Search NASA⌕ Search

SEARCH · Search NASA

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 1,747 records · Page 97

Example of Occupational Surveillance in a Telemedicine Setting: Application of Epidemiologic Methods at NASA Johnson Space Center

In 2010, NASA implemented Lifetime Surveillance of Astronaut Health, a formal occupational surveillance program for the U.S. astronaut corps. Because of the nature of the space environment, space medicine presents unique challenges and opportunities for epidemiologists. One such example is the use of telemedicine while crewmembers are in flight, where the primary source of information about crew health is verbal communication between physicians and their crewmembers. Due to restricted medical capabilities, the available health information is primarily crewmember report of signs and symptoms, rather than diagnoses. As epidemiologists at NASA, Johnson Space Center, we have shifted our paradigm from tracking diagnoses based on traditional terrestrial clinical practice to one in which we also incorporate reported symptomology as potential antecedents of disease. In this presentation we describe how characterization of reported signs and symptoms can be used to establish incidence rates for inflight immunologic events. We describe interdisciplinary data sources of information that are used in combination with medical information to analyze the data. We also delineate criteria for symptom classification inclusion. Finally, we present incidence tables and graphs to illustrate the final outcomes. Using signs and symptoms reported via telemedicine, the epidemiologists provide summary evidence regarding incidence of potential inflight medical conditions. These results inform our NASA physicians and scientists, and support evaluation of the occupational health risks associated with spaceflight.

Babiak-Vazquez, Adriana↗

TPSAS-NF1676L-13204-DND

Invasive perennial pepperweed (Lepidium latifolium) has spread rapidly throughout the western United States in the past fifteen years. Pepperweed outcompetes many native species for water and nutrients, disturbing sensitive ecosystems. The purpose of this study is to map the contemporary distribution of pepperweed throughout the wetland ecosystem of the restored South San Francisco Bay Salt Ponds and create a habitat suitability model to predict future spread. Pepperweed reflectance data were collected in-situ with the GER 1500 spectroradiometer along with presence and absence pepperweed GPS data points. A Spectral Angle Mapper (SAM) classification algorithm (Method A) was used to distinguish pepperweed spectra and map its distribution on an EO-1 Hyperion image of the study area. Similarly, a supervised classification was run on an ASTER image of the study area. A GIS multivariate habitat suitability model was created to predict areas most susceptible to pepperweed colonization. Variables incorporated into the model were tidal extent, propensity for disturbance, pond salinity, proximity to levees and channels, and terrain curvature. A Generalized Additive Model (GAM) was also used to generate a suitability map (Method B) and investigate the statistical probability that each variable contributed to predict pepperweed spread. Results from the GAM revealed distance to channels, distance to disturbance factors, extreme pond salinity and curvature as statistically significant in determining the locations of suitable pepperweed habitats

Andrew Nguyen↗

Automated classification of scientific publications linked to GES DISC datasets

The data collections archived and distributedby the GES DISC NASA data center arewidely utilized for various Earth Science studies.As these collections are created, many researchworks are published regarding the collections, algorithms,validations and applications. SinceGES DISC collects these publications and providestheir citations for the users, it is helpful tocategorize them based on how they relate to the datasetsthey are associated with. Specifically,whether the publication that is linked to GES DISCdataset is using it for applicational research,or if it describes the algorithm for dataset creation,or the validation of the dataset, or providesthe general overview of the data collection. Currently,this process requires simple manuallabelling, and as such, may be possible to solve viaautomation. To approach this problem, wedeveloped machine learning classifiers to predictthe category a publication belongs to. We usedmanually labeled publications as training data forsupervised machine learning algorithms:Random Forest and Naive Bayes. We achieved classificationaccuracy that is substantially betterthan the baseline accuracy, thus greatly improvingthe efficiency of the publication internalanalysis.

