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 1,567 records · Page 87

Combining In-situ Diagnostics and Data Analytics for Discovery of Process-Structure-Property Relationships in AM parts – A Step Toward Digital Twins

In-situ additive manufacturing (AM) diagnostic tools (e.g., optical/infrared imaging, acoustic, etc.) already exist to correlate process anomalies to printed part defects. This current work aimed to augment existing capabilities by: 1) Incorporating in-situ imaging w/ machine learning (ML) image processing software (ORNL- developed "Peregrine") for AM process anomaly detection 2) Synchronizing multiple in-situ sensors for simultaneous analysis of AM build events 3) Correlating in-situ AM process data, generated part defects and part mechanical properties The key R&D question investigated was to determine if these new combined hardware/software tools could be used to successfully quantify defect distributions for parts build via SNL laser powder bed fusion (LPBF) machines, aiming to better understand data-driven process-structure-property- performance relationships. High resolution optical cameras and acoustic microphones were successfully integrated in two LPBF machines and linked to the Peregrine ML software. The software was successfully calibrated on both machines and used to image hundreds of layers of multiple builds to train the ML software in identifying printed part vs powder. The software's validation accuracy to identify this aspect increased from 56% to 98.8% over three builds. Lighting conditions inside the chamber were found to significantly impact ML algorithm predictions from in-situ sensors, so these were tailored to each machine's internal framework. Finally, 3D part reconstructions were successfully generated for a build from the compressed stack of layer-wise images. Resolution differences nearest and furthest from the optical camera were discussed. Future work aims to improve optical resolution, increase process anomalies identified, and integrate more sensor modalities.

36 MATERIALS SCIENCE↗

One Galaxy Sample to Rule Them All: Halo Occupation Distribution Modeling of DES Year 3 Source Galaxies

Abstract For the joint analysis of second-order weak-lensing and galaxy clustering statistics, so-called 3 × 2 analyses, the selection and characterization of optimal galaxy samples is a major area of research. One promising choice is to use the same galaxy sample as lenses and sources, which reduces the systematics parameter space that describes the uncertainties related to galaxy samples. Such a “lens-equal-source” analysis significantly improves the self-calibration of photo- z systematics, leading to improved cosmological constraints. With the aim of enabling a lens-equal-source analysis on small scales, we investigate the halo–galaxy connection of DES Year 3 source galaxies. We develop a technique to construct mock source galaxy populations by matching COSMOS/UltraVISTA photometry to U niverse M achine galaxies. These mocks predict a source halo occupation distribution (HOD) that exhibits significant redshift evolution, nontrivial central incompleteness, and galaxy assembly bias. We produce multiple realizations of mock source galaxies drawn from the U niverse M achine posterior, with added uncertainties in the measured Dark Energy Survey photometry and galaxy shapes. We fit a modified HOD formalism to these realizations to produce priors on the galaxy–halo connection for cosmological analyses. We additionally train an emulator that predicts this HOD to ∼2% accuracy from redshift z = 0.1−1.3 that models the dependence of this HOD on (1) observational uncertainties in galaxy size and photometry and (2) uncertainties in the U niverse M achine predictions.

Salcedo, Andrés N. (ORCID:000000031420527X)↗

EngenuitySC Commercialization and Entrepreneurial Training Project

A team led by EngenuitySC has performed education and outreach on development of advanced energy markets that will enable wider use of clean energy technologies. This report details the efforts that have made significant advances to improve the market place through education, outreach, and increased communications between industry members. The project resulted in two self-funded industry clusters known as the Fuel Cell Collaborative and NuHub. This project has focused on building and strengthening the leading clean energy clusters in South Carolina: nuclear energy and fuel cell technologies. For the nuclear industry, a new cluster was developed that is now known as NuHub. This cluster has already engaged over 25 nuclear industry leaders or suppliers, four public sector partners, six community economic development foundations, and nearly ten academic partners in a 175 mile radius between Augusta, Georgia and Charlotte, North Carolina. Our outreach has touched over 2,000 stakeholders through the website alone, not including the public audiences and members of the business community reached through news stories and releases that were distributed to over 620 print and online publications. NuHub has established a formal leadership structure, developed subcommittees to focus on industry issues, instituted educational programs for the workforce, and created an industry funding structure that will sustain the industry cluster and mission. NuHub has participated in a wide-variety of community building and outreach activities since its formation under this grant. In the two years since its creation in 2010, we have initiated efforts focused in four main areas that correlate with the four NuHub subcommittees including: innovation, workforce development, industry engagement, and marketing and communications. NuHub successfully raised over $\$$160,000 in both public and private funding, which has supported work to grow the cluster and engage partners including NuScale, Fluor, and Holtec International for research about deployment of advanced small modular reactor (SMR) technologies. The workforce training efforts from NuHub have focused on assisting existing industry to fill positions needed to construct and operate new nuclear plants being built at the VC Summer plant in Jenkinsville, SC and at Plant Votgle in Augusta, Georgia both of whom are constructing the first nuclear reactors (Westinghouse AP 1000 units), to be built in over 30 years. This includes a partnership with Midlands Technical College to train reactor operators and the development of training facilities to support workforce development activities. It is anticipated that approximately 70 students a year will be trained through these programs in the next five years, and it will be expanded to meet new industry needs.

