Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed 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 1,279 records · Page 71
All sourcesNASA NTRSDOE OSTI
DOE OSTI2019

Cybersecurity for the Future Electric Grid

As connectivity and distributed energy levels increase, so does the number of access points for potential cyber threats. With legacy systems that were not designed to protect against cyber vulnerabilities, the approach to securing the electric grid must change. Learn how the National Renewable Energy Laboratory (NREL) offers the ideal balance of expertise and infrastructure for cutting-edge research on cybersecurity and the future grid.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Learning likelihood ratios with neural network classifiers

The likelihood ratio is a crucial quantity for statistical inference in science that enables hypothesis testing, construction of confidence intervals, reweighting of distributions, and more. Many modern scientific applications, however, make use of data- or simulation-driven models for which computing the likelihood ratio can be very difficult or even impossible. By applying the so-called “likelihood ratio trick,” approximations of the likelihood ratio may be computed using clever parametrizations of neural network-based classifiers. A number of different neural network setups can be defined to satisfy this procedure, each with varying performance in approximating the likelihood ratio when using finite training data. We present a series of empirical studies detailing the performance of several common loss functionals and parametrizations of the classifier output in approximating the likelihood ratio of two univariate and multivariate Gaussian distributions as well as simulated high-energy particle physics datasets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

The increasing incidence and severity of wildfires underscores the necessity of accurately predicting their behavior. While high-fidelity models derived from first principles offer physical accuracy, they are too computationally expensive for use in real-time fire response. Low-fidelity models sacrifice some physical accuracy and generalizability via the integration of empirical measurements, but enable real-time simulations for operational use in fire response. Machine learning techniques have demonstrated the ability to bridge these objectives by learning first-principles physics while achieving computational speedups. While deep learning approaches have demonstrated the ability to predict wildfire propagation over large time periods, time-resolved fire-spread predictions are needed for active fire management. Here, in this work, we evaluate the ability of deep learning approaches in accurately modeling the time-resolved dynamics of wildfires. We use an autoregressive process in which a convolutional recurrent deep learning model makes predictions that propagate a wildfire over 15 min increments. We apply the model to four simulated datasets of increasing complexity, containing both field fires with homogeneous fuel distribution as well as real-world topologies sampled from the California region of the United States. We show that even after 100 autoregressive predictions representing more than 24 h of simulated fire spread, the resulting models generate stable and realistic propagation dynamics, achieving a Jaccard score between 0.89 and 0.94 when predicting the resulting fire scar. The inference time of the deep learning models are examined and compared, and directions for future work are discussed.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

Probabilistic Short-Term Wind Forecasting Based on Pinball Loss Optimization

Probabilistic wind power forecasts that quantify the uncertainty in wind output have the potential to aid in the economic grid integration of wind power at large penetration levels. In this paper, a novel probabilistic wind forecasting approach based on pinball loss optimization is proposed, in conjunction with a multi-model machine learning based ensemble deterministic forecasting framework. By assuming the point-forecasted value as the mean at each point, one unknown parameter (i.e., standard deviation) of a predictive distribution at each forecasting point is determined by minimizing the pinball loss. A surrogate model is developed to represent the unknown distribution parameter as a function of deterministic forecasts. This surrogate model can be used together with deterministic forecasts to predict the unknown distribution parameter and thereby generate probabilistic forecasts. Numerical results of case studies show that the proposed method has improved the pinball loss by up to 35% compared to a baseline quantile regression forecasting model.

17 WIND ENERGY↗
DOE OSTI2021

Phasor-Measurement-Unit-Based Data Analytics Using Digital Twin and PhasorAnalytics Software

