Search NASA⌕ Search

SEARCH · Search NASA

Results for “Algorithm 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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
NASA NTRS2013

Mapping Impervious Surfaces Globally at 30m Resolution Using Global Land Survey Data

Impervious surfaces, mainly artificial structures and roads, cover less than 1% of the world's land surface (1.3% over USA). Regardless of the relatively small coverage, impervious surfaces have a significant impact on the environment. They are the main source of the urban heat island effect, and affect not only the energy balance, but also hydrology and carbon cycling, and both land and aquatic ecosystem services. In the last several decades, the pace of converting natural land surface to impervious surfaces has increased. Quantitatively monitoring the growth of impervious surface expansion and associated urbanization has become a priority topic across both the physical and social sciences. The recent availability of consistent, global scale data sets at 30m resolution such as the Global Land Survey from the Landsat satellites provides an unprecedented opportunity to map global impervious cover and urbanization at this resolution for the first time, with unprecedented detail and accuracy. Moreover, the spatial resolution of Landsat is absolutely essential to accurately resolve urban targets such a buildings, roads and parking lots. With long term GLS data now available for the 1975, 1990, 2000, 2005 and 2010 time periods, the land cover/use changes due to urbanization can now be quantified at this spatial scale as well. In the Global Land Survey - Imperviousness Mapping Project (GLS-IMP), we are producing the first global 30 m spatial resolution impervious cover data set. We have processed the GLS 2010 data set to surface reflectance (8500+ TM and ETM+ scenes) and are using a supervised classification method using a regression tree to produce continental scale impervious cover data sets. A very large set of accurate training samples is the key to the supervised classifications and is being derived through the interpretation of high spatial resolution (approx. 2 m or less) commercial satellite data (Quickbird and Worldview2) available to us through the unclassified archive of the National Geospatial Intelligence Agency (NGA). For each continental area several million training pixels are derived by analysts using image segmentation algorithms and tools and then aggregated to the 30m resolution of Landsat. Here we will discuss the production/testing of this massive data set for Europe, North and South America and Africa, including assessments of the 2010 surface reflectance data. This type of analysis is only possible because of the availability of long term 30m data sets from GLS and shows much promise for integration of Landsat 8 data in the future.

global land survey↗
NASA NTRSDate not supplied

Feature Selection in High-Dimensional Space with Applications to Gene Expression Data

Recent years have seen rapid growth in high-dimensional datasets. Most existing machine learning (ML) algorithms fail in high-dimensional settings where many features could be redundant. A critical process of feature selection is thus applied in such a setting that helps in identifying the most relevant features while removing redundant ones. With the increase in high dimensionality, one is also faced with problems of efficiency and interpretation in performing such selection methods. Therefore, this paper proposes a “novel” feature selection framework that uses an ensemble of interpretable ML algorithms to perform feature selection and the ranking of final features. Finally, this framework is applied to a gene expression dataset obtained through collaboration with the National Aeronautics and Space Administration (NASA)’s Biological and Physical Sciences (BPS) team and helps identify important and relevant genes contributing to specific target attributes through classification tasks.

Nishan Pantha↗
NASA NTRS1994

A comparison of spectral decorrelation techniques and performance evaluation metrics for a wavelet-based, multispectral data compression algorithm

Future space-based, remote sensing systems will have data transmission requirements that exceed available downlinks necessitating the use of lossy compression techniques for multispectral data. In this paper, we describe several algorithms for lossy compression of multispectral data which combine spectral decorrelation techniques with an adaptive, wavelet-based, image compression algorithm to exploit both spectral and spatial correlation. We compare the performance of several different spectral decorrelation techniques including wavelet transformation in the spectral dimension. The performance of each technique is evaluated at compression ratios ranging from 4:1 to 16:1. Performance measures used are visual examination, conventional distortion measures, and multispectral classification results. We also introduce a family of distortion metrics that are designed to quantify and predict the effect of compression artifacts on multi spectral classification of the reconstructed data.

