Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “generative machine learning”

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 703 records · Page 39
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

mphys-surrogate-model

This repository contains python scripts for building and studying reduced-order-modeling representations of droplet coalescence for eventual use in atmospheric models. The included data are generated from high-fidelity superdroplet methods and are utilized by machine learning pipelines to build data-driven models of droplet size distributions that evolve under coalescence. This repository further includes scripts to determine prediction (uncertainty) intervals on the data-driven model products based on conformal prediction.

Katona, JonasE [Lawrence Livermore National Labora↗
DOE OSTI2026

ML-Shock-Time-Series-Synthesis

Open-source machine learning tools for GPU-batched synthetic shock time-series generation, GPU-accelerated batched Shock Response Spectrum (SRS) computation, and standardized benchmark datasets.

Watts, Adam↗
DOE OSTI2023

CCSI Toolset 3.19 Release

CCSI Toolset 3.19 Release Highlights A gradient generation tool was developed to support GENN models in FOQUS. Certain machine learning tools train gradient-enhanced neural network (GENN) models which can be more accurate for complex datasets given a priori knowledge of model derivatives. However, the derivatives must be known beforehand and are not often available for process data. This tool automatically predicts the gradients for a training dataset in a form usable by common GENN trainers, such as Surrogate Modeling Toolbox. Support was added for Surrogate Modeling Toolbox GENN models in FOQUS, including updates to the run methods, node properties, test framework, documentation and optional dependencies list. Users can train/save Surrogate Modeling Toolbox gradient-enhanced neural network (GENN) models with custom objects and produce .pkl files compatible with the Machine Learning/Artificial Intelligence Plugin in FOQUS. A simpler implementation of the ordering algorithm in the Sequential Design of Experiments (SDOE) module was included. The SDOE examples documentation was updated. The Optimality-Based Design of Experiments was updated to improve the error handling when the results are None.

AS↗
DOE OSTI2021

Seascape Interface Control Document (V.1)

This paper serves as the Interface Control Document (ICD) for the Seascape automated test harness developed at Sandia National Laboratories. The primary purposes of the Seascape system are: (1) provide a place for accruing large, curated, labeled data sets useful for developing and evaluating detection and classification algorithms (including, but not limited to, supervised machine learning applications) (2) provide an automated structure for specifying, running and generating reports on algorithm performance. Seascape uses GitLab, Nexus, Solr, and Banana, open source codes, together with code written in the Python language, to automatically provision and configure computational nodes, queue up jobs to accomplish algorithms test runs against the stored data sets, gather the results and generate reports which are then stored in the Nexus artifact server.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Seascape Interface Control Document (V. 2)

This paper serves as the Interface Control Document (ICD) for the Seascape automated test harness developed at Sandia National Laboratories. The primary purposes of the Seascape system are: (1) provide a place for accruing large, curated, labeled data sets useful for developing and evaluating detection and classification algorithms (including, but not limited to, supervised machine learning applications) (2) provide an automated structure for specifying, running and generating reports on algorithm performance. Seascape uses GitLab, Nexus, Solr, and Banana, open source codes, together with code written in the Python language, to automatically provision and configure computational nodes, queue up jobs to accomplish algorithms test runs against the stored data sets, gather the results and generate reports which are then stored in the Nexus artifact server.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Seascape Interface Control Document

This paper serves as the Interface Control Document (ICD) for the Seascape automated test harness developed at Sandia National Laboratories. The primary purposes of the Seascape system are: (1) provide a place for accruing large, curated, labeled data sets useful for developing and evaluating detection and classification algorithms (including, but not limited to, supervised machine learning applications) (2) provide an automated structure for specifying, running and generating reports on algorithm performance. Seascape uses GitLab, Nexus, Solr, and Banana, open source software, together with code written in the Python language, to automatically provision and configure computational nodes, queue up jobs to accomplish algorithms test runs against the stored data sets, gather the results and generate reports which are then stored in the Nexus artifact server.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Extreme-scale stochastic optimization and simulation via learning-enhanced decomposition and parallelization (Final Technical Report)

