Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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

Resilient Control of Networked Microgrids Using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations

Improving system-level resiliency of networked microgrids against adversarial cyber-attacks is an important aspect in the current regime of increased inverter-based resources (IBRs). To achieve that, this paper contributes in designing a hierarchical control layer, in conjunction with the existing control layers, resilient to adversarial attack signals. Considering model complexities, unknown dynamical behaviors of IBRs, and privacy issues regarding data sharing in multi-party-owned microgrids, designing such a control layer is non-trivial. Here, to tackle these issues, a novel federated reinforcement learning (Fed-RL) method is proposed. To grasp the interconnected dynamics of networked microgrids, the paper develops Federated Soft Actor-Critic (FedSAC) algorithm following the vertical structure of implementing Fed-RL. Next, utilizing the OpenAI Gym interface, we built a custom set-up in GridLAB-D/HELICS co-simulation platform, named Resilient RL Co-simulation (ResRLCoSIM), to train the RL agents with IEEE 123-bus benchmark comprising 3 interconnected microgrids. Finally, the learned policies in the simulation are transferred to the real-time hardware-in-the-loop (HIL) test-bed developed using the high-fidelity Hypersim platform. Finally, experiments show that the simulator-trained RL controllers achieve desirable performance with the test-bed platform, validating the minimization of the sim-to-real gap.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Temperature Profile of the Solution Vessel of an Accelerator-Driven Subcritical Fissile Solution System

Dynamic System Simulation (DSS) models of fissile solution systems have been developed and verified against a variety of historical configurations. DSS techniques have been applied specifically to subcritical accelerator-driven systems using fissile solution fuels of uranium. Initial DSS models were developed in DESIRE, a specialized simulation scripting language. In order to tailor the DSS models to specifically meet needs of system designers they were converted to a Visual Studio implementation, and one of these subsequently to National Instrument’s LabVIEW for human factors engineering and operator training. Specific operational characteristics of subcritical accelerator-driven systems have been examined using a DSS model tailored to this particular class using fissile fuel.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Advancing spatiotemporal forecasts of CO 2 plume migration using deep learning networks with transfer learning and interpretation analysis

Accurate and timely forecasts of CO 2 plume distribution throughout the injection and post-injection phases are crucial for detecting plume migration, assessing leakage risks, and supporting operational decisions in geologic carbon storage (GCS). Current convolutional neural network-based approaches primarily focus on spatial information and overlook temporal dependencies in plume distributions, thus limiting their ability to capture dynamic movement effects and provide accurate predictions of plume migration. In this work, we propose two deep learning models, Auto-Encoder (AE)-LSTM and Encoder-Decoder (ED)-ConvLSTM, each uniquely designed to capture both spatial and temporal features. We apply the proposed methods to forecast the dynamic distribution of CO 2 plumes based on 108 reservoir simulations over a 30-year injection and a 30-year post-injection period. The results indicate that the ED-ConvLSTM model outperforms the AE-LSTM model in accurately predicting the spatiotemporal dynamics of CO 2 plume migration, achieving R 2 values above 0.99. To provide a deeper understanding of these model predictions, we employ a gradient-based explanation method on the trained models. This approach provides insights into the influence of input variables on plume migration forecasts and uncovers the underlying prediction mechanisms of the proposed models. Furthermore, we introduce a transfer learning technique, enabling fast and accurate plume migration forecasting in the post-injection phase by leveraging the trained model during the injection phase. This reduces the necessity for extensive data collection or re-training. In conclusion, the methods proposed in our work enhances the performance and interpretability of CO 2 plume migration forecasts, thereby facilitating informed decision-making throughout the entire lifecycle of GCS applications.

58 GEOSCIENCES↗

Production of Relativistic Electron Bunch with Tunable Current Distribution

We proposed a novel method for tailoring the current distribution of relativistic electron bunches. The technique relies on a recently proposed transverse-to-longitudinal phase space exchange. The bunch is transversely shaped and the phase space exchange mechanism converts this transverse profile into a current profile. The technique provides a tool for generating arbitrary current profiles in a tunable fashion. We demonstrate, via computer simulations, the method and its application to tailor specific current profiles such as, e.g., linearly ramped profiles and train of femtosecond micro-bunches that have application in plasma and dielectric wakefield accelerators.