Matic, Roy M.↗
NASA NTRS2013

UAVSAR Program: Initial Results from New Instrument Capabilities

UAVSAR is an imaging radar instrument suite that serves as NASA's airborne facility instrument to acquire scientific data for Principal Investigators as well as a radar test-bed for new radar observation techniques and radar technology demonstration. Since commencing operational science observations in January 2009, the compact, reconfigurable, pod-based radar has been acquiring L-band fully polarimetric SAR (POLSAR) data with repeat-pass interferometric (RPI) observations underneath NASA Dryden's Gulfstream-III jet to provide measurements for science investigations in solid earth and cryospheric studies, vegetation mapping and land use classification, archaeological research, soil moisture mapping, geology and cold land processes. In the past year, we have made significant upgrades to add new instrument capabilities and new platform options to accommodate the increasing demand for UAVSAR to support scientific campaigns to measure subsurface soil moisture, acquire data in the polar regions, and for algorithm development, verification, and cross-calibration with other airborne/spaceborne instruments.

P-band polarimetry↗
NASA NTRS1974

Automated thematic mapping and change detection of ERTS-1 images

Results of an automated thematic mapping investigation using ERTS-1 MSS images are presented. A diffraction pattern analysis of MSS images led to the development of spatial signatures for farm land, urban areas, and mountains. Four spatial features are employed to describe the spatial characteristics of image cells in the digital data. Three spectral features are combined with the spatial features to form a seven dimensional vector describing each cell. Then, the classification of the feature vectors is accomplished by using the maximum likelihood criterion. Three ERTS-1 images from the Phoenix, Arizona area were processed, and recognition rates between 85% and 100% were obtained for the terrain classes of desert, farms, mountains and urban areas. To eliminate the need for training data, a new clustering algorithm has also been developed.

Gramenopoulos, N.↗
NASA NTRS1982

Appendix B: Principles of computer processing of LANDSAT data

Computer processing facilitates extraction of information from every pixel by executing a variety of functional operations, called processed algorithms, in general or specialized routines. The best results are obtained when data from more than one multispectral band are used together. Multivariate tatistical analysis, computer tape characteristics, processing modes, and a choice of systems (batch or interactive) are discussed. The major operations in computer processing elaborated include: preprocessing, enhancement, effects of rationing, and classification. Techniques for multisource data correlation are considered with emphasis on geobased systems.

Source record↗
NASA NTRS2011

Compact Polarimetry in a Low Frequency Spaceborne Context

Compact polarimetry has been shown to be an interesting alternative mode to full polarimetry when global coverage and revisit time are key issues. It consists on transmitting a single polarization, while receiving on two. Several critical points have been identified, one being the Faraday rotation (FR) correction and the other the calibration. When a low frequency electromagnetic wave travels through the ionosphere, it undergoes a rotation of the polarization plane about the radar line of sight for a linearly polarized wave, and a simple phase shift for a circularly polarized wave. In a low frequency radar, the only possible choice of the transmit polarization is the circular one, in order to guaranty that the scattering element on the ground is illuminated with a constant polarization independently of the ionosphere state. This will allow meaningful time series analysis, interferometry as long as the Faraday rotation effect is corrected for the return path. In full-polarimetric (FP) mode, two techniques allow to estimate the FR: Freeman method using linearly polarized data, and Bickel and Bates theory based on the transformation of the measured scattering matrix to a circular basis. In CP mode, an alternate procedure is presented which relies on the bare surface scattering properties. These bare surfaces are selected by the conformity coefficient, invariant with FR. This coefficient is compared to other published classifications to show its potential in distinguishing three different scattering types: surface, doublebounce and volume. The performances of the bare surfaces selection and FR estimation are evaluated on PALSAR and airborne data. Once the bare surfaces are selected and Faraday angle estimated over them, the correction can be applied over the whole scene. The algorithm is compared with both FP techniques. In the last part of the paper, the calibration of a CP system from the point of view of classical matrix transformation methods in polarimetry is proposed.

radar polarization diversity↗
NASA NTRS1990

A multisensor approach to sea ice classification for the validation of DMSP-SSM/I passive microwave derived sea ice products

The validation of sea ice products derived from the Special Sensor Microwave Imager (SSM/I) on board a DMSP platform is examined using data from the Landsat MSS and NOAA-AVHRR sensors. Image processing techniques for retrieving ice concentrations from each type of imagery are developed and results are intercompared to determine the ice parameter retrieval accuracy of the SSM/I NASA-Team algorithm. For case studies in the Beaufort Sea and East Greenland Sea, average retrieval errors of the SSM/I algorithm are between 1.7 percent for spring conditions and 4.3 percent during freeze up in comparison with Landsat derived ice concentrations. For a case study in the East Greenland Sea, SSM/I derived ice concentration in comparison with AVHRR imagery display a mean error of 9.6 percent.

