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 1,009 records · Page 56

A comparison of two methods for classifying forestland

Two methods of developing land-cover classifications using Landsat multispectral data were compared. The first method, called P-1, uses a semi-automated approach to develop training statistics which characterize the land-cover types. The second, called multicluster blocks, depends more on analyst interaction to produce the training statistics used by the classifier. The results showed that P-1 performed as well as the multicluster-blocks approach on a mountainous study area in southwestern Colorado. These results may interest any resource discipline which has available to it ground-checked or photointerpreted information. P-1 can use this information directly to output a land-cover classification with little analyst interaction.

Nelson, R. F.↗

Novel Histogram Based Unsupervised Classification Technique to Determine Natural Classes From Biophysically Relevant Fit Parameters to Hyperspectral Data

Hyperspectral image analysis has benefited from an array of methods that take advantage of the increased spectral depth compared to multispectral sensors; however, the focus of these developments has been on supervised classification methods. Lack of a priori knowledge regarding land cover characteristics can make unsupervised classification methods preferable under certain circumstances. An unsupervised classification technique is presented in this paper that utilizes physically relevant basis functions to model the reflectance spectra. These fit parameters used to generate the basis functions allow clustering based on spectral characteristics rather than spectral channels and provide both noise and data reduction. Histogram splitting of the fit parameters is then used as a means of producing an unsupervised classification. Unlike current unsupervised classification techniques that rely primarily on Euclidian distance measures to determine similarity, the unsupervised classification technique uses the natural splitting of the fit parameters associated with the basis functions creating clusters that are similar in terms of physical parameters. The data set used in this work utilizes the publicly available data collected at Indian Pines, Indiana. This data set provides reference data allowing for comparisons of the efficacy of different unsupervised data analysis. The unsupervised histogram splitting technique presented in this paper is shown to be better than the standard unsupervised ISODATA clustering technique with an overall accuracy of 34.3/19.0% before merging and 40.9/39.2% after merging. Finally, this improvement is also seen as an improvement of kappa before/after merging of 24.8/30.5 for the histogram splitting technique compared to 15.8/28.5 for ISODATA.

58 GEOSCIENCES↗

Remote Monitoring System Design Requirements for Accountable Nuclear Materials at the Nevada National Security Site

The Nevada National Security Site (NNSS) worked with other sites within the Department of Energy National Nuclear Security Administration weapons complex to develop design requirements for a Remote Monitoring System. System objectives include: • Continuous monitoring of packaging (containers) within a Facility's buildings to meet Material Control and Accountability (MC&A) inventory requirements. • Remotely access and receive monitoring data for tamper detection/alarm, tracking information, environmental conditions, equipment metadata (serial number, date of manufacturer, etc.), and assessment video feeds. • All data processing, storage/retrieval, and communications will be protected in a manner commensurate with its trust level and classification. • Remotely collected and processed data will be securely stored, backed up, and archived. • Current and historical data will accessible within and outside of a Building (location). • Automated creation of reports and data visualization. • Design features to facilitate the potential future integration with the Facility's physical security alarm and display system. The requirements may be used to develop an integrated conceptual design or may be used in a modular fashion to inform separate designs. The guiding principles in developing the system objectives include: • For MC&A needs, remotely perform the physical inventory and evidence collection of tamper for Security Category I and II packaged material within a facility and be capable of satisfying guidelines establish by DOE M 470.4-6, “Nuclear Material Control and Accountability.” • For personnel safety needs: o Meet/satisfy Nuclear Explosive Safety requirements. o Minimize the exposure of personnel to radiation to be as low as reasonably achievable (ALARA) in accordance with NSTec Radiological Controls Manual (Ref TBD). • For DOE nuclear materials, Building environment shall be controlled to meet requirements for packaged nuclear materials specified in weapons laboratory literature.

