Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data classification”

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 1,729 records · Page 96
All sourcesNASA NTRSDOE OSTI
NASA NTRS1982

Optimization of a Non-traditional Unsupervised Classification Approach for Land Cover Analysis

The conditions under which a hybrid of clustering and canonical analysis for image classification produce optimum results were analyzed. The approach involves generation of classes by clustering for input to canonical analysis. The importance of the number of clusters input and the effect of other parameters of the clustering algorithm (ISOCLS) were examined. The approach derives its final result by clustering the canonically transformed data. Therefore the importance of number of clusters requested in this final stage was also examined. The effect of these variables were studied in terms of the average separability (as measured by transformed divergence) of the final clusters, the transformation matrices resulting from different numbers of input classes, and the accuracy of the final classifications. The research was performed with LANDSAT MSS data over the Hazleton/Berwick Pennsylvania area. Final classifications were compared pixel by pixel with an existing geographic information system to provide an indication of their accuracy.

Boyd, R. K.↗
NASA NTRS1981

Land use project (comparison of LANDSAT with aircraft-derived land cover data for a proposed highway project)

The Maryland Automated Geographic Information System is described as well as the development of a general land cover classification with level 2 separation for vegetation categories for a 95,000-acre study area in Howard and Anne Arundel Counties. An accuracy analysis was performed on two subsections of the entire study area. The 1:24,000 scale land use map and the high in altitude infrared photography were determined to the best source of ground truth for the analysis. Results show that (1) delineation of deciduous and coniferous forested areas from LANDSAT data compared well with results from infrared photography; (2) general classification of agricultural areas showed acceptable results; (3) delineation of residential areas had the highest error rates (difference in interpretation and cover type assignment methods was a primary factor); and (4) LANDSAT-derived land cover data is to be used as an ancillary data source in a Maryland statewide land cover inventory.

Rugoski, T.↗
DOE OSTI2024

RECON Label Quality Report

The final quality of any AI/ML system is directly related to the quality of the input data used to train the system. In this case, we are trying to build a reliable image classifier that can correctly identify electrical components in x-ray images. The classification confidence is directly related to the quality of the labels in the training data, which are used in developing the AI/ML classifier. Incorrect or incomplete labels can substantially hinder the performance of the system during the training process, as it tries to compensate for variations that should not exist. Image labels are entered by subject matter experts, and in general can be assumed to be correct. However, this is not a guarantee, so developing ways to measure label quality and help identify or reject bad labels is important, especially as the database continues to grow. Given the current size of the database, a full manual review of each component is not feasible. This report will highlight the current state of the “RECON” x-ray image database and summarize several recent developments to try to help ensure high quality labeling both now and in the future. Questions that we hope to answer with this development include: 1) Are there any components with incorrect labels? 2) Can we suggest labels for components that are marked “Unknown”? 3) What kind of overall confidence do we have in the quality of the existing labels? 4) What systems or procedures can we put in place to maximize label quality?

42 ENGINEERING↗
DOE OSTI2026

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

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

Chemical vapor deposition↗
DOE OSTI2021

Autonomous Sensor System for Wind Turbine Blade Collision Detection

This paper presents an automated blade collision detection system for use on wind turbines, toward the goal of supporting monitoring and quantitative assessment of wind energy impacts on wildlife. A wireless, multisensor module mounted at the blade root measures surface vibrations, and a blade-mounted camera provides image capture of colliding objects. Using sensor data recorded during field testing of the system on an operational wind turbine, we present the development, training, and testing of automated detection algorithms for collision detection using machine-learning approaches. In particular, we compare the use of a new two-step, anomaly-based classification algorithm with conventional adaptive boosting and amplitude-based detection techniques, where the two-step approach improves average precision for the experimental data set. This integrated sensor and classification systems demonstrates a new approach for automated, on-blade collision detection for wind turbines, with broad utility across structural health monitoring applications.