08 HYDROGEN↗

Airborne hyperspectral imaging of nitrogen deficiency on crop traits and yield of maize by machine learning and radiative transfer modeling

Nitrogen is an essential nutrient that directly affects plant photosynthesis, crop yield, and biomass production for bioenergy crops, but excessive application of nitrogen fertilizers can cause environmental degradation. To achieve sustainable nitrogen fertilizer management for precision agriculture, there is an urgent need for nondestructive and high spatial resolution monitoring of crop nitrogen and its allocation to photosynthetic proteins as that changes over time. Here, we used visible to shortwave infrared (400–2400 nm) airborne hyperspectral imaging with high spatial (0.5 m) and spectral (3–5 nm) resolutions to accurately estimate critical crop traits, i.e., nitrogen, chlorophyll, and photosynthetic capacity (CO 2 -saturated photosynthesis rate, V max,27 ), at leaf and canopy scales, and to assess nitrogen deficiency on crop yield. We conducted three airborne campaigns over a maize (Zea mays L.) field during the growing season of 2019. Physically based soil-canopy Radiative Transfer Modeling (RTM) and data-driven approaches i.e. Partial-Least Squares Regression (PLSR) were used to retrieve crop traits from hyperspectral reflectance, with ground truth of leaf nitrogen, chlorophyll, V max,27 , Leaf Area Index (LAI), and harvested grain yield. To improve computational efficiency of RTMs, Random Forest (RF) was used to mimic RTM simulations to generate machine learning surrogate models RTM-RF. The results show that prior knowledge of soil background and leaf angle distribution can significantly reduce the ill-posed RTM retrieval. RTM-RF achieved a high accuracy to predict leaf chlorophyll content (R 2 = 0.73) and LAI (R 2 = 0.75). Meanwhile, PLSR exhibited better accuracy to predict leaf chlorophyll content (R 2 = 0.79), nitrogen concentration (R 2 = 0.83), nitrogen content (R 2 = 0.77), and V max,27 (R 2 = 0.69) but required measured traits for model training. We also found that canopy structure signals can enhance the use of spectral data to predict nitrogen related photosynthetic traits, as combining RTM-RF LAI and PLSR leaf traits well predicted canopy-level traits (leaf traits × LAI) including canopy chlorophyll (R 2 = 0.80), nitrogen (R 2 = 0.85) and V max,27 (R 2 = 0.82). Compared to leaf traits, we further found that canopy-level photosynthetic traits, particularly canopy V max,27 , have higher correlation with maize grain yield. This study highlights the potential for synergistic use of process-based and data-driven approaches of hyperspectral imaging to quantify crop traits that facilitate precision agricultural management to secure food and bioenergy production.

54 ENVIRONMENTAL SCIENCES↗

Half-cycle-pulse-train induced state redistribution of Rydberg atoms

Population transfer between low-lying Rydberg states independent of the initial state is realized using a train of half-cycle pulses with pulse durations much shorter than the classical orbital period. We demonstrate experimentally the population transfer from initial states around n=50 with 10% of the population de-excited down to n<40 as well as up to the continuum. This is a demonstration of a state-independent de-excitation technique applicable to the currently produced state distribution of antihydrogen. The measured population transfer matches well to a model of the process for one-dimensional atoms.