36 MATERIALS SCIENCE↗

Implementation of disruptive designs for gas turbine components using direct energy deposition additive manufacturing

This research aims to develop a framework for establishing the correlation between in-situ monitoring data, process parameters, and microstructure evolution in blown-powder laser-directed energy deposition (DED) additive manufacturing (AM). To achieve this, a comprehensive manufacturing framework has been developed, spanning from in-situ data acquisition, melt-pool simulation, microstructure modeling, and statistical microstructure quantification. A machine learning-based surrogate model is constructed to predict melt pool geometry directly from in-situ coaxial camera data. The surrogate model is trained using outputs from a high-fidelity melt pool simulation, which provides accurate melt pool dimension data under varying process conditions. The predicted melt pool geometry is then used as input to a microstructure model to predict microstructural features. To rigorously compare and analyze microstructures, the project introduces statistical metrics that quantify differences based on key features such as morphology and texture. Microstructures are represented using advanced statistical descriptors including angular chord length distribution, two-point spatial statistics, orientation distribution function, and global spherical harmonic. These representations are used to compute four distinct “dissimilarity scores” that quantitatively capture differences in texture and morphology. This framework is demonstrated to enable automated calibration of simulation parameters by minimizing discrepancies between simulated and target microstructures. The technology developed in this project enables direct correlation between in-situ monitoring data and resulting microstructure, paving the way for adaptive microstructure control in metal AM. This capability strengthens the connection between process parameters and final material properties, facilitating more precise and reliable material design.

36 MATERIALS SCIENCE↗

Securing Sensitive Flight and Engine Simulation Data Using Smart Card Technology

NASA Glenn Research Center has developed a smart card prototype capable of encrypting and decrypting disk files required to run a distributed aerospace propulsion simulation. Triple Data Encryption Standard (3DES) encryption is used to secure the sensitive intellectual property on disk pre, during, and post simulation execution. The prototype operates as a secure system and maintains its authorized state by safely storing and permanently retaining the encryption keys only on the smart card. The prototype is capable of authenticating a single smart card user and includes pre simulation and post simulation tools for analysis and training purposes. The prototype's design is highly generic and can be used to protect any sensitive disk files with growth capability to urn multiple simulations. The NASA computer engineer developed the prototype on an interoperable programming environment to enable porting to other Numerical Propulsion System Simulation (NPSS) capable operating system environments.

Blaser, Tammy M.↗

Using probability distribution function as a scaling approach to incorporate soil heterogeneity into biogeochemical models for greenhouse gas predictions (Final Technical Report)

The project investigated biogeochemical processes at terrestrial-aquatic interfaces (TAIs), focusing on soil microsite heterogeneity and its impact on greenhouse gas (GHG) fluxes. Using laboratory experiments, modeling, and data integration, researchers explored redox-driven microbial processes under fluctuating hydrological conditions. Key advancements included modifying the DAMM-GHG model to incorporateelectron acceptor availability and enhancing the AquaMEND model for improved microbial metabolism representation. Results highlighted microsite redox variability as a key driver of GHG fluxes, informing Earth system models. The project fostered interdisciplinary collaborations, student training, and the development of novel modeling frameworks to improve Earth'senergy budget.

54 ENVIRONMENTAL SCIENCES↗

Climatology of Cloud-Top Radiative Cooling in Marine Shallow Clouds

A one-year’s worth of near-global marine shallow single-layer cloud top radiative cooling (CTRC) is derived from a radiative transfer model with inputs from the satellite cloud retrievals and reanalysis sounding. The mean cloud top radiative flux divergence is 61 Wm -2 , decomposed into the longwave and shortwave components of 73 and -11 W m -2 , respectively. Equatorward of 30°N/S, the CTRC is largely a reflection of free-atmospheric specific humidity distribution: a dry atmosphere enhances CTRC by reducing downward thermal radiation. Consequently, the cooling minimizes in the “wet” tropics and maximizes in the “dry” eastern subtropics. Poleward of 30°N/S, the CTRC decreases slightly due to the colder clouds that emit less effectively. Furthermore, the CTRC exhibits distinctive seasonal cycles with stronger cooling in the winter and has amplitudes of order 10–20 Wm -2 in stratocumulus-rich regions. The datasets were used to train a machine-learning model that substantially speeds up the retrieval.