Stochastic optimization and simulation models ubiquitously arise in designing and operating complex service/engineering systems. They can be extreme in scale due to high-dimensional data and decisions, and can also involve decisions made sequentially in response to newly revealed data, both causing significant computational challenge. The objective of this research is to explore a unified framework that integrates machine learning with discrete optimization and risk-averse modeling, to improve the efficiency of decomposition paradigms for stochastic optimization and simulations at extreme scale. The models we consider represent a broad class of complex decision-making problems, where 0-1 or continuous decisions are made before and/or after knowing multiple sources of uncertainties that could be correlated. We will employ machine learning methods to dynamically decide and prioritize computational procedures, including cut generation, branching, and bounding of the optimal objective. Furthermore, the research will shed new lights on the traditional decomposition algorithms for extreme-scale computing. Deliverables of the research include new modeling and computational methods for advancing the state-of-the-art research in optimization and simulation, bringing many relevant risk-averse, data-driven optimization problems in practice within the range of tractability. Examples include distributed computing server scheduling and sensor deployment for monitoring critical infrastructures. Success in this effort will enable progress in solving multiple extreme-scale problems in the complex system design and operations arising from DoE missions in energy, environment, and national security.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Simulated meteorological impacts of offshore wind turbines and sensitivity to the amount of added turbulence kinetic energy

Offshore wind energy projects are currently in development off the east coast of the United States and may influence the local meteorology of the region. Wind power production and other commercial uses in this area are related to atmospheric conditions, and so it is important to understand how future wind plants may change the local meteorology. In the absence of measurements of potential wind plant impacts on meteorology, simulations offer the next-best possible insight into wake effects on boundary layer height, temperature, fluxes, and wind speeds. However, simulation tools that capture these effects offer multiple options for representing the amount of turbine-added turbulence that may impact assessments of micrometeorological effects. To explore this sensitivity, we compare 1 year of simulations from the Weather Research and Forecasting (WRF) model with and without wind plants incorporated, focusing on the lease area south of Massachusetts and Rhode Island. The simulations with wind plants are repeated to include both the maximum and minimum amounts of added turbulence to provide bounds on the potential impacts. We assess changes in wind speeds, 2 m temperature, surface heat flux, turbulence kinetic energy (TKE), and boundary layer height during different stability classifications and ambient wind speeds over the entire year and compare results for the degree of added turbulence in the wind plant simulations. Because the wake behavior may be a function of boundary layer stability, in this paper, we also present a machine learning algorithm to quantify the area and distance of the wake generated by the wind plant. This analysis enables us to identify the relationship between wake extent and boundary layer height. We find that hub-height wind speed is reduced within and downwind of the wind plant, with the strongest impacts occurring during stable conditions and faster wind speeds in region 3 of the turbine power curve, although impacts lessen as wind speeds increase past 15 m s−1. In contrast, wind speeds near the surface decrease when no turbine-added turbulence is included but can increase for stably stratified conditions when 100 % of possible TKE is included in the simulations. TKE increases at hub height in the simulations with added TKE for all stability classes, suggesting that atmospheric stability does not immediately modify the TKE generated by turbines. Negligible changes in hub-height TKE manifest in the simulations without the added TKE. At the surface, TKE increases in the simulations with maximum added turbulence only for unstable conditions. In the no-added-turbulence simulations, surface TKE decreases slightly in neutral and unstable simulations. Differences in 2 m temperatures and surface heat fluxes are small but vary considerably with atmospheric stability and the amount of added TKE. Boundary layer heights increase within the wind plant when turbine-added turbulence is included and decrease slightly downwind during stable conditions. In contrast, with no added turbulence, the boundary layer height is in general reduced in stable conditions with wind speeds less than 15 m s −1 and slightly increased in neutral conditions. Finally, shallower upwind boundary layer heights tend to correlate with larger wake areas and distances, though other factors likely also play a role in determining the extent of the wind plant wake. These simulation-based results provide a bound for micrometeorological impacts of wind plant wakes: simulations that couple the atmosphere to the ocean may reduce these impacts, and we await observational verification.

