SEARCH · Engineering Papers

Results for “Training Analysis”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 847 records · Page 47

All sources NASA NTRS DOE OSTI

NASA NTRS2012

Estimation and Bias Correction of Aerosol Abundance using Data-driven Machine Learning and Remote Sensing

Air quality information is increasingly becoming a public health concern, since some of the aerosol particles pose harmful effects to peoples health. One widely available metric of aerosol abundance is the aerosol optical depth (AOD). The AOD is the integrated light extinction coefficient over a vertical atmospheric column of unit cross section, which represents the extent to which the aerosols in that vertical profile prevent the transmission of light by absorption or scattering. The comparison between the AOD measured from the ground-based Aerosol Robotic Network (AERONET) system and the satellite MODIS instruments at 550 nm shows that there is a bias between the two data products. We performed a comprehensive analysis exploring possible factors which may be contributing to the inter-instrumental bias between MODIS and AERONET. The analysis used several measured variables, including the MODIS AOD, as input in order to train a neural network in regression mode to predict the AERONET AOD values. This not only allowed us to obtain an estimate, but also allowed us to infer the optimal sets of variables that played an important role in the prediction. In addition, we applied machine learning to infer the global abundance of ground level PM2.5 from the AOD data and other ancillary satellite and meteorology products. This research is part of our goal to provide air quality information, which can also be useful for global epidemiology studies.

Malakar, Nabin K.↗

NASA NTRS2012

Using M and S to Improve Human Decision Making and Achieve Effective Problem Solving in an International Environment

In the international arena, decision makers are often swayed away from fact-based analysis by their own individual cultural and political bias. Modeling and Simulation-based training can raise awareness of individual predisposition and improve the quality of decision making by focusing solely on fact vice perception. This improved decision making methodology will support the multinational collaborative efforts of military and civilian leaders to solve challenges more effectively. The intent of this experimental research is to create a framework that allows decision makers to "come to the table" with the latest and most significant facts necessary to determine an appropriate solution for any given contingency.

Christie, Vanessa L.↗

NASA NTRSDate not supplied

DELTA: An Open-Source Framework to Simplify Machine Learning with Satellite Imagery

DELTA (Deep Earth Learning, Tools, and Analysis) is an open-source framework developed at NASA to simplify running and training machine learning (ML) models on satellite imagery. Users new to machine learning can run existing ML models on satellite imagery with minimal setup and configuration. For experienced ML users, DELTA helps simplify data engineering, preprocessing steps, and reduces the need for boilerplate code that needs written to make satellite imagery datasets palatable for machine learning. This lets data scientists focus on model development while DELTA handles the imagery manipulation. This presentation will demonstrate DELTA’s functionality and share some examples from an active project using it for flood mapping using imagery from multiple satellite sources

Michael von Pohle↗

NASA NTRSDate not supplied

DELTA: An Open-Source Framework to Simplify Machine Learning with Satellite Imagery

deep learning↗

NASA NTRSDate not supplied

GT2024-128885: Flow Reconstruction in a Transonic Turbine Cascade using Physics-Informed Neural Networks (PINNs)

This presentation investigates the application of Physics-Informed Neural Networks (PINNs) for the analysis of turbine blades in a transonic cascade. PINNs are a machine learning method trained on losses calculated from reconstructed governing equations, assigned boundary/initial conditions, and measured data. We reconstruct the 2-D flow field in a transonic turbine cascade in two ways: the traditional forward approach (without training/experimental data) and by training the PINN using experimental data. We then compare the PINN solutions to measured data. This is repeated for three different turbine blades with distinct loading characteristics. The experimental data used for training is the static pressure measurements along the suction and pressure sides of each blade. The PINN is trained utilizing all available data, half the available data, data from only the leading edge region, and data from only the trailing edge region. It's shown that the PINN can reconstruct the flow field in all cases with acceptable errors. Cases where the PINN is trained on all the data, and even half the data, resulted in the lowest errors. The exit Mach number is inferred for each case and compared to the experimentally calculated value.

