SEARCH · Engineering Papers

Results for “Training Analysis”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 721 records · Page 40

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Lateral Variations Across the Southern San Andreas Fault Zone Revealed From Analysis of Traffic Signals at a Dense Seismic Array

Abstract We image the shallow seismic structure across the Southern San Andreas Fault (SSAF) using signals from freight trains and trucks recorded by a dense nodal array, with a linear component perpendicular to SSAF and two 2D subarrays centered on the Banning Fault and Mission Creek Fault (MCF). Particle motion analysis in the frequency band 2–5 Hz shows that the examined traffic sources can be approximated as moving single‐ or multi‐point sources that primarily induce Rayleigh waves. Using several techniques, we resolve strong lateral variations of Rayleigh wave velocities and Q ‐values across the SSAF, including 35% velocity reduction across MCF toward the northeast and strong attenuation around the two fault strands. We further resolve 10% mass density reduction and 45% shear modulus decrease across the MCF. These findings suggest that the MCF is currently the main strand of the SSAF in the area with important implications for seismic hazard assessments.

58 GEOSCIENCES↗

DOE OSTI2026

HARMONY: Large-Scale Architecture Search for Efficient Hybrid Language Models

As large language models scale to trillions of parameters, their computational and memory requirements present critical challenges for efficient training and deployment. While Mixture of Experts (MoE) architectures enable efficient scaling through sparse parameter activation, and state-space models like Mamba offer linear-time complexity, principled methods for combining these paradigms remain undeveloped. We introduce HARMONY (Hybrid Architecture Research for Mamba, Optimized with Neural efficiencY), a multi-objective evolutionary neural architecture search framework for discovering efficient hybrid language models that integrate Transformer attention mechanisms, Mixture-of-Experts routing, and Mamba state-space components. Through large-scale distributed search using 16,384 MI250X GPUs on the Frontier supercomputer, HARMONY explores a comprehensive design space encompassing six attention variants (MHA, MQA, GQA, MLA, SWA, and Mamba-2), variable MoE configurations with both routed and shared experts, and extensive Mamba hyperparameters. Our framework discovers heterogeneous architectures that balance training performance with computational efficiency through multi-objective optimization incorporating latency penalties and fitness-based selection. Analysis of discovered architectures reveals that optimal hybrid designs favor heterogeneous component mixing rather than homogeneous patterns, with Mamba-2 and Multi-Head Latent Attention (MLA) emerging as preferred mechanisms. Discovered architectures demonstrate superior training efficiency: our best configuration achieves a final perplexity of 1.0874 with 2.38B parameters while processing 4,320 tokens/second, outperforming significantly larger manually designed models. Full-scale evaluation shows HARMONY's top architectures achieve better loss trajectories than equivalently-sized models using state-of-the-art configurations including Mixtral, Jamba, and Samba. Additionally, we demonstrate 91% weak scaling efficiency when training discovered 36B-parameter models across 1,024 GPUs. HARMONY is released as an open framework with comprehensive tools for building and training hybrid models using expert-data-pipeline parallelism, democratizing access to automated architecture design for next-generation language models.

Herron, Emily [ORNL] (ORCID:0000000273008172)↗

DOE OSTI2023

DeepDataProfiler: A Platform and Methodology for the Analysis and Interpretation of Neural Networks

The DeepDataProfiler is a methodology and framework for providing interpretability to trained neural networks. Its approach is to decompose a network into a weighted graph of neurons and synapses and link the components of the graph to human identifiable concepts. By identifying concepts important to the network and tracking the decision process employed by the network, the network becomes more transparent and less like a black box. Spurious decisions and poor generalization strategies can be identified and a measure of trustworthiness can be established.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Wave Detection and Tracking Within a Rotating Detonation Engine Through Object Detection