Steffen, K.↗
NASA NTRSDate not supplied

Benchmark Models for Classification of Radiation Type Induced in Immune Cells

NASA Biological and Physical Sciences and the Science Mission Directorate have published a benchmark dataset of mouse immune cells subjected to radiation-induced DNA damage. The dataset comprises ML-ready microscopic imagery of said cells, including labels indicating radiation type and dose. The machine learning team at NASA Interagency Implementation and Advanced Concept Team (IMPACT) created multiple benchmark models. Initially, we conducted a preliminary analysis using thresholding. The algorithm used thresholds on average brightness of the available images to classify them into their respective radiation type. We also tested machine learning approaches. Convolutional Neural Networks (CNN) emerged as the best-performing model. This poster presents the benchmark scores obtained by the models.

Vishal Perekadan↗
NASA NTRS2016

Machine-z: Rapid Machine-Learned Redshift Indicator for Swift Gamma-Ray Bursts

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce 'machine-z', a redshift prediction algorithm and a 'high-z' classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve approximately 100 per cent recall. The most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

gamma-ray burst: general↗
NASA NTRS2004

Putting Priors in Mixture Density Mercer Kernels

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly infinite dimensional feature space. We describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using predefined kernels. These data adaptive kernels can en- code prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS). The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains template for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic- algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code. The results show that the Mixture Density Mercer-Kernel described here outperforms tree-based classification in distinguishing high-redshift galaxies from low- redshift galaxies by approximately 16% on test data, bagged trees by approximately 7%, and bagged trees built on a much larger sample of data by approximately 2%.

Srivastava, Ashok N.↗
NASA NTRS1982

Antarctic sea ice concentrations inferred from Nimbus 5 ESMR and Landsat imagery

Landsat Multispectral Scanner near-infrared band images (MSS-7) are used to calculate Antarctic ice concentration values and these results are quantitatively compared to those derived from Nimbus 5 electrically scanning microwave radiometer (ESMR) brightness temperature data. The set of images includes regions near the ice edge and near the continental boundary during late winter or spring. The percentage of ice cover is derived from the microwave data, using an algorithm that incorporates the brightness temperature emissivity and interpolated climatological physical temperatures and that is not dependent on spatial resolution. Cloud-free Landsat images are used to provide an alternative determination of large-scale ice concentrations, but this method is limited in its ability to resolve individual ice flows, especially near the ice edge. A proportional classification procedure is applied to Landsat data based on observed reflection and the results are correlated with similarly-derived ESMR ice concentration values. The corresponding ice concentration values are found to agree to + or - 15%, with the largest uncertainties occurring in regions of low ice concentration.

Comiso, J. C.↗
NASA NTRS1990

Remote sensing of Earth terrain

Remote sensing of earth terrain is examined. The layered random medium model is used to investigate the fully polarimetric scattering of electromagnetic waves from vegetation. The model is used to interpret the measured data for vegetation fields such as rice, wheat, or soybean over water or soil. Accurate calibration of polarimetric radar systems is essential for the polarimetric remote sensing of earth terrain. A polarimetric calibration algorithm using three arbitrary in-scene reflectors is developed. In the interpretation of active and passive microwave remote sensing data from the earth terrain, the random medium model was shown to be quite successful. A multivariate K-distribution is proposed to model the statistics of fully polarimetric radar returns from earth terrain. In the terrain cover classification using the synthetic aperture radar (SAR) images, the applications of the K-distribution model will provide better performance than the conventional Gaussian classifiers. The layered random medium model is used to study the polarimetric response of sea ice. Supervised and unsupervised classification procedures are also developed and applied to synthetic aperture radar polarimetric images in order to identify their various earth terrain components for more than two classes. These classification procedures were applied to San Francisco Bay and Traverse City SAR images.

