Search NASA⌕ Search

SEARCH · Search NASA

Results for “High Performance Networking”

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 1,657 records · Page 92
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

On-Detector Machine Learning for Beam-Induced Background Rejection at a 10 TeV Muon Collider

A 10 TeV Muon Collider is a compelling candidate for a future energy-frontier facility, offering unprecedented opportunities to explore the fundamental laws of particle physics. Muon decays in the collider ring produce intense beam-induced background (BIB) that can overwhelm detector occupancy and exceed readout bandwidth constraints. We investigate the potential of on-detector Machine Learning for BIB rejection in the vertex detector, exploiting pixel cluster shapes to distinguish background from collision products. We study three classes of lightweight neural-network architectures, and evaluate their implementation feasibility using high-level synthesis. Selected architectures achieve 88 to 90% data reduction at 99% signal efficiency, while requiring hardware resources compatible with potential ASIC implementation. These results demonstrate the potential of performing substantial BIB rejection directly in the pixel readout, providing a strategy for meeting the tracker readout requirements at a future Muon Collider.

Abadjiev, Daniel [Chicago U.]↗
DOE OSTI2021

Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods

Abstract The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical, and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve a useful degree of accuracy. In this paper, we present a computationally inexpensive, accurate, data-driven surrogate model that directly learns the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. We integrate a statistically representative, low-dimensional description of the microstructure, obtained directly from phase-field simulations, with either a time-series multivariate adaptive regression splines autoregressive algorithm or a long short-term memory neural network. The neural-network-trained surrogate model shows the best performance and accurately predicts the nonlinear microstructure evolution of a two-phase mixture during spinodal decomposition in seconds, without the need for “on-the-fly” solutions of the phase-field equations of motion. We also show that the predictions from our machine-learned surrogate model can be fed directly as an input into a classical high-fidelity phase-field model in order to accelerate the high-fidelity phase-field simulations by leaping in time. Such machine-learned phase-field framework opens a promising path forward to use accelerated phase-field simulations for discovering, understanding, and predicting processing–microstructure–performance relationships.

36 MATERIALS SCIENCE↗
NASA NTRSDate not supplied

Systems Health Monitoring: Integrating FMEA into Bayesian Networks

The foreseeable high traffic density suggests that a large number of electric propulsion systems will enter the airspace, and that they will also operate at high frequency, e.g., large number of take offs and landings per unit time. The reliability of such critical systems is therefore key to ensure high safety standards in the low-altitude airspace. Diagnostic systems, which aim at identifying incipient faults, can mitigate unexpected failures or lower-than-expected reliability by performing early fault detection by monitoring the systems. A key element of fault diagnosis is fault detection and isolation (FDI), which complexity increases with the complexity of the system itself, namely the number of subsystems and components, interactions among sub-systems, and the number of sensors available. The proposed approach leverages combination of failure mode and effect analysis (FMEA) integrated with Bayesian networks, thus introducing dependability structures into a diagnostic framework to aid FDI. Faults and failure events from the FMEA are mapped within a Bayesian network, where network edges replicate the links embedded within FMEAs. The integrated framework enables the fault isolation process by identifying the probability of occurrence of specific faults or root causes given evidence observed through sensor signals. In this work, sub systems of Urban Air Mobility (UAM) type vehicle like avionics, structures, power-train etc. are taken into account to show the approach at the system level. This work integrates early design phase in the development of UAM type vehicles with diagnostic tools, which are often developed later in the product life-cycle, or retrofitted at a later time on systems. Failure mode and effect analysis (FMEA) derived for the system in the design phase is embedded within a Bayesian network (BN).

UAM↗
DOE OSTI2019

Screening Compounds for Fast Pyrolysis and Catalytic Biofuel Upgrading Using Artificial Neural Networks

