Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed training”

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 1,549 records · Page 86
All sourcesNASA NTRSDOE OSTI
NASA NTRS1990

Telepresence and Space Station Freedom workstation operations

The Space Station Freedom workstation system is a distributed network of computer based workstations that provides the man-machine interfaces for controlling space station systems. This includes control of external manipulator, robotic and free flyer devices by crewmembers in the space station's pressurized shirt-sleeve environment. These remotely controlled devices help minimize the requirement for costly crew extravehicular activity (EVA) time for such tasks as station assembly and payload support. Direct window views may be used for controlling some of the systems, but many activities will be remote or require levels of detail not possible by direct observation. Since controlling remote devices becomes more difficult when direct views are inadequate or unavailable, many performance enhancing techniques have been considered for representing information about remote activities to the operator. Described here are the telepresence techniques under consideration to support operations and training. This includes video enhancements (e.g., graphic and text overlays and stereo viewing), machine vision systems, remote activity animation, and force reflection representation.

Jensen, Dean G.↗
DOE OSTI2022

What you get is not always what you see—pitfalls in solar array assessment using overhead imagery

Effective integration planning for small, distributed solar photovoltaic (PV) arrays into electric power grids requires access to high quality data: the location and power capacity of individual solar PV arrays. Unfortunately, national databases of small-scale solar PV do not exist; those that do are limited in their spatial resolution, typically aggregated up to state or national levels. While several promising approaches for solar PV detection have been published, strategies for evaluating the performance of these models are often highly heterogeneous from study to study. The resulting comparison of these methods for practical applications for energy assessments becomes challenging and may imply that the reported performance evaluations overly optimistic. The heterogeneity comes in many forms, each of which we explore in this work: the degree of diversity of the locations and sensors (e.g. different satellites, aerial photography) from which the training and validation data originate, the validation of ground truth (manual annotation of imagery vs known solar PV locations), the level of spatial aggregation (e.g. array-level vs regional estimates), and inconsistencies in the training and validation datasets (e.g. different datasets are used for each study and those data are not always made accessible). For each, we discuss emerging practices from the literature to address them or suggest directions of future research. As part of our investigation, we evaluate solar PV identification performance in two large regions: the entire state of Connecticut and the city of San Diego, CA. In Connecticut, we also use 33,114 known parcel-level solar PV installations from Berkeley Lab’s Tracking the Sun dataset to evaluate parcel-level performance and evaluate capacity estimates using 169 municipalities. We also make our code (which we call SolarMapper), pre-trained models, training data, and predictions publicly available and provide a web portal for interactively inspecting each prediction that was made. Here our findings suggest that traditional performance evaluation of the automated identification of solar PV from satellite imagery may be optimistic due to common limitations in the validation process. The takeaways from this work are intended to inform and catalyze the large-scale practical application of automated solar PV assessment techniques by energy researchers and professionals.

14 SOLAR ENERGY↗
DOE OSTI2024

Online MCMC Thinning with Kernelized Stein Discrepancy

A fundamental challenge in Bayesian inference is efficient representation of a target distribution. Many nonparametric approaches do so by sampling a large number of points using variants of Markov chain Monte Carlo (MCMC). Here, we propose an MCMC variant that retains only those posterior samples which exceed a kernelized Stein discrepancy (KSD) threshold, which we call KSD thinning. We establish the convergence and complexity trade-offs for several settings of KSD thinning as a function of the KSD threshold parameter, sample size, and other problem parameters. We provide experimental comparisons against other online nonparametric Bayesian methods that generate low-complexity posterior representations. We observe superior consistency/complexity trade-offs across a range of settings including MCMC sampling on two Bayesian inference problems from the biological sciences, and 10 × inference speedup and storage reduction for Bayesian neural networks with no loss of accuracy and no increase in training time. Our code is available at https://github.com/colehawkins/KSD-Thinning.