Machine Learning↗

NASA NTRSDate not supplied

Exploring the Capabilities of a Machine Learning Algorithm to Detect Space Weather-Significant Emerging Active Regions

Active regions are a source of various phenomena responsible for Space Weather disturbances; therefore, developing a technology for early warning about upcoming magnetic activity is crucial to mitigate its impact. However, observational limitations and the high nonlinearity of processes associated with the accumulation of magnetic flux and its interaction with the surrounding plasma during the emergence through the convection zone make early activity detection a challenging problem. To address these challenges, we developed a physics-driven machine learning model that allows us to detect active regions (ARs) before they become visible on the solar surface by analyzing the power spectra of acoustic oscillations observed by the SDO/HMI instrument. This study is based on a time series of Doppler shift maps of 31x31-degree areas tracked with the Carrington rotation rate for four days before and after the emergence. The Doppler shift time series are processed into the oscillation power maps for four frequency ranges and accompanied by line-of-sight magnetograms and the continuum intensity maps from SDO/HMI. The resulting data are converted into a 1D time series representing the mean temporal variations of these quantities. The redacted time series are used as input to predict AR emergence using the Long Short Term Memory (LSTM) method. The training of the LSTM model is based on 40 ARs, which includes an independent analysis for each sub region that exhibits AR emergence or remains quiet. The emergence of magnetic flux (defined as a decrease of the continuum intensity) was detected with the developed LSTM algorithm from 5 to 48 hours before the reported time by NOAA. The developed model is capable of pointing to the time and location of active region formation. In this presentation, we discuss reasons that impact how early in advance the model can identify the upcoming activity and the possibility of improving the current predictive skills and steps to transition to the operational forecast.

Heliophysics↗

DOE OSTI2024

Geometry-aware training of factorized layers in tensor Tucker format

Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during train and inference of large networks. Given its easy implementation and flexibility, one promising approach is layer factorization, which reshapes weight tensors into a matrix format and parameterizes it as the product of two rank-r matrices. However, this family of approaches often requires an initial full-model warm-up phase, prior knowledge of a feasible rank, and it is sensitive to parameter initialization.In this work, we introduce a novel approach to train the factors of a Tucker decomposition of the weight tensors. Our training proposal proves to be optimal in locally approximating the original unfactorized dynamics and stable for the initialization. Furthermore, the rank of each mode is dynamically updated during training.We provide a theoretical analysis of the algorithm, showing convergence, approximation and local descent guarantees. The method's performance is further illustrated through a variety of experiments, showing remarkable training compression rates and comparable or even better performance than the full baseline and alternative layer factorization strategies.

Zangrando, Emanuele [Gran Sasso Science Institute ↗

NASA NTRS2006

Probabilistic Classification Using Elemental Abundance Distributions and Lossless Image Compression in Apollo 17 Lunar Dust Samples from Mare Serenitatis

We have previously outlined a strategy for the detection of fossils [Storrie-Lombardi and Hoover, 2004] and extant microbial life [Storrie-Lombaudi and Hoover, 20051 during robotic missions to Mars using co-registered structural and chemical signatures. Data inputs included image lossless compression indices to estimate relative textural complexity and elemental abundance distributions. Two exploratory classification algorithms (principal component analysis and hierarchical cluster analysis) provide an initial tentative classification of all targets. Nonlinear stochastic neural networks are then trained to produce a Bayesian estimate of algorithm classification accuracy. The strategy previously has been successful in distinguishing regions of biotic and abiotic alteration of basalt glass from unaltered samples. [Storrie-Lombardi and Fisk, 2004; Storrie-Lombardi and Fisk, 2004] Such investigations of abiotic versus biotic alteration of terrestrial mineralogy on Earth are compromised by .the difficulty finding mineralogy completely unaffected by the ubiquitous presence of microbial life on the planet. The renewed interest in lunar exploration offers an opportunity to investigate geological materials that may exhibit signs of aqueous alteration, but are highly unlikely to contain contaminating biological weathering signatures. We here present an extension of our earlier data set to include lunar dust samples obtained during the Apollo 17 mission. Apollo 17 landed in the Taurus-Littrow Valley in Mare Serenitatis. Most of the rock samples from this region of the lunar highlands are basalts comprised primarily of plagioclase and pyroxene and selected examples of orange and black volcanic glass. SEM images and elemental abundances (C6, N7, O8, Na11, Mg12, Al13, Si14, P15, S16, Cll7, K19, Ca20, Fe26) for a series of targets in the lunar dust samples are compared to the extant cyanobacteria, fossil trilobites, Orgueil meteorite, and terrestrial basalt targets previously discussed. The data set provides a first step in producing a quantitative probabilistic methodology for geobiological analysis of returned lunar samples or in situ exploration.