A major objective of this project was to apply GE’s commercial machine learning and data analytics toolsets to large-scale, real-world, anonymized Phasor Measurement Unit (PMU) datasets in order to extract signatures, correlated and/or causal factors, and precursor patterns associated with significant power system phenomena. The project had a particular emphasis on extraction of insights relevant to asset health monitoring, real-time load modeling and cybersecurity monitoring. Additionally, the team was directed to undertake a comprehensive data quality analysis for the provided datasets and encouraged to estimate the ‘machine-learning readiness’ of the datasets by documenting any major obstacles to the application of commercial machine learning algorithms. To accomplish the aforementioned objectives, the project team’s work centered around the identification of key event signatures and application of the identified event signatures for event detection and event classification. The industry-validated, semi-supervised machine learning strategy employed for event signature identification involved several major tasks, including data-preprocessing, generation of an overabundance of features, normal data identification, normality modeling, and event signature identification through a methodical, quantitative ranking of features in order of relevance to each studied event type. Throughout the project, data quality issues and mitigation techniques were investigated. In this report, insights are provided regarding the readiness of the provided synchrophasor datasets for application of machine learning and data analytics. The methodologies employed for this technical strategy are summarized in this report. With regards to data preprocessing and feature generation, the provided Training and Test Datasets were ingested into GE’s big data environment. Subsequently, the team applied bad data cleansing and data imputation scripts, event detection scripts, and application programming interfaces (APIs) to the datasets for convenient data access. The project team completed development and validation of dozens of physics-based, statistics-based and transformation-based feature functions used for the extraction of over 60 synchrophasor features. Using a new parallel feature generation technology developed on this project, over 60 features have been rapidly generated for the full two years’ worth of Training and Test Dataset data associated with both the Eastern and Western interconnects. Even accommodating for temporal down-sampling inherent to the feature extraction procedure, this parallel feature generation activity resulted in a massive feature set with a storage requirement approximately equal to that of the raw training dataset itself. With regards to normal data identification and normality modeling, a normality model was built using the feature data extracted from the Training Dataset and iteratively refined subsequent to incremental adjustments and expansions of the Training Dataset feature data. With respect to event characterization and signature identification, an event signature identification pipeline was developed and used in conjunction with the normality model to identify over 15 event signatures for key event categories within the Training Dataset. The identified event signatures were used to characterize hundreds of key events in terms of relative severity, duration, and location of the event. An investigation was undertaken to identify correlated and causal factors involved in transformer events. A separate investigation into temporal trends in ring-down analysis results was undertaken to determine possible associations between system dynamics and various other factors such as loading, season or year. To validate the identified event signatures, additional work was undertaken to develop signature-based anomaly detection and classification tools suitable for convenient application to the synchrophasor datasets. The anomaly detection and classification tools, suitable for online application, were then applied to the entirety of the Eastern Interconnect Training and Test Datasets. Performance of the event detection and classification tools was evaluated upon receipt of the Test Dataset event logs (i.e., the labels for events contained in the Test Dataset), and promising results were obtained despite several challenges (documented herein) associated with application of supervised or semi-supervised machine learning methods to large-scale, anonymized datasets. Finally, the detection and classification tools were used to detect, classify, and characterize thousands of new events not included in the original event logs provided by the DOE within both the Training and Test Datasets.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2019

Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems

Here, we present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems. Leveraging recent advances in variational inference with implicit distributions, we put forth a statistical inference framework that enables the end-to-end training of surrogate models on paired input–output observations that may be stochastic in nature, originate from different information sources of variable fidelity, or be corrupted by complex noise processes. The resulting surrogates can accommodate high-dimensional inputs and outputs and are able to return predictions with quantified uncertainty. Furthermore, the effectiveness our approach is demonstrated through a series of canonical studies, including the regression of noisy data, multi-fidelity modeling of stochastic processes, and uncertainty propagation in high-dimensional dynamical systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Exploring the Value of Learned Representations for Automated Syndromic Definitions

Objective: To better define and automate biosurveillance syndrome categorization using modern unsupervised vector embedding techniques. Introduction: Comprehensive medical syndrome definitions are critical for outbreak investigation, disease trend monitoring, and public health surveillance. However, because current definitions are based on keyword string-matching, they may miss important distributional information in free text and medical codes that could be used to build a more general classifier. Here, we explore the idea that individual ICD codes can be categorized by examining their contextual relationships across all other ICD codes. We extend previous work in representation learning with medical data [1] by generating dense vector embeddings of these ICD codes found in emergency department (ED) visit records. The resulting representations capture information about disease co-occurrence that would typically require SME involvement and support the development of more robust syndrome definitions.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

“Inverting” X-ray Absorption Spectra of Catalysts by Machine Learning in Search for Activity Descriptors

