to map the encoded ERT to encoded permeability. This mixup training and unsupervised learning allowed us to build a fast and reasonably accurate DL-based inverse model under limited simulation data. Results show that proposed weak supervised learning can capture salient spatial features in the 3D permeability field. Quantitatively, the average mean squared error (in terms of the natural log) on the strongly labeled training, validation, and test datasets is less than 0.5. The R 2 -score (global metric) is greater than 0.75, and the percent error in each cell (local metric) is less than 10%. Finally, an added benefit in terms of computational cost is that the proposed DL-based inverse model is at least O(10 4 ) times faster than running a forward model once it is trained. Data generation, DL model training, and hyperparameter tuning to identify optimal neural network architectures utilized high-performance computing resources while the DL inference is performed on a standard laptop. Approximately, O(10 5 ) processor hours are used for generating data and DL tuning and training. We acknowledge that the data generation and DL model development are expensive. But once a DL model is trained, it can be re-used for inversion rapidly for the given system, with set physics and domain. Note that traditional inversion may require multiple forward model simulations (e.g., in the order of 10 to 1000), which are very expensive. This computational savings ≈ O(10 5 ) – O(10 7 )) makes the proposed DL-based inverse model attractive for subsurface imaging and real-time ERT monitoring applications due to fast and yet reasonably accurate estimations of permeability field.

58 GEOSCIENCES↗
DOE OSTI2024

New insights into the flow dynamics of a deep freshwater aquifer in the semi-arid and saline Cuvelai-Etosha Basin, Northern Namibia: Results of a multi-environmental tracer study

Study region A paleo-megafan system of the Cubango River in the northern parts of the semi-arid Cuvelai-Etosha Basin, shared by Angola and Namibia. It hosts a deep freshwater aquifer, the so-called Kalahari-Ohangwena 2 (KOH-2), with the potential to resolve the imminent regional water supply shortages. Study focus Hydrogeochemical and multi-environmental tracer studies incorporating the use of age tracers 14 C, 36 Cl, 81 Kr and 4 He to determine the age of groundwater and provide insights into the flow dynamics of the KOH-2. New hydrological insights for the region Stable water isotopes and noble gas thermometry show that in a period with higher rainfall and recharge, temperatures were at least 3 – 4 °C lower than today. Several arguments led to the conclusion that younger groundwater, possibly of an age of 35,000 years, is mixed with ancient saline pore water. These include: 1) the correlation of measured 36 Cl and 81 Kr ratios, as well as 4 He concentrations, using a binary mixing model, and 2) the substantial variation in 81 Kr ages, ranging from 40,000 to 170,000 years, over relatively short distances—a phenomenon challenging to explain by advective groundwater flow equations. Consequently, the ages derived from 81 Kr measurements serve as indicators of the extent of freshening and therefore describe mixing ages rather than absolute travel times.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

DNN-based policies for stochastic AC OPF

We report a prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2020

Hydrogen Dynamics in Supercritical Water Probed by Neutron Scattering and Computer Simulations

In this work, an investigation of supercritical water is presented combining inelastic and deep inelastic neutron scattering experiments and molecular dynamics simulations based on a machine-learned potential of ab initio quality. The local hydrogen dynamics is investigated at 250 bar and in the temperature range of 553–823 K, covering the evolution from subcritical liquid to supercritical gas-like water. The evolution of libration, bending, and stretching motions in the vibrational density of states is studied, analyzing the spectral features by a mode decomposition. Moreover, the hydrogen nuclear momentum distribution is measured, and its anisotropy is probed experimentally. It is shown that hydrogen bonds survive up to the higher temperatures investigated, and we discuss our results in the framework of the coupling between intramolecular modes and intermolecular librations. Results show that the local potential affecting hydrogen becomes less anisotropic within the molecular plane in the supercritical phase, and we attribute this result to the presence of more distorted hydrogen bonds.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Evolution of microscopic heterogeneity and dynamics in choline chloride-based deep eutectic solvents