Storrie-Lombardi, Michael C.↗

DOE OSTI2020

Construction of a Code Verification Matrix for Heat Conduction With Finite Element Code Applications

When establishing the pedigree of a simulation tool, code verification is used to ensure that the implemented numerical algorithm is a faithful representation of its underlying mathematical model. During this process, numerical results on various meshes are systematically compared to a reference analytic solution. The selection of analytic solutions can be a laborious process, as it is difficult to establish adequate code confidence without performing redundant work. In this report we address this issue by applying a physics-based process that establishes a set of reference problems. In this process, code simulation options are categorized and systematically tested, which ensures that gaps in testing are easily identified and addressed. The resulting problems are primarily intended for code verification analysis but may also be useful for comparison to other simulation codes, troubleshooting activities, or training exercises. The process is used to select fifteen code verification problems relevant for the one-dimensional steady-state heat conduction equation. These problems are applicable to a wide variety of simulation tools, but, in this work, a demonstration is performed using the finite element-based nuclear fuel performance code BISON. Convergence to the analytic solution at the theoretical rate is quantified for a selection of the problems, which establishes a baseline pedigree for the code. Not only can this standard set of conduction solutions be used for verification of other codes, but also the physics-based process for selecting problems can be utilized to quantify and expand testing for any simulation tool.

42 ENGINEERING↗

DOE OSTI2025

The Profiled Feldman-Cousins Method for Confidence Interval Construction for the Nova 3-Flavor Oscillation Analysis

The small interaction cross-section of neutrinos makes experimental neutrino physics particularly responsive to technological advancements. A significant development leveraged by the NOvA experiment is large-scale parallel processing, enabling novel computational approaches to longstanding experimental challenges. Central to managing the resulting high-throughput data is NOvA’s implementation of the Freight Train model, designed for efficient data production and handling.This dissertation details the methodology and execution of the NOvA 2024 3-Flavor Oscillation Analysis, supported by a comprehensive dataset spanning ten years. It emphasizes frequentist results refined through the Feldman-Cousins (FC) technique, specifically addressing confidence interval corrections in parameter estimation. The computational intensity associated with Feldman-Cousins arises from extensive Monte Carlo simulations, which were substantially mitigated through parallel computing on the Perlmutter supercomputer at the National Energy Research Scientific Computing Center (NERSC), employing the MPI framework.To further enhance computational efficiency, an Importance Sampling method is introduced and evaluated, demonstrating significant potential to reduce complexity, particularly in exploring extreme parameter space regions. This thesis presents both the successful application of advanced computational resources and the development of sophisticated statistical techniques, aiming to enhance the precision and scope of neutrino oscillation analyses.

Dye ajdye11190@gmail.com, Andrew Joseph [Mississip↗

DOE OSTI2021

Early Battery Performance Prediction for Mixed Use Charging Profiles Using Hierarchal Machine Learning

A key step limiting how fast batteries can be deployed is the time necessary to provide evaluation and validation of performance. Using data analysis approaches, such as machine learning, the validation process can be accelerated. However, questions on the validity of projecting models trained on limited data or simple cycling profiles, such as constant current cycling, to real-world scenarios with complex loads remains. Here, we present the ability to predict performance with less than 1.2% mean absolute percent error when trained on cells aged using complex electric vehicle discharge profiles, and either AC Level 2 charge or DC Fast charge profiles, using only the first 45 cycles, namely 5% of the total testing time. While error is low across the projections, this study also highlights that battery lifetime analysis using only cycling data may not extrapolate safely to certain real-world conditions due to the impact of calendar degradation.

25 ENERGY STORAGE↗

NASA NTRS1986

The use of multidate multichannel radiance data in urban feature analysis

Two images were obtained from thematic mappers on Landsats 4 and 5 over the Washington, DC area during November 1982 and March 1984. Selected training areas containing different types of urban land use were examined,one area consisting entirely of forest. Mean digital radiance values for each bandpass in each image were examined, and variances, standard deviations, and covariances between bandpasses were calculated. It has been found that two bandpasses caused forested areas to stand out from other land use types, especially for the November 1982 image. In order to evaluate quantitatively the possible utility of the principal components analysis in selected feature extraction, the eigenvectors were evaluated for principal axes rotations which rendered each selected land use type most separable from all other land use types. The evaluated eigenvectors were plotted as a function of land use type, whose order was decided by considering anticipated shadow component and by examining the relative loadings indicative of vegetation for each of the principal components for the different features considered. The analysis was performed for each seven-band image separately and for the two combined images. It was found that by combining the two images, more dramatic land use type separation could be obtained.