99 GENERAL AND MISCELLANEOUS↗

Remote Monitoring System Design Requirements for Accountable Nuclear Materials at the Nevada National Security Site

The Nevada National Security Site (NNSS) worked with other sites within the Department of Energy National Nuclear Security Administration weapons complex to develop design requirements for a Remote Monitoring System. System objectives included: Continuous monitoring of packaging (containers) within a Facility's buildings to meet Material Control and Accountability (MC&A) inventory requirements. Remotely access and receive monitoring data for tamper detection/alarm, tracking information, environmental conditions, equipment metadata (serial number, date of manufacture, etc.), and assessment video feeds. All data processing, storage/retrieval, and communications will be protected in a manner commensurate with its trust level and classification. Remotely collected and processed data will be securely stored, backed up, and archived. Current and historical data will accessible within and outside of a Building (location). Automated creation of reports and data visualization. Design features to facilitate the potential future integration with the Facility's physical security alarm and display system. The requirements may be used to develop an integrated conceptual design or may be used in a modular fashion to inform separate designs. The guiding principles in developing the system objectives include: For MC&A needs, remotely perform the physical inventory and evidence collection of tamper for Security Category I and II packaged material within a facility and be capable of satisfying guidelines establish by DOE M 470.4-6, “Nuclear Material Control and Accountability.” For personnel safety needs: Meet/satisfy Nuclear Explosive Safety requirements. Minimize the exposure of personnel to radiation to be as low as reasonably achievable (ALARA) in accordance with NSTec Radiological Controls Manual. For DOE nuclear materials, Building environment shall be controlled to meet requirements for packaged nuclear materials specified in weapons laboratory literature.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Nationwide forestry applications program: Ten-Ecosystem Study (TES) site 5 report, Kershaw County, South Carolina, report 4

The author has identified the following significant results. The Kershaw County site, South Carolina, was selected to be representative of both the oak-pine ecosystem and the southeastern pine ecosystem. The following processing results have concluded that: (1) early spring LANDSAT data provide the best contrast between forest features; (2) level 2 forest features (softwood, hardwood, grassland, and water) can be classified with an accuracy of 70% + or - 5.7% at the 90% confidence level; (3) level 3 species classification was inconclusive; (4) temporal data did not provide a significant increase in classification accuracy of level 2 features, over single date classification to warrant the additional processing; and (5) training fields from only 10% of the site can be used to classify the entire site.

Dillman, R. D.↗

Pose Classification Using Three-Dimensional Atomic Structure-Based Neural Networks Applied to Ion Channel–Ligand Docking

The identification of promising lead compounds showing pharmacological activities toward a biological target is essential in early stage drug discovery. With the recent increase in available small-molecule databases, virtual high-throughput screening using physics-based molecular docking has emerged as an essential tool in assisting fast and cost-efficient lead discovery and optimization. However, the best scored docking poses are often suboptimal, resulting in incorrect screening and chemical property calculation. We address the pose classification problem by leveraging data-driven machine learning approaches to identify correct docking poses from AutoDock Vina and Glide screens. To enable effective classification of docking poses, we present two convolutional neural network approaches: a three-dimensional convolutional neural network (3D-CNN) and an attention-based point cloud network (PCN) trained on the PDBbind refined set. We demonstrate the effectiveness of our proposed classifiers on multiple evaluation data sets including the standard PDBbind CASF-2016 benchmark data set and various compound libraries with structurally different protein targets including an ion channel data set extracted from Protein Data Bank (PDB) and an in-house KCa3.1 inhibitor data set. Our experiments show that excluding false positive docking poses using the proposed classifiers improves virtual high-throughput screening to identify novel molecules against each target protein compared to the initial screen based on the docking scores.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Waveband evaluation of proposed thematic mapper in forest cover classification

This study involved the evaluation of the characteristics of multispectral scanner data relative to forest cover type mapping, using NASA's NS-001 multispectral scanner to simulate the proposed Thematic Mapper (TM). The objectives were to determine: (1) the optimum number of wavebands to utilize in computer classifications of TM data; (2) which channel combinations provide the highest expected classification accuracy; and (3) the relative merit of each channel in the context of the cover classes examined. Transformed divergence was used as a measure of statistical distance between spectral class densities associated with each of twelve cover classes. The maximum overall mean pair-wise transformed divergence was used as the basis for evaluating all possible waveband combinations available for use in computer-assisted forest cover classifications.

