Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed 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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
NASA NTRS2011

Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data

This paper seeks to improve low-cost labeling in terms of training set reliability (the fraction of correctly labeled training items) and test set performance for multi-view learning methods. Co-training is a popular multiview learning method that combines high-confidence example selection with low-cost (self) labeling. However, co-training with certain base learning algorithms significantly reduces training set reliability, causing an associated drop in prediction accuracy. We propose the use of ensemble labeling to improve reliability in such cases. We also discuss and show promising results on combining low-cost ensemble labeling with active (low-confidence) example selection. We unify these example selection and labeling strategies under collaborative learning, a family of techniques for multi-view learning that we are developing for distributed, sensor-network environments.

machine learning↗
DOE OSTI2023

High–Resolution Maps of Near–Surface Permafrost for Three Watersheds on the Seward Peninsula, Alaska Derived From Machine Learning

Permafrost soils are a critical component of the global carbon cycle and are locally important because they regulate the hydrologic flux from uplands to rivers. Furthermore, degradation of permafrost soils causes land surface subsidence, damaging infrastructure that is crucial for local communities. Regional and hemispherical maps of permafrost are too coarse to resolve distributions at a scale relevant to assessments of infrastructure stability or to illuminate geomorphic impacts of permafrost thaw. Here we train machine learning models to generate meter–scale maps of near–surface permafrost for three watersheds in the discontinuous permafrost region. The models were trained using ground truth determinations of near–surface permafrost presence from measurements of soil temperature and electrical resistivity. We trained three classifiers: extremely randomized trees (ERTr), support vector machines (SVM), and an artificial neural network (ANN). Model uncertainty was determined using k–fold cross validation, and the modeled extents of near–surface permafrost were compared to the observed extents at each site. At–a–site near–surface permafrost distributions predicted by the ERTr produced the highest accuracy (70%–90%). However, the transferability of the ERTr to the sites outside of the training data set was poor, with accuracies ranging from 50% to 77%. The SVM and ANN models had lower accuracies for at–a–site prediction (70%–83%), yet they had greater accuracy when transferred to the non–training site (62%–78%). These models demonstrate the potential for integrating high–resolution spatial data and machine learning models to develop maps of near–surface permafrost extent at resolutions fine enough to assess infrastructure vulnerability and landscape morphology influenced by permafrost thaw.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

AI-Based Optimal Design and Controls Can Greatly Reduce Carbon Emissions and Enhance Resilience in Residential Communities in Cold Climates

Net-zero energy residential communities are crucial for achieving decarbonization goals, but the high-penetration photovoltaic (PV) in those communities is posing challenges to the distribution grid. Traditional design and operation of net-zero communities rely on rule-of-thumb methods and may not work in complex scenarios. Artificial intelligence and machine learning methods can optimally size PV for net-zero energy, identify user preferences and usage patterns, and fully unlock the potential of distributed energy resources to address distribution grid issues.

artificial intelligence↗
DOE OSTI2021

Physics-Based Feature Extraction from Bulk Time-Series PMU Datasets for Event Detection

In this work, two physics-based feature extraction techniques are developed for bulk time-series phasor measurement unit (PMU) datasets collected from the field to train the machine learning model for anomaly detection. Two approaches have been developed to extract useful features for different types of events. An admittance-based feature extraction technique is developed to detect events that involve line outages and system topology variations. The developed algorithm extracts the system equivalent admittance variation. Additionally, Fielder’s Theory is utilized to further reduce the potential computation burden by sectionalizing large-scale grids and datasets into smaller areas. Second, an oscillation-based feature extraction technique is developed to detect low-frequency oscillations in power grids. The dominant oscillation modes in the grids are extracted using energy-sorted Prony analysis. The extracted dominant oscillation modes by the developed work exhibit a high fitting resolution. Finally, the developed techniques have been validated using large-scale and real-world datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Generating realistic building electrical load profiles through the Generative Adversarial Network (GAN)