Rohan Dayal↗

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields in the last two decades, in part thanks to an increasing culture of open data sharing and reuse. Due to its capability for identifying complex relationships and patterns, AI/ML methodology is particularly well suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are many key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Even with the positive culture of Open Science and data sharing, inexperienced researchers working quickly without proper checks can produce models that perform poorly outside of the immediate training dataset. Lessons learned from biological AI/ML research indicate that Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Andrew Casaletto↗

Developing Open-Source Training Materials for AI/ML and Space Biological Sciences Using NASA Cloud-Based Data

Artificial Intelligence (AI) and Machine Learning (ML) has gained significant traction in the biological and biomedical research fields, in part due to a culture of open data sharing and reuse. AI/ML methodology is well-suited to recognize and predict biological patterns from high-dimensional next-generation sequencing data (e.g. whole genome sequencing, transcriptomic sequencing), as well as from biological or medical imaging data (e.g. microscopy, computed tomography, ultrasound, magnetic resonance imaging, radiography). These methodologies hold particular promise for space biosciences research and automated space health monitoring systems. However, there are key considerations for properly training, validating, and testing a machine learning model in biological research or clinical application. Inexperienced researchers can produce models that perform poorly outside of the training dataset. Open Science principles such as data sharing and open-source code must go hand-in-hand with publicly available, high-quality training curricula in best practices, with modules centered on real-life scientific use cases and data so future AI/ML practitioners gain experience on real problems. Here we present the development of open-source training materials for AI/ML and space biosciences, as part of the NASA Transform to Open Science Training (TOPST) initiative. We develop 4 independent training programs, focused on the following topics: 1) Fundamentals of Machine Learning and Space Biosciences Domain, 2) Open Science, Artificial Intelligence, and Ethical Best Practices for Data Sharing and Analysis, 3) Using AI/ML Classification to Identify Gene Networks Affected By Space Exposure in Mouse Liver, and 4) Using Neural Networks to Find DNA Damage Patterns in Immune Cells after Radiation. All programs leverage cloud-based NASA biological datasets. The curriculum we present will enable worldwide access to training in AI/ML and scientific analysis.

James Casaletto↗

The UCLA Cosmochemistry Database

The UCLA Cosmochemistry Database was initiated as part of a data-rescue and -storage project aimed at archiving a variety of cosmochemical data acquired at University of California, Los Angeles (UCLA). The data collection includes elemental compositions of extraterrestrial materials analyzed by UCLA cosmochemists over the last five decades. The analytical techniques include atomic absorption spectrometry (AAS) and neutron activation analysis (NAA) at UCLA. The data collection is stored on the Astromaterials Data System (Astromat). We provide both interactive tables and downloadable datasheets for users to access all data. The UCLA Cosmochemistry Database archives cosmochemical data that are essential tools for increasing our understanding of the nature and origin of extraterrestrial materials. Future studies can reference the data collection in the examination, analysis, and classification of newly acquired extraterrestrial samples.

Bidong Zhang↗

Development of Real-Time Quantitative Safety Evaluation Method for Nuclear Power Plants

Human operators involved with large process control systems such as nuclear power plants (NPPs) perform significant roles in the operation of systems. In this reason, deficiencies in human factors such as poor HSI (Human System Interface) design, procedure, and training, are significant contributing factors to NPPs incidents and accidents. In this regard, many kinds of studies including human reliability analysis (HRA), operation support system, automation, have been conducted in order to reduce human errors. Among these fields of studies, automation has its own specialty since it mainly focuses on eliminating the human error-inducing tasks to reduce human error, while other topics are primarily focusing on reducing human error by aiding human operators during operation. It is commonly believed that replacing human operators to the automated system would guarantee greater efficiency, lower workloads, and fewer human errors. However, these beliefs are not always true in large and complex systems such as NPP, since excessive automation can generate new roles for human operators, change human operators' activities in unexpected ways, and inducing 'out-of-the-loop' (OOTL) problem. Especially, although human error probability drastically increases during abnormal situations in NPP due to overload of information, high workload, and short time available for diagnosis, automation is not actively adopted since conventional machine learning techniques are neither capable nor reliable to handle overwhelmingly complex abnormal situations in NPP. Recently, newly developed 'deep learning' techniques have been actively applied to many fields, and some of these studies proved that the artificial intelligences (AI) based on deep learning techniques show better performance than that of human being. In 2015, deep Q-network (DQN) which is one of the deep learning techniques was developed and applied to train AI that automatically plays various Atari 2800 games, and this AI surpassed the human-level playing in many kind of games. Also in 2016, 'AlphaGo', which was developed by 'Google Deepmind' based on deep learning technique to play the game of Go, was defeated Se-dol Lee who is the World Go champion with score of 4:1. In the point of view that the game of Go is considered as one of the challenging area in machine learning field, it is verified that these new machine learning techniques can perform well, even better than the human being in high-complexity tasks. Previously, most of AI applications in nuclear field were focusing on supporting human operators' tasks such as diagnosis and decision making by rapid classification and prediction, based on fixed training data sets. However, it is expected that AI can be applied to solve more complicated problems (i.e. automation during abnormal states in NPP) by adopting advanced machine learning methodologies. In order to apply the automation system in NPP, firstly it is needed to evaluate the status of the plant quantitatively in real-time, since the information about which state is better (i.e. safe) or worse (i.e. unsafe) is essential for training properly working automation AI. Currently, there are several methodologies for NPP safety evaluation such as probabilistic safety assessment (PSA), safety performance indicator (SPI). However, existing methodologies are not feasible for development of automated system since they are not capable for the cases which are not included in the underlying model, not able to consider delicate changes in the NPP, and hard to evaluate in real-time. Therefore, development of new NPP safety evaluation methodology which can cover previously mentioned requirements is needed to conduct the study on NPP automation further. In this study, the concept of early warning score (EWS) in medical field was adopted to develop the methodology which can evaluate the safety level of the NPP quantitatively and in real-time. (authors)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Combined spectral and spatial processing of ERTS imagery data