17 WIND ENERGY↗
DOE OSTI2019

Efficient surrogate modeling methods for large-scale Earth system models based on machine-learning techniques

Abstract. Improving predictive understanding of Earth system variability and change requires data–model integration. Efficient data–model integration for complex models requires surrogate modeling to reduce model evaluation time. However, building a surrogate of a large-scale Earth system model (ESM) with many output variables is computationally intensive because it involves a large number of expensive ESM simulations. In this effort, we propose an efficient surrogate method capable of using a few ESM runs to build an accurate and fast-to-evaluate surrogate system of model outputs over large spatial and temporal domains. We first use singular value decomposition to reduce the output dimensions and then use Bayesian optimization techniques to generate an accurate neural network surrogate model based on limited ESM simulation samples. Our machine-learning-based surrogate methods can build and evaluate a large surrogate system of many variables quickly. Thus, whenever the quantities of interest change, such as a different objective function, a new site, and a longer simulation time, we can simply extract the information of interest from the surrogate system without rebuilding new surrogates, which significantly reduces computational efforts. We apply the proposed method to a regional ecosystem model to approximate the relationship between eight model parameters and 42 660 carbon flux outputs. Results indicate that using only 20 model simulations, we can build an accurate surrogate system of the 42 660 variables, wherein the consistency between the surrogate prediction and actual model simulation is 0.93 and the mean squared error is 0.02. This highly accurate and fast-to-evaluate surrogate system will greatly enhance the computational efficiency of data–model integration to improve predictions and advance our understanding of the Earth system.

58 GEOSCIENCES↗
DOE OSTI2023

Reclassification of ASFV into 7 Biotypes Using Unsupervised Machine Learning

In 2007, an outbreak of African swine fever (ASF), a deadly disease of domestic swine and wild boar caused by the African swine fever virus (ASFV), occurred in Georgia and has since spread globally. Historically, ASFV was classified into 25 different genotypes. However, a newly proposed system recategorized all ASFV isolates into 6 genotypes exclusively using the predicted protein sequences of p72. However, ASFV has a large genome that encodes between 150–200 genes, and classifications using a single gene are insufficient and misleading, as strains encoding an identical p72 often have significant mutations in other areas of the genome. We present here a new classification of ASFV based on comparisons performed considering the entire encoded proteome. A curated database consisting of the protein sequences predicted to be encoded by 220 reannotated ASFV genomes was analyzed for similarity between homologous protein sequences. Weights were applied to the protein identity matrices and averaged to generate a genome-genome identity matrix that was then analyzed by an unsupervised machine learning algorithm, DBSCAN, to separate the genomes into distinct clusters. We conclude that all available ASFV genomes can be classified into 7 distinct biotypes.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2018

Machine Learning Reveals Missing Edges and Putative Interaction Mechanisms in Microbial Ecosystem Networks

Different organisms in a microbial community may drastically affect each other’s growth phenotypes, significantly affecting the community dynamics, with important implications for human and environmental health. Novel culturing methods and the decreasing costs of sequencing will gradually enable high-throughput measurements of pairwise interactions in systematic coculturing studies. However, a thorough characterization of all interactions that occur within a microbial community is greatly limited both by the combinatorial complexity of possible assortments and by the limited biological insight that interaction measurements typically provide without laborious specific follow-ups. Here, we show how a simple and flexible formal representation of microbial pairs can be used for the classification of interactions via machine learning. The approach we propose predicts with high accuracy the outcome of yet-to-be performed experiments and generates testable hypotheses about the mechanisms of specific interactions.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
DOE OSTI2021