As the operational time window of experimental rotating detonation engines (RDEs) is expanded and the technology matures toward integration within gas turbines, monitoring techniques must evolve to offer computationally efficient and highly time-resolved diagnostics. In this study, computer vision object detection methodology that seeks to reduce data processing time and calculate wave velocity within drastically reduced time intervals as compared to traditional high-frame-rate RDE images analysis techniques is proposed. The adapted you-only-look-once object detection network is trained to detect individual detonation waves within single down-axis RDE images. The wave location and rotational direction detected within a frame are tracked through a series of high-speed images to calculate the frame-to-frame wave velocity with the time-step resolution of $\mathrm{20 μs}$ across a series of frames. The analysis of the annotation box size and image linearization effects is presented, demonstrating the lowest frame-to-frame velocity total uncertainty of $\mathrm{±3.8\%}$ and the highest classification speed of 9.5 frames per second using linearized images. Linearized images “unwrap” the RDE annulus pixel region to a reduced image size. Here, this new method offers great reductions in data processing times and unsteady detonation behavior insight at intervals more comparable to the timescales of detonation wave interactions via the application of machine learning to experimental RDE data.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2023

Machine learning simulation of finite element analysis in augmented reality

Media, method and system for approximating a finite element analysis texture map for an object. To accomplish this, the object is converted to a computer generated model and finite element analysis is performed for a plurality of different simulated inputs to generate a plurality of simulated mappings. Each simulated mapping is converted into a simulated texture map. A machine learning model is trained on the simulated inputs and simulated texture maps to generate a texture map which approximates a finite element analysis. The machine learning model receives a user input and generates the texture map therefrom. The texture map is then wrapped to the object and displayed.

Scherer, Derek Carl↗

NASA NTRS2023

Marin County Wildland Fires: Examining Fuel Load and Land Cover Change to Inform Fire Prevention and Suppression Decisions in Marin County, CA

Heightened occurrence of severe wildfires in the Western United States is increasing the need to better understand regions of high potential wildfire severity and develop methodologies for identifying the best locations for fuels reduction and active wildfire suppression, especially in populated regions such as Marin County, California. Marin County, located in the San Francisco Bay Area, has had significant development in the wildland-urban interface and periods of highly wildfire-prone conditions. The NASA DEVELOP team collaborated with Fire Foundry (a Marin-based fire service workforce development program) and the Marin County Fire Department to develop models to assist with fire management. Using data from Sentinel-2A, PlanetScope, ECOSTRESS, a county-wide LiDAR mapping effort, Landsat 7 Enhanced Thematic Mapper (ETM+), and Landsat 8 Operational Land Imager (OLI), our team developed a number of input data layers for three different models to evaluate wildfire severity. One model performed a suitability analysis with weights based on scientific literature; another model utilized a U-Net Convolutional Neural Network trained on previous fires in Marin and neighboring Sonoma County to predict the difference normalized burn severity; and the third inputted data layers into the FlamMap tool that outputs risk categories. We compared model outputs and performed a weighted overlay analysis to identify specific locations where a fireline could be constructed to interrupt the progress of an active fire. These tools will assist partners in preparing for and managing active wildfire situations.

Remote sensing↗

DOE OSTI2025

An efficient hybrid downscaling framework to estimate high-resolution river hydrodynamics