Latty, R. S.↗

Galaxy morphological classification in deep-wide surveys via unsupervised machine learning

ABSTRACT Galaxy morphology is a fundamental quantity, which is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology (e.g. as a prior for photometric-redshift measurements and as contextual data for transient light-curve classifications). While a rich literature exists on morphological-classification techniques, the unprecedented data volumes, coupled, in some cases, with the short cadences of forthcoming ‘Big-Data’ surveys (e.g. from the LSST), present novel challenges for this field. Large data volumes make such data sets intractable for visual inspection (even via massively distributed platforms like Galaxy Zoo), while short cadences make it difficult to employ techniques like supervised machine learning, since it may be impractical to repeatedly produce training sets on short time-scales. Unsupervised machine learning, which does not require training sets, is ideally suited to the morphological analysis of new and forthcoming surveys. Here, we employ an algorithm that performs clustering of graph representations, in order to group image patches with similar visual properties and objects constructed from those patches, like galaxies. We implement the algorithm on the Hyper-Suprime-Cam Subaru-Strategic-Program Ultra-Deep survey, to autonomously reduce the galaxy population to a small number (160) of ‘morphological clusters’, populated by galaxies with similar morphologies, which are then benchmarked using visual inspection. The morphological classifications (which we release publicly) exhibit a high level of purity, and reproduce known trends in key galaxy properties as a function of morphological type at z < 1 (e.g. stellar-mass functions, rest-frame colours, and the position of galaxies on the star-formation main sequence). Our study demonstrates the power of unsupervised machine learning in performing accurate morphological analysis, which will become indispensable in this new era of deep-wide surveys.

Martin, G.↗

Lunar and Planetary Science XXXV: Mars: Gullies, Fluids, and Rocks

The session "Mars: Gullies, Fluids, and Rocks" included the following reports:Gullies on Mars and Constraints Imposed by Mars Global Surveyor Data; Gullies on Mars: Origin by Snow and Ice Melting and Potential for Life Based on Possible Analogs from Devon Island, High Arctic; Formation of Recent Martian Gullies by Avalanches of CO2 Frost; Martian Slope Streaks and Gullies: Origins as Dry Granular Flows; Depths and Geologic Setting of Northern Hemisphere Gullies (and Comparison to Their Southern Counterparts); Mars as a Salt-, Acid-, and Gas-Hydrate World; Composition of Simulated Martian Brines and Implications for the Origin of Martian Salts; Evaporation Rates of Brine on Mars; Hydrogeology of the Valles Marineris-Chaotic Terrain Transition Zone, Mars; Measured Fluid Flow in an Active H2O-CO2 Geothermal Well as an Analog to Fluid Flow in Fractures on Mars: Preliminary Report; Understanding Rock Breakdown on Earth and Mars: Geomorphological Concepts and Facet Mapping Methods; Classification and Distribution of Mars Pathfinder Rocks Using Quantitative Morphologic Indices; and Systematic Rock Classification in a Data-poor Environment: Application to Mars.

Source record↗

Evaluation of change detection techniques for monitoring coastal zone environments

Development of satisfactory techniques for detecting change in coastal zone environments is required before operational monitoring procedures can be established. In an effort to meet this need a study was directed toward developing and evaluating different types of change detection techniques, based upon computer aided analysis of LANDSAT multispectral scanner (MSS) data, to monitor these environments. The Matagorda Bay estuarine system along the Texas coast was selected as the study area. Four change detection techniques were designed and implemented for evaluation: (1) post classification comparison change detection, (2) delta data change detection, (3) spectral/temporal change classification, and (4) layered spectral/temporal change classification. Each of the four techniques was used to analyze a LANDSAT MSS temporal data set to detect areas of change of the Matagorda Bay region.