Deep eutectic solvents (DESs) are an emerging class of non-aqueous solvents that are potentially scalable, easy to prepare and functionalize for many applications ranging from biomass processing to energy storage technologies. Predictive understanding of the fundamental correlations between local structure and macroscopic properties is needed to exploit the large design space and tunability of DESs for specific applications. Here, we employ a range of computational and experimental techniques that span length-scales from molecular to macroscopic and timescales from picoseconds to seconds to study the evolution of structure and dynamics in model DESs, namely Glyceline and Ethaline, starting from the parent compounds. We show that systematic addition of choline chloride leads to microscopic heterogeneities that alter the primary structural relaxation in glycerol and ethylene glycol and result in new dynamic modes that are strongly correlated to the macroscopic properties of the DES formed.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Deep Learning and Structural Imaging of Materials

Deep learning has had a transformative effect on numerous domains and is actively utilized by many scientists in data-intensive fields such as high-energy physics and cosmology. Materials science, and in particular, the structural imaging of materials with electrons and X-rays are projected to enter the age of scientific data torrents, positioning them as new application spaces for modern artificial intelligence. In this contribution, we provide a synopsis on the foundations and latest progress in deep learning and present an in-depth application of utilizing modern deep artificial neural networks in scanning transmission electron microscopy to extract structural material properties. We use this case study to expose the strengths of deep learning-based models and discuss their current limitations, in the process highlighting their potential use in other data-intensive structural imaging modalities.

Laanait, Nouamane↗
DOE OSTI2020

Co-op at Sandia National Laboratories (July - December 2019, Final Report)

This co-op was performed at Sandia National Laboratories (SNL) within the Weapon Surety Engineering 11 Department (9435), which is a customer-focused organization that provides engineering and system analysis expertise to ensure a safe deterrent throughout the entire weapon lifecycle. Engineers in 9435 develop a deep knowledge in both component and system function to support rigorous evaluation and mitigation of potential failure modes. They operate across multiple engineering disciplines (mechanical, electrical, computer, materials and systems engineering) with opportunities to develop crossdisciplinary capability. The team supports a variety of stockpile systems and is part of the product teams during development, design and production, as well as advanced concept and exploratory efforts. 9435 engineers use their extensive component and system knowledge, as well as experimental data and modeling, to ensure products function as intended with assured safety. Members of the department learn the function of multiple components, how those components integrate within the system and apply surety principles and processes to ensure a safe, secure, reliable, and effective U.S. nuclear deterrent.

42 ENGINEERING↗
DOE OSTI2023

Evaluation of Nuclear Spent Fuel Disposal in Clay-Bearing Rock - Process Model Development and Experimental Studies