Bayesian inference↗
NASA NTRSDate not supplied

Supervised Machine Learning Approach for Classifying Earth Science Publications

The data collections archived and distributed by the GES DISC NASA data center are widely utilized for various Earth Science studies. As these collections are created, many research works are published regarding these collections' algorithms, their validation, and their applications. As NASA data centers collect these publications for public use, it is helpful to categorize them based on how they relate to their associated datasets. Specifically, whether the publication linked to the GES DISC dataset is using it for applicational research, describing the algorithm used for the dataset creation, validating the dataset, or providing a general overview of the data collection. Currently, this process requires simple manual labeling, and as such, it may be possible to solve via automation. To approach this problem, machine learning classifiers were developed to predict a publication's category. Manually labeled publications were used as the training data for the supervised machine learning algorithms, specifically Random Forest and Multinomial Naïve Bayes. After balancing the dataset and implementing the Multinomial Naïve Bayes algorithm, the classification accuracy achieved was substantially higher than the baseline accuracy, thus significantly improving the efficiency of publication labeling.

Rohan Dayal↗
DOE OSTI2024

Physics-informed heterogeneous graph neural networks for DC blocker placement

The threat of geomagnetic disturbances (GMDs) to the reliable operation of the bulk energy system has spurred the development of effective strategies for mitigating their impacts. One such approach involves placing transformer neutral blocking devices, which interrupt the path of geomagnetically induced currents (GICs) to limit their impact. The high cost of these devices and the sparsity of transformers that experience high GICs during GMD events, however, calls for a sparse placement strategy that involves high computational cost. To address this challenge, we developed a physics-informed heterogeneous graph neural network (PIHGNN) for solving the graph-based dc-blocker placement problem. Our approach combines a heterogeneous graph neural network (HGNN) with a physics-informed neural network (PINN) to capture the diverse types of nodes and edges in ac/dc networks and incorporates the physical laws of the power grid. We train the PIHGNN model using a surrogate power flow model and validate it using case studies. Results demonstrate that PIHGNN can effectively and efficiently support the deployment of GIC dc-current blockers, ensuring the continued supply of electricity to meet societal demands. Furthermore, our approach has the potential to contribute to the development of more reliable and resilient power grids capable of withstanding the growing threat that GMDs pose.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

From Vehicles to Systems: Understanding Freight Transportation as a Connected Energy, Infrastructure, and Operations System

The U.S. freight system may need to handle 50% more cargo by 2050. Upgrading our freight system requires modernizing capital-intensive, long-lived assets including freight trains, ports, and terminal infrastructure. NLR is advancing freight system solutions spanning ALTRIOS, the first digital twin for the full freight rail system; ALTRIOS-LIFTS, which can create digital twins of freight terminals; INFORMES, the first national model of the intermodal freight system; MARINESim, used to simulate and optimize ocean-going vessel operations; and more. These modeling and simulation tools enable data-driven decision-making across freight modes and systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decompose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep-learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high-level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for a one-year lead hourly load below $5\%$ MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗
DOE OSTI2021

Universal Monte Carlo Event Generator

With the Jefferson Lab 12 GeV physics program underway and plans for the future Electron-Ion Collider (EIC), the nuclear physics community is entering a new era of exploration of QCD phenomena involving extensive data taking and event-level processing. This brings with it the potential for unprecedented access to multidimensional particle momentum distributions (PMDs) that can be connected to various theoretical frameworks by unfolding the emergent quantum mechanical properties of QCD using the PMDs. In practice, the PMDs are rendered as discretized histograms (typically one- or two-dimensional projections), and detector effects must be taken into account to unfold the pure detector effect-free PMDs that can be connected with theory. One of the challenges in this new era is obtaining faithful reconstructions of the multidimensional PMDs that preserve all of the inherent particle correlations. In this LDRD project we developed a novel approach using machine learning (ML) that solves this challenge, by avoiding entirely the need to use histograms as the main numerical technique to obtain the detector effect-free PMDs. The new approach is, moreover, scalable to higher dimensional PMDs. The central idea involves training neural networks (NNs) to generate synthetic event-level data (momenta 4-vectors of final state particles) to preserve all correlations among the particles. This is achieved by converting the trial synthetic vertex-level events to detector-level events using detector simulators. The NNs are then tuned using a specialized distance metric between the synthetic detector events and the real detector events.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS1993