Abstract There is significant interest among researchers in finding economically sustainable alternatives to fossil-derived drop-in fuels and fuel additives. Fast pyrolysis, a method for converting biomass into liquid hydrocarbons with the potential for use as fuels or fuel additives, is a promising technology that can be two to three times less expensive at scale when compared to alternative approaches such as gasification and fermentation. However, many bio-oils directly derived from fast pyrolysis have a high oxygen content and high acidity, indicating poor performance in diesel engines when used as fuels or fuel additives. Thus, a combination of selective fast pyrolysis and chemical catalysis could produce tuned bioblendstocks that perform optimally in diesel engines. The variance in performance for derived compounds introduces a feedback loop in researching acceptable fuels and fuel additives, as various combustion properties for these compounds must be determined after pyrolysis and catalytic upgrading occurs. The present work aims to reduce this feedback loop by utilizing artificial neural networks trained with quantitative structure-property relationship values to preemptively screen pure component compounds that will be produced from fast pyrolysis and catalytic upgrading. The quantitative structure-property relationship values selected as inputs for models are discussed, the cetane number and sooting propensity of compounds derived from the catalytic upgrading of phenol are predicted, and the viability of these compounds as fuels and fuel additives is analyzed. The model constructed to predict cetane number has a test set prediction root-mean-squared error of 9.874 cetane units, and the model constructed to predict yield sooting index has a test set prediction root-mean-squared error of 13.478 yield sooting index units (on the unified scale).

09 BIOMASS FUELS↗
DOE OSTI2022

Star–Galaxy Image Separation with Computationally Efficient Gaussian Process Classification

Abstract We introduce a novel method for discerning optical telescope images of stars from those of galaxies using Gaussian processes (GPs). Although applications of GPs often struggle in high-dimensional data modalities such as optical image classification, we show that a low-dimensional embedding of images into a metric space defined by the principal components of the data suffices to produce high-quality predictions from real large-scale survey data. We develop a novel method of GP classification hyperparameter training that scales approximately linearly in the number of image observations, which allows for application of GP models to large-size Hyper Suprime-Cam Subaru Strategic Program data. In our experiments, we evaluate the performance of a principal component analysis embedded GP predictive model against other machine-learning algorithms, including a convolutional neural network and an image photometric morphology discriminator. Our analysis shows that our methods compare favorably with current methods in optical image classification while producing posterior distributions from the GP regression that can be used to quantify object classification uncertainty. We further describe how classification uncertainty can be used to efficiently parse large-scale survey imaging data to produce high-confidence object catalogs.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Efficient Super-Resolution of Near-Surface Climate Modeling Using the Fourier Neural Operator

Downscaling methods are critical in efficiently generating high-resolution atmospheric data. However, state-of-the-art statistical or dynamical downscaling techniques either suffer from the high computational cost of running a physical model or require high-resolution data to develop a downscaling tool. Here, we demonstrate a recently proposed zero-shot super-resolution method, the Fourier neural operator (FNO), to efficiently perform downscaling without the need for high-resolution data. Because the FNO learns dynamics in Fourier space, FNO is a resolution-invariant emulator; it can be trained at a coarse resolution and produces emulation at any high resolution. We applied FNO to downscale a 4-km resolution Weather Research and Forecasting (WRF) Model simulation of near-surface heat-related variables over the Great Lakes region. The FNO is driven by the atmospheric forcings, and topographic features used in the WRF model at the same resolution. We incorporated a physics-constrained loss in FNO by using the Clausius-Clapeyron relation to better constrain the relations among the emulated states. Trained on merely 600 WRF snapshots at 4-km resolution, the FNO shows comparable performance with a widely used convolutional network, U-Net, achieving averaged modified Kling-Gupta Efficiency of 0.88 and 0.94 on the test dataset for temperature and pressure, respectively. We then employed the FNO to produce 1-km emulations to reproduce the fine climate features. Further, by taking the WRF simulation as ground truth, we show consistent performances at the two resolutions, suggesting the reliability of FNO in producing high-resolution dynamics. Our study demonstrates the potential of using FNO for zero-shot super-resolution in generating first-order estimation on atmospheric modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Assessing electrogenetic activation via a network model of biological signal propagation