Weismiller, R. A.↗

Structure of the Newcastle disease virus hemagglutinin-neuraminidase (HN) ectodomain reveals a four-helix bundle stalk

The paramyxovirus hemagglutinin-neuraminidase (HN) protein plays multiple roles in viral entry and egress, including binding to sialic acid receptors, activating the fusion (F) protein to activate membrane fusion and viral entry, and cleaving sialic acid from carbohydrate chains. HN is an oligomeric integral membrane protein consisting of an N-terminal transmembrane domain, a stalk region, and an enzymatically active neuraminidase (NA) domain. Structures of the HN NA domains have been solved previously; however, the structure of the stalk region has remained elusive. The stalk region contains specificity determinants for F interactions and activation, underlying the requirement for homotypic F and HN interactions in viral entry. Mutations of the Newcastle disease virus HN stalk region have been shown to affect both F activation and NA activities, but a structural basis for understanding these dual affects on HN functions has been lacking. Here, we report the structure of the Newcastle disease virus HN ectodomain, revealing dimers of NA domain dimers flanking the N-terminal stalk domain. The stalk forms a parallel tetrameric coiled-coil bundle (4HB) that allows classification of extensive mutational data, providing insight into the functional roles of the stalk region. Mutations that affect both F activation and NA activities map predominantly to the 4HB hydrophobic core, whereas mutations that affect only F-protein activation map primarily to the 4HB surface. Two of four NA domains interact with the 4HB stalk, and residues at this interface in both the stalk and NA domain have been implicated in HN function.

59 BASIC BIOLOGICAL SCIENCES↗

Identification and Photometric Classification of Extragalactic Transients in the Vera C. Rubin Observatory’s Data Preview 1

The Vera C. Rubin Observatory will soon survey the southern sky, delivering a depth and sky coverage that is unprecedented in time-domain astronomy. As part of commissioning, Data Preview 1 (DP1) has been released. It comprises a Legacy Survey of Space and Time (LSST) Commissioning Camera observing campaign between 2024 November and December with multiband imaging of seven fields, covering roughly 0.4 deg 2 each, providing a first glimpse into the data products that will become available once the LSST begins. In this work, we search three fields for extragalactic transients. We identify eight new likely supernovae (SNe), and three known ones from a sample of 369,644 difference image analysis objects. Photometric classification using Superphot+ assigns subclasses with >95% confidence to only one SN Ia and one SN II in this sample. Our findings are in agreement with SN detection rate predictions of 15 ± 4 SNe from simulations using simsurvey. The SN detection rate in the data is possibly affected by the lack of suitable templates. Nevertheless, this work demonstrates the quality of the data products delivered in DP1 and indicates that the Rubin Observatory’s LSST is well placed to fulfill its discovery potential in time-domain astronomy.

Freeburn, James [University of North Carolina, Cha↗

Wetland classification on the Alaskan North Slope

An interactive supervised wetland classification was performed on Landsat digital data for three sites on the North Slope of Alaska. Color-coded classification maps identifying 10 wetland subcategories were produced. Field observations, topographic maps, and aerial photographs were employed as collateral data in classifying and verifying the Landsat information.

Morrow, J. W.↗

Urban remote sensing applications: TIMS observations of the City of Scottsdale

A research program has been initiated between Arizona State University and the City of Scottsdale, Arizona to study the potential applications of TIMS (Thermal Infrared Multispectral Scanner) data for urban scene classification, desert environmental assessment, and change detection. This program is part of a long-term effort to integrate remote sensing observations into state and local planning activities to improve decision making and future planning. Specific test sites include a section of the downtown Scottsdale region that has been mapped in very high detail as part of a pilot program to develop an extensive GIS database. This area thus provides excellent time history of the evolution of the city infrastructure, such as the timing and composition of street repavement. A second area of study includes the McDowell intensive study by state and local agencies to assess potential sites for urban development as well as preservation. These activities are of particular relevance as the Phoenix metropolitan area undergoes major expansion into the surrounding desert areas. The objectives of this study in urban areas are aimed at determining potential applications of TIMS data for classifying and assessing land use and surface temperatures. Land use centers on surface impermeability studies for storm runoff assessment and pollution control. These studies focus on determining the areal abundance of urban vegetation and undeveloped soil. Highly experimental applications include assessment and monitoring of pavement condition. Temperature studies focus on determining swimming pool area and temperature for use in monitoring evaporating and urban water consumption. These activities are of particular relevance as the Phoenix metropolitan area undergoes major expansion into the surrounding desert area.