17 WIND ENERGY↗
NASA NTRS2012

An Automated Algorithm to Screen Massive Training Samples for a Global Impervious Surface Classification

An algorithm is developed to automatically screen the outliers from massive training samples for Global Land Survey - Imperviousness Mapping Project (GLS-IMP). GLS-IMP is to produce a global 30 m spatial resolution impervious cover data set for years 2000 and 2010 based on the Landsat Global Land Survey (GLS) data set. This unprecedented high resolution impervious cover data set is not only significant to the urbanization studies but also desired by the global carbon, hydrology, and energy balance researches. A supervised classification method, regression tree, is applied in this project. A set of accurate training samples is the key to the supervised classifications. Here we developed the global scale training samples from 1 m or so resolution fine resolution satellite data (Quickbird and Worldview2), and then aggregate the fine resolution impervious cover map to 30 m resolution. In order to improve the classification accuracy, the training samples should be screened before used to train the regression tree. It is impossible to manually screen 30 m resolution training samples collected globally. For example, in Europe only, there are 174 training sites. The size of the sites ranges from 4.5 km by 4.5 km to 8.1 km by 3.6 km. The amount training samples are over six millions. Therefore, we develop this automated statistic based algorithm to screen the training samples in two levels: site and scene level. At the site level, all the training samples are divided to 10 groups according to the percentage of the impervious surface within a sample pixel. The samples following in each 10% forms one group. For each group, both univariate and multivariate outliers are detected and removed. Then the screen process escalates to the scene level. A similar screen process but with a looser threshold is applied on the scene level considering the possible variance due to the site difference. We do not perform the screen process across the scenes because the scenes might vary due to the phenology, solar-view geometry, and atmospheric condition etc. factors but not actual landcover difference. Finally, we will compare the classification results from screened and unscreened training samples to assess the improvement achieved by cleaning up the training samples. Keywords:

Tan, Bin↗
NASA NTRS1996

Global Single and Multiple Cloud Classification with a Fuzzy Logic Expert System

An unresolved problem in remote sensing concerns the analysis of satellite imagery containing both single and multiple cloud layers. While cloud parameterizations are very important both in global climate models and in studies of the Earth's radiation budget, most cloud retrieval schemes, such as the bispectral method used by the International Satellite Cloud Climatology Project (ISCCP), have no way of determining whether overlapping cloud layers exist in any group of satellite pixels. Coakley (1983) used a spatial coherence method to determine whether a region contained more than one cloud layer. Baum et al. (1995) developed a scheme for detection and analysis of daytime multiple cloud layers using merged AVHRR (Advanced Very High Resolution Radiometer) and HIRS (High-resolution Infrared Radiometer Sounder) data collected during the First ISCCP Regional Experiment (FIRE) Cirrus 2 field campaign. Baum et al. (1995) explored the use of a cloud classification technique based on AVHRR data. This study examines the feasibility of applying the cloud classifier to global satellite imagery.

Welch, Ronald M.↗
DOE OSTI2025

Long-term measurements of ice nucleating particles at Atmospheric Radiation Measurement (ARM) sites worldwide

Ice nucleating particles (INPs) play a critical role in cloud microphysics and precipitation formation, yet long-term, spatially extensive observational datasets remain limited. Here, we present one of the most comprehensive publicly available datasets of immersion-mode INP concentrations using a single analytical method, generated through the U.S. Department of Energy's (DOE) Atmospheric Radiation Measurement (ARM) user facility. INP filter samples have been collected across a broad range of environments – including agricultural plains, Arctic coastlines, high-elevation mountain sites, marine regions, and urban areas – via fixed observatories, mobile facility deployments, and vertically-resolved tethered balloon system operations. We describe the standardized processing and quality assurance pipeline, from filter collection and processing using the Ice Nucleation Spectrometer to final data products archived on the ARM Data Discovery portal. The dataset includes both total INP concentrations and selectively treated samples, allowing for classification of biological, organic, and inorganic INP types. It features a continuous 5-year record of INP measurements from a central U.S. site, with data collection still ongoing. Seasonal and site-specific differences in INP concentrations are illustrated through intercomparisons at −10 and −20 °C, revealing distinct regional sources and atmospheric drivers. We also outline mechanisms for researchers to access existing data, request additional sample analyses, and propose future field campaigns involving ARM INP measurements. This dataset supports a wide range of scientific applications, from observational and mechanistic studies to model development, and provides critical constraints on aerosol-cloud interactions across diverse atmospheric regimes (Creamean et al., 2024, 2020b; https://doi.org/10.5439/1770816).