JSC Director's Discretionary Fund 1992 Annual Report

Annual report of the Johnson Space Center Director's Discretionary Fund documenting effective use of resources. The $1,694,000 funding for FY92 was distributed among 27 projects. The projects are an overall aid to the NASA mission, as well as providing development opportunities for the science and engineering staff with eventual spinoff to commercial uses. Projects described include space-based medical research such as the use of stable isotopes of deuterium and oxygen to measure crew energy use and techniques for noninvasive motion sickness medication. Recycling essentials for space crew support is conducted in the Regenerative Life Support and the Hybrid Regenerative Water Recovery test beds. Two-phase fluid flow simulated under low-gravity conditions, hypervelocity particle impact on open mesh bumpers, and microcalorimetry to measure the long-term hydrazine/material compatibility were investigated. A patent application was made on a shape-memory-alloy release nut. Computer estimate of crew accommodations for advanced concepts was demonstrated. Training techniques were evaluated using multimedia and virtual environment. Upgrades of an electronic still camera provide high resolution images from orbit are presented.

Jenkins, Lyle↗
DOE OSTI2024

Celebrating Notable Advances in Compound Semiconductors: A Tribute to Dr. Wladyslaw Walukiewicz

The Special Topic "Native Defects, Impurities and the Electronic Structure of Compound Semiconductors" is dedicated to Dr. Wladyslaw (Wladek) Walukiewicz, our esteemed colleague who passed away on November 9, 2022, at age 76. It is not often that a scientist is able to profoundly impact more than one to two scientific topics in their lifetime. Dr. Walukiewicz, a condensed matter theorist by training, arguably did that for at least four. While his scientific accomplishments tell the story of a successful career and valuable contributions, it does not convey the entire story. For the rest, one has only to look at the community of researchers he brought together across the globe. Dr. Walukiewicz conducted his work with curiosity, integrity, and respect for others that elevated those around him. Here, we pay tribute to Dr. Walukiewicz's ideas and the legacy he leaves behind.

defects↗
DOE OSTI2024

Development of message passing-based graph convolutional networks for classifying cancer pathology reports

Abstract Background Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. Results We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. Conclusions Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Automating the Analysis of Large Language Models Responses through Zero-Shot Question Answering

Recent advancements in Large Language Models (LLMs) have shown significant potential in various applications, yet their evaluation, particularly in zero-shot question answering scenarios, remains a challenging task. In this study, our objective was to explore precision metrics for Large Language Models (LLM) and design and implement a software pipeline to automatically evaluate LLMs' outputs under zero-shot question answering. Zero-shot question answering involves a model providing answers to questions about topics it hasn't seen during training. It leverages the principles of zero-shot learning by relying on semantic understanding and generalization from related knowledge. The data used was metadata from medical databases on congenital heart disease. We explored eleven LLM metrics and selected three for our evaluation: BLEU, BERTScore, and MoverScore. BLEU calculates a score based on the overlap of n-grams (contiguous sequences of n items, typically words) between the machine-generated translation and the reference translations. Higher BLEU scores indicate better correspondence between the machine-generated and human-generated translations. BERTScore is a metric used to evaluate the quality of machine-generated text by measuring the similarity of token embeddings produced by BERT (Bidirectional Encoder Representations from Transformers) between the generated text and reference text. MoverScore is a metric that quantifies the dissimilarity between the distributions of word embeddings from machine-generated text and reference text, emphasizing semantic similarity over exact token overlap. We also introduced HBKI, a composite metric summarizing these approaches. We tested five models —GPT-3, Llama-2, Gemini 1.5 Pro, Solar 10.7B, and Mixtral-8x7b. Our software pipeline, designed and implemented using Object-Oriented Programming principles, allows users to customize the selection and extraction of features for topics of interest in their own research. Our results show that MoverScore delivered the most precise evaluation of the LLM's outputs, while Mixtral-8x7b achieved the best overall performance in extracting metadata from the databases.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1984

Severe storm initiation and development from satellite infrared imagery and Rawinsonde data