Christensen, Philip R.↗

Feature Learning for Multispectral Satellite Imagery Classification Using Neural Architecture Search

Automated classification of remote sensing data is an integral tool for earth scientists, and deep learning has proven very successful at solving such problems. However, building deep learning models to process the data requires expert knowledge of machine learning. We introduce DELTA, a software toolkit to bridge this technical gap and make deep learning easily accessible to earth scientists. Visual feature engineering is a critical part of the machine learning lifecycle, and hence is a key area that will be automated by DELTA. Hand-engineered features can perform well, but require a cross functional team with expertise in both machine learning and the specific problem domain, which is costly in both researcher time and labor. The problem is more acute with multispectral satellite imagery, which requires considerable computational resources to process. In order to automate the feature learning process, a neural architecture search samples the space of asymmetric and symmetric autoencoders using evolutionary algorithms. Since denoising autoencoders have been shown to perform well for feature learning, the autoencoders are trained on various levels of noise and the features generated by the best performing autoencoders evaluated according to their performance on image classification tasks. The resulting features are demonstrated to be effective for Landsat-8 flood mapping, as well as benchmark datasets CIFAR10 and SVHN.

Robert Campbell↗

Interpretable boosted-decision-tree analysis for the Majorana Demonstrator

The Majorana Demonstrator is a leading experiment searching for neutrinoless double-beta decay with high purity germanium detectors (HPGe). Machine learning provides a new way to maximize the amount of information provided by these detectors, but the data-driven nature makes it less interpretable compared to traditional analysis. An interpretability study reveals the machine's decision-making logic, allowing us to learn from the machine to feedback to the traditional analysis. In this work, we have presented the first machine learning analysis of the data from the Majorana Demonstrator; this is also the first interpretable machine learning analysis of any germanium detector experiment. Two gradient boosted decision tree models are trained to learn from the data, and a game-theory-based model interpretability study is conducted to understand the origin of the classification power. By learning from data, this analysis recognizes the correlations among reconstruction parameters to further enhance the background rejection performance. By learning from the machine, this analysis reveals the importance of new background categories to reciprocally benefit the standard Majorana analysis. This model is highly compatible with next-generation germanium detector experiments like LEGEND since it can be simultaneously trained on a large number of detectors.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Reflectance measurements for the detection and mapping of soil limitations

During 1971 and 1972 research was conducted on two fallow fields in the proposed Oahe Irrigation Project to investigate the relationship between the tonal variations observed on aerial photographs and the principal soil limitations of the area. A grid sampling procedure was used to collected detailed field data during the 1972 growing season. The field data was compared to imagery collected on May 14, 1971 at 3050 meters altitude. The imagery and field data were initially evaluated by a visual analysis. Correlation and regression analysis revealed a highly significant correlation and regression analysis revealed a highly significant correlation between the digitized color infrared film data and soil properties such as organic matter content, color, depth to carbonates, bulk density and reflectivity. Computer classification of the multiemulsion film data resulted in maps delineating the areas containing claypan and erosion limitations. Reflectance data from the red spectral band provided the best results.

Benson, L. A.↗

On the error in crop acreage estimation using satellite (LANDSAT) data

The problem of crop acreage estimation using satellite data is discussed. Bias and variance of a crop proportion estimate in an area segment obtained from the classification of its multispectral sensor data are derived as functions of the means, variances, and covariance of error rates. The linear discriminant analysis and the class proportion estimation for the two class case are extended to include a third class of measurement units, where these units are mixed on ground. Special attention is given to the investigation of mislabeling in training samples and its effect on crop proportion estimation. It is shown that the bias and variance of the estimate of a specific crop acreage proportion increase as the disparity in mislabeling rates between two classes increases. Some interaction is shown to take place, causing the bias and the variance to decrease at first and then to increase, as the mixed unit class varies in size from 0 to 50 percent of the total area segment.

Chhikara, R.↗