A general procedure is presented for extracting textural properties of blocks of image data. These features are calculated in the spatial domain, taking into account the statistical nature of texture. The procedure is based on the assumption that the texture information in an image is contained in the overall or 'average' spatial relationship which the gray tones in the image have to one another. The spatial gray-tone dependence matrix is discussed together with the spectral features used in the study and the land use classification studies conducted. The results of the study show the usefulness of using both spectral and textural characteristics of ERTS multispectral scanner data for developing classification procedures.

Haralick, R. M.↗

Unsupervised Classification of Global Radar Units on Venus

Characterization of the Venusian surface in terms of its radar properties was accomplished by application of an unsupervised, linear discriminant algorithm to two Pioneer-Venus (PV) Orbiter radar data sets: the RMS-slope (surface roughness) and reflectivity. Both databases were spatially filtered to the same effective resolution of 100 km prior to classification. A recent supervised classification study using these data was based on presupposed morphologic significance of selected data ranges. The knowledge of both Venusian geology and the geologic significance of the radar data is so limited that the data warrant a more unsupervised approach; for this study a linear discriminant classifier was chosen. This approach is purely statistical, thereby removing any observer bias. Statistical significance of the resulting clusters was evaluated by an ancillary program in which an F test utilizing the Mahalanobis' distance.

Kozak, R. C.↗

Preparation of urban land use inventories by machine-processing of ERTS MSS data

Spectral classes of urban phenomena identified from ERTS multispectral scanner data in Milwaukee included Surburban, Inner City, Industry, Grassy (open area), Road, Wooded Suburb, Water, Cloud, and Shadow. The Milwaukee spectral class statistics were used to classify the Chicago area, within the same ERTS frame, and similar results were achieved. In another ERTS frame, Marion County (Indianapolis) data were classified into similar classes. The Marion County ERTS study was supported by a land use classification of an area near downtown Indianapolis that utilized 12-band MSS data collected by aircraft from 3000 feet. The results of the ERTS analyses suggest that satellite data will be a useful tool for the urban planner for monitoring urban land use.

Todd, W.↗

Preparation of urban land use inventories by machine processing of ERTS MSS data

Spectral classes of urban phenomena identified from Earth Resources Technology Satellite (ERTS) multispectral scanner data in Milwaukee included suburban inner city, industry, grassy (open area), road, wooded suburb, water cloud, and shadow. The Milwaukee spectral class statistics were used to classify the Chicago area, within the same ERTS frame, and similar results were achieved. In another ERTS frame, Marion County (Indianapolis) data were classified into similar classes. The Marion County ERTS study was supported by a land use classification of an area near downtown Indianapolis that utilized 12-band MSS data collected by aircraft from 3000 feet. The results of the ERTS analyses suggest that satellite data will be a useful tool for the urban planner for monitoring urban land use.