54 ENVIRONMENTAL SCIENCES↗

Machine Learning for Mapping Multipactor Susceptibility in RF Systems: Capabilities and Generalization Constraints

Multipactor is a surface-driven electron avalanche phenomenon that degrades the performance and reliability of radio-frequency (RF) systems in particle accelerator and vacuum electronics applications. Multipactor behavior in a given device structure is conventionally assessed through susceptibility charts, which provide a parameter-space characterization of the instability. In this work, we assess the capabilities of machine-learning (ML) models to learn and predict such susceptibility charts and analyze the constraints governing their generalization across materials. Using a simulation-derived dataset spanning six distinct secondary-electron-yield material profiles in a canonical two-surface planar geometry, we train supervised regression models and artificial neural networks to predict the time-averaged electron growth rate, δavg, across the relevant parameter space. Model performance is evaluated using metrics that explicitly probe the structure of susceptibility charts, including Intersection over Union, Structural Similarity Index, and correlation analysis. Tree-based ensemble models outperform neural-network models in reconstructing susceptibility regions and in generalizing across material domains. Principal-component analysis reveals disjoint material feature distributions, indicating that the piecewise mode structure of multipactor susceptibility is difficult to represent with a single global model and that generalization is constrained by data coverage rather than by model complexity. An exhaustive reduced-coverage study further shows that sparse material-space coverage can yield mean performance in the same general range but producing large variability in the susceptibility-region overlap. These results clarify the capabilities of ML-based surrogate models for parameter-space characterization of multipactor discharge. They also provide guidance for their appropriate use in RF system design.

43 PARTICLE ACCELERATORS↗

A variational encoder–decoder approach to precise spectroscopic age estimation for large Galactic surveys

Constraints on the formation and evolution of the Milky Way Galaxy require multidimensional measurements of kinematics, abundances, and ages for a large population of stars. Ages for luminous giants, which can be seen to large distances, are an essential component of studies of the Milky Way, but they are traditionally very difficult to estimate precisely for a large data set and often require careful analysis on a star-by-star basis in asteroseismology. Because spectra are easier to obtain for large samples, being able to determine precise ages from spectra allows for large age samples to be constructed, but spectroscopic ages are often imprecise and contaminated by abundance correlations. Here we present an application of a variational encoder–decoder on cross-domain astronomical data to solve these issues. The model is trained on pairs of observations from APOGEE and Kepler of the same star in order to reduce the dimensionality of the APOGEE spectra in a latent space while removing abundance information. The low dimensional latent representation of these spectra can then be trained to predict age with just ∼1000 precise seismic ages. We demonstrate that this model produces more precise spectroscopic ages (∼ 22 per cent overall, ∼ 11 per cent for red-clump stars) than previous data-driven spectroscopic ages while being less contaminated by abundance information (in particular, our ages do not depend on [α/M]). We create a public age catalogue for the APOGEE DR17 data set and use it to map the age distribution and the age-[Fe/H]-[α/M] distribution across the radial range of the Galactic disc.

79 ASTRONOMY AND ASTROPHYSICS↗

Integrating Atmospheric Specifications into Seismoacoustic Event Localization

This report investigates the integration of infrasound and seismic data to improve event localization accuracy, specifically focusing on a surface explosion at the Utah Training and Testing Range (UTTR). Utilizing the Seismoacoustic Bayesian Event Locator (SABEL) framework, we incorporated atmospheric specifications derived from Ground to Space (G2S) profiles to enhance celerity-range priors. Our analysis revealed that while the combination of infrasound and seismic observations significantly reduced localization uncertainty, challenges remained, particularly with returns at distances less than 200 km from the source and the influence of specific observations on location estimates. The results indicate that broader celerity distributions, such as those from Blom et al. (2020), facilitate better alignment with ground truth locations compared to narrower models. Overall, this work demonstrates the promise of seismoacoustic approaches in refining event localization and highlights the need for further exploration of celerity-range models to ensure reliable outcomes.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

