Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “network acceleration”

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 1,153 records · Page 64
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Accurate Machine Learning for Predicting the Viscosities of Deep Eutectic Solvents

Deep eutectic solvents (DESs) are emerging as environmentally friendly designer solvents for mass transport and heat transfer processes in industrial applications; however, the lack of accurate tools to predict and thus control their viscosities under both a range of environmental factors and formulations hinders their general application. While DESs may serve as designer solvents, with nearly unlimited combinations, this unfortunately makes it experimentally infeasible to comprehensively measure the viscosities of all DESs of potential industrial interest. To assist in the design of DESs, we have developed several new machine learning (ML) models that accurately and rapidly predict the viscosities of a diverse group of DESs at different temperatures and molar ratios using, to date, one of the most comprehensive data sets containing the properties of over 670 DESs over a wide range of temperatures (278.15–385.25 K). Three ML models, including support vector regression (SVR), feed forward neural networks (FFNNs), and categorical boosting (CatBoost), were developed to predict DES viscosity as a function of temperature and molar ratio and contrasted with multilinear and two-factor polynomial regression baselines. Further, quantum chemistry-based, COSMO-RS-derived sigma profile (σ-profile) features were used as inputs for the ML models. The CatBoost model is excellent at externally predicting DES viscosity, as indicated by high R 2 (0.99) and low root-mean-square-error (RMSE) and average absolute relative deviations (AARD) (5.22%) values for the testing data sets, and 98% of the data points lie within the 15% of AARD deviations. Furthermore, SHapley additive explanation (SHAP) analysis was employed to interpret the ML results and rationalize the viscosity predictions. The result is an ML approach that accurately predicts viscosity and will aid in accelerating the design of appropriate DESs for industrial applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Many-body expansion based machine learning models for octahedral transition metal complexes

Abstract Graph-based machine learning (ML) models for material properties show great potential to accelerate virtual high-throughput screening of large chemical spaces. However, in their simplest forms, graph-based models do not include any 3D information and are unable to distinguish stereoisomers such as those arising from different orderings of ligands around a metal center in coordination complexes. In this work we present a modification to revised autocorrelation descriptors, a molecular graph featurization method, for predicting spin state dependent properties of octahedral transition metal complexes (TMCs). Inspired by analytical semi-empirical models for TMCs, the new modeling strategy is based on the many-body expansion (MBE) and allows one to tune the captured stereoisomer information by changing the truncation order of the MBE. We present the necessary modifications to include this approach in two commonly used ML methods, kernel ridge regression and feed-forward neural networks. On a test set composed of all possible isomers of binary TMCs, the best MBE models achieve mean absolute errors (MAEs) of 2.75 kcal mol −1 on spin-splitting energies and 0.26 eV on frontier orbital energy gaps, a 30%–40% reduction in error compared to models based on our previous approach. We also observe improved generalization to previously unseen ligands where the best-performing models exhibit MAEs of 4.00 kcal mol −1 (i.e. a 0.73 kcal mol −1 reduction) on the spin-splitting energies and 0.53 eV (i.e. a 0.10 eV reduction) on the frontier orbital energy gaps. Because the new approach incorporates insights from electronic structure theory, such as ligand additivity relationships, these models exhibit systematic generalization from homoleptic to heteroleptic complexes, allowing for efficient screening of TMC search spaces.

Meyer, Ralf (ORCID:0000000322360261)↗
DOE OSTI2023

Active Learning Framework

Machine learning (ML) of interatomic potentials show great promise to accelerate scientific simulation, e.g., by emulating expensive computations at a high accuracy but much reduced computational cost. Training datasets are calculated from computationally expensive ab initio quantum mechanics methods, density functional theory (DFT). Trained on this data, an ML model can be very successful in predicting energy and forces for new atomic configurations. A critical factor is the quality and diversity of the training dataset. Thus, a highly automated approach to dataset construction based on active learning framework is designed suitable for material physics. The active learning scheme begins with fully randomized atomic configurations. Then, many Molecular Dynamics (MD) trajectories are simulated using current ML potentials, where each MD trajectory is initialized to a random disordered configuration. The temperature is varied in order to diversify the sampled configuration during these simulations. The variance of predictions for eight neural networks within an ensemble is analyzed to determine whether the model is operating as expected. This helps in determining whether collecting more data would be helpful to the model by checking the ensemble variance is greater than the threshold. In this case, the MD trajectory is terminated and the final atomic configuration is placed on a queue (SQL database) for DFT calculations and added to training dataset. Periodically, ML model is retrained to the updated training model. This Active Learning loop is iterated until the cost of MD simulations becomes prohibitively expensive. The MD simulations will hopefully be sufficiently robust to support nucleation after many active learning iterations. In this sense, active learning scheme must automatically discover the important low energy and nonequilibrium physics.