Building electrical load profiles can improve understanding of building energy efficiency, demand flexibility, and building-grid interactions. Current approaches to generating load profiles are time-consuming and not capable of reflecting the dynamic and stochastic behaviors of real buildings; some approaches also trigger data privacy concerns. In this study, we proposed a novel approach for generating realistic electrical load profiles of buildings through the Generative Adversarial Network (GAN), a machine learning technique that is capable of revealing an unknown probability distribution purely from data. The proposed approach has three main steps: (1) normalizing the daily 24-hour load profiles, (2) clustering the daily load profiles with the k-means algorithm, and (3) using GAN to generate daily load profiles for each cluster. The approach was tested with an open-source database – the Building Data Genome Project. We validated the proposed method by comparing the mean, standard deviation, and distribution of key parameters of the generated load profiles with those of the real ones. The KL divergence of the generated and real load profiles are within 0.3 for majority of parameters and clusters. Additionally, results showed the load profiles generated by GAN can capture not only the general trend but also the random variations of the actual electrical loads in buildings. We report the proposed GAN approach can be used to generate building electrical load profiles, verify other load profile generation models, detect changes to load profiles, and more importantly, anonymize smart meter data for sharing, to support research and applications of grid-interactive efficient buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2020

Deep Generative Models that Solve PDEs: Distributed Computing for Training Large Data-Free Models

Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been recently reported that successfully solve PDEs, with examples including deep feed forward networks, generative networks, and deep encoder-decoder networks. However, practical adoption of these approaches is limited by the difficulty in training these models, especially to make predictions at large output resolutions (≥1024×1024). Here we report on a software framework for data parallel distributed deep learning that resolves the twin challenges of training these large SciML models - training in reasonable time as well as distributing the storage requirements. Our framework provides several out of the box functionality including (a) loss integrity independent of number of processes, (b) synchronized batch normalization, and (c) distributed higher-order optimization methods. We show excellent scalability of this framework on both cloud as well as HPC clusters, and report on the interplay between bandwidth, network topology and bare metal vs cloud. We deploy this approach to train generative models of sizes hitherto not possible, showing that neural PDE solvers can be viably trained for practical applications. We also demonstrate that distributed higher-order optimization methods are 2-3× faster than stochastic gradient-based methods and provide minimal convergence drift with higher batch-size.

PDEs↗
DOE OSTI2021

Probing Active Sites in Cu x Pd y Cluster Catalysts by Machine-Learning-Assisted X-ray Absorption Spectroscopy

Size-selected clusters are important model catalysts because of their narrow size and compositional distributions, as well as enhanced activity and selectivity in many reactions. Still, their structure-activity relationships are, in general, elusive. The main reason is the difficulty in identifying and quantitatively characterizing the catalytic active site in the clusters when it is confined within subnanometric dimensions and under the continuous structural changes the clusters can undergo in reaction conditions. Using machine learning approaches for analysis of the operando X-ray absorption near-edge structure spectra, we obtained accurate speciation of the Cu x Pd y cluster types during the propane oxidation reaction and the structural information about each type. As a result, we elucidated the information about active species and relative roles of Cu and Pd in the clusters.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Learning Optimal Power Flow Solutions using Linearized Models in Power Distribution Systems

Solving nonlinear optimal power flow (OPF) problem is computationally expensive, and poses scalability challenges for power distribution networks. An alternative to solving the original nonlinear OPF is the linear approximated OPF models. Although, these linear approximated OPF models are fast, the resulting solutions may result in significant optimality gap. Lately, the application of machine learning (ML) methods in successfully solving the nonlinear OPF has been reported. These methods learn and estimate the nonlinear control policies using a purely data-driven approach. In this paper, we propose an approach to complements the ML based approach to solving OPF using solutions from known linearized OPF model. Specifically, we use supervised learning to map the solutions of linear OPF to nonlinear control variables. Unlike, the traditional ML based methods for OPF that approximate the full distribution feeder model using function approximation, our approach uses a two-node approximation of radial networks. The proposed approach is validated using IEEE 123 bus test system for OPF solutions obtained using the nonlinear OPF models.

optimal power flow, power distribution systems, su↗
DOE OSTI2026

Uncertainty guided online ensemble for non-stationary data streams in fusion science

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.

AI↗
NASA NTRS2023

A Global Land Cover Training Dataset From 1984 to 2020

State-of-the-art cloud computing platforms such as Google Earth Engine (GEE) enable regional-to-global land cover and land cover change mapping with machine learning algorithms. However, collection of high-quality training data, which is necessary for accurate land cover mapping, remains costly and labor-intensive. To address this need, we created a global database of nearly 2 million training units spanning the period from 1984 to 2020 for seven primary and nine secondary land cover classes. Our training data collection approach leveraged GEE and machine learning algorithms to ensure data quality and biogeographic representation. We sampled the spectral-temporal feature space from Landsat imagery to efficiently allocate training data across global ecoregions and incorporated publicly available and collaborator-provided datasets to our database. To reflect the underlying regional class distribution and post-disturbance landscapes, we strategically augmented the database. We used a machine learning-based cross-validation procedure to remove potentially mis-labeled training units. Our training database is relevant for a wide array of studies such as land cover change, agriculture, forestry, hydrology, urban development, among many others.