74 ATOMIC AND MOLECULAR PHYSICS↗

Integrating Learning and Physics based Computation for Fast Online Transient Analysis

In this work, a novel method that integrates learning and physics based computation is developed for greatly accelerating the simulation of full power system transient trajectories. To solve the dynamic algebraic equations, the method replaces the time-consuming dynamic computation for generator dynamics with trained predictors, while retaining the time-efficient algebraic computation of solving AC-power flow (PF) for power systems. In particular, a predictor is trained for each generator, and the system trajectories are computed by alternating steps of calling the predictors and solving AC-PF. The proposed method also allows fully parallelizable training strategies and a flexible trade-off between training time and testing accuracy. Comprehensive evaluations of the proposed method for transient/dynamic contingency analysis of the New York/New England 16-machine 68-bus power systems demonstrate excellent performance and significant acceleration of computation.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Vegetative and geologic mapping of the western Seward Peninsula, Alaska, based on ERTS-1 imagery

ERTS-1 scene 1009-22095 (Western Seward Peninsula, Alaska) has been studied, partly as a training exercise, to evaluate whether direct visual examination of individual and custom color-composite prints can provide new information on the vegetation and geology of this relatively well known area of Alaska. The vegetation analysis reveals seven major vegetation types, only four of which are described on existing vegetation maps. In addition, the ERTS analysis provides greater detail than the existing maps on the areal distribution of vegetation types. The geologic analysis demonstrates that most of the major rock units and geomorphic boundaries shown on the available geologic maps could also be identified on the ERTS data. Several major high-angle faults were observed, but the zones of thrust faults which are much less obvious.

Anderson, J. H.↗

BEAST: Expanding Sustainable Data Infrastructure for High-Enthalpy Facilities

Reproducible, data-driven thermal protection system (TPS) research requires that experimental records from high-enthalpy testing be consistently structured, traceable, and accessible across campaigns and institutions. In practice, however, arcjet and plasma facilities data remain largely fragmented: raw diagnostics are stored in ad hoc formats, material sample histories are disconnected from test conditions, and metadata standards are absent, precluding systematic cross-campaign analysis and long-term reuse. BEAST (Backend for Experiment Analysis, Storage, and Traceability) is an open-source, web-based platform that addresses these limitations by providing a unified, queryable infrastructure for high-enthalpy ground-test data [1]. First presented at the 15th Ablation Workshop [2], BEAST has since undergone significant development. The platform ingests and structures multi-channel time-series diagnostics, facility configurations, and material property records within a common provenance model, ensuring end-to-end traceability from raw sensor acquisition to reduced experimental quantities. A versioned material library links specimen identity and processing history to the specific runs in which each sample was tested. An integrated modeling workbench enables training and evaluation of regression models directly on archived experimental data, supporting condition interpolation and the construction of empirical material response databases. Beyond its original deployment at NASA Ames Research Center, BEAST has been designed to be facility-agnostic, with ongoing efforts to extend its adoption to other facilities. Its modular architecture accommodates heterogeneous diagnostic setups and facility types, and its future open-source distribution allows institutions to build on a common data standard rather than maintaining isolated, bespoke solutions. BEAST is further integrated within a broader ecosystem of companion tools: arcjetCV [3] extracts recession rates and shock standoff distances from high-speed video using computer vision, and miniSTARscan [4] provides sub-minute, portable photogrammetric surface reconstruction of test articles before and after exposure. All tools share a common data schema, enabling seamless ingestion of surface geometry, imagery, and time-series data into a single, coherent experimental record.

Database↗

BEAST: Expanding Sustainable Data Infrastructure for High-Enthalpy Facilities

Reproducible, data-driven thermal protection system (TPS) research requires that experimental records from high-enthalpy testing be consistently structured, traceable, and accessible across campaigns and institutions. In practice, however, arcjet and plasma facilities data remain largely fragmented: raw diagnostics are stored in ad hoc formats, material sample histories are disconnected from test conditions, and metadata standards are absent, precluding systematic cross-campaign analysis and long-term reuse. BEAST (Backend for Experiment Analysis, Storage, and Traceability) is an open-source, web-based platform that addresses these limitations by providing a unified, queryable infrastructure for high-enthalpy ground-test data [1]. First presented at the 15th Ablation Workshop [2], BEAST has since undergone significant development. The platform ingests and structures multi-channel time-series diagnostics, facility configurations, and material property records within a common provenance model, ensuring end-to-end traceability from raw sensor acquisition to reduced experimental quantities. A versioned material library links specimen identity and processing history to the specific runs in which each sample was tested. An integrated modeling workbench enables training and evaluation of regression models directly on archived experimental data, supporting condition interpolation and the construction of empirical material response databases. Beyond its original deployment at NASA Ames Research Center, BEAST has been designed to be facility-agnostic, with ongoing efforts to extend its adoption to other facilities. Its modular architecture accommodates heterogeneous diagnostic setups and facility types, and its future open-source distribution allows institutions to build on a common data standard rather than maintaining isolated, bespoke solutions. BEAST is further integrated within a broader ecosystem of companion tools: arcjetCV [3] extracts recession rates and shock standoff distances from high-speed video using computer vision, and miniSTARscan [4] provides sub-minute, portable photogrammetric surface reconstruction of test articles before and after exposure. All tools share a common data schema, enabling seamless ingestion of surface geometry, imagery, and time-series data into a single, coherent experimental record.