The rapid growth of methods emerging in the past decade for synthesis of “designer” catalysts—ranging from the size and shape-selected nanoparticles to mass-selected clusters, to precisely engineered bimetallic surfaces, to single site and pair site catalysts—has opened opportunities for tailoring the catalyst structure for the desired activity and selectivity. It has also sharpened the need for developing approaches to the operando characterization, ones that identify the catalytic active sites and follow their evolutions in reaction conditions. Commonly used methods for determination of the activity descriptors in the nanocatalysts, based on the correlation between the changes in catalyst performance and evolution of its structural and electronic properties, are hampered by the paucity of experimental techniques that can detect such properties with high accuracy and in reaction conditions. Out of many such techniques, X-ray absorption spectroscopy (XAS) stands out as an element-specific method that is very sensitive to the local geometric and electronic properties of the metal atoms and their surroundings and, therefore, is able to track catalyst structure modifications in operando conditions. Despite the vast amount of structure-specific information (such as, e.g., the charge states and radial distribution function of neighbors of selected atomic species) stored in the XAS data of catalysts, extracting it from the spectra is challenging, especially in the conditions of low metal weight loading, nanoscale dimensions, heterogeneous size and composition distributions, and harsh reaction environment. In this Perspective, we discuss the recent developments in XAS data analysis achieved by employing supervised and unsupervised machine learning (ML) methods for structural characterization of catalysts. By benefiting from the sensitivity of ML methods to subtle variations in experimental data, a previously “hidden” relationship between the X-ray absorption spectrum and descriptors of material’s structure and/or composition can be found, as illustrated on representative examples of mono-, hetero-, and nonmetallic catalysts. In the case of supervised ML, the experimental spectra can be rapidly “inverted”, and the structure of the catalyst can be tracked in real time and in reaction conditions. Finally, emerging opportunities for catalysis research that the ML methods enable, such as high-throughput data analysis, and their applications to other experimental probes of catalyst structure are discussed.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Quantifying Atomically Dispersed Catalysts Using Deep Learning Assisted Microscopy

The catalytic performance of atomically dispersed catalysts (ADCs) is greatly influenced by their atomic configurations, such as atom–atom distances, clustering of atoms into dimers and trimers, and their distributions. Scanning transmission electron microscopy (STEM) is a powerful technique for imaging ADCs at the atomic scale; however, most STEM analyses of ADCs thus far have relied on human labeling, making it difficult to analyze large data sets. Here, we introduce a convolutional neural network (CNN)-based algorithm capable of quantifying the spatial arrangement of different adatom configurations. The algorithm was tested on different ADCs with varying support crystallinity and homogeneity. Results show that our algorithm can accurately identify atom positions and effectively analyze large data sets. Here, this work provides a robust method to overcome a major bottleneck in STEM analysis for ADC catalyst research. We highlight the potential of this method to serve as an on-the-fly analysis tool for catalysts in future in situ microscopy experiments.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. Here, the novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial- temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad- GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Updated distribution maps of predominant Culex mosquitoes across the Americas

Abstract Background Estimates of the geographical distribution of Culex mosquitoes in the Americas have been limited to state and provincial levels in the United States and Canada and based on data from the 1980s. Since these estimates were made, there have been many more documented observations of mosquitoes and new methods have been developed for species distribution modeling. Moreover, mosquito distributions are affected by environmental conditions, which have changed since the 1980s. This calls for updated estimates of these distributions to understand the risk of emerging and re-emerging mosquito-borne diseases. Methods We used contemporary mosquito data, environmental drivers, and a machine learning ecological niche model to create updated estimates of the geographical range of seven predominant Culex species across North America and South America: Culex erraticus , Culex nigripalpus , Culex pipiens , Culex quinquefasciatus , Culex restuans , Culex salinarius , and Culex tarsalis . Results We found that Culex mosquito species differ in their geographical range. Each Culex species is sensitive to both natural and human-influenced environmental factors, especially climate and land cover type. Some prefer urban environments instead of rural ones, and some are limited to tropical or humid areas. Many are found throughout the Central Plains of the USA. Conclusions Our updated contemporary Culex distribution maps may be used to assess mosquito-borne disease risk. It is critical to understand the current geographical distributions of these important disease vectors and the key environmental predictors structuring their distributions not only to assess current risk, but also to understand how they will respond to climate change. Since the environmental predictors structuring the geographical distribution of mosquito species varied, we hypothesize that each species may have a different response to climate change. Graphical abstract

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Real-Time Edge AI for Distributed Systems (READS): Progress on Beam Loss De-Blending for the Fermilab Main Injector and Recycler