Radost Stanimirova↗
DOE OSTI2025

PowerModel-AI: A First On-the-Fly Machine-Learning Predictor for AC Power Flow Solutions

The real-time creation of machine-learning models via active or on-the-fly learning has attracted considerable interest across various scientific and engineering disciplines. These algorithms enable machines to build models autonomously while remaining operational. Through a series of query strategies, the machine can evaluate whether newly encountered data fall outside the scope of the existing training set. In this study, we introduce PowerModel-AI, an end-to-end machine learning software designed to accurately predict AC power flow solutions. We present detailed justifications for our model design choices and demonstrate that selecting the right input features effectively captures load flow decoupling inherent in power flow equations. Our approach incorporates on-the-fly learning, where power flow calculations are initiated only when the machine detects a need to improve the dataset in regions where the model’s suboptimal performance is based on specific criteria. Otherwise, the existing model is used for power flow predictions. This study includes analyses of five Texas A&M synthetic power grid cases, encompassing the 14-, 30-, 37-, 200-, and 500-bus systems. The training and test datasets were generated using PowerModels.jl, an open-source power flow solver/optimizer developed at Los Alamos National Laboratory, NM, USA.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Multi-Kernel Adaptive Support Vector Machine for Scalable Predictive Maintenance

Application of data-driven solutions across an industry is challenging, since the data are often stored locally, and increasing privacy and security concerns restrict access to the data. In addition, it is highly unlikely that all potential data patterns are captured in a single data source. Because it is highly unlikely that all potential data patterns are captured in a single data source, machine learning (ML) models developed from a single source cannot be robust enough. An alternative is to train the ML model at each source and develop a distributed knowledge discovery and aggregation approach to build global knowledge. In this paper, we develop and demonstrate a distributed ML model, federated transfer learning (FTL), using a multi-kernel-based adaptive support vector machine (MK-A-SVM). For federated learning (FL), the multi-kernel (MK) approach enables feature-specific model aggregation under data heterogeneity; whereas for transfer learning (TL) the adaptive model enables utilization of an aggregated model from a different task. The proposed approach is validated using nuclear power plant (NPP) vertical motor-driven pump data to predict the health condition of vertical motor-driven pumps as an anomaly detection. The efficiency of the proposed approach is also quantified and compared with neural network.

42 ENGINEERING↗
DOE OSTI2023

Accelerating Machine Learning Inference with GPUs in ProtoDUNE Data Processing

Abstract We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission tools, we attempt to reprocess the data by running several thousand concurrent grid jobs, a rate we expect to be typical of current and future neutrino physics experiments. We process most of the dataset with the GPU version of our processing algorithm and the remainder with the CPU version for timing comparisons. We find that a 100-GPU cloud-based server is able to easily meet the processing demand, and that using the GPU version of the event processing algorithm is two times faster than processing these data with the CPU version when comparing to the newest CPUs in our sample. The amount of data transferred to the inference server during the GPU runs can overwhelm even the highest-bandwidth network switches, however, unless care is taken to observe network facility limits or otherwise distribute the jobs to multiple sites. We discuss the lessons learned from this processing campaign and several avenues for future improvements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Python Codebase and Jupyter Notebooks - Applications of Machine Learning Techniques to Geothermal Play Fairway Analysis in the Great Basin Region, Nevada

Git archive containing Python modules and resources used to generate machine-learning models used in the "Applications of Machine Learning Techniques to Geothermal Play Fairway Analysis in the Great Basin Region, Nevada" project. This software is licensed as free to use, modify, and distribute with attribution. Full license details are included within the archive. See "documentation.zip" for setup instructions and file trees annotated with module descriptions.