Creamean, Jessie M. [Colorado State Univ., Fort Co↗
NASA NTRS2019

Satellite-Based Assessment of Grassland Conversion and Related Fire Disturbance in the Kenai Peninsula, Alaska

Spruce beetle-induced (Dendroctonus rufipennis (Kirby)) mortality on the Kenai Peninsula has heightened local wildfire risk as canopy loss facilitates the conversion from bare to fire-prone grassland. We collected images from NASA satellite-based Earth observations to visualize land cover succession at roughly five-year intervals following a severe, mid-1990's beetle infestation to the present. We classified these data by vegetation cover type to quantify grassland encroachment patterns over time. Raster band math provided a change detection analysis on the land cover classifications. Results indicate the highest wildfire risk is linked to herbaceous and black spruce land cover types, The resulting land cover change image will give the Kenai National Wildlife Refuge (KENWR) ecologists a better understanding of where forests have converted to grassland since the 1990s. These classifications provided a foundation for us to integrate digital elevation models (DEMs), temperature, and historical fire data into a model using Python for assessing and mapping changes in wildfire risk. Spatial representations of this risk will contribute to a better understanding of ecological trajectories of beetle-affected landscapes, thereby informing management decisions at KENWR.

Risk modeling↗
DOE OSTI2020

Feature‐shared adaptive‐boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images

Purpose In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of subsolid pulmonary nodules. These nodules can be classified as atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). The automatic determination of a nodule's invasiveness based on chest CT scans can guide treatment planning. However, it is challenging, owing to the insufficiency of training data and their interclass similarity and intraclass variation. To address these challenges, we propose a two‐stage deep learning strategy for this task: prior‐feature learning followed by adaptive‐boost deep learning. Methods The adaptive‐boost deep learning is proposed to train a strong classifier for invasiveness classification of subsolid nodules in chest CT images, using multiple 3D convolutional neural network (CNN)‐based weak classifiers. Because ensembles of multiple deep 3D CNN models have a huge number of parameters and require large computing resources along with more training and testing time, the prior‐feature learning is proposed to reduce the computations by sharing the CNN layers between all weak classifiers. Using this strategy, all weak classifiers can be integrated into a single network. Results Tenfold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 noninvasive (AAH and AIS) and 592 invasive nodules (MIA and IAC). Ablation experimental results indicated that the proposed binary classifier achieved an accuracy of with an AUC of 81.3 . These results are superior compared to those achieved by three experienced chest imaging specialists who achieved an accuracy of , , and , respectively. About 200 additional nodules were also collected. These nodules covered 50 cases for each category (AAH, AIS, MIA, and IAC, respectively). Both binary and multiple classifications were performed on these data and the results demonstrated that the proposed method definitely achieves better performance than the performance achieved by nonensemble deep learning methods. Conclusions It can be concluded that the proposed adaptive‐boost deep learning can significantly improve the performance of invasiveness classification of pulmonary subsolid nodules in CT images, while the prior‐feature learning can significantly reduce the total size of deep models. The promising results on clinical data show that the trained models can be used as an effective lung cancer screening tool in hospitals. Moreover, the proposed strategy can be easily extended to other similar classification tasks in 3D medical images.

Wang, Jun↗
NASA NTRS1977

Three approaches to the classification of inland wetlands

In the Dismal Swamp project, seasonal, color-infrared aerial photographs and LANDSAT digital data were interpreted for a detailed analysis of the vegetative communities in a large, highly altered wetland. In Western Tennessee, seasonal high altitude color-infrared aerial photographs provided the hydrologic and vegetative information needed to map inland wetlands, using a classification system developed for the Tennessee Valley Region. In Florida, color-infrared aerial photographs were analyzed to produce wetland maps using three existing classification systems to evaluate the information content and mappability of each system. The methods used in each of the three projects can be extended or modified for use in the mapping of inland wetlands in other parts of the United States.