Flow depth and velocity are the most important hydrodynamic variables that govern various river functions, including water resources, navigation, sediment transport, and biogeochemical cycling. Existing high-resolution flow depth simulations rely on either computationally expensive river hydrodynamic models (RHMs) or data-driven models with formidable training costs, whereas data-driven modeling of flow velocity has rarely been explored. Here, using the hybrid Low-fidelity, Spatial analysis, and Gaussian process learning (LSG) model, we developed a downscaling approach to construct high-resolution flow depth and velocity from a two-dimensional (2-D) RHM simulation at coarse resolution. The LSG models were trained and tested in an urban watershed in Houston using two different hurricane-driven flood events. The high-resolution (as fine as 30 m resolution) and low-resolution (mostly 1000 m resolution) meshes include 664 724 and 14 536 grid cells, respectively. The results showed that through downscaling, the simulation errors were reduced to less than one-fourth and one-third of the errors of the low-resolution 2-D RHM for flow depth and velocity, respectively. Our analysis further revealed that the dominant uncertainty sources of the downscaled hydrodynamics are different, with flow velocity dominated by the dimensionality reduction error, which we reduced by using a regionalized training procedure. The downscaling approach achieves an 84-fold acceleration in computational time compared to the high-resolution 2-D RHM, making high-fidelity ensemble flood modeling feasible. More importantly, the developed method provides an opportunity to couple large-scale hydrodynamical processes with local physical, chemical, and biological processes in river models.

Tan, Zeli [Pacific Northwest National Laboratory (↗

DOE OSTI2025

Criticality analysis of nuclear binding energy neural networks

Machine learning methods, in particular deep learning methods such as artificial neural networks (ANNs) with many layers, have become widespread and useful tools in nuclear physics. However, these ANNs are typically treated as ‘black boxes’, with their architecture (width, depth, and weight/bias initialization) and the training algorithm and parameters chosen empirically by optimizing learning based on limited exploration. We test a non-empirical approach to understanding and optimizing nuclear physics ANNs by adapting a criticality analysis based on renormalization group flows in terms of the hyperparameters for weight/bias initialization, training rates, and the ratio of depth to width. This treatment utilizes the statistical properties of neural network initialization to find a generating functional for network outputs at any layer, allowing for a path integral formulation of the ANN outputs as a Euclidean statistical field theory. We use a prototypical example to test the applicability of this approach: a simple ANN for nuclear binding energies. We find that with training using a stochastic gradient descent optimizer, the predicted criticality behavior is realized, and optimal performance is found with critical tuning. However, the use of an adaptive learning algorithm leads to somewhat superior results without concern for tuning and thus obscures the analysis. Nevertheless, the criticality analysis offers a way to look within the black box of ANNs, which is a first step towards potential improvements in network performance beyond using adaptive optimizers.

artificial neural network↗

DOE OSTI2022

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student t process regression. We apply Student t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Autonomous phase mapping of gold nanoparticles synthesis with differentiable models of spectral shape

Autonomous experimentation–or self-driving labs–offers a systematic approach to accelerate materials discovery by integrating automated synthesis, characterization, and data-driven decision-making. We present a closed-loop workflow for the on-demand synthesis and structural characterization of colloidal gold nanoparticles, enabling direct mapping from composition to nanoscale structure. Our framework leverages differentiable models of spectral shape to address two central tasks in self-driving labs: (a) phase mapping, or identifying compositional regions with distinct structural behavior; and (b) material retrosynthesis, or optimizing compositions for target structure. Using functional data analysis, we develop a data-driven model with generative pre-training, active learning, and high-throughput experiments to predict spectral responses across composition space. We demonstrate the approach on seed-mediated growth of gold nanoparticles, showcasing its ability to extract design rules, reveal secondary interactions, and efficiently navigate morphology space. Gradient-based optimization of the models enables inverse design, making this a unified platform.

36 MATERIALS SCIENCE↗

DOE OSTI2020

A Look Inside the Black Box: Using graph-theoretical descriptors to interpret a Continuous-Filter Convolutional Neural Network (CF-CNN) trained on the global and local minimum energy structures of neutral water clusters

