Search NASA⌕ Search

SEARCH · Search NASA

Results for “training efficiency”

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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Multifidelity Active Learning for Failure Estimation of TRISO Nuclear Fuel

The Tristructural isotropic (TRISO)-coated particle fuel is a robust nuclear fuel proposed to be used for multiple modern nuclear technologies. Therefore, characterizing its safety is vital for the reliable operation of nuclear technologies. However, the TRISO fuel failure probabilities are small and the computational model is time consuming to evaluate them using traditional Monte Carlo-type approaches. In the paper, we present a multifidelity active learning approach to efficiently estimate small failure probabilities given an expensive computational model. Active learning suggests the next best training set for optimal subsequent predictive performance and multifidelity modeling uses cheaper low-fidelity models to approximate the high-fidelity model output. After presenting the multifidelity active learning approach, we apply it to efficiently predict TRISO failure probability and make comparisons to the reference results.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Industrial Energy Assessment Training Effectiveness Evaluation: An Eye-Tracking Study

It is essential to understand the effectiveness of any training program so it can be improved accordingly. Various studies have applied standard metrics for the evaluation of visual behavior to recognize the areas of interest that attract individuals’ attention as there is a high correlation between attentional behavior and where one is focusing on. However, through reviewing the literature, we believe that studies that applied eye-tracking technologies for training purposes are still limited, especially in the industrial energy assessment training field. In this paper, the effectiveness of industrial energy assessment training was quantitatively evaluated by measuring the attentional allocation of trainees using eye-tracking technology. Moreover, this study identifies the areas that require more focus based on evaluating the performance of subjects after receiving the training. Additionally, this research was conducted in a controlled environment to remove the distractions that may be caused by environmental factors to only concentrate on variables that influence the learning behavior of subjects. The experiment results showed that after receiving the training, the subjects’ performance in energy assessment was significantly improved in two areas: production, and recycling and waste management, and the designed training program enhanced the knowledge of participants in identifying energy-saving opportunities to the knowledge level of experienced participants.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

Enhanced accuracy through ensembling of randomly initialized auto-regressive models for dynamical systems

Computational mechanics simulations using traditional finite element methods (FEM) require prohibitively expensive computational resources for real-time engineering applications, design optimization, and digital twin implementations. While machine learning (ML) surrogate models offer significant computational speedups, autoregressive ML models for time-dependent mechanical systems suffer from error accumulation that compromises long-term prediction reliability - a critical concern for engineering applications where accuracy over extended time horizons is essential for safety and performance assessments. Here, we propose a deep ensemble framework specifically designed to address this challenge in computational mechanics applications, where multiple ML surrogate models with random weight initializations are trained in parallel and their predictions aggregated during inference. This approach leverages statistical diversity to maximize information gain from a fixed set of training data and to mitigate error propagation, while maintaining the computational efficiency that makes ML surrogates attractive for engineering practice. We validate the framework on three representative problems spanning critical areas of computational mechanics: stress field evolution in heterogeneous microstructures under complex loading (relevant to advanced materials design and composite analysis), planetary-scale shallow water dynamics (applicable to environmental and geotechnical engineering), and Gray-Scott reaction-diffusion systems (relevant to mass transport and chemical process engineering). Across all test cases, the ensemble approach demonstrates consistent error reduction of 15-33% compared to individual models. The codes for this work are available on GitHub (https://github.com/Graham-Brady-Research-Group/AutoregressiveEnsemble_SpatioTemporal_Evolution).

autoregressive prediction↗
DOE OSTI2025

Reduced-order modeling for efficient cross section library development in high-temperature gas reactor pebble-bed depletion analysis

Accurate modeling of running-in and equilibrium conditions in pebble-bed reactors (PBRs) requires precise microscopic multigroup neutron cross sections. In Griffin, deterministic neutronics calculations rely on multivariate interpolation over large cross section libraries, resulting in significant memory usage and performance bottlenecks. This work, together with a companion paper on Griffin integration, explores reduced-order models (ROMs) to replace interpolation with lightweight surrogates. Several ROM techniques are benchmarked, with deep neural networks (DNNs) demonstrating superior memory efficiency, scalability, and predictive accuracy. A total of 295 DNNs were trained to build a comprehensive isotope library, integrated into Griffin through a custom LibTorch interface for depletion analysis. Initial results demonstrate that DNN-based ROMs drastically reduce memory demands while preserving accuracy, enabling finer tabulations and additional state variables without overhead. In conclusion, the framework also supports online cross section generation and real-time DNN updates through transfer learning, improving fidelity by capturing self-shielding and evolving nuclide compositions during burnup.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Designing reinforcement learning algorithms for building HVAC control: From experimental observation to simulation comparisons