Duggin, M. J.↗

NASA NTRS1992

Prediction of space sickness in astronauts from preflight fluid, electrolyte, and cardiovascular variables and Weightless Environmental Training Facility (WETF) training

Nine preflight variables related to fluid, electrolyte, and cardiovascular status from 64 first-time Shuttle crewmembers were differentially weighted by discrimination analysis to predict the incidence and severity of each crewmember's space sickness as rated by NASA flight surgeons. The nine variables are serum uric acid, red cell count, environmental temperature at the launch site, serum phosphate, urine osmolality, serum thyroxine, sitting systolic blood pressure, calculated blood volume, and serum chloride. Using two methods of cross-validation on the original samples (jackknife and a stratefied random subsample), these variables enable the prediction of space sickness incidence (NONE or SICK) with 80 percent sickness and space severity (NONE, MILD, MODERATE, of SEVERE) with 59 percent success by one method of cross-validation and 67 percent by another method. Addition of a tenth variable, hours spent in the Weightlessness Environment Training Facility (WETF) did not improve the prediction of space sickness incidences but did improve the prediction of space sickness severity to 66 percent success by the first method of cross-validation of original samples and to 71 percent by the second method. Results to date suggest the presence of predisposing physiologic factors to space sickness that implicate fluid shift etiology. The data also suggest that prior exposure to fluid shift during WETF training may produce some circulatory pre-adaption to fluid shifts in weightlessness that results in a reduction of space sickness severity.

Simanonok, K.↗

DOE OSTI2025

2025 TEM Workshop

The TEM Data Management Workshop will take place on August 26 from 9 a.m. to 12 p.m. MT, and will be held virtually on TEAMS. The primary goal of this workshop is to engage NSUF users and stakeholders in discussions about the data needs for the utilization of AI and ML in the analysis of TEM data. Key topics to be covered include data storage, data sharing, data tagging, metadata inclusion, standardized data formats, data augmentation, and annotated training datasets. Additionally, the workshop will provide valuable insights into resources such as the Nuclear Research Data System (NRDS) for data storage and sharing, as well as open-source codes for data analysis.

Bachhav, Mukesh↗

DOE OSTI2022

Identification and assignment of rotational spectra using artificial neural networks

A method of identifying molecular parameters may include receiving observed transition frequencies, generating transition frequency sets and a spectral parameter sets, training one or more artificial neural networks by analyzing the transition frequency sets and the spectral parameter sets, analyzing the observed transition frequencies using the one or more trained artificial neural networks to predict estimated spectral parameters, and identifying molecular parameters by analyzing the estimated spectral parameters. A molecular parameter identification system may include a rotational spectrometer, a user interface, and a spectrum analysis application that may retrieve observed transition frequencies, identify a Hamiltonian type by a neural network analyzing the observed transition frequencies, select a second trained artificial neural network based on the identified Hamiltonian type, analyze observed transition frequencies using the second artificial neural network to identify estimated spectral parameters, and identify molecular parameters.