Nebgen, Benjamin↗
DOE OSTI2023

Advanced Research Directions on AI for Science, Energy, and Security: Report on Summer 2022 Workshops

Over the past decade, fundamental changes in artificial intelligence (AI)—from foundational to applied—have delivered dramatic insights across a wide breadth of U.S. Department of Energy (DOE) mission space. AI is helping to augment and improve scientific and engineering workflows (e.g., for control, design, and dramatic performance gains through surrogate models) in national security, the Office of Science, and DOE’s applied energy programs. The progress and potential for AI in DOE science was captured in the 2020 “AI for Science” report from the DOE laboratory community in collaboration with academia and industry. Specific scientific areas ready to further leverage the power of AI ranged from the scale and performance of computational models to data analysis to creating new classes of observations using computer vision. Since that report, the scale and scope of scientific AI have accelerated, revealing new, emergent properties that yield insights that go beyond enabling opportunities to being potentially transformative in the way that scientific problems are posed and solved. Thus, under the guidance of both the Office of Science (SC) and the National Nuclear Security Administration (NNSA), the DOE national laboratories organized a series of workshops in 2022 to gather input on new and rapidly emerging opportunities and challenges of scientific AI. This 2023 report is a synthesis of those workshops. The scientific community believes AI can have a foundational impact on a broad range of DOE missions, including science, energy, and national security. Further, DOE has unique capabilities that enable the community to drive progress in scientific use of AI, building on long-standing DOE strengths and investments in computation, data, and communications infrastructure, spanning the Energy Sciences Network (ESnet), the Exascale Computing Project (ECP), and integrative programs such as the NNSA Office of Defense Programs Advanced Simulation and Computing (ASC) and the SC Scientific Discovery through Advanced Computing (SciDAC) programs.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1998

The Paradox of Filamented Coronal Hole Flow but Uniform High Speed Wind

Plumes and rays in coronal holes are nearly radially aligned density striations that follow the ambient magnetic field. They have long been known, but have gained new interest with growing awareness that coronal hole flow is inherently filamentary. In retrospect, filamentary flow should have been no surprise. This is because,Beta much less than 1 in coronal holes inside approximately 10 Solar radius, allowing the flow to be filamentary down to the smallest scale of photospheric magnetic activity. While the magnetic field itself is locally smooth across any height above ca. 50,000 km, SOHO/MDI has shown that the photospheric magnetic field is a complex array of rapidly evolving small bipoles that are constantly emerging, evolving, and cancelling. The resulting activity is manifested in microflares, concentrated in the magnetic network, that produce Impulsive injections at the footpoints of coronal field lines. The uneven distribution of this activity in space and time is the source of coronal hole filamentation. What is surprising is that the radial flow speed also exhibits filamentary structure. It is not well described as smooth, spherically symmetric, diverging flow, but instead ranges from 300 to over 1000 km/s at 5.5 Solar radius among field-aligned filaments like those seen in plumes and rays [Feldman et al., JGR, Dec. 1997]. This is completely unlike the constant high speed solar wind reported beyond 0.3 AU. Consequently, plumes and filamentary structure must be strongly mixed, and the mixing must be far along by 0.3 AU to be consistent with Helios observations. The paradox is what causes the mixing? Existing models of coronal heating and solar wind acceleration hardly address this issue. One possibility we are investigating is the MHD Kelvin-Helmholtz instability, to which the shear between plumes and interplume corona is expected to become unstable at 5-10 Solar radius. This instability can be simulated and followed far into the nonlinear regime and may lead to Alfvenic fluctuations like those seen at 1 AU.