Introduction: Molecular communication is the transfer of information encoded by molecular structure and activity. We examine molecular communication within bacterial consortia as cells with diverse biosynthetic capabilities can be assembled for enhanced function. Their coordination, both in terms of engineered genetic circuits within individual cells as well as their population-scale functions, is needed to ensure robust performance. We have suggested that “electrogenetics,” the use of electronics to activate specific genetic circuits, is a means by which electronic devices can mediate molecular communication, ultimately enabling programmable control. Methods: Here, we have developed a graphical network model for dynamically assessing electronic and molecular signal propagation schemes wherein nodes represent individual cells, and their edges represent communication channels by which signaling molecules are transferred. We utilize graph properties such as edge dynamics and graph topology to interrogate the signaling dynamics of specific engineered bacterial consortia. Results: We were able to recapitulate previous experimental systems with our model. In addition, we found that networks with more distinct subpopulations (high network modularity) propagated signals more slowly than randomized networks, while strategic arrangement of subpopulations with respect to the inducer source (an electrode) can increase signal output and outperform otherwise homogeneous networks. Discussion: We developed this model to better understand our previous experimental results, but also to enable future designs wherein subpopulation composition, genetic circuits, and spatial configurations can be varied to tune performance. We suggest that this work may provide insight into the signaling which occurs in synthetically assembled systems as well as native microbial communities.

Chun, Kayla↗
DOE OSTI2025

Search for Higgs boson decays into a Z boson and a light hadronically decaying resonance in pp collisions at s =13 TeV with the ATLAS detector

A search for decays of the Higgs boson into a Z boson and a light resonance, with a mass of 0.5–3.5 GeV, is performed using the full 140 fb−1 dataset of 13 TeV proton–proton collisions recorded by the ATLAS detector during LHC Run 2. Leptonic decays of the Z boson and hadronic decays of the light resonance are considered. The resonance can be interpreted as a J / ψ or η c meson, an axion-like particle, or a light pseudoscalar predicted in two-Higgs-doublet models. Due to its low mass, this resonance is produced with a high Lorentz boost in the laboratory frame and therefore reconstructed as a single small-radius jet of hadrons. A neural network is used to correct the Monte Carlo simulation of the total expected background using data from sideband regions. Two additional neural networks are used to distinguish signal from background, enhancing the purity of the signal region. A binned profile-likelihood fit is performed on the final-state invariant mass distribution. No significant excess of events relative to the expected background is observed, and upper limits at 95% confidence level are set on the Higgs boson's branching fraction to a Z boson and a light resonance. The exclusion limit is ∼10% for the lower masses, and increases for higher masses. Upper limits on the effective coupling C Z H eff / Λ of an axion-like particle to a Higgs boson and Z boson are also set at 95% confidence level, and range from 0.9 to 2 TeV−1.

Aad, G↗
DOE OSTI2023

An in situ formed inorganic conductive network enables high stability and rate capability of single-crystalline nickel-rich cathodes

Single-crystalline Ni-rich cathodes are promising for the next generation of high-energy-density Li-ion batteries due to their better capacity retention than their polycrystalline counterparts. However, there is still much room for improving the electrochemical performances when considering their surface degradation and severe kinetic hindrance during cycling. Herein, we report a strategy to construct an in situ formed robust Li-conductive Li 3 PO 4 layer on the surface of cathode particles. This Li-conductive layer significantly increases the Li-ion diffusion coefficients and suppresses detrimental surface phase transformation. In situ XRD reveals that the improved kinetics alleviate the local stress at high voltage. The as-prepared single-crystalline LiNi 0.83 Co 0.12 Mn 0.05 O 2 delivers good durability (96.8% after 100 cycles at 1C) and excellent rate capability (177.08 mA h g -1 at 5C). Here, this work provides a facile and efficient strategy to improve the cycling performance and boost the rate capability of single-crystalline Ni-rich cathodes.

25 ENERGY STORAGE↗
DOE OSTI2013

Retrospective Evaluation Reveals That Long-term Androgen Deprivation Therapy Improves Cause-Specific and Overall Survival in the Setting of Dose-Escalated Radiation for High-Risk Prostate Cancer