Advanced supervisory-level control with reinforcement learning (RL) is regarded as a promising solution for HVAC systems to minimize energy consumption while maintaining thermal comfort and indoor air quality. However, most RL applications were conducted in the simulation environment rather than real-world HVAC systems. This paper developed a value-based RL controller termed Deep Q-Network (DQN) for a typical central HVAC system and evaluated its performance in a building test facility. By comparing DQN with a rule-based controller, the study not only demonstrated the cases where DQN could properly maintain indoor comfort but also discussed possible reasons why DQN failed in some other situations. Recognizing the limitations of value-based RL algorithms from the experimental tests, a simulation study was conducted to compare DQN with an alternative RL approach, an actor–critic algorithm termed Deep Deterministic Policy Gradient (DDPG). In scenarios with a relatively large action space, DDPG outperformed DQN by requiring fewer computational resources and achieving better thermal comfort, lower energy consumption, and more stable control actions. The findings suggest that the ability of DDPG to handle continuous control variables more effectively allows for faster convergence in training and more precise control in practice, which enhances the overall efficiency and reliability of the HVAC system.

Guo, Fangzhou↗
DOE OSTI2023

Toward prediction of turbulent atmospheric flows over propagating oceanic waves via machine-learning augmented large-eddy simulation

Wind-wave interactions have important effects on the energy harvesting of offshore wind farms. High-fidelity large-eddy simulation (LES) is a powerful approach for investigating wind-wave interactions in turbulent oceanic environments. Due to the large scale of the flow domain and the high grid resolution required to resolve multi-scale flow motions, however, brute-force LES of wind-wave interactions is computationally very expensive. We propose augmenting brute-force LES via machine-learning data-driven modeling (ML-LES) to dramatically reduce the computational time required to obtain converged turbulence statistics when the brute-force approach is employed. Namely, we employ a convolutional neural network (CNN) autoencoder trained and validated with LES data sets to develop a highly efficient ML-LES approach for computing turbulence statistics from just a few snapshots of instantaneous LES flow fields. Further, our results demonstrate the accuracy and efficiency of ML-LES in predicting the mean velocity, velocity fluctuations, and turbulence kinetic energy in highly stretched computational grid systems required to carry out simulations in real-life oceanic environments.

42 ENGINEERING↗
DOE OSTI2026

Multireference Methods for Chemistry and Materials Science: Automated Active Spaces, Efficient Dynamic Correlation, and Extended Systems

While multiconfigurational approaches have long been relegated to expert practitioners working on a case-by-case basis, recent developments have increasingly made these methods more routine and applicable to broader sets of systems. This article outlines the state-of-the-art in multiconfigurational approaches, with an emphasis on moving from delicate hand-selected pathways through configuration space toward more robust and efficient approaches to treating a host of challenging chemical systems accurately. First, we overview recent work in automated active-space selection, which has enabled increasingly large-scale applications of multireference methods to modeling vertical excitations and reactivity. Second, we highlight the increasingly efficient methods for recovering correlation energy beyond the active space, as headlined by extensions of pair-density functional theory and its role in accurate and efficient treatment of excited-state dynamics and its utilization to train machine-learned potentials. Finally, we highlight recent efforts to treat extended systems that until recently have lied beyond the traditional limits of active-space methods, giving center stage to product-form wave functions of the localized active space family of methods that allow for the computation of multiconfigurational band structures. These recent advancements point to a broader use of multireference approaches for high-impact chemical and materials science applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Machine Learning Interatomic Potentials for Modeling Framework Flexibility and Water Uptake in NbOFFIVE-1-Ni Metal–Organic Framework