Gammon, P. T.↗
NASA NTRS1984

Microwave and optical remote sensing of forest vegetation

The objectives and anticipated results of a study to define the strengths and limitations of microwave (SIR-B) and optical (thematic Mapper) data, singly and in combination, for the purpose of characterizing forest cover types and condition classes are described. Other specific objectives include: (1) the assessment of the effectiveness of a contextual classification algorithm (SECHO); (2) evaluation of the utility of different look angles of SAR data in determining differences in stand density of commercial forests; and (3) the determination of the effectiveness of the L-band HH polarized SIR-B data in differentiating forest-stand densities.

Hoffer, R. M.↗
NASA NTRS2005

The Optimization of Trained and Untrained Image Classification Algorithms for Use on Large Spatial Datasets

The HARVIST project seeks to automatically provide an accurate, interactive interface to predict crop yield over the entire United States. In order to accomplish this goal, large images must be quickly and automatically classified by crop type. Current trained and untrained classification algorithms, while accurate, are highly inefficient when operating on large datasets. This project sought to develop new variants of two standard trained and untrained classification algorithms that are optimized to take advantage of the spatial nature of image data. The first algorithm, harvist-cluster, utilizes divide-and-conquer techniques to precluster an image in the hopes of increasing overall clustering speed. The second algorithm, harvistSVM, utilizes support vector machines (SVMs), a type of trained classifier. It seeks to increase classification speed by applying a "meta-SVM" to a quick (but inaccurate) SVM to approximate a slower, yet more accurate, SVM. Speedups were achieved by tuning the algorithm to quickly identify when the quick SVM was incorrect, and then reclassifying low-confidence pixels as necessary. Comparing the classification speeds of both algorithms to known baselines showed a slight speedup for large values of k (the number of clusters) for harvist-cluster, and a significant speedup for harvistSVM. Future work aims to automate the parameter tuning process required for harvistSVM, and further improve classification accuracy and speed. Additionally, this research will move documents created in Canvas into ArcGIS. The launch of the Mars Reconnaissance Orbiter (MRO) will provide a wealth of image data such as global maps of Martian weather and high resolution global images of Mars. The ability to store this new data in a georeferenced format will support future Mars missions by providing data for landing site selection and the search for water on Mars.

Kocurek, Michael J.↗
DOE OSTI2020

ASCENDS: Advanced data SCiENce toolkit for Non-Data Scientists

Recently, advances in machine learning and artificial intelligence have been playing more and more critical roles in a wide range of areas. For the last several years, industries have shown that how learning from data, identifying patterns and making decisions with minimal human intervention can be extremely useful to their business (e.g., image classification, recommending a product to a customer, finding friends in a social network, predicting customers actions, etc.). These success stories have been motivating scientists who study physics, chemistry, materials, medicine, and many other subjects, to explore a new pathway of utilizing machine learning techniques like regression and classification for their scientific activities. However, most existing machine learning tools, systems, and methodologies have been developed for programming experts but not for scientists (or any users) who have no or little knowledge of programming. ASCENDS is a toolkit that is developed to assist scientists (or any persons) who want to use their data for machine learning tasks, more specifically, correlation analysis, regression, and classification. ASCENDS does not require programming skills. Instead, it provides a set of simple but powerful CLI (Command Line Interface) and GUI (Graphic User Interface) tools for non-data scientists to be able to intuitively perform advanced data analysis and machine learning techniques. ASCENDS has been implemented by wrapping around opensource software including Keras, TensorFlow, and scikit-learn.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1975

Geological mapping in northwestern Saudi Arabia using LANDSAT multispectral techniques

Various computer enhancement and data extraction systems using LANDSAT data were assessed and used to complement a continuing geologic mapping program. Interactive digital classification techniques using both the maximum-likelihood and thresholding statistical approaches achieve very limited success in areas of highly dissected terrain. Computer enhanced imagery developed by color compositing stretched MSS ratio data was constructed for a test site in northwestern Saudi Arabia. Initial results indicate that several igneous and sedimentary rock-types can be discriminated.

Blodget, H. W.↗
NASA NTRS1977

Remote sensing data processing - Two years ago, today, and two years from today

Certain technical problems arising in the recent past (1975) in the field of the processing of remote sensing data are reviewed including approaches to the analysis of Landsat MSS data and technical difficulties which must be overcome to achieve operational data processing. The current status of remote sensing data processing is then examined with emphasis on such current technical issues as training selection and labeling, sampling schemes and classification and mensuration. Hardware projections are made for the near future (1979) relative to the development of remote sensing data processing.