The geographical distribution of potential temperatures, mixing ratio, and streamlines of flow patterns at 850, 700, and 500 mb heights are used to understand the prestorm convection and the horizontal convergence of moisture. From the analysis of 21 tornadoes the following conclusions are reached: (1) Strong horizontal convergence of moisture appeared at the 850, 700, and 500 mb levels in the area 12 hours before the storm formation; (2) An abundantly moist atmosphere below 3 km (700 mb) becomes convectively unstable during the time period between 12 and 24 hours before the initiation of the severe storms; (3) Strong winds veering with height with direction parallel to the movement of a dryline, surface fronts, etc; (4) During a 36-hour period, a tropopause height in the areas of interest is lowest at the time of tornadic cloud formation; (5) A train of gravity waves is detected before and during the cloud formation period. Rapid-scan infrared imagery provides near real-time information on the life cycle of the storm which can be summarized as follows: (1) Enhanced convection produced an overshooting cloud top penetrating above the tropopause, making the mass density of the overshooting cloud much greater than the mass density of the surrounding air; (2) The overshooting cloud top collapsed at the end of the mature stage of the cloud development; (3) The tornado touchdown followed the collapse of the overshooting cloud top.

Hung, R. J.↗
DOE OSTI2020

SuperCDMS Event Reconstruction Using Convolutional Neural Networks [Thesis]

The SuperCDMS experiment uses cryogenic silicon and germanium detectors to search for dark matter candidates such as WIMPs (Weakly Interacting Massive Particles) streaming through the Earth. Collisions in the silicon and germanium crystals are expected to produce phonons whose thermal signatures can be measured. This thesis first describes the integration of a new Signal Distribution Unit (SDU) to the SuperCDMS data acquisition system, which allows for synchronization of multiple detectors and electronic/mechanical noise characterization via accelerometer, antenna, and AC phase measurements. From SuperCDMS detector data it is necessary to reconstruct the energies of the particle events. This thesis explores the use of Convolutional Neural Networks (CNNs) to perform this reconstruction and finds that, although they perform well, changing the noise model breaks the model and requires the neural network to be retrained. In order to mitigate this issue, a new CNN model is proposed which includes the noise Power Spectral Density (PSD) of the data as an additional input to the CNN. While it proves to be effective as a denoising algorithm, it still fails for data with a different noise model. However, including data from multiple PSDs in the neural network training sample allows it to handle data with different types of noise while still maintaining the quality of the reconstruction. Nevertheless, neural networks trained even on multiple PSDs do not robustly handle data taken with PSDs dissimilar to those in the training sample, suggesting that CNNs may need to be retrained whenever the noise environment changes in a significant way.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Signal-preserving CMB component separation with machine learning

Analysis of microwave sky signals, such as the cosmic microwave background, often requires component separation using multifrequency methods, whereby different signals are isolated according to their different frequency behaviors. Many so-called blind methods, such as the internal linear combination (ILC), make minimal assumptions about the spatial distribution of the signal or contaminants, and only assume knowledge of the frequency dependence of the signal. The ILC produces a minimum-variance linear combination of the measured frequency maps. In the case of Gaussian, statistically isotropic fields, this is the optimal linear combination, as the variance is the only statistic of interest. However, in many cases the signal we wish to isolate, or the foregrounds we wish to remove, are non-Gaussian and/or statistically anisotropic (in particular for the case of Galactic foregrounds). In such cases, it is possible that machine learning (ML) techniques can be used to exploit the non-Gaussian features of the foregrounds and thereby improve component separation. However, many ML techniques require the use of complex, difficult-to-interpret operations on the data. We propose a hybrid method whereby we train an ML model using only combinations of the data that , and combine the resulting ML-predicted foreground estimate with the ILC solution to reduce the error from the ILC. We demonstrate our methods on simulations of extragalactic temperature and Galactic polarization foregrounds and show that our ML model can exploit non-Gaussian features, such as point sources and spatially varying spectral indices, to produce lower-variance maps than ILC—e.g., reducing the variance of the B-mode residual by factors of up to 5—while preserving the signal of interest in an unbiased manner. Moreover, we often find improved performance even when applying our ML technique to foreground models on which it was not trained. Published by the American Physical Society 2025