Modeling the Swift BAT trigger algorithm with machine learning

To draw inferences about gamma-ray burst (GRB) source populations based on Swift observations, it is essential to understand the detection efficiency of the Swift burst alert telescope (BAT). This study considers the problem of modeling the Swift/BAT triggering algorithm for long GRBs, a computationally expensive procedure, and models it using machine learning algorithms. A large sample of simulated GRBs from Lien et al. is used to train various models: random forests, boosted decision trees (with AdaBoost), support vector machines, and artificial neural networks. The best models have accuracies of ≳97% (≲3% error), which is a significant improvement on a cut in GRB flux, which has an accuracy of 89.6% (10.4% error). These models are then used to measure the detection efficiency of Swift as a function of redshift z, which is used to perform Bayesian parameter estimation on the GRB rate distribution. We find a local GRB rate density of n{sub 0}∼0.48{sub −0.23}{sup +0.41} Gpc{sup −3} yr{sup −1} with power-law indices of n{sub 1}∼1.7{sub −0.5}{sup +0.6} and n{sub 2}∼−5.9{sub −0.1}{sup +5.7} for GRBs above and below a break point of z{sub 1}∼6.8{sub −3.2}{sup +2.8}. This methodology is able to improve upon earlier studies by more accurately modeling Swift detection and using this for fully Bayesian model fitting.

79 ASTRONOMY AND ASTROPHYSICS↗

Reconstruction of Galaxy Star Formation Histories through SED Fitting:The Dense Basis Approach

We introduce the dense basis method for Spectral Energy Distribution (SED) fitting. It accurately recovers traditional SED parameters, including M {sub *}, SFR, and dust attenuation, and reveals previously inaccessible information about the number and duration of star formation episodes and the timing of stellar mass assembly, as well as uncertainties in these quantities. This is done using basis star formation histories (SFHs) chosen by comparing the goodness-of-fit of mock galaxy SEDs to the goodness-of-reconstruction of their SFHs. We train and validate the method using a sample of realistic SFHs at z = 1 drawn from stochastic realizations, semi-analytic models, and a cosmological hydrodynamical galaxy formation simulation. The method is then applied to a sample of 1100 CANDELS GOODS-S galaxies at 1 10{sup 9.5} M{sub ⊙}. About 40% of the CANDELS galaxies have SFHs whose maximum occurs at or near the epoch of observation. The dense basis method is scalable and offers a general approach to a broad class of data-science problems.

79 ASTRONOMY AND ASTROPHYSICS↗

Fault detection and diagnosis using neural network approaches

Neural networks can be used to detect and identify abnormalities in real-time process data. Two basic approaches can be used, the first based on training networks using data representing both normal and abnormal modes of process behavior, and the second based on statistical characterization of the normal mode only. Given data representative of process faults, radial basis function networks can effectively identify failures. This approach is often limited by the lack of fault data, but can be facilitated by process simulation. The second approach employs elliptical and radial basis function neural networks and other models to learn the statistical distributions of process observables under normal conditions. Analytical models of failure modes can then be applied in combination with the neural network models to identify faults. Special methods can be applied to compensate for sensor failures, to produce real-time estimation of missing or failed sensors based on the correlations codified in the neural network.