Database↗

Darlington tritium removal facility and station upgrading plant dynamic process simulation

Ontario Power Generation Nuclear (OPGN) has a 4 x 880 MWe CANDU nuclear station at its Darlington Nuclear Div. located in Bowmanville. The station has been operating a Tritium Removal Facility (TRF) and a D{sub 2}O station Upgrading Plant (SUP) since 1989. Both facilities were designed with a Distributed Control System (DCS) and programmable logic controllers (PLC) for process control. This control system was replaced with a DCS only, in 1998. A dynamic plant simulator was developed for the Darlington TRF (DTRF) and the SUP, as part of the computer control system replacement. The simulator was used to test the new software, required to eliminate the PLCs. The simulator is now used for operator training and testing of process control software changes prior to field installation. Dynamic simulation will be essential for the ITER isotope separation system, where the process is more dynamic than the relatively steady-state DTRF process. This paper describes the development and application of the DTRF and SUP dynamic simulator, its benefits, architecture, and the operational experience with the simulator. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Dynamic Temporal Graph Sequence Data for Resilience-Oriented Distribution Network Reconfiguration

This dataset comprises temporal dynamic graph sequences generated from power grid simulations focused on grid reconfiguration to enhance resilience. The simulations model failure propagation under varying conditions, with nodes assigned distinct failure probabilities. For each time step, the dataset captures the evolution of node states (functional or failed) and features critical to grid operations, such as pv_output, load_profile, load_dispatch, dg_output, loss, and voltage. Node types include sources, normal loads, and nodes with specific equipment like PVs, micro turbines, or shunt capacitors. The dataset is structured to support the training of dynamic graph neural networks, facilitating research on node feature prediction and edge dynamics under failure scenarios. Three distinct configurations are included, providing a robust foundation for modeling power grid resilience.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

A biology-informed similarity metric for simulated patches of human cell membrane

Complex scientific inquiries rely increasingly upon large and autonomous multiscale simulation campaigns, which fundamentally require similarity metrics to quantify ‘sufficient’ changes among data and/or configurations. However, subject matter experts are often unable to articulate similarity precisely or in terms of well-formulated definitions, especially when new hypotheses are to be explored, making it challenging to design a meaningful metric. Furthermore, the key to practical usefulness of such metrics to enable autonomous simulations lies in in situ inference, which requires generalization to possibly substantial distributional shifts in unseen, future data. Here, we address these challenges in a cancer biology application and develop a meaningful similarity metric for ‘patches’—regions of simulated human cell membrane that express interactions between certain proteins of interest and relevant lipids. In the absence of well-defined conditions for similarity, we leverage several biology-informed notions about data and the underlying simulations to impose inductive biases on our metric learning framework, resulting in a suitable similarity metric that also generalizes well to significant distributional shifts encountered during the deployment. We combine these intuitions to organize the learned embedding space in a multiscale manner, which makes the metric robust to incomplete and even contradictory intuitions. Our approach delivers a metric that not only performs well on the conditions used for its development and other relevant criteria, but also learns key spatiotemporal relationships without ever being exposed to any such information during training.

97 MATHEMATICS AND COMPUTING↗

Graph neural networks for detecting anomalies in scientific workflows

Identifying and addressing anomalies in complex, distributed systems can be challenging for reliable execution of scientific workflows. We model these workflows as directed acyclic graphs (DAGs), where the nodes and edges of the DAGs represent jobs and their dependencies, respectively. We develop graph neural networks (GNNs) to learn patterns in the DAGs and to detect anomalies at the node (job) and graph (workflow) levels. We investigate workflow-specific GNN models that are trained on a particular workflow and workflow-agnostic GNN models that are trained across the workflows. Our GNN models, which incorporate both individual job features and topological information from the workflow, show improved accuracy and efficiency compared to conventional learning methods for detecting anomalies. While joint trained with multiple scientific workflows, our GNN models reached an accuracy more than 80% for workflow level and 75% for job level anomalies. In addition, we illustrate the importance of hyperparameter tuning method in our study that can significantly improve the metric(s) measure of evaluating the GNN models. Finally, we integrate explainable GNN methods to provide insights on job features in the workflow that cause an anomaly.