This report represents the milestone deliverable M2SF-23SN010301072 “Evaluation of Nuclear Spent Fuel Disposal in Clay-Bearing Rock - Process Model Development and Experimental Studies” The report provides a status update of FY23 activities for the work package Argillite Disposal work packages for the DOE-NE Spent Fuel Waste Form Science and Technology (SFWST) Program. Clay-rich geological media (often referred as shale or argillite) are among the most abundant type of sedimentary rock near the Earth’s surface. Argillaceous rock formations have the following advantageous attributes for deep geological nuclear waste disposal: widespread geologic occurrence, found in stable geologic settings, low permeability, self-sealing properties, low effective diffusion coefficient, high sorption capacity, and have the appropriate depth and thickness to host nuclear waste repository concepts. The DOE R&D program under the Spent Fuel Waste Science Technology (SFWST) campaign has made key progress (through experiment, modeling, and testing) in the study of chemical and physical phenomena that could impact the long-term safety assessment of heat-generating nuclear waste disposition in clay/shale/argillaceous rock. International collaboration activities comprising field-scale heater tests, field data monitoring, and laboratory-scale experiments provide key information on changes to the engineered barrier system (EBS) material exposed high thermal loads. Moreover, consideration of direct disposal of large capacity dual-purpose canisters (DPCs) as part of the back-end SNF waste disposition strategy has generated interest in improving our understanding of the effects of elevated temperatures on the engineered barrier system (EBS) design concepts. Chemical and structural analyses of sampled bentonite material from laboratory tests at elevated temperatures are key to the characterization of thermal effects affecting bentonite clay barrier performance. The knowledge provided by these experiments is crucial to constrain the extent of sacrificial zones in the EBS design during the thermal period. Thermal, hydrologic, mechanical, and chemical (THMC) data collected from heater tests and laboratory experiments have been used in the development, validation, and calibration of THMC simulators to model near-field coupled processes. This information leads to the development of simulation approaches to assess issues on coupled processes involving porous media flow, transport, geomechanical phenomena, chemical interactions with barrier/geologic materials, and the development of EBS concepts. These lines of knowledge are central to the design of deep geological backfilled repository concepts where temperature plays a key role in the EBS behavior, potential interactions with host rock, and long-term performance in the safety assessment.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2024

RANGERS: Methodology Report on Design and Performance Assessment of Engineered Barrier Systems in a Salt Repository for HLW/SNF

Salt formations are one of the potential host rocks for the final disposal of high-level radioactive waste (HLW) in deep geological repositories, both in Germany and the United States. The safe isolation of radioactive waste in these repositories relies on a multi-barrier system, combining engineered and natural barriers. The natural barrier is provided by the salt rock itself, known for its self-sealing properties and long-term stability. The engineered barrier, on the other hand, comprises sealing components strategically placed within the repository to enhance its containment capabilities. In both Germany and the United States, long-term safety assessments require demonstrating the integrity of the natural barrier for a period of up to 1 million years. Concurrently, the engineered barrier system (EBS) must maintain its structural and functional integrity until the long-term sealing, such as the granular salt backfill material, has re-consolidated to its final low porosity and permeability. Based on extensive expertise and experience with engineered barriers in salt formations, BGE TECHNOLOGY GmbH and Sandia National Laboratories have partnered to develop a robust methodology for the integrity and performance assessment of EBS in HLW repositories through the RANGERS project. This collaborative effort aims to establish a unified approach to geotechnical engineering, repository design, integrity and performance evaluation of EBS in salt repositories.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Automated, high-accuracy classification of textured microstructures using a convolutional neural network

Crystallographic texture is an important descriptor of material properties but requires time-intensive electron backscatter diffraction (EBSD) for identifying grain orientations. While some metrics such as grain size or grain aspect ratio can distinguish textured microstructures from untextured microstructures after significant grain growth, such morphological differences are not always visually observable. This paper explores the use of deep learning to classify experimentally measured textured microstructures without knowledge of crystallographic orientation. A deep convolutional neural network is used to extract high-order morphological features from binary images to distinguish textured microstructures from untextured microstructures. The convolutional neural network results are compared with a statistical Kolmogorov–Smirnov tests with traditional morphological metrics for describing microstructures. Results show that the convolutional neural network achieves a significantly improved classification accuracy, particularly at early stages of grain growth, highlighting the capability of deep learning to identify the subtle morphological patterns resulting from texture. The results demonstrate the potential of a convolutional neural network as a tool for reliable and automated microstructure classification with minimal preprocessing.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Unlocking plant-microbial interactions in deep Mollisols in the Midwestern US: Linking depth gradients in roots, microbial activity, and soil carbon in agroecosystems