Prozuments, Kirills↗

DOE OSTI2022

Use of Machine Learning on PMU Data for Transmission System Fault Analysis

Synchrophasor technology has been used for monitoring, control, and protection of bulk power system for over 10 years. Deployment of phasor measurement units (PMUs) in the USA power system has surpassed 3000 units installed in the transmission substations as stand-alone intelligent electronic devices (IEDs) or as a software add-on to other devices such as digital protective relays (DPRs) or digital fault recorders (DFRs). By now, thousands of terabytes of PMU data may have been captured and stored by various transmission system operators (TSOs) and independent system operators (ISOs). This creates an opportunity to deploy advanced machine learning (ML) techniques to detect and classify faults recorded by PMUs automatically to be used by the system operators for rapid, critical decision-making when manual analysis of the past or unfolding events is not feasible. In this paper we offer a brief background on how the automated fault analysis may be done using DPR and/or DFR data, and compare some of the legacy approaches to the new ML approaches in the context of the system-wide PMU recordings. We then offer insights from developing practical ML solutions that have been applied on field recordings captured by close to 450 PMUs from all three US interconnections (Western, Eastern and ERCOT) over two years (2016-2017). We identify and illustrate ML challenges we addressed: inaccurate data, data with scarce and temporally imprecise fault labels, data recorded by PMUs sparsely located at substations resulting in the fault records taken afar from the ends of the faulted lines, data containing only positive sequence values, and data taken at different voltage levels. We then illustrate the ML model results for fault analysis under different application scenarios. The novelty of this study is not only in the design, implementation, and performance analysis of the ML algorithms, but also in the use of advanced fault modelling and simulation approaches to improve the training results when developing supervised ML models for fault detection and classification. Extensive simulations of faults were conducted on a 14-bus power system to create a training dataset with over 1400 accurately labelled faults. This dataset was applied to enhance the accuracy of fault detection and classification of machine learning-based models trained with small number of labelled faults in large datasets recorded in the grid interconnections ranging from 5,000 to 70,000 buses.

Synchrophasors, Machine Learning, Fault Analysis, ↗

DOE OSTI2024

Evaluation of the Radioactive Material Release in the Harborview Research and Training Building and Implications for Emergency Response

On May 2, 2019, during the 137 Cs source recovery operation, a source capsule in a research irradiator containing approximately 77.1 TBq was breached. Based on a geometric reconstruction analysis of the damage to the capsule, approximately 46.3 GBq (0.04%) was impacted by the chop saw (grinder) inside a Mobile Hot Cell (MHC) on the loading dock at the University of Washington Harborview Research and Training (HRT) Building. A very small fraction of the material impacted, less than 1%) was released from the Mobile Hot Cell and then to the rest of the HRT Building. The objectives of this project were to assess the accidental release of 137 CsCl and its implications related to emergency response methods and the ramifications of 137 CsCl transport. The phenomenology of this event was also compared with past alkali halide dispersal events. The vast number of measurements and samples collected by the remediation contractors, the Department of Energy's Nuclear Emergency Support Team, and the small number of retrospective samples collected by the authors informed the analysis. The techniques included (1) autoradiography and electron microscopy of samples collected from the HRT Building and the irradiator, (2) 3D visualization of deposition on surfaces and within the ventilation system, and (3) a study of the damage to the source capsule to evaluate the Cs particle size and particle composition due to the grinding accident. Subsequently, the cesium contaminant transport through the numerous pathways in the building was reconstructed to assess the deposition on surfaces as a function of particle size. The implications for emergency response are relevant to data quality and management. A Data Quality Objective (DQO) guides data collection methods so that they have appropriate accuracy and precision for the intended application. Recommendations were made with respect to the sample collection protocols and sample archival.

61 RADIATION PROTECTION AND DOSIMETRY↗

DOE OSTI2022

CONGO²: Scalable Online Anomaly Detection and Localization in Power Electronics Networks

Rapid and accurate detection and localization of electronic disturbances simultaneously are important for preventing its potential damages and determining potential remedies. Existing anomaly detection methods are severely limited by the low accuracy, the expensive computational cost and the need for highly trained personnel. There is an urgent need for a scalable online algorithm for in-field analysis of large-scale power electronics networks. Here in this paper, we propose a fast and accurate algorithm for anomaly detection and localization of power electronics networks: stratified colored-node graph (CONGO2). This algorithm hierarchically models the change of correlated waveforms and then correlated sensors using the colored-node graph. By aggregating the change of each sensor with its neighbors’ inputs, we can spontaneously identify and localize the anomaly that cannot be detected by data collected from a single sensor. As our proposed method only focuses on the changes within a short time frame, it is highly computational efficient and only needs small data storage. Thus, our method is ideal for online and reliable anomaly detection and localization of large-scale power electronic networks. Compared to existing anomaly detection methods, our method is entirely data-driven without training data, highly accurate and reliable for wide-spectrum anomalies detection, and more importantly, capable of both detection and localization. Thus, it is ideal for infield deployment for large-scale power electronic networks. As illustrated by a distributed energy resources (DERs) power grid with 37-node, our method can effectively detect and localize various cyber and physical attacks.

42 ENGINEERING↗