97 MATHEMATICS AND COMPUTING↗

Nearest Neighbor Algorithms for Pattern Classification

A solution of the discrimination problem is considered by means of the minimum distance classifier, commonly referred to as the nearest neighbor (NN) rule. The NN rule is nonparametric, or distribution free, in the sense that it does not depend on any assumptions about the underlying statistics for its application. The k-NN rule is a procedure that assigns an observation vector z to a category F if most of the k nearby observations x sub i are elements of F. The condensed nearest neighbor (CNN) rule may be used to reduce the size of the training set required categorize The Bayes risk serves merely as a reference-the limit of excellence beyond which it is not possible to go. The NN rule is bounded below by the Bayes risk and above by twice the Bayes risk.

Barrios, J. O.↗

Visualization of Atmospheric Water Vapor Data for SAGE

The goal of this project was to develop visualization tools to study the water vapor dynamics using the Stratospheric Aerosol and Gas Experiment 11 (SAGE 11) water vapor data. During the past years, we completed the development of a visualization tool called EZSAGE, and various Gridded Water Vapor plots, tools deployed on the web to provide users with new insight into the water vapor dynamics. Results and experiences from this project, including papers, tutorials and reviews were published on the main Web page. Additional publishing effort has been initiated to package EZSAGE software for CD production and distribution. There have been some major personnel changes since Fall, 1998. Dr. Mou-Liang Kung, a Professor of Computer Science assumed the PI position vacated by Dr. Waldo Rodriguez who was on leave. However, former PI, Dr. Rodriguez continued to serve as a research adviser to this project to assure smooth transition and project completion. Typically in each semester, five student research assistants were hired and trained. Weekly group meetings were held to discuss problems, progress, new research direction, and activity planning. Other small group meetings were also held regularly for different objectives of this project. All student research assistants were required to submit reports for conference submission.

Kung, Mou-Liang↗

Privacy-preserving federated learning: Application to behind-the-meter solar photovoltaic generation forecasting

Here, the growing usage of decentralized renewable energy sources has made accurate estimation of their aggregated generation crucial for maintaining grid flexibility and reliability. However, the majority of distributed photovoltaic (PV) systems are behind-the-meter (BTM) and invisible to utilities, leading to three challenges in obtaining an accurate forecast of their aggregated output. Firstly, traditional centralized prediction algorithms used in previous studies may not be appropriate due to privacy concerns. There is therefore a need for decentralized forecasting methods, such as federated learning (FL), to protect privacy. Secondly, there has been no comparison between localized, centralized, and decentralized forecasting methods for BTM PV production, and the trade-off between prediction accuracy and privacy has not been explored. Lastly, the computational time of data-driven prediction algorithms has not been examined. This article presents a FL power forecasting method for PVs, which uses federated learning as a decentralized collaborative modeling approach to train a single model on data from multiple BTM sites. The machine learning network used to design this FL-based BTM PV forecasting model is a multi-layered perceptron, which ensures privacy and security of the data. Comparing the suggested FL forecasting model to non-private centralized and entirely private localized models revealed that it has a high level of accuracy, with an RMSE that is 18.17% lower than localized models and 9.9% higher than centralized models.

14 SOLAR ENERGY↗

The Heuristic Dynamic Programming Approach in Boost Converters

In this study, a heuristic dynamic programming controller is proposed to control a boost converter. Conventional controllers such as proportional-integral-derivative (PID) or proportional-integral (PI) are designed based on the linearized small-signal model near the operating point. Therefore, the performance of the controller during the start-up, the load change, or the input voltage variation is not optimal since the system model changes by varying the operating point. The heuristic dynamic programming controller optimally controls the boost converter by following the approximate dynamic programming. The advantage of the HDP is that the neural network-based characteristic of the proposed controller enables boost converters to easily cope with large disturbances. An HDP with a well-trained critic and action networks can perform as an optimal controller for the boost converter. To compare the effectiveness of the traditional PI-based and the HDP boost converter, the simulation results are provided.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Advanced Vehicles and Fuels Systems: Cooperative Research and Development Final Report, CRADA number CRD-03-00129

Midwest Research Institute (MRI) and AVL Powertrain Engineering, Inc. (AVL) have executed a Software and Trademark License Agreement (Software License) by which AVL is granted the exclusive right to use, modify and improve and to commercialize by reproducing, distributing and granting sublicenses in, certain computer software known as ADVISOR 2003.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