Suess, Steven T.↗
DOE OSTI2024

HDBind: encoding of molecular structure with hyperdimensional binary representations

Traditional methods for identifying “hit” molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

DAmodel: hierarchical Bayesian modelling of DA white dwarfs for spectrophotometric calibration

We use hierarchical Bayesian modelling to calibrate a network of 32 all-sky faint DA white dwarf (DA WD) spectrophotometric standards (⁠16.5 < V , 19.5⁠) alongside three CALSPEC standards, from 912 Å to 32 μm. The framework is the first of its kind to jointly infer photometric zero points and WD parameters (surface gravity log g⁠, effective temperature T eff ⁠, extinction A V ⁠, dust relation parameter R V ) by simultaneously modelling both photometric and spectroscopic data. We model panchromatic Hubble Space Telescope Wide Field Camera 3 (HST/WFC3) UVIS and IR photometry, HST/STIS UV spectroscopy, and ground-based optical spectroscopy to sub-per cent precision. Photometric residuals for the sample are the lowest yet yielding < 0.004 mag RMS on average from the UV to the NIR, achieved by jointly inferring time-dependent changes in system sensitivity and WFC3/IR count-rate nonlinearity. Our GPU-accelerated implementation enables efficient sampling via Hamiltonian Monte Carlo, critical for exploring the high-dimensional posterior space. The hierarchical nature of the model enables population analysis of intrinsic WD and dust parameters. Inferred spectral energy distributions from this model will be essential for calibrating the James Webb Space Telescope as well as next-generation surveys, including Vera Rubin Observatory’s Legacy Survey of Space and Time and the Nancy Grace Roman Space Telescope.

methods: statistical↗
DOE OSTI2026

Location Identifiers, Metadata, and Map for Field Measurements at the East-Taylor Watershed Community Observatory, Colorado, USA (Version 3.3)

This dataset contains identifiers, metadata, and a map of the locations where field measurements have been conducted at the East-Taylor Watershed Community Observatory located in the Upper Colorado River Basin, United States. This is version 3.3 of the dataset and replaces the prior version 3.2 (see below for details on changes between the versions). Dataset description: The East River-Taylor Watershed is the primary field site of the Watershed Function Scientific Focus Area (WFSFA) and the Rocky Mountain Biological Laboratory. Researchers from several institutions generate highly diverse hydrological, biogeochemical, climate, vegetation, geological, remote sensing, and model data at the East-Taylor Watershed in collaboration with the WFSFA. Thus, the purpose of this dataset is to maintain an inventory of the field locations and instrumentation to provide information on the field activities in the East-Taylor Watershed and coordinate data collected across different locations, researchers, and institutions. The dataset contains (1) a README file with information on the various files, (2) three csv files describing the metadata collected for each surface point location, plot and region registered with the WFSFA, (3) csv files with metadata and contact information for each surface point location registered with the WFSFA, (4) a csv file with with metadata and contact information for plots, (5) a csv file with metadata for geographic regions and sub-regions within the watershed, (6) a compiled xlsx file with all the data and metadata which can be opened in Microsoft Excel, (7) a kml map of the locations plotted in the watershed which can be opened in Google Earth, (8) a jpg image of the kml map which can be viewed in any photo viewer, and (9) a zipped file with the registration templates used by the SFA team to collect location metadata. The zipped template file contains two csv files with the blank templates (point and plot), two csv files with instructions for filling out the location templates, and one compiled xlsx file with the instructions and blank templates together. Additionally, the templates in the xlsx include drop down validation for any controlled metadata fields. Persistent location identifiers (Location_ID) are determined by the WFSFA data management team and are used to track data and samples across locations. Dataset uses: This location metadata is used to update the Watershed SFA’s publicly accessible Field Information Portal (an interactive field sampling metadata exploration tool; https://wfsfa-data.lbl.gov/watershed/), the kml map file included in this dataset, and other data management tools internal to the Watershed SFA team. Version Information: The latest version of this dataset publication is version 3.3. This version contains 167 new point locations, 1 new plot, and 2 new geographic regions. Overall, there are a total of 1439 point locations, 75 plots, and 54 geographic regions. Additionally, the kml map of locations and image now includes two boundaries (Upper Ohio Creek (UO) and Carbon Creek (CA)) outside of the East River watershed (USGS HUC-10) and accompanying stream network that represents areas of focus. Refer to methods for further details on the version history. This dataset will be updated on a periodic basis with new measurement location information. Researchers interested in having their East-Taylor Watershed measurement locations added to this list should reach out to the WFSFA data management team at wfsfa-data@googlegroups.com. Acknowledgments: Please cite this dataset if using any of the location metadata in other publications or derived products. If using the location metadata for the 2018 NEON hyperspectral campaign, additionally cite Chadwick et al. (2020). doi:10.15485/1618130. This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231. Part of this work was performed at SLAC Accelerator Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-76SF00515.