Robust implementation of generative modeling with parametrized quantum circuits

Although the performance of hybrid quantum-classical algorithms is highly dependent on the selection of the classical optimizer and the circuit ansätze, a robust and thorough assessment on-hardware of such features has been missing to date. From the optimizer perspective, the primary challenge lies in the solver’s stochastic nature, and their significant variance over the random initialization. Therefore, a robust comparison requires one to perform several training curves for each solver before one can reach conclusions about their typical performance. Since each of the training curves requires the execution of thousands of quantum circuits in the quantum computer, such a robust study remained a steep challenge for most hybrid platforms available today. In this work, we leverage on Rigetti’s Quantum Cloud Services (QCS™) to overcome this implementation barrier, and we study the on-hardware performance of the data-driven quantum circuit learning (DDQCL) for three different state-of-the-art classical solvers, and on two-different circuit ansätze associated to different entangling connectivity graphs for the same task. Additionally, we assess the gains in performance from varying circuit depths. To evaluate the typical performance associated with each of these settings in this benchmark study, we use at least five independent runs of DDQCL towards the generation of quantum generative models capable of capturing the patterns of the canonical Bars and Stripes dataset. In this experimental benchmarking, the gradient-free optimization algorithms show an outstanding performance compared to the gradient-based solver. In particular, one of them had better performance when handling the unavoidable noisy objective function to be minimized under experimental conditions.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Results and lessons learned from accelerating radio frequency modeling using machine learning [slides]

The “advanced tokamak” reactor concept is a leading candidate for a steady state fusion pilot plant. An advanced tokamak (AT) sustains a majority of the required plasma current with effects resulting from maintenance of the peaked pressure at the device center. This current is augmented by auxiliary current drive sources. These auxiliary actuators may consist of neutral particle beams and/or radio frequency (RF) systems such as lower hybrid current drive (LHCD) and high harmonic fast wave (HHFW) current drive using radio and microwaves from antennas. The primary focus of this work is to develop models of RF current profile control suitable for use in integrated modeling frameworks and for real-time control in experiments. Direct physics models of RF current drive can be computationally intensive. In order to achieve predictive times appropriate for the thousands of calls needed in real-time control of experiments and for use in integrated models, we will apply modern machine learning (ML) techniques to accelerate these models and interpolate their results. To generate the fast and accurate models for use in control level algorithms and integrated modeling we need to replace present models with high dimensional interpolation of their results. We will perform additional simulations across a broader parameter range for EAST and other tokamaks in different physics regimes (Alcator C-Mod, DIII-D, WEST, CFETR, ARC, ITER) and combine them into a larger database for training and testing of the ML models. Further testing of the control level models with experimental current profile data from EAST and C-Mod tokamaks will provide additional confirmation of the control level model before integration in a tokamak control system or integrated modeling suite. ML will be used to optimize the selection of training data consisting of RF current driven at different values of density profile, temperature profile, plasma current, and wavenumber. ML will also be used to facilitate classification of current drive from these input data. The output of this effort will be a validated classifier capable of determining the current drive profiles for HHFW CD and LHCD on a mille-second timescale. This will provide a breakthrough capability enabling real-time control of RF driven current profiles in experiments including ITER ICRF and use integrated modeling frameworks requiring thousands of current profile calculations in discharge simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Tutorial: Machine-Learning-Based CREASE-2D Analysis of 2D SAXS Profiles to Characterize Anisotropic Nanostructures in Soft Materials

We present a tutorial to guide users on how to extend the Computational Reverse Engineering Analysis of Scattering Experiments-2D (CREASE-2D) framework to interpret their experimental two-dimensional small-angle scattering (SAS) data from soft materials (e.g., polymers, peptide amphiphiles, biomolecular fibrils). Unlike most traditional SAS analysis approaches, which typically rely on azimuthally averaged onedimensional (1D) profiles, CREASE-2D utilizes the complete 2D scattering profile to reveal information about anisotropy in the structure. In past applications, CREASE has provided insights into complex structural features, including the cross-sectional shapes of assembled nanostructures and dispersity in these features, which are difficult to discern with existing analytical models. While (1D- ) CREASE has been applied to SANS and SAXS data, this tutorial shares the steps for implementing CREASE-2D using an example of a dipeptide solution system, for which we have SAXS data. We present details for these steps involved in using CREASE-2D to interpret SAXS profiles: how to preprocess SAXS data, define relevant structural features, generate three-dimensional real-space structures for specific values of these features, train a machine learning (ML) surrogate model to predict scattering profiles for given structural features, and optimize these features using genetic algorithms (GA). Then, we use these steps to interpret complex 2DSAXS data collected from dipeptide solutions that, in microscopy images, exhibit nanoscale structures that could be elliptical tubes/ flat tapes/cylinders or a combination of these cross sections. Open-source codes, computational hardware, and software requirements, as well as the strengths and limitations of this protocol, are also presented. We expect researchers working with (soft) biomaterials, peptide amphiphiles, amphiphilic polymer solutions, polymer nanocomposites, and blends of particles/polymers will find this CREASE-2D method and this tutorial of use.