Purpose: To evaluate the role of androgen deprivation therapy (ADT) and duration for high-risk prostate cancer patients treated with dose-escalated radiation therapy (RT). Methods and Materials: A retrospective analysis of high-risk prostate cancer patients treated with dose-escalated RT (minimum 75 Gy) with or without ADT was performed. The relationship between ADT use and duration with biochemical failure (BF), metastatic failure (MF), prostate cancer-specific mortality (PCSM), non-prostate cancer death (NPCD), and overall survival (OS) was assessed as a function of pretreatment characteristics, comorbid medical illness, and treatment using Fine and Gray's cumulative incidence methodology. Results: The median follow-up time was 64 months. In men with National Comprehensive Cancer Network defined high-risk prostate cancer treated with dose-escalated RT, on univariate analysis, both metastasis (P<.0001; hazard ratio 0.34; 95% confidence interval 0.18-0.67; cumulative incidence at 60 months 13% vs 35%) and PCSM (P=.015; hazard ratio 0.41; 95% confidence interval 0.2-1.0; cumulative incidence at 60 months 6% vs 11%) were improved with the use of ADT. On multivariate analysis for all high-risk patients, Gleason score was the strongest negative prognostic factor, and long-term ADT (LTAD) improved MF (P=.002), PCSM (P=.034), and OS (P=.001). In men with prostate cancer and Gleason scores 8 to 10, on multivariate analysis after adjustment for other risk features, there was a duration-dependent improvement in BF, metastasis, PCSM, and OS, all favoring LTAD in comparison with STAD or RT alone. Conclusion: For men with high-risk prostate cancer treated with dose-escalated EBRT, this retrospective study suggests that the combination of LTAD and RT provided a significant improvement in clinical outcome, which was especially true for those with Gleason scores of 8 to 10.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2023

Localized High-Concentration Electrolytes Get More Localized

Liquid electrolytes in batteries are typically treated as macroscopically homogeneous ionic transport media, despite having complex chemical composition and atomistic solvation structures, thus leaving a knowledge gap of microstructural characteristics. A promising electrolyte system design has recently been developed with the title of a localized high-concentration electrolyte (LHCE). These electrolytes are a summation of three components – a charge-carrying salt, a solvent that solvates the salt, and a diluent that is sparingly interactive with the salt in terms of ion solvation. This creates the perception of a high-concentration electrolyte (HCE) with high anion-cation interactions that supports a salt-derived, stable solid-electrolyte interphase, while an LHCE improves bulk electrolyte properties, such as ionic conductivity and viscosity, when compared to an HCE. Much trial by error design of this LHCE concept has been supported by simulations to confirm ionic interactions, cycling data to confirm cell stability, and post-mortem analysis to provide evidence of mechanisms. However, a systematic design to extend the capabilities of LHCEs is still to be desired. Here, we analyzed a specific LHCE mixture to dictate the best viable mixture that extends the localization of solvation structures while maintaining viable cell-level capabilities. We seek to observe and understand solvent-to-salt interactions that impact electrolyte performance. These interactions range from single-ion solvation, multidentate interactions (i.e., solvation-driven clustering), to more widespread network-level interactions. With the support of both experimental and computational analysis of different electrolyte features, we have begun a methodology of formulating the most ideal LHCE mixtures for improving the cyclability of high-capacity battery chemistries.

25 ENERGY STORAGE↗
DOE OSTI2018

Modeling Large-Scale Slim Fly Networks Using Parallel Discrete-Event Simulation

As supercomputers approach exascale performance, the increased number of processors translates to an increased demand on the underlying network interconnect. We present that the slim fly network topology, a new low-diameter, low-latency, and low-cost interconnection network, is gaining interest as one possible solution for next-generation supercomputing interconnect systems. In this article, we present a high-fidelity slim fly packet-level model leveraging the Rensselaer Optimistic Simulation System (ROSS) and Co-Design of Exascale Storage (CODES) frameworks. We validate the model with published work before scaling the network size up to an unprecedented 1 million compute nodes and confirming that the slim fly observes peak network throughput at extreme scale. In addition to synthetic workloads, we evaluate large-scale slim fly models with real communication workloads from applications in the Design Forward program with over 110,000 MPI processes. We show strong scaling of the slim fly model on an Intel cluster achieving a peak network packet transfer rate of 2.3 million packets per second and processing over 7 billion discrete events using 128 MPI tasks. Enabled by the strong performance capabilities of the model, we perform a detailed application trace and routing protocol performance study. Lastly, through analysis of metrics such as packet latency, hop count, and congestion, we find that the slim fly network is able to leverage simple minimal routing and achieve the same performance as more complex adaptive routing for tested DOE benchmark applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