The Fermilab Main Injector enclosure houses two accelerators, the Main Injector and Recycler. During normal operation, high intensity proton beams exist simultaneously in both. The two accelerators share the same beam loss monitors (BLM) and monitoring system. Beam losses in the Main Injector enclosure are monitored for tuning the accelerators and machine protection. Losses are currently attributed to a specific machine based on timing. However, this method alone is insufficient and often inaccurate, resulting in more difficult machine tuning and unnecessary machine downtime. Machine experts can often distinguish the correct source of beam loss. This suggests a machine learning (ML) model may be producible to help de-blend losses between machines. Work is underway as part of the Fermilab Real-time Edge AI for Distributed Systems Project (READS) to develop a ML empowered system that collects streamed BLM data and additional machine readings to infer in real-time, which machine generated beam loss.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Optimizing High-Throughput Inference on Graph Neural Networks at Shared Computing Facilities with the NVIDIA Triton Inference Server

Abstract With machine learning applications now spanning a variety of computational tasks, multi-user shared computing facilities are devoting a rapidly increasing proportion of their resources to such algorithms. Graph neural networks (GNNs), for example, have provided astounding improvements in extracting complex signatures from data and are now widely used in a variety of applications, such as particle jet classification in high energy physics (HEP). However, GNNs also come with an enormous computational penalty that requires the use of GPUs to maintain reasonable throughput. At shared computing facilities, such as those used by physicists at Fermi National Accelerator Laboratory (Fermilab), methodical resource allocation and high throughput at the many-user scale are key to ensuring that resources are being used as efficiently as possible. These facilities, however, primarily provide CPU-only nodes, which proves detrimental to time-to-insight and computational throughput for workflows that include machine learning inference. In this work, we describe how a shared computing facility can use the NVIDIA Triton Inference Server to optimize its resource allocation and computing structure, recovering high throughput while scaling out to multiple users by massively parallelizing their machine learning inference. To demonstrate the effectiveness of this system in a realistic multi-user environment, we use the Fermilab Elastic Analysis Facility augmented with the Triton Inference Server to provide scalable and high-throughput access to a HEP-specific GNN and report on the outcome.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

Emerging Plug Load Management Technologies that Save Energy and Time

This fact sheet introduces two emerging technologies that could streamline plug load management (PLM) for increased energy savings for building owners: learning behavior algorithms (LBA) and automatic and dynamic load detection (ADLD). Plug loads are responsible for 47% of the energy consumed in commercial buildings, yet their distributed and ever-changing nature makes them challenging to manage. PLM systems exist today that use smart plugs to meter and control devices at the outlet level, but their uptake has been relatively slow in part because of the significant labor required for installation and maintenance. LBA and ADLD may address these challenges and provide additional energy efficiency and nonenergy benefits.

Plug and process loads, PPL, plug loads, plug load↗
DOE OSTI2023

Deep learning assisted jet tomography for the study of Mach cones in QGP

Abstract Mach cones are expected to form in the expanding quark-gluon plasma (QGP) when energetic quarks and gluons traverse the hot medium at a velocity faster than the speed of sound in high-energy heavy-ion collisions. The shape of the Mach cone and the associated diffusion wake are sensitive to the initial jet production location and the propagation direction of the parton shower relative to the radial flow because of the distortion caused by the collective expansion of the QGP and the large density gradient. The shape of jet-induced Mach cones and their distortions in heavy-ion collisions provide a unique and direct probe of the dynamical evolution and the equation of state of QGP. However, it is difficult to identify the Mach cone and the diffusion wake in current experimental measurements of final hadron distributions because they are averaged over all possible initial jet production locations and parton-shower propagation directions. To overcome this difficulty, we develop a deep learning assisted jet tomography which uses the full information of the final hadrons from jets to localize the initial jet production positions. This method can help to constrain the initial regions of jet production in heavy-ion collisions and enable a differential study of Mach-cones with different path lengths and orientations relative to the radial flow of the QGP in heavy-ion collisions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2026

Integrating very-high-resolution imagery, Sentinel-2 time-series data, and machine learning to map shrub fractional abundance across arid and semi-arid ecosystems in China