Holmes, Q. A.↗
NASA NTRS1965

Ground testing at MSFC

The large-scale field collection of acoustic data and their analysis are described in this review. The entire sound-field program has the purpose of solving complex problems of excessive noise propagation associated with the static test firing of large space-booster powerplants. The site of data collection has been Mississippi Test Facility (MTF), where far-field sound-propagation and correlated meteorological measurements were initiated in 1962. The statistical evaluation of sound-measurement data shows that the polar distribution of sound in the springtime (at MTF) is determined mainly by the temperature field of the atmosphere. Greater deformation of sound-intensity polar distribution occurs in the autumn as a result of the influence of the wind field. The data on sound attenuation as a function of distance from its source revealed attenuation in excess of the expected magnitude. The excess was mainly between 1 and 10 kilometers from the source, with maximum attenuation (17 to 18 decibels) near 6 kilometers. Excess sound attenuation was compared with calculated sound dispersion. For all sound frequencies in all seasons the deviation between reference and empirical attenuation values formed a bell-shaped distribution on a semilogarithmic plot. The physical causes for the sound- attenuation behavior are considered to be atmospheric diffraction and scattering effects. Statistical analysis of sod-intensity extremes indicated amplification of the sound signals by focusing which could be expected along selected azimuths. Empirical amplification values showed the maximum occurring in winter (50 decibels at 22 kilometers). For the analysis of correlation between empirical sound data and local atmospheric sound- propagation conditions, #e concept of analytical classification of sound-velocity profiles has been developed. Examination of over a quarter-million individual sound-velocity profiles indicates that 33 profile types for heights up to 3 kilometers constitute the empirical possibilities of sound-propagation conditions in southeastern United States. Since the focusing qualities of each sound- velocity profile can be determined as a class characteristic, the overall probabilities of focusing occurrence can he obtained. The severity of focusing, as based upon lateral spread of focusing areas, has been determined. The data for MTF indicate focusing is most severe in winter, with the direction toward east being most affected. Sound propagation is a fluctuating phenomenon because atmospheric conditions vary continuously. A measuring system for analyzing the nonstationary sound-propagation phenomena has been established. The analysis of the acoustic fluctuation data is sup- posed to provide "dynamic” perturbation functions of sound, which are to be superimposed on the related characteristic sound-velocity-profile type. The ultimate result of the program will be the establishment of reliable contingency tables showing the relationship between atmospheric parameters and far-field sound intensities. These data will be the basis for more accurate sound-propagation forecasting for static firing tests.

STATIC TESTING↗
NASA NTRS2019

A Global Climatology of Extratropical Transition Part II: Statistical Performance of the Cyclone Phase Space

This study analyzes the differences between an objective, automated identification of tropical cyclones (TCs) that undergo extratropical transition (ET), and the designation of ET determined subjectively by human forecasters in best-track data in all basins globally. The objective identification of ET is based on the cyclone phase space (CPS), calculated from the Japanese 55-year Reanalysis (JRA-55) or the ECMWF Interim Reanalysis (ERA-Interim). The resulting classification into “ET storms” and “non-ET storms” underlies the global climatology of ET presented in Part I of this study. Here, the authors investigate how well the CPS classifications agree with those in the best-track records calculated from JRA-55 or from ERA-Interim data. According to F1 scores and Matthews correlation coefficients (MCCs), the classification of ET storms in the CPS agrees best with the best-track classification in the Western North Pacific (MCC > 0.7) and the North Atlantic (MCC > 0.5). In other basins, the correlation between the CPS classification and the best-track classification is only slightly higher than that of a random classification. The JRA-55 classification achieves higher performance scores than does the ERA-Interim classification, and the differences are statistically significant in all basins. The lower performance of ERA-Interim is mainly due to a higher false alarm rate, particularly in the Eastern North Pacific. Overall, the results show that while the CPS-based classifications are good enough to be useful for many purposes, there is almost certainly room for improvement – in the representation of the storms in reanalyses, in our objective metrics of ET, and in our scientific understanding of the ET process.

Melanie Bieli↗