Deep-rooted plants may build soil carbon (C) stocks, but most research has focused on shallow soils, leaving gaps in our understanding of how shifts in the balance between decomposition and C inputs drive soil C accumulation with depth. Thus, our objectives were to: (1) link depth gradients in root biomass with microbial activity and soil C stocks down to 1 m, and (2) examine the potential of simple C inputs to prime soil C across depths. To this end, we dug 5 quantitative soil pits in Argiudolls under mature perennial miscanthus plots in the SoyFACE Farm (Champaign-Urbana, IL). We added 13 C labeled glucose to our soils to determine the fate of simple C inputs with depth. We found that fine root biomass, total soil C, mineral-associated organic C (MAOC), particulate organic C (POC), and microbial activity (as measured by potential enzyme activity) declined with depth. POC declined more rapidly than MAOC, resulting in an increase in the ratio of MAOC-to-POC. Root biomass, enzyme activity (either acid phosphatase or n-acetyl-glucosaminadase) activity, and microbial respiration explained 74% and 38% of the variability in soil total C and MAOC, respectively, while POC was dependent on root biomass and microbial respiration (47%). Although the incorporation of simple 13 C inputs into MAOC was similar across depths, these inputs led to greater net MAOC losses in shallow soils than in deeper soils between 50 and 100 cm. The divergent impact of simple C inputs across depths may suggest that MAOC in shallow soils is more susceptible to priming losses, while C inputs into deep soils may instead be more persistent. Collectively, our results suggest that depth gradients in soil C stocks represents a balance between inputs, decomposition, and microbial necromass production and that increases in root C inputs by deep-rooted plants may have the potential to build stable MAOC.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Improving Protein–Ligand Interaction Modeling with cryo-EM Data, Templates, and Deep Learning in 2021 Ligand Model Challenge

Elucidating protein–ligand interaction is crucial for studying the function of proteins and compounds in an organism and critical for drug discovery and design. The problem of protein–ligand interaction is traditionally tackled by molecular docking and simulation, which is based on physical forces and statistical potentials and cannot effectively leverage cryo-EM data and existing protein structural information in the protein–ligand modeling process. In this work, we developed a deep learning bioinformatics pipeline (DeepProLigand) to predict protein–ligand interactions from cryo-EM density maps of proteins and ligands. DeepProLigand first uses a deep learning method to predict the structure of proteins from cryo-EM maps, which is averaged with a reference (template) structure of the proteins to produce a combined structure to add ligands. The ligands are then identified and added into the structure to generate a protein–ligand complex structure, which is further refined. The method based on the deep learning prediction and template-based modeling was blindly tested in the 2021 EMDataResource Ligand Challenge and was ranked first in fitting ligands to cryo-EM density maps. These results demonstrate that the deep learning bioinformatics approach is a promising direction for modeling protein–ligand interactions on cryo-EM data using prior structural information.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Deep learning-based spatio-temporal fusion for high-fidelity ultra-high-speed X-ray radiography

Full-field ultra-high-speed (UHS) X-ray imaging experiments have been well established to characterize various processes and phenomena. However, the potential of UHS experiments through the joint acquisition of X-ray videos with distinct configurations has not been fully exploited. In this paper, we investigate the use of a deep learning-based spatio-temporal fusion (STF) framework to fuse two complementary sequences of X-ray images and reconstruct the target image sequence with high spatial resolution, high frame rate and high fidelity. We applied a transfer learning strategy to train the model and compared the peak signal-to-noise ratio (PSNR), average absolute difference (AAD) and structural similarity (SSIM) of the proposed framework on two independent X-ray data sets with those obtained from a baseline deep learning model, a Bayesian fusion framework and the bicubic interpolation method. The proposed framework outperformed the other methods with various configurations of the input frame separations and image noise levels. With three subsequent images from the low-resolution (LR) sequence of a four times lower spatial resolution and another two images from the high-resolution (HR) sequence of a 20 times lower frame rate, the proposed approach achieved average PSNRs of 37.57 dB and 35.15 dB, respectively. When coupled with the appropriate combination of high-speed cameras, the proposed approach will enhance the performance and therefore the scientific value of UHS X-ray imaging experiments.

deep learning↗