SPIKANs: separable physics-informed Kolmogorov–Arnold networks

Physics-Informed Neural Networks (PINNs) have emerged as a promising method for solving partial differential equations (PDEs) in scientific computing. While PINNs typically use multilayer perceptrons (MLPs) as their underlying architecture, recent advancements have explored alternative neural network structures. One such innovation is the Kolmogorov–Arnold Network (KAN), which has demonstrated benefits over traditional MLPs, including faster neural scaling and better interpretability. The application of KANs to physics-informed learning has led to the development of Physics-Informed KANs (PIKANs), enabling the use of KANs to solve PDEs. However, despite their advantages, KANs often suffer from slower training speeds, particularly in higher-dimensional problems where the number of collocation points grows exponentially with the dimensionality of the system. To address this challenge, we introduce Separable Physics-Informed Kolmogorov–Arnold Networks (SPIKANs). This novel architecture applies the principle of separation of variables to PIKANs, decomposing the problem such that each dimension is handled by an individual KAN. This approach drastically reduces the computational complexity of training without sacrificing accuracy, facilitating their application to higher-dimensional PDEs. Through a series of benchmark problems, we demonstrate the effectiveness of SPIKANs, showcasing their superior scalability and performance compared to PIKANs and highlighting their potential for solving complex, high-dimensional PDEs in scientific computing.

Kolmogorov-Arnold networks↗
DOE OSTI2023

SpeckleNN: a unified embedding for real-time speckle pattern classification in X-ray single-particle imaging with limited labeled examples

With X-ray free-electron lasers (XFELs), it is possible to determine the three-dimensional structure of noncrystalline nanoscale particles using X-ray single-particle imaging (SPI) techniques at room temperature. Classifying SPI scattering patterns, or `speckles', to extract single-hits that are needed for real-time vetoing and three-dimensional reconstruction poses a challenge for high-data-rate facilities like the European XFEL and LCLS-II-HE. Here, we introduce SpeckleNN, a unified embedding model for real-time speckle pattern classification with limited labeled examples that can scale linearly with dataset size. Trained with twin neural networks, SpeckleNN maps speckle patterns to a unified embedding vector space, where similarity is measured by Euclidean distance. We highlight its few-shot classification capability on new never-seen samples and its robust performance despite having only tens of labels per classification category even in the presence of substantial missing detector areas. Without the need for excessive manual labeling or even a full detector image, our classification method offers a great solution for real-time high-throughput SPI experiments.

47 OTHER INSTRUMENTATION↗
DOE OSTI2019

Agronomic performance of 27 Populus clones evaluated after two 3–year coppice rotations in Henan, China

Selecting superior clones is the first step for commercial short–rotation coppice cultures to provide biomass and bioenergy. Till date, such selection for hybrid Populus clones in middle China is absent. Here we describe the growth, aboveground biomass production and cell wall composition of 27 hybrid poplar clones in Henan, China for two 3–year rotations. Significant variation in these three characteristics over two triennial rotation coppices among the 27 poplar clones was observed. During two 3–year rotation coppices, clones ‘276’, ‘02–17’, and ‘599’ showed relatively higher tree heights and larger basal diameters than those of the other clones. However, the most productive clones were ‘36’ and ‘01–30’. At the end of the second triennial rotation, the aboveground biomass production reached 18 Mg ha–1 year–1. For the cell wall composition analysis, the cellulose contents of clones ‘01–243’ and ‘2001’ were relatively high, while the xylose contents of clones ‘01–30’ and ‘65’ were relatively high. Cluster analysis based on height, basal diameter, biomass, heat value, cellulose content, and survival rate revealed five growth potential classes. Accordingly, clones ‘03–332’, ‘36’, and ‘599’ exhibited high biomass and growth and had the greatest potential to serve as excellent biomass producers in Henan, China. In addition, the expression patterns of 20 key regulatory genes were analyzed, and an integrated coexpression network was constructed. This field trial provides a comprehensive quantification and evaluation of the agronomic performance of 27 poplar clones in Henan, China. The results of this study and the analytical strategies provide an efficient mechanism for selecting clones that will perform well agronomically in local environments. The expression of key genes and the integrated coexpression network provide the molecular mechanisms of poplar biomass performance.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Automating the detection of hydrological barriers and fragmentation in wetlands using deep learning and InSAR