2018 NEON and 2025 CHESS Campaigns↗
DOE OSTI2023

Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients

Nuclear reactor safety and efficiency can be enhanced through the development of accurate and fast methods for prediction of reactor transient (RT) states. Physics informed neural networks (PINNs) leverage deep learning methods to provide an alternative approach to RT modeling. Applications of PINNs in monitoring of RTs for operator support requires near real-time model performance. However, as with all machine learning models, development of a PINN involves time-consuming model training. Here, we show that a transfer learning (TL-PINN) approach achieves significant performance gain, as measured by reduction of the number of iterations for model training. Using point kinetic equations (PKEs) model with six neutron precursor groups, constructed with experimental parameters of the Purdue University Reactor One (PUR-1) research reactor, we generated different RTs with experimentally relevant range of variables. The RTs were characterized using Hausdorff and Fréchet distance. We have demonstrated that pre-training TL-PINN on one RT results in up to two orders of magnitude acceleration in prediction of a different RT. The mean error for conventional PINN and TL-PINN models prediction of neutron densities is smaller than 1%. We have developed a correlation between TL-PINN performance acceleration and similarity measure of RTs, which can be used as a guide for application of TL-PINNs.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

High-accuracy emulators for observables in ΛCDM, N eff, Σ m ν, and w cosmologies

ABSTRACT We use the emulation framework CosmoPower to construct and publicly release neural network emulators of cosmological observables, including the cosmic microwave background (CMB) temperature and polarization power spectra, matter power spectrum, distance-redshift relation, baryon acoustic oscillation (BAO) and redshift-space distortion (RSD) observables, and derived parameters. We train our emulators on Einstein–Boltzmann calculations obtained with high-precision numerical convergence settings, for a wide range of cosmological models including ΛCDM, wCDM, ΛCDM + Neff, and ΛCDM + Σmν. Our CMB emulators are accurate to better than 0.5 per cent out to ℓ = 104, which is sufficient for Stage-IV data analysis, and our P(k) emulators reach the same accuracy level out to $k=50 \, \, \mathrm{Mpc}^{-1}$, which is sufficient for Stage-III data analysis. We release the emulators via an online repository (CosmoPower Organisation), which will be continually updated with additional extended cosmological models. Our emulators accelerate cosmological data analysis by orders of magnitude, enabling cosmological parameter extraction analyses, using current survey data, to be performed on a laptop. We validate our emulators by comparing them to class and camb and by reproducing cosmological parameter constraints derived from Planck TT, TE, EE, and CMB lensing data, as well as from the Atacama Cosmology Telescope Data Release 4 CMB data, Dark Energy Survey Year-1 galaxy lensing and clustering data, and Baryon Oscillation Spectroscopic Survey Data Release 12 BAO and RSD data.

Astronomy & Astrophysics↗
DOE OSTI2025

Traffic Control via Connected and Automated Vehicles (CAVs): An Open-Road Field Experiment with 100 CAVs

The CIRCLES project aims to reduce instabilities in traffic flow, which are naturally occurring phenomena due to human driving behavior. Also called “phantom jams” or “stop-and-go waves,” these instabilities are a significant source of wasted energy. Toward this goal, the CIRCLES project designed a control system, referred to as the MegaController by the CIRCLES team, that could be deployed in real traffic. Our field experiment, the MegaVanderTest (MVT), leveraged a heterogeneous fleet of 100 longitudinally controlled vehicles as Lagrangian traffic actuators, each of which ran a controller with the architecture described in this article. The MegaController is a hierarchical control architecture that consists of two main layers. The upper layer is called the Speed Planner and is a centralized optimal control algorithm. It assigns speed targets to the vehicles, conveyed through the LTE cellular network. The lower layer is a control layer, running on each vehicle. It performs local actuation by overriding the stock adaptive cruise controller, using the stock onboard sensors. The Speed Planner ingests live data feeds provided by third parties as well as data from our own control vehicles and uses both to perform the speed assignment. The architecture of the Speed Planner allows for the modular use of standard control techniques, such as optimal control, model predictive control (MPC), kernel methods, and others. The architecture of the local controller allows for the flexible implementation of local controllers. Corresponding techniques include deep reinforcement learning (RL), MPC, and explicit controllers. Depending on the vehicle architecture, all onboard sensing data can be accessed by the local controllers or only some. Likewise, control inputs vary across different automakers, with inputs ranging from torque or acceleration requests for some cars to electronic selection of adaptive cruise control (ACC) setpoints in others. The proposed architecture technically allows for the combination of all possible settings proposed previously, that is {Speed Planner algorithms} × {local Vehicle Controller algorithms} × {full or partial sensing} × {torque or speed control}. As a result, most configurations were tested throughout the ramp up to the MegaVandertest (MVT).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