Brown, Stephen↗
DOE OSTI2025

Deconvoluting thermomechanical effects in X-ray diffraction data using machine learning

X-ray diffraction is ideal for probing the sub-surface state during complex or rapid thermomechanical loading of crystalline materials. However, challenges arise as the size of diffraction volumes increases due to spatial broadening and because of the inability to deconvolute the effects of different lattice deformation mechanisms. Here, we present a novel approach that uses combinations of physics-based modeling and machine learning to deconvolve thermal and mechanical elastic strains for diffraction data analysis. The method builds on a previous effort to extract thermal strain distribution information from diffraction data. The new approach is applied to extract the evolution of the thermomechanical state during laser melting of an Inconel 625 wall specimen which produces significant residual stress upon cooling. A combination of heat transfer and fluid flow, elasto-plasticity and X-ray diffraction simulations is used to generate training data for machine-learning (Gaussian process regression, GPR) models that map diffracted intensity distributions to underlying thermomechanical strain fields. First-principles density functional theory is used to determine accurate temperature-dependent thermal expansion and elastic stiffness used for elasto-plasticity modeling. The trained GPR models are found to be capable of deconvoluting the effects of thermal and mechanical strains, in addition to providing information about underlying strain distributions, even from complex diffraction patterns with irregularly shaped peaks.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Gluon helicity in the nucleon from lattice QCD and machine learning

We present the first lattice QCD determination of the light cone gluon helicity correlation parton distribution function (PDF) with numerical evidence toward disfavoring negative gluon polarization in the nucleon. We present a solution for eliminating an inevitable contamination term that dominates the Euclidean correlations and makes determining gluon helicity PDF unfeasible. The proposed synergy between lattice QCD and artificial intelligence offers a superior platform to alleviate the defining challenge of extracting quark and gluon PDFs from the lattice data that are available in a limited domain due to a finite range of accessible hadron momenta. We suggest a systematically improvable method to extract PDFs from the lattice data, independent of inadequate parametrizations. The result of the gluon helicity will improve our understanding of the role of spin in the strong interaction and the nucleon-spin structure.

Lattice QCD↗
NASA NTRSDate not supplied

Comparison of Entry Descent and Landing Aerodynamic Databases with Uncertainty Quantification Developed Using Machine Learning Techniques

When developing the aerodynamic databases for use in trajectory simulations, it is important to develop a system of metrics to qualify which aerodynamic models are best to use. Since aerodynamics are just one input into trajectory simulations, the results of these simulations do not reflect on the quality of the aerodynamic database used. This means that aerodynamic database comparisons must be done offline. While traditional metrics that focus on mean/nominal predictions are a good first step, more robust estimates of the prediction interval become important as more focused uncertainty models are developed. We explore the limitations of evaluating aerodynamic models based purely on nominal-centered response surfaces. Before elaborating and evaluating metrics based on distributed models, the value of evaluating prediction interval and confidence interval are discussed to conclude that prediction intervals are more relevant to the use of trajectory analysis. Several metrics to evaluate the prediction interval are introduced with a focus on the standard calibration metric. Finally, we compare candidate models using both mean and distributed metrics. A finalized candidate model developed using state of the art machine learning methods is compared to a baseline model developed using traditional aerodynamic database modeling techniques.

Aerodynamic Database↗
DOE OSTI2025

CGSim: A Simulation Framework for Large Scale Distributed Computing Environment

Large-scale distributed computing infrastructures such as the Worldwide LHC Computing Grid (WLCG) require comprehensive simulation tools for evaluating performance, testing new algorithms, and optimizing resource allocation strategies. However, existing simulators suffer from limited scalability, hardwired algorithms, lack of real-time monitoring, and inability to generate datasets suitable for modern machine learning approaches. We present CGSim, a simulation framework for large-scale distributed computing environments that addresses these limitations. Built upon the validated SimGrid simulation framework, CGSim provides high-level abstractions for modeling heterogeneous grid environments while maintaining accuracy and scalability. Key features include a modular plugin mechanism for testing custom workflow scheduling and data movement policies, interactive real-time visualization dashboards, and automatic generation of event-level datasets suitable for AI-assisted performance modeling. We demonstrate CGSim’s capabilities through a comprehensive evaluation using production ATLAS PanDA workloads, showing significant calibration accuracy improvements across WLCG computing sites. Scalability experiments show near-linear scaling for multi-site simulations, with distributed workloads achieving 6 × better performance compared to single-site execution. The framework enables researchers to simulate WLCG-scale infrastructures with hundreds of sites and thousands of concurrent jobs within practical time budget constraints on commodity hardware.

Vatsavai, Sairam Sri [Brookhaven National Laborato↗