Shrub fractional abundance (SFA), the proportion of shrub cover per unit area, serves as a critical indicator of environmental aridity and ecosystem health in arid and semi-arid regions, particularly across the Mongolian steppe. However, large-scale SFA mapping in Mongolian steppe ecosystems remains challenging due to the small crown size of shrubs, their sparse distribution, and spectral overlap with coexisting low vegetation (e.g., grasses and herbs), which hinders accurate detection using coarser-resolution satellite data or traditional field surveys. To address these challenges, we developed a two-step approach that integrates very-high-resolution (VHR) imagery, time-series Sentinel-2 data, and deep learning techniques. First, we generated high-accuracy benchmark maps of individual shrub crowns from 0.5 m VHR imagery by combining manual segmentation with a hybrid deep learning framework (Dino V2 and convolutional neural networks). Second, we used these shrub crown maps as training data to build an XGBoost model for predicting SFA from 20 m Sentinel-2 time-series data, leveraging phenological information to improve estimation. We validated our approach across 70 sites (1km 2 each) in the Inner Mongolia Autonomous Region, which is representative of Mongolian steppe ecosystems. From VHR imagery, we mapped 1.31 million shrub crowns with an accuracy of R 2 = 0.92. Scaling up with Sentinel-2 data yielded regional SFA maps with an R 2 = 0.60. Further SHAP (SHapley Additive exPlanations) analysis on the developed XGBoost model revealed that phenological metrics (particularly observations in early-May, mid-July, and late-September), which distinguish shrub phenology from that of other land cover types (e.g., grasses and bare soil), were the most influential predictors of SFA. Finally, our regional SFA maps uncovered unimodal relationships between shrub distribution and climate variables, peaking at mean annual minimum temperatures near 0 °C and annual precipitation around 200 mm. Collectively, these findings demonstrate how the integration of multi-source remote sensing and machine learning can overcome historical limitations in SFA mapping, enabling accurate, spatially continuous assessments across vast Inner-Mongolian steppe ecosystems. Our framework has the potential to be applied to other steppe ecosystems and dryland ecosystems across the Mongolian steppe and beyond, offering a foundation for improved monitoring and ecological impact assessments in the face of global climate changes.

Arid and semi-arid landscapes↗
DOE OSTI2017

HPC formulations of optimization algorithms for tensor completion

Tensor completion is a powerful tool used to estimate or recover missing values in multi-way data. It has seen great success in domains such as product recommendation and healthcare. Tensor completion is most often accomplished via low-rank sparse tensor factorization, a computationally expensive non-convex optimization problem which has only recently been studied in the context of parallel computing. In this work, we study three optimization algorithms that have been successfully applied to tensor completion: alternating least squares (ALS), stochastic gradient descent (SGD), and coordinate descent (CCD++). We explore opportunities for parallelism on shared- and distributed-memory systems and address challenges such as memory- and operation-efficiency, load balance, cache locality, and communication. Among our advancements are a communication-efficient CCD++ algorithm, an ALS algorithm rich in level-3 BLAS routines, and an SGD algorithm which combines stratification with asynchronous communication. Furthermore, we show that introducing randomization during ALS and CCD++ can accelerate convergence. We evaluate our parallel formulations on a variety of real datasets on a modern supercomputer and demonstrate speedups through 16384 cores. Further, these improvements reduce time-to-solution from hours to seconds on real-world datasets. We show that after our optimizations, ALS is advantageous on parallel systems of small-to-moderate scale, while both ALS and CCD++ provide the lowest time-to-solution on large-scale distributed systems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Structural design challenges and implications for high temperature concentrating solar power receivers

High operating temperatures along with diurnal cycling and high operating stresses bring many material and engineering challenges for concentrated solar power (CSP) receivers. Current design rules in ASME Boiler and Pressure Vessel (B&PV) Code for high temperature structural components were not intended for CSP components. The paper reviews the design rules in several sections of ASME B&PV Code in terms of their applicability in designing high temperature CSP receivers. With some restrictions and modifications, the conditions assumed in the design rules in Section III, Division 5 of ASME B&PV Code are found to closely resemble the loading conditions of CSP receiver, including accounting for the interaction between creep and fatigue damage. Further, the paper applies the proposed design rules to an external tubular receiver design and discusses several lessons learned from the design study. The creep damage accumulation due to high thermal stresses resulting from circumferentially non-uniform flux distribution is found to control the design of CSP receivers. Several mitigation actions to improve the design life of receivers are also discussed.

14 SOLAR ENERGY↗