Data-Driven RANS Turbulence Closures for Forced Convection Flow in Reactor Downcomer Geometry

Recent progress in data-driven turbulence modeling has shown its potential to enhance or replace traditional equation-based Reynolds-averaged Navier-Stokes (RANS) turbulence models. Here, this work utilizes invariant neural network (NN) architectures to model Reynolds stresses and turbulent heat fluxes in forced convection flows (when the models can be decoupled). As the considered flow is statistically one dimensional, the invariant NN architecture for the Reynolds stress model reduces to the linear eddy viscosity model. To develop the data-driven models, direct numerical and RANS simulations in vertical planar channel geometry mimicking a part of the reactor downcomer are performed. Different conditions and fluids relevant to advanced reactors (sodium, lead, unitary-Prandtl-number fluid, and molten salt) constitute the training database. The models enabled accurate predictions of velocity and temperature, and compared to the baseline k–τ turbulence model with the simple gradient diffusion hypothesis, do not require tuning of the turbulent Prandtl number. The data-driven framework is implemented in the open-source graphics processing unit–accelerated spectral element solver nekRS and has shown the potential for future developments and consideration of more complex mixed convection flows.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
NASA NTRS1999

Tracker: Image-Processing and Object-Tracking System Developed

Tracker is an object-tracking and image-processing program designed and developed at the NASA Lewis Research Center to help with the analysis of images generated by microgravity combustion and fluid physics experiments. Experiments are often recorded on film or videotape for analysis later. Tracker automates the process of examining each frame of the recorded experiment, performing image-processing operations to bring out the desired detail, and recording the positions of the objects of interest. It can load sequences of images from disk files or acquire images (via a frame grabber) from film transports, videotape, laser disks, or a live camera. Tracker controls the image source to automatically advance to the next frame. It can employ a large array of image-processing operations to enhance the detail of the acquired images and can analyze an arbitrarily large number of objects simultaneously. Several different tracking algorithms are available, including conventional threshold and correlation-based techniques, and more esoteric procedures such as "snake" tracking and automated recognition of character data in the image. The Tracker software was written to be operated by researchers, thus every attempt was made to make the software as user friendly and self-explanatory as possible. Tracker is used by most of the microgravity combustion and fluid physics experiments performed by Lewis, and by visiting researchers. This includes experiments performed on the space shuttles, Mir, sounding rockets, zero-g research airplanes, drop towers, and ground-based laboratories. This software automates the analysis of the flame or liquid s physical parameters such as position, velocity, acceleration, size, shape, intensity characteristics, color, and centroid, as well as a number of other measurements. It can perform these operations on multiple objects simultaneously. Another key feature of Tracker is that it performs optical character recognition (OCR). This feature is useful in extracting numerical instrumentation data that are embedded in images. All the results are saved in files for further data reduction and graphing. There are currently three Tracking Systems (workstations) operating near the laboratories and offices of Lewis Microgravity Science Division researchers. These systems are used independently by students, scientists, and university-based principal investigators. The researchers bring their tapes or films to the workstation and perform the tracking analysis. The resultant data files generated by the tracking process can then be analyzed on the spot, although most of the time researchers prefer to transfer them via the network to their offices for further analysis or plotting. In addition, many researchers have installed Tracker on computers in their office for desktop analysis of digital image sequences, which can be digitized by the Tracking System or some other means. Tracker has not only provided a capability to efficiently and automatically analyze large volumes of data, saving many hours of tedious work, but has also provided new capabilities to extract valuable information and phenomena that was heretofore undetected and unexploited.

Klimek, Robert B.↗
NASA NTRS2003

Navigation Concepts for the James Webb Space Telescope

This paper evaluates the performance that can be achieved using candidate ground and onboard navigation approaches for operation of the James Webb Space Telescope, which will be in an orbit about the Sun-Earth L2 libration point. The ground navigation approach processes standard range and Doppler measurements from the Deep Space Network The onboard navigation approach processes celestial object measurements and/or ground-to- spacecraft Doppler measurements to autonomously estimate the spacecraft s position and velocity and Doppler reference frequency. Particular attention is given to assessing the absolute position and velocity accuracy that can be achieved in the presence of the frequent spacecraft reorientations and momentum unloads planned for this mission. The ground navigation approach provides stable navigation solutions using a tracking schedule of one 30-minute contact per day. The onboard navigation approach that uses only optical quality celestial object measurements provides stable autonomous navigation solutions. This study indicates that unmodeled changes in the solar radiation pressure cross-sectional area and modeled momentum unload velocity changes are the major error sources. These errors can be mitigated by modeling these changes, by estimating corrections to compensate for the changes, or by including acceleration measurements.