A Continuous Filter Convolutional Neural Network (CF-CNN) was trained to predict the potential energy of water cluster networks \ce{(H2O)_{\textit{N}}}, \textit{N}=10--30, corresponding to local minima lying within 5 kcal/mol from the putative minima taken from a newly published database containing over 5 million unique networks. The chemical sampling space of the database was characterized using chemical descriptors derived from graph theory, which led to the identification of important trends in the topology, connectivity, polygon structures associated with the various networks as a function of cluster size. The resulting graphs are available alongside the original database at \url{https://sites.uw.edu/wdbase/}. The CF-CNN trained on a subset of 500,000 networks for (\textit{N}=10, 30) yielded a mean absolute error of 0.002$\pm$0.002 kcal/mol per water molecule, giving the trained CF-CNN the highest accuracy of any neural network-based surrogate model to date. In addition, clusters of sizes not included in the training set exhibited errors of the same magnitude, indicating that the CF-CNN ptotocol is general enough to accurately predict energies of networks for both smaller and larger sizes than those used during training. The graph-theoretical descriptors were developed in order to analyze the properties of the full database and interpret the predictive power of the CF-CNN. Using topology measures, such as the Wiener index and the average shortest path length along with two similarity measures, we showed that all networks from the test set were within the range of the ones from the training set, suggesting that the training set covered the chemical space of interest quite well. Our graph analysis suggests that the mean degree and number of polygons for networks with larger errors tend to lie further from the mean than those with lower errors. The generality of the used CF-CNN was thus demonstrated, while the use of the graph-theoretical descriptors assisted in interpreting the predicted results.

Bilbrey, Jenna A.↗

DOE OSTI2026

The LCLStream Ecosystem for Multi-Institutional Dataset Exploration

We describe a new end-to-end experimental data streaming framework designed from the ground up to support new types of applications – AI training, extremely high-rate X-ray time-of-flight analysis, crystal structure determination with distributed processing, and custom data science applications and visualizers yet to be created. Throughout, we use design choices merging cloud microservices with traditional HPC batch execution models for security and flexibility. This project makes a unique contribution to the DOE Integrated Research Infrastructure (IRI) landscape. By creating a flexible, API-driven data request service, we address a significant need for high-speed data streaming sources for the X-ray science data analysis community. With the combination of data request API, mutual authentication web security framework, job queue system, high-rate data buffer, and complementary nature to facility infrastructure, the LCLStreamer framework has prototyped and implemented several new paradigms critical for future generation experiments.

Rogers, David [ORNL] (ORCID:0000000251871768)↗

DOE OSTI2020

TrackTable Trajectory Analysis

Tracktable is designed for analysis and rendering of the trajectories of moving objects such as planes, trains, automobiles and ships. Its purpose is to operate on large sets of trajectories (millions) to help a user detect, analyze and display patterns. It will also be used to disseminate trajectory research results from Sandia's PANTHER Grand Challenge LDRD.

Wilson, AndrewT.↗

DOE OSTI2024

Optimizing Residential HVAC Systems: Evaluating How the Usage of Smart Diagnostic Tools for Quality Installation and Commissioning Impacts System Performance and HVAC Contractor Businesses

The adoption of digital quality installation and fault detection tools has the potential to transform the $14 billon residential heating, ventilating, and air conditioning (HVAC) service and installation industry. Increased market penetration can be accelerated by providing an increased understanding of the energy and economic value proposition of the usage of these tools. In tandem with energy and HVAC system performance impact research and analysis, the Southface Team investigated the economic business implications for HVAC service and installation contractors adopting the use of measureQuick (mQ), a smart diagnostic app that aids in quality installation and fault detection and works agnostically with Bluetooth-enabled HVAC technician tools.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2026

Liquid centrifugation-based isotope separation of 7 Li, 37 Cl and D

Liquid centrifugation is an emerging method to separate isotopes. By spinning a liquid containing target isotopes (e.g., pure chemical or solution), the heavier isotope will be enriched at the outer part of a centrifuge, and the lighter ones will be enriched at the inner part of a centrifuge. The separation capability is positively correlated with rotation speed, outer radius and mass difference between isotopes to separate. This award targets to understand whether liquid centrifugation is effective in separating isotopes important for nuclear fission technologies. The results include the following three sections: 1) Effects of solute concentration on isotope separation; 2) Preliminary progress of building a low-speed countercurrent centrifuge, and 3) Analysis on possible candidates for 7 Li and 37 Cl. The award trained one research scientist, one Ph.D. student, one master student, and one undergraduate on liquid centrifugation and isotope measurements.