Kramer, Mark A.↗

Monitoring CO2 sources and sinks from space : the Orbiting Carbon Observatory (OCO) Mission

NASA's Orbiting Carbon Observatory (OCO) will make the first space-based measurements of atmospheric carbon dioxide (CO2) with the precision, resolution, and coverage needed to characterize the geographic distribution of CO2 sources and sinks and quantify their variability over the seasonal cycle. OCO is currently scheduled for launch in 2008. The observatory will carry a single instrument that incorporates three high-resolution grating spectrometers designed to measure the near-infrared absorption by CO2 and molecular oxygen (O2) in reflected sunlight. OCO will fly 12 minutes ahead of the EOS Aqua platform in the Earth Observing System (EOS) Afternoon Constellation (A-Train). The in-strument will collect 12 to 24 soundings per second as the Observatory moves along its orbit track on the day side of the Earth. A small sampling footprint (<3 km2 at nadir) was adopted to reduce biases in each sounding associated with clouds and aerosols and spatial variations in surface topography. A comprehensive ground-based validation program will be used to assess random errors and biases in the XCO2 product on regional to continental scales. Measurements collected by OCO will be assimilated with other environmental measurements to retrieve surface sources and sinks of CO2. This information could play an important role in monitoring the integrity of large scale CO2 sequestration projects.

carbon dioxide sources and sinks↗

NASA's Earth Observing System (EOS): Delivering on the Dream, Today and Tomorrow

This paper describes the successful operations of NASA's Earth Observing System (EOS) satellites over the past 10 years and the plans for the future. Excellent operations performance has been a key factor in the overall success of EOS. The EOS Program was conceived in the 1980s and began to take shape in the early 1990s. EOS consists of a series of satellites that study the Earth as an interrelated system. It began with the launch of Terra in December 1999, followed by Aqua in May 2002, and Aura in July 2004. A key EOS goal is to provide a long-term continuous data set to enable the science community to develop a better understanding of land, ocean, and atmospheric processes and their interactions. EOS has produced unprecedented amounts of data which are used all over the world free of charge. Mission operations have resulted in data recovery for Terra, Aqua, and Aura that have consistently exceeded mission requirements. The paper describes the ground systems and organizations that control the EOS satellites, capture the raw data, and distribute the processed science data sets. The paper further describes how operations have evolved since 1999. Examples of this evolution include (a) the implementation of new mission safety requirements for orbital debris monitoring; (b) technology upgrades to keep facilities at the state of the art; (c) enhancements to meet changing security requirements; and (d) operations management of the 2 international Earth Observing Constellations of 11 satellites known as the "Morning Constellation" and the "A-Train". The paper concludes with a view into the future based on the latest spacecraft status, lifetime projections, and mission plans.

Kelly, Angelita C.↗

Ice-Over-Water Cloud Identification in an Artificial Neural Network Approach

An artificial neural network (ANN) algorithm, employing several Aqua MODIS channels, the retrieved cloud phase and total cloud visible optical depth, and temperature and humidity vertical profiles is trained to detect multilayer (ML) ice-over-water cloud systems identified by matched 2008 CloudSat and CALIPSO (CC) data. The trained MLANN was applied to 2009 MODIS data resulting in combined ML and single layer detection accuracies of 87% (89%) and 86% (89%) for snow-free (snow-covered) regions during the day and night, respectively. When corrected for the viewing-zenith-angle dependence of each parameter, the ML fraction detected is relatively invariant across the swath. Compared to the CC ML variability, the MLANN is robust seasonally and interannually, and produces similar distribution patterns over the globe, except in the polar regions. Additional research is needed to conclusively evaluate the VZA dependence and further improve the MLANN accuracy. This approach should greatly improve the monitoring of cloud vertical structure using operational passive sensors.

MODIS↗

Predicting solid state material platforms for quantum technologies

Semiconductor materials provide a compelling platform for quantum technologies (QT). However, identifying promising material hosts among the plethora of candidates is a major challenge. Therefore, we have developed a framework for the automated discovery of semiconductor platforms for QT using material informatics and machine learning methods. Different approaches were implemented to label data for training the supervised machine learning (ML) algorithms logistic regression, decision trees, random forests and gradient boosting. We find that an empirical approach relying exclusively on findings from the literature yields a clear separation between predicted suitable and unsuitable candidates. In contrast to expectations from the literature focusing on band gap and ionic character as important properties for QT compatibility, the ML methods highlight features related to symmetry and crystal structure, including bond length, orientation and radial distribution, as influential when predicting a material as suitable for QT.

36 MATERIALS SCIENCE↗