Long, Anne↗
DOE OSTI2024

Application of deep learning methods for beam size control during user operation at the Advanced Light Source

Past research at the Advanced Light Source (ALS) provided a proof-of-principle demonstration that deep learning methods could be effectively employed to compensate for the significant perturbations to the transverse electron beam size induced by user-controlled adjustments of the insertion devices. However, incorporating these methods into the ALS’ daily operations has faced notable challenges. The complexity of the system’s operational requirements and the significant upkeep demands has restricted their sustained application during user operation. Here, we introduce the development of a more robust neural network (NN)-based algorithm that utilizes a novel online fine-tuning approach and its systematic integration into the day-to-day machine operations. Our analysis emphasizes the process of NN model selection, demonstrates the superior performance of the NN-based method over traditional feedback methods, and examines the effectiveness and resilience of the new algorithm during user-operation scenarios. Published by the American Physical Society 2024

43 PARTICLE ACCELERATORS↗
DOE OSTI2021

Effect of Soil Properties and Input Motion on Site Amplification Using Validated Nonlinear Soil Model

Here, three-dimensional (3-D) nonlinear site response analyses are conducted using finite element models of actual soil profiles from ten nuclear power plant (NPP) sites in the United States to investigate the effects of soil properties and input motions on site amplification. The modeling approach developed in this study combines several novel elements, such as 3-D analysis (including vertical motions), nonlinear inelastic behavior of soil (strain-dependent shear modulus reduction and hysteretic damping), formulation of nonreflecting boundary conditions at the base, and generation of realistic outcrop ground motions for specific sites. All these elements of the modeling approach are first validated using actual data from five earthquakes at three downhole array stations recorded in the Kiban-Kyoshin network (KiK-net), Japan. The same approach is then used to develop site models of ten NPP sites in the United States and corresponding ground motions that are spectrally matched to the site hazard spectra. Eight sets of three-component input motions are used in the study and are categorized on the basis of presence or absence of a near-field pulse in the seed ground motions used for spectral matching. It is found that all sites retain a definite site amplification function regardless of the input motion, provided that the seed motion is spectrally matched to the site hazard spectra. The magnitude of site amplification and frequencies at which they occur depend upon soil properties, particularly the shear wave velocity profile and the constitutive relationship (strain-dependent shear modulus reduction and hysteretic damping) of soil. Amplification of spectral acceleration in the vertical direction (up-down motion) is found to be just as much as, if not more than, the amplification in the horizontal direction. Peak shear strain is found to be about 20% larger for near-field motions compared to far-field motions whereas maximum horizontal site amplification for far-field motions is found to be consistently larger than that of near-field motions, even though the differences between the two remain within the scatter resulting from individual ground motions.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

ESnet-JLab FPGA Accelerated Transport (data plane) [EJFAT (udplb)] v1.0

The ESnet-JLab FPGA Accelerated Transport system is a solution for streaming high-speed scientific measurement data from Data Acquisition Systems (DAQs) to high-performance computing facilties. It is generally compatible with many science workflows, and makes no assumptions about the specifics of any particular experiment. This program (udplb) implements the data plane portion of the EJFAT system. It is an FPGA design that rewrites and forwards data packets from a UDP-based scientific workflow to high-performance compute nodes. It depends on another program (udplbd, disclosed separately) to implement the control system.

Bengough, Peter [Malleable Networks, Inc.]↗
DOE OSTI2021

Simulation of Electron-Proton Scattering Events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)

We apply generative adversarial network (GAN) technology to build an event generator that simulates particle production in electron-proton scattering that is free of theoretical assumptions about underlying particle dynamics. The difficulty of efficiently training a GAN event simulator lies in learning the complicated patterns of the distributions of the particles physical properties. We develop a GAN that selects a set of transformed features from particle momenta that can be generated easily by the generator, and uses these to produce a set of augmented features that improve the sensitivity of the discriminator. The new Feature-Augmented and Transformed GAN (FAT-GAN) is able to faithfully reproduce the distribution of final state electron momenta in inclusive electron scattering, without the need for input derived from domain-based theoretical assumptions. The developed technology can play a significant role in boosting the science of existing and future accelerator facilities, such as the Electron-Ion Collider.

Alanazi, Yasir↗