Metal–organic frameworks (MOFs), with their distinctive porous structures and tunable chemical properties, have shown immense promise in the separation and storage of gases. Currently, the accurate simulation of their adsorptive properties remains challenging, especially for systems where the molecules fit very tightly into the pores. Traditional simulation methods often approximate the frameworks as rigid and do not account for the framework flexibility seen in materials such as NbOFFIVE-1-Ni. First-principles molecular dynamics (FPMD) simulations offer the desired accuracy in modeling this flexibility but are limited by their extensive computational demands, rendering them impractical for long simulations. Conversely, classical force field-based simulations offer computational efficiency but lack the necessary accuracy. Here, to break this accuracy-efficiency trade-off, we have developed machine learning interatomic potentials trained on energies and forces from FPMD to model the framework flexibility of NbOFFIVE-1-Ni in the presence of water over nanosecond time scales. Furthermore, by integrating MLIP-driven molecular dynamics (MLIP-MD) with grand canonical Monte Carlo (GCMC) simulations, we further incorporated framework flexibility into adsorption predictions, yielding water adsorption isotherms that better align with experimental data compared to those of conventional GCMC simulations. These advances offer new opportunities for the design and optimization of MOFs in gas storage and separation applications.

adsorption↗
DOE OSTI2026

APSO-enhanced algebraic derivative estimation approach for real-time traffic flow prediction on critical road sections during wildfire evacuation

In rapid-onset disaster scenarios such as wildfires, evacuation traffic often significantly deviates from historical patterns, rendering conventional data-driven forecasting methods less effective. To address this challenge, we propose an improved algebraic derivative estimation (ADE) incorporating particle swarm optimization (PSO) for real-time traffic flow prediction. Our approach dynamically adjusts the ADE prediction time window at each step by minimizing a cost function based on the mean and variance of accumulated forecasting errors within the window, thereby balancing bias and variability. We evaluate the method using traffic data from the January 2025 California wildfires, focusing on key road segments critical for large-scale evacuations. The results demonstrate that our approach surpasses established machine learning and deep learning models—XGBoost, LSTM, and GRU—in predictive accuracy and maintains high computational efficiency. Notably, the proposed method eliminates the need for offline model training. Moreover, rapid PSO-based tuning enables real-time deployment, which provides a crucial advantage in scenarios where evacuation timings and road closures change dynamically. In conclusion, these findings highlight the benefits of the PSO-enhanced ADE framework for emergency traffic management, where rapid, data-sparse forecasts are essential for effective evacuation planning.

Algebraic derivative estimation↗
DOE OSTI2026

Autoregressive long-horizon prediction of plasma edge dynamics *

Accurate modeling of scrape-off layer (SOL) and divertor-edge dynamics is vital for designing plasma-facing components in fusion devices. High-fidelity edge fluid/neutral codes such as SOLPS-ITER capture SOL physics with high accuracy, but their computational cost limits broad parameter scans and long transient studies. We present transformer-based, autoregressive surrogates for efficient prediction of 2D, time-dependent plasma edge state fields. Trained on SOLPS-ITER spatiotemporal data for the KSTAR tokamak, the surrogates forecast electron temperature, electron density, and radiated power over extended horizons. We evaluate model variants trained with increasing autoregressive horizons (1–100 steps) on short- and long-horizon prediction tasks. Longer-horizon training systematically improves rollout stability and mitigates error accumulation, enabling stable predictions over hundreds to thousands of steps and reproducing key dynamical features such as the motion of high-radiation regions. Measured end-to-end wall-clock times show the surrogate is orders of magnitude faster than SOLPS-ITER, enabling rapid parameter exploration. Prediction accuracy degrades when the surrogate enters physical regimes not represented in the training dataset, motivating future work on data enrichment and physics-informed constraints. Overall, this approach provides a fast, accurate surrogate for computationally intensive plasma edge simulations, supporting rapid scenario exploration, control-oriented studies, and progress toward real-time applications in fusion devices.

autoregressive deep learning↗
DOE OSTI2021

Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n e ) and electron temperature (T e ) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I p ), toroidal magnetic field (B Φ ), neutral beam heating power (P NBI ) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