Kong, Jin AU↗
NASA NTRS2018

Refining the Safety - Liveness Classification of Temporal Properties According to Monitorability

Runtime verification is the topic of analyzing execution traces using formal techniques. It includes monitoring the execution of a system against temporal properties, commonly to detect violations. Not every temporal property is fully monitorable however: in some cases, the correctness of the execution does not depend on any finite prefix. We study the connection between monitorability and Lamport’s classification of properties to safety and liveness and their dual classes.We refine the definition of monitorability and provide algorithms to check which verdicts can be expected, a priori and during runtime verification.

Peled, Doron↗
NASA NTRS1991

Near ground level sensing for spatial analysis of vegetation

Measured changes in vegetation indicate the dynamics of ecological processes and can identify the impacts from disturbances. Traditional methods of vegetation analysis tend to be slow because they are labor intensive; as a result, these methods are often confined to small local area measurements. Scientists need new algorithms and instruments that will allow them to efficiently study environmental dynamics across a range of different spatial scales. A new methodology that addresses this problem is presented. This methodology includes the acquisition, processing, and presentation of near ground level image data and its corresponding spatial characteristics. The systematic approach taken encompasses a feature extraction process, a supervised and unsupervised classification process, and a region labeling process yielding spatial information.

Sauer, Tom↗
NASA NTRS2019

Image Labeler: A Web Interface to Catalog Earth Science Events

Advances in machine learning (ML) have made it possible to automatically detect Earth science phenomena from satellite imagery. While useful, ML algorithms typically require an extensive dataset containing labeled images for training. Systematic labeling and management of such datasets is quite cumbersome. With this in mind, we present the Image Labeler. Image Labeler is a fast and scalable cloud-based tool that facilitates the rapid development of Earth science event databases, in order to aid automated ML-based image classification.

Case Study↗
NASA NTRS2020

An Evaluation of Clouds and Radiation in a Large-Scale Atmospheric Model Using a Cloud Vertical Structure Classification

We revisit the concept of the cloud vertical structure (CVS) classes we have previously employed to classify the planet's cloudiness (Oreopoulos et al., 2017). The CVS classification reflects simple combinations of simultaneous cloud occurrence in the three standard layers traditionally used to separate low, middle, and high clouds and was applied to a dataset derived from active lidar and cloud radar observations. This classification is now introduced in an atmospheric global climate model, specifically a version of NASA's GEOS-5, in order to evaluate the realism of its cloudiness and of the radiative effects associated with the various CVS classes. Such classes can be defined in GEOS-5 thanks to a sub column cloud generator paired with the model's radiative transfer algorithm, and their associated radiative effects can be evaluated against observations. We find that the model produces 50% more clear skies than observations in relative terms and produces isolated high clouds that are slightly less frequent than in observations, but optically thicker, yielding excessive planetary and surface cooling. Low clouds are also brighter than in observations, but underestimates of the frequency of occurrence (by ~20% in relative terms) help restore radiative agreement with observations. Overall the model better reproduces the longwave radiative effects of the various CVS classes because cloud vertical location is substantially constrained in the CVS framework.

Lee, Dongmin↗
NASA NTRS1977

Annual Symposium on Machine Processing of Remotely Sensed Data, 4th, Purdue University, West Lafayette, Ind., June 21-23, 1977, Proceedings

Papers are presented on a variety of techniques for the machine processing of remotely sensed data. Consideration is given to preprocessing methods such as the correction of Landsat data for the effects of haze, sun angle, and reflectance and to the maximum likelihood estimation of signature transformation algorithm. Several applications of machine processing to agriculture are identified. Various types of processing systems are discussed such as ground-data processing/support systems for sensor systems and the transfer of remotely sensed data to operational systems. The application of machine processing to hydrology, geology, and land-use mapping is outlined. Data analysis is considered with reference to several types of classification methods and systems.

Morrison, D. B.↗