The loss of hydrological connectivity and fragmentation of natural wetlands is a widespread driver of wetland degradation. Understanding where and how natural connectivity is impaired is essential for managing, protecting and remediating these ecosystems. Wetland Interferometric Synthetic Aperture Radar (Wetland InSAR) can provide information on surface flow orientation in wetlands at a high spatial resolution, which can be used for barrier detection. However, the broad application of this approach is constrained by the labour-intensive manual delineation of barriers based on mapped water levels. This study presents the first deep learning-based methodology for the automated detection of hydrological barriers. We trained a deep convolutional network to segment edge features of hydrological barriers in 25 image pairs captured by ALOS PALSAR-1 L-Band InSAR between 2006 and 2011. The training dataset consists of manually labelled and delineated barriers showing abrupt changes in water surface elevation and wrapped interferograms with high coherence. We tested this method across three wetland sites: the Everglades and southern Louisiana wetlands (United States) and the Cienaga de Zapata (Cuba). Across these sites, the convolutional network detected hydrological barriers with up to 84% accuracy. The model performed particularly well for linear hydrological barriers such as roads, dikes, and channels. Notably, some barriers impede flow only seasonally, appearing during low water levels and disappearing when water levels rise. Our automated approach to detecting and assessing wetland hydrologic connectivity can be applied more broadly to support the effective management of fragmented wetland ecosystems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Mechanically and Thermally Enhanced 3D-Printed Photocurable Polymer Nanocomposites Containing Functionalized Chitin Nanowhiskers by Stereolithography

Additive manufacturing, or simply 3D printing (3DP), where objects are built through layer-wise material deposition, has gained significant academic and industrial attention as a result of the development of advanced and functional materials requiring rapid, customized, and flexible solutions. In the context of green manufacturing, diversifying environmentally and economically sustainable material portfolios is an essential endeavor for the success of 3DP technology that uses widely available, highly valuable, and renewable materials. Here, we used stereolithography (SLA) for processing methacrylate-based photocurable resins containing crab shell-derived chitin nanowhiskers (CNWs), which are surface-functionalized by reactive acrylate groups. Results from full spectral, thermal, structural, and topological analyses corroborate not only the surface functionalization of CNWs but also indicate the presence of these photocurable CNW (pCNW) fillers in the 3D-printed nanocomposites. Owing to the strong interfacial bond induced by the physical and chemical crosslinking between the pCNW and methacrylate (MA) polymer matrix, the internally formulated nanocomposites displayed enhanced thermomechanical properties (e.g., storage modulus and glass transition temperature) compared to those of commercially available pure SLA resins. For instance, the inclusion of 0.5 wt % pCNW improved the tensile strength and stiffness to up to 78 and 71%, respectively, without compromising the toughness and ductility of the printed material. Accordingly, this result also evidences the compatibility between the filler and resin materials. Consequently, the formation of a crosslinked network in the nanocomposite structure results in a higher thermal stability and activation energy (i.e., up to ~79%) for all the hybrid materials than the pristine MA. Finally, the high-resolution SLA print features, dimensional accuracy, and enhanced mechanical performance of our microstructure-forming functionalized chitin-based nanocomposites make them promising materials for a wide range of robust and high-performance industrial applications.

36 MATERIALS SCIENCE↗
DOE OSTI2024

PreMevE‐MEO: Predicting Ultra‐Relativistic Electrons Using Observations From GPS Satellites

Abstract Ultra‐relativistic electrons with energies greater than or equal to two megaelectron‐volt (MeV) pose a major radiation threat to spaceborne electronics, and thus specifying those highly energetic electrons has a significant meaning to space weather communities. Here we report the latest progress in developing our predictive model for MeV electrons in the outer radiation belt. The new version, primarily driven by electron measurements made along medium‐Earth‐orbits (MEO), is called PREdictive MEV Electron (PreMevE)‐MEO model that nowcasts ultra‐relativistic electron flux distributions across the whole outer belt. Model inputs include >2 MeV electron fluxes observed in MEOs by a fleet of GPS satellites as well as electrons measured by one Los Alamos satellite in the geosynchronous orbit. We developed an innovative Sparse Multi‐Inputs Latent Ensemble NETwork (SmileNet) which combines convolutional neural networks with transformers, and we used long‐term in situ electron data from NASA's Van Allen Probes mission to train, validate, optimize, and test the model. It is shown that PreMevE‐MEO can provide hourly nowcasts with high model performance efficiency and high correlation with observations. This prototype PreMevE‐MEO model demonstrates the feasibility of making high‐fidelity predictions driven by observations from longstanding space infrastructure in MEO, thus has great potential of growing into an invaluable space weather operational warning tool.

79 ASTRONOMY AND ASTROPHYSICS↗