End-to-end codesign of Hessian-aware quantized neural networks for FPGAs

Here, we develop an end-to-end workflow for the training and implementation of co-designed neural networks (NNs) for efficient field-programmable gate array (FPGA) hardware. Our approach leverages Hessian-aware quantization of NNs, the Quantized Open Neural Network Exchange intermediate representation, and the hls4ml tool flow for transpiling NNs into FPGA firmware. This makes efficient NN implementations in hardware accessible to nonexperts in a single open sourced workflow that can be deployed for real-time machine-learning applications in a wide range of scientific and industrial settings. We demonstrate the workflow in a particle physics application involving trigger decisions that must operate at the 40-MHz collision rate of the CERN Large Hadron Collider (LHC). Given the high collision rate, all data processing must be implemented on FPGA hardware within the strict area and latency requirements. Based on these constraints, we implement an optimized mixed-precision NN classifier for high-momentum particle jets in simulated LHC proton-proton collisions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

CIS Project 22359, Final Technical Report. Discretized Posterior Approximation in High Dimensions

Our primary aim in this work is to understand how to efficiently obtain reliable uncertainty quantification in automatic learning algorithms with limited training datasets. Standard approaches rely on cross-validation to tune hyper parameters. Unfortunately, when our datasets are too small, holdout datasets become unreliable—albeit unbiased—measures of prediction quality due to the lack of adequate sample size. We should not place confidence in holdout estimators under conditions wherein the sample variance is both large and unknown. More poigniantly, our training experiments on limited data (Duersch and Catanach, 2021) show that even if we could improve estimator quality under these conditions, the typical training trajectory may never even encounter generalizable models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Midwest Industrial Assessment Center (Final Technical Report)

The Midwest IAC’s prime center was at the University of Missouri (MU) and the satellite center was at Wichita State University, Kansas. During the 5-year period we conducted at least 96 energy assessments, with recommended energy cost savings of $10.3 million of which $6.5 million was implemented savings. The implemented energy savings were 0.63 Terra BTU and CO2 emissions reduction was 400,000 tons. Thirty-five students completed requirements for a certificate of completion from DOE. IAC students received training in cybersecurity basics and application to manufacturing, fundamentals of energy efficiency, ISO50001, smart manufacturing.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Hydra: Computer Vision for Data Quality Monitoring

Hydra: Computer Vision for Data Quality Monitoring Mar 13, 2024, 4:15 PM 30m Charles B. Wang Center, Stony Brook University Poster Track 1: Computing Technology for Physics Research Poster session with coffee break Speaker Ayan Roy Description Hydra is an extensible framework for training, managing, and deploying machine learning models for near real-time data quality monitoring. It is designed to take some of the burden off of shift crews by providing ‘round-the-clock’ monitoring of plots representing the data being collected. The Hydra system is backed by a database which is leveraged for near push button training and is primarily controlled and viewed through a set of web interfaces. This web interface contains a simple-to-use web based GUI for labeling of the datasets used in training; making it possible to label thousands of images quickly and efficiently. To aid in the analysis of Hydra inferences gradCAM, a method of interpretability, is performed and overlaid on the target image, highlighting regions of interest, making diagnosis of problems much faster. Development began in 2019 for the GlueX Experiment in Hall-D, the Hydra system has grown to encompass all of the experimental halls at Jefferson Laboratory. This talk will focus on the features of Hydra as well as provide details of the challenges present with deploying to disparate experimental halls. With a roadmap of development established, Hydra aims to continue to grow in richness of feature set and expand to encompass other monitoring tasks in differing communities.

Roy, Ayan↗
DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Prediction of DIII-D Pedestal Structure from Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. An experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (ne) and electron temperature (Te) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (Ip), toroidal magnetic field (Bφ), neutral beam heating power (PNBI) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1994

Agile manufacturing: The factory of the future

The factory of the future will require an operating methodology which effectively utilizes all of the elements of product design, manufacturing and delivery. The process must respond rapidly to changes in product demand, product mix, design changes or changes in the raw materials. To achieve agility in a manufacturing operation, the design and development of the manufacturing processes must focus on customer satisfaction. Achieving greatest results requires that the manufacturing process be considered from product concept through sales. This provides the best opportunity to build a quality product for the customer at a reasonable rate. The primary elements of a manufacturing system include people, equipment, materials, methods and the environment. The most significant and most agile element in any process is the human resource. Only with a highly trained, knowledgeable work force can the proper methods be applied to efficiently process materials with machinery which is predictable, reliable and flexible. This paper discusses the affect of each element on the development of agile manufacturing systems.

Loibl, Joseph M.↗