Todd, W.↗

Evaluating LANDSAT wildland classification accuracies

Procedures to evaluate the accuracy of LANDSAT derived wildland cover classifications are described. The evaluation procedures include: (1) implementing a stratified random sample for obtaining unbiased verification data; (2) performing area by area comparisons between verification and LANDSAT data for both heterogeneous and homogeneous fields; (3) providing overall and individual classification accuracies with confidence limits; (4) displaying results within contingency tables for analysis of confusion between classes; and (5) quantifying the amount of information (bits/square kilometer) conveyed in the LANDSAT classification.

Toll, D. L.↗

Digital data processing of ERTS-1 imagery of Delaware Bay

A user-oriented Earth Resources Data Center is in operation at Bendix Aerospace, which a capable of automatically producing classification imagery and thematic maps from ERTS computer compatible tapes. The ERDC is now being used to process ERTS-1 data under a subcontract from the University of Delaware. ERTS coverage of Delaware Bay has been processed to produce classification imagery of water masses in the bay, and a map of all land-water boundaries along the shoreline including wetlands and inland lakes. Imagery, the user's video monitor color display, the data processing facility, and methodology are described.

Conrod, A. C.↗

Development of a Random-Forest Cloud-Regime Classification Model Based on Surface Radiation and Cloud Products

Various methods have been developed to characterize cloud type, otherwise referred to as cloud regime. These include manual sky observations, combining radiative and cloud vertical properties observed from satellite, surface-based remote sensing, and digital processing of sky imagers. While each method has inherent advantages and disadvantages, none of these cloud-typing methods actually includes measurements of surface shortwave or longwave radiative fluxes. Here, a method that relies upon detailed, surface-based radiation and cloud measurements and derived data products to train a random-forest machine-learning cloud classification model is introduced. Measurements from five years of data from the ARM Southern Great Plains site were compiled to train and independently evaluate the model classification performance. A cloud-type accuracy of approximately 80% using the random-forest classifier reveals that the model is well suited to predict climatological cloud properties. Furthermore, an analysis of the cloud-type misclassifications is performed. While physical cloud types may be misreported, the shortwave radiative signatures are similar between misclassified cloud types. From this, we assert that the cloud-regime model has the capacity to successfully differentiate clouds with comparable cloud–radiative interactions. Therefore, we conclude that the model can provide useful cloud-property information for fundamental cloud studies, inform renewable energy studies, and be a tool for numerical model evaluation and parameterization improvement, among many other applications.

54 ENVIRONMENTAL SCIENCES↗

Differentiating elements of the soil-vegetation complex

The application of remote sensing to study soil-vegetation systems requires quantification and precise location of ground observation data such that they can be correlated with multispectral aerial acquired data. Griddling and sampling of an area for exact identification in a known address on magnetic tape containing multispectral scanner data produces quantitative physico-chemical parameters and the energy which is radiating from within the soil-vegetation complex of an area. Example classifications and spectral mappings of soils made from multispectral scanner data are included.

Baumgardner, M. F.↗

Study of the characteristics of seismic signals generated by natural and cultural phenomena

Seismic data recorded at the Tonto Forest Seismological Observatory in Arizona and the Uinta Basin Seismological Observatory in Utah were used to compare the frequency of occurrence, severity, and spectral content of ground motions resulting from earthquakes, and other natural and man-made sources with the motions generated by sonic booms. A search of data recorded at the two observatories yielded a classification of over 180,000 earthquake phase arrivals on the basis of frequency of occurrence versus maximum ground velocity. The majority of the large ground velocities were produced by seismic surface waves from moderate to large earthquakes in the western United States, and particularly along the Pacific Coast of the United States and northern Mexico. A visual analysis of raw film seismogram data over a 3-year period indicates that local and regional seismic events, including quarry blasts, are frequent in occurrence, but do not produce ground motions at the observatories comparable to either the large western United States earthquakes or to sonic booms. Seismic data from the Nevada Test Site nuclear blasts were used to derive magnitude-distance-sonic boom overpressure relations.

Goforth, T. T.↗

Low-pass spatial filtering of satellite radar data

Thirty-four low-pass spatial filter treatments were applied to a multi-angle SIR-B data set to reduce speckle effects and improve classification performance. These treatments were based on four algorithms: square mean, separable mean, square median, and separable recursive median. The filtered images were evaluated using both quantitative and qualitative techniques. It was determined that the square median algorithm implemented at two iterations with a window size of 3 by 3 produced the best overall results with the 28.5-m SIR-B data.

Mueller, Paul W.↗