CREASE↗
DOE OSTI2020

A machine learning-based fast frequency response control for a VSC-HVDC system

An HVDC system can realize a very fast frequency response to the disturbed system under a contingency because its active power control is decoupled from the frequency deviation. However, most of existing HVDC frequency control strategies are coupled with system primary frequency control and secondary frequency control. Since the traditional system frequency control is dominated by the thermal generators, the advantage of the fast response of the HVDC system is not made fully used. The development of a frequency response estimation based on a machine learning algorithm provides another approach to improve the frequency response capability of the HVDC system. Different from other frequency deviation tracking strategies, a machine learning based HVDC frequency response control can directly increase the power flow of a HVDC system by estimation of the system generator or load lost. In this paper, a fast frequency response control using a HVDC system for a large power system disturbance based on the multivariate random forest regression (MRFR) algorithm is proposed. The simulation is carried out with an integrated power system model based on the North American interconnections. The simulation results indicate that the proposed MRFR based frequency response control can significantly improve the frequency low point during an event, while stabilizing the frequency in advance.

42 ENGINEERING↗
DOE OSTI2026

Development of physics-consistent conditional diffusion model to overcome data scarcity in critical heat flux

Deep generative modeling provides a powerful pathway to overcome data scarcity in energy-related applications where experimental data are often limited. By learning the underlying probability distribution of the training dataset, deep generative models, such as the diffusion model, can generate high-fidelity synthetic samples that statistically resemble the training data. Such synthetic data generation can significantly enrich the size and diversity of the available training data, and more importantly, improve the robustness of downstream machine learning models in predictive tasks. The objective of this paper is to investigate the effectiveness of diffusion models for overcoming data scarcity in nuclear energy applications. By leveraging a public dataset on critical heat flux which covers a wide range of commercial nuclear reactor operational conditions, we developed a diffusion model that can generate an arbitrary amount of synthetic samples. Since a vanilla diffusion model can only generate samples randomly, we also developed a conditional diffusion model capable of generating targeted critical heat flux data under user-specified thermal-hydraulic conditions. The performance of the diffusion model was evaluated based on its ability to capture empirical feature distributions and pair-wise correlations, as well as to maintain physical consistency. The results showed that both the diffusion model and conditional diffusion model can successfully generate realistic and physics-consistent critical heat flux data. Furthermore, uncertainty quantification results demonstrate that the conditional diffusion model is highly effective in augmenting critical heat flux data while maintaining acceptable levels of uncertainty.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

A Review on Machine Learning for Neutrino Experiments

Neutrino experiments study the least understood of the Standard Model particles by observing their direct interactions with matter or searching for ultra-rare signals. The study of neutrinos typically requires overcoming large backgrounds, elusive signals, and small statistics. The introduction of state-of-the-art machine learning tools to solve analysis tasks has made major impacts to these challenges in neutrino experiments across the board. Machine learning algorithms have become an integral tool of neutrino physics, and their development is of great importance to the capabilities of next generation experiments. An understanding of the roadblocks, both human and computational, and the challenges that still exist in the application of these techniques is critical to their proper and beneficial utilization for physics applications. This review presents the current status of machine learning applications for neutrino physics in terms of the challenges and opportunities that are at the intersection between these two fields.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