07 ISOTOPE AND RADIATION SOURCES↗

DOE OSTI2026

Battery Life Prediction Using Reduced-Order Physics Models and Machine Learning (CRADA Final Report)

Phase 1 (Original CRADA, plus no-cost extension modifications #1-3, 6/1/2017 to 3/13/2021): The Australian Department of Defence (AUDoD) is performing accelerated aging tests of Li-ion batteries to benchmark their reliability and degradation characteristics. Using its previously developed battery lifetime predictive model framework, the National Laboratory of the Rockies (NLR) will develop analytical models based the AUDoD data to predict lifetime of the multiple Li-ion battery chemistries under real-world use scenarios of interest to AUDoD. The NLR model is based on physical degradation mechanisms encountered by Li-ion batteries and has been previously validated. Phase 2 (CRADA modification #4, plus no-cost extension modification #5, 2/22/2021 to 3/30/2025): Train and support Australian Department of Defence personnel to use NLR software for model-based estimation of Li-ion battery lifetime using accelerated battery aging data collected by the Australian Department of Defence. Under separate DOE funding from 2019 to 2021, NLR enhanced its battery life-prediction software using machine learning algorithms to automate portions of the model-fitting process, requiring significantly less labor and expert judgment and also adding uncertainty quantification, increasing statistical rigor. Under Phase 2, NLR will customize NLR Software and provide it to AuDoD. NLR will enhance its NLR Model to capture aging modes of AuDoD's multi-cell modules, including cell-balancing effects. NLR will develop example single-cell and multi-cell models based on one AuDoD battery aging dataset. NLR will train AuDoD personnel on NLR Software. By the conclusion of the project, NLR will have provided AuDoD the training materials, a user manual and software needed to perform their own analysis of additional and/or future battery aging datasets.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

Transience of the Retinal Output Is Determined by a Great Variety of Circuit Elements

Retinal ganglion cells (RGCs) encrypt stimulus features of the visual scene in action potentials and convey them toward higher visual centers in the brain. Although there are many visual features to encode, our recent understanding is that the ~46 different functional subtypes of RGCs in the retina share this task. In this scheme, each RGC subtype establishes a separate, parallel signaling route for a specific visual feature (e.g., contrast, the direction of motion, luminosity), through which information is conveyed. The efficiency of encoding depends on several factors, including signal strength, adaptational levels, and the actual efficacy of the underlying retinal microcircuits. Upon collecting inputs across their respective receptive field, RGCs perform further analysis (e.g., summation, subtraction, weighting) before they generate the final output spike train, which itself is characterized by multiple different features, such as the number of spikes, the inter-spike intervals, response delay, and the rundown time (transience) of the response. These specific kinetic features are essential for target postsynaptic neurons in the brain in order to effectively decode and interpret signals, thereby forming visual perception. We review recent knowledge regarding circuit elements of the mammalian retina that participate in shaping RGC response transience for optimal visual signaling.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2022

WaterTAP3 Model Input Data for NAWI's Eight Source Water Baseline Analyses

This folder contains the input data for the WaterTAP3 model that was used for the eight NAWI (National Alliance for Water Innovation) source water baselines studies published in the Environmental Science and Technology special issue: Technology Baselines and Innovation Priorities for Water Treatment and Supply. There are also eight other separate DAMS submissions, one per source water, that include the model results for the published studies. In this data submission, all model inputs across the eight baselines are included. The data structure and content are described in a README.txt file. For more details on how to use the data in WaterTAP3 please refer to the model documentation and GitHub site found at "WaterTAP3 Github" linked in the submission resources.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