McCarthy, Fiona (ORCID:0000000253893565)↗
NASA NTRS2009

The Integrated Medical Model: A Risk Assessment and Decision Support Tool for Space Flight Medical Systems

The Integrated Medical Model (IMM) is a decision support tool that is useful to mission planners and medical system designers in assessing risks and designing medical systems for space flight missions. The IMM provides an evidence based approach for optimizing medical resources and minimizing risks within space flight operational constraints. The mathematical relationships among mission and crew profiles, medical condition incidence data, in-flight medical resources, potential crew functional impairments, and clinical end-states are established to determine probable mission outcomes. Stochastic computational methods are used to forecast probability distributions of crew health and medical resource utilization, as well as estimates of medical evacuation and loss of crew life. The IMM has been used in support of the International Space Station (ISS) medical kit redesign, the medical component of the ISS Probabilistic Risk Assessment, and the development of the Constellation Medical Conditions List. The IMM also will be used to refine medical requirements for the Constellation program. The IMM outputs for ISS and Constellation design reference missions will be presented to demonstrate the potential of the IMM in assessing risks, planning missions, and designing medical systems. The implementation of the IMM verification and validation plan will be reviewed. Additional planned capabilities of the IMM, including optimization techniques and the inclusion of a mission timeline, will be discussed. Given the space flight constraints of mass, volume, and crew medical training, the IMM is a valuable risk assessment and decision support tool for medical system design and mission planning.

Kerstman, Eric↗
DOE OSTI2022

Wavelet and Deep-Learning-Based Approach for Generation System Problematic Parameters Identification and Calibration

Accurate models of generation systems are critical for maintaining reliable and secure grid operations. In this paper, a novel and systematic approach is proposed to identify and calibrate the generation system problematic parameters using continuous wavelet transform (CWT) and advanced deep-learning technology. The phasor measurement unit (PMU) data are used through “event playback” to check whether the parameter calibration is required, and if yes, a group of suspicious parameters will be identified as the primary problematic parameter candidates (PPCs). These primary PPCs are randomly perturbed to generate the event playback simulation data, which are used by the CWT and convolutional neural networks (CNNs) to further narrow down the primary PPCs into a smaller set of candidates. Then, the identified candidates are perturbed again to generate massive event playback simulation data for training a parameter calibration neural network. Here, we designed a multi-output neural network structure to find the mappings between the perturbed parameters and the simulation data using both CNN and long short-term memory (LSTM) models. Finally, the well-trained and tested CNN-LSTM model is used to estimate the accurate value of the suspicious parameters with actual PMU measurements. The proposed CNN-LSTM network can accurately and reliably estimate the generation-system problematic parameters, and has better performance when compared to other machine-learning methods, such as the multilayer perceptron network and the conditional variational autoencoder method. The accuracy and effectiveness of the proposed approach have been validated through simulation and real-world data.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2005

Towards an A-train Aerosol Assimilation System: Assimilation of MODIS Aerosol Optical Thickness Retrievals into a Global Aerosol Transport and Radiation Model

To understand the role of atmospheric aerosols in Earth's climate system we ideally require a global, three-dimensional, and temporally continuous system of measurements. The view of aerosols provided by a single polar-orbiting satellite instrument (e.g., MODIS), while providing the greatest spatial coverage of any measurement system available, can offer only a single relevant observation per day of a particular location. Furthermore, the quantitative interpretation of those observations is subject to considerable uncertainty because of we do not know the aerosol optical properties or vertical profiles well enough. Ground-based and in situ measurements can provide missing detail about aerosol vertical and optical properties, but lack the spatial (and sometimes temporal) coverage desired. Chemical transport models treating the aerosol lifecycle complement this picture by providing three-dimensional, global, and continuous aerosol fields, but suffer from poor constraints on their initial conditions (e.g., the aerosol source, sink, and transformation mechanisms). Here we present a global, three- dimensional aerosol transport model and assimilation system. The model assimilates the MODIS aerosol optical thickness product to constrain its aerosol distributions and burdens. We provide an analysis of the model aerosol distributions as constrained by ground-based sun photometer measurements and aerosol products from other satellite measurements.

Colarco, P.↗