SEARCH · Search NASA
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.
Several schemes for discriminating severe weather phenomena with the aid of different algorithms are examined. The schemes were tested on the same sample. A comparative estimate of the effectiveness of the different algorithms for classifying thunderstorms and showers is carried out.
A cluster analysis technique is used to identify 16 "archetypal" vertical radar profile types from a large, globally representative sample of profiles from the TRMM Precipitation Radar. These include nine convective types (7 of these deep convective) and seven stratiform types (5 of these clearly glaciated). Radar profile classification provides an alternative to conventional deep convective storm metrics, such as 30 dBZ echo height, maximum reflectivity or VIL. As expected, the global frequency of occurrence of deep convective profile types matches satellite-observed total lightning production, including to very small scall local features. Each location's "mix" of profile types provides an objective description of the local convective spectrum, and in turn, is a first step in objectively classifying convective regimes. These classifiers are tested as inputs to a neural network which attempts to predict lightning occurrence based on radar-only storm observations, and performance is compared with networks using traditional radar metrics as inputs.
While radar does not provide detailed begetation discrimination, it provide the means to separate areas of different moisture conditions. Thus, the use of LANDSAT Thematic Mapper (TM) in conjunction with the microwave data was attempted. If successful, information on shoreline cover, emergent wetland vegetation and extent, and submerged grassbeds would provide much needed data for planning and maintenance of wetlands. Originally, the goal was to determine the accuracy with which one could categorize various types of vegetation and land use within an inland wetland using LANDSAT TM data. First, a Level 1/2 supervised classification was performed. Following a more detailed ground trust survey, a Level 3 classification was done. Aircraft L-band radar data were received and the decision was made to merge the TM and L-band data and assess whether vegetation catagories within the wetland areas could be better defined. Preliminary results indicate vegetation delineation is improved for open agricultural areas and water, but other features are more confused.
We apply a technique developed in the field of vector quantization to the problem of unsupervised classification of radar imagery of wetlands.
This work investigates two machine learning techniques: Support Vector Machine (SVM) and Autoencoders (AE)with SVM layer for classification of radar trajectories as General Aviation (GA), fixed-wing small Unmanned Aerial System (sUAS), or not-an-aircraft using radar data recorded from sUAS. Onboard identification of intruder aircraft type is useful for planning avoidance maneuvers and is necessary to provide autonomous systems to meet or exceed the avoidance capability of a human pilot. Aircraft classification can identify intruder aircraft that are not part of the team and may be violating a Temporary Flight Restriction. Aircraft classification is needed in monitoring an airspace where multiple aircraft are teaming on a shared task. Scalable Traffic Management for Emergency Response Operations (STEReO) is a NASA project aimed at improving disaster response by enabling large scale aircraft operations through the teaming of manned aircraft with sUAS to maximize emergency response resources. To this end, this work uses trajectories and radar derived features to classify aircraft from a multirotor sUAS. The AE + SVM generated the strongest classification overall accuracy of 93.5% using the first 4 seconds of radar track data for tracks that activated the avoidance system. Subsampling the available track data increased the available training data with the maximum aircraft recall of 0.94 achieved using the SVM with 1 second track data.
Classification of synthetic aperture radar (SAR) images has important applications in geology, agriculture, and the military. A statistical model for SAR images is reviewed and a maximum likelihood classification algorithm developed for the classification of agricultural fields based on the model. It is first assumed that the target feature information is known a priori. The performance of the algorithm is then evaluated in terms of the probability of incorrect classification. A technique is also presented to extract the needed feature information from a SAR image; then both the feature extraction and the maximum likelihood classification algorithms are tested on a SEASAT-A SAR image.
The information content in polarimetric SAR images is examined, and the polarimetric image variables containing the information that is important to the classification of terrain features in the images are determined. It is concluded that accurate classification can be done when just over half of the image variables are retained. A reduction in image data dimensionality gives storage savings, and can lead to the improvement of classifier performance. In addition, it is shown that a simplified radar system with only phase-calibrated CO-POL or SINGLE TX channels can give classification performance which approaches that of a fully polarimetric radar.
Computer analysis of ERS-1 and RADARSAT ScanSAR narrow images of Great Lakes ice cover using a supervised classification technique indicates that different ice types in the ice cover can be identified and mapped and that wind speed and direction can have a strong influence on the backscatter from open water.
Scattering mechanisms identified via polarization signatures. Algorithm automatically classifies radar-backscattering mechanisms in images produced by synthetic-aperture-radar polarimeter. Uses full polarimetric data from each picture element. These data generally expressed in terms of complex 2 by 2 scattering matrix equivalent to three independent amplitudes and three independent phases representing relationships between horizontally- and vertically-polarized components of transmitted and backscattered signals.
NASA/JPL AIRSAR data were acquired over Minto Flats, Alaska on 18 July 1993. These data.
Explore the source record for details and available documents.
A preliminary study of the application of Doppler radar to the classification of birds is reported. The desirability for improvements in bird classification stems primarily from the hazards they present to jet aircraft in flight and in the vicinity of airports. A secondary need exists in the study of bird migration. The wing body and tail motion of a bird in flight reflect signals which, when analyzed properly present a signature of wing beat pattern which is unique for each bird species. Although the results of this investigation did not validate the feasibility of classifying bird species, they do indicate that a more thorough investigation is warranted. Certain gross characteristics such as wing beat rates, multiple bird patterns, and bird maneuverability, were indicated clearly in the results. Large birds with slow wing beat rates appear to be the most optimum subject for further study with the X-band Doppler radar used in this investigation.
Peculiarities of the radar information about clouds are examined in comparison with visual data. An objective radar classification is presented and the relation of it to the meteorological classification is shown. The advisability of storage and summarization of the primary radar data for regime purposes is substantiated.
Airborne radar data acquired with a 13.3 GHz scatterometer over a test-site near Colby, Kansas were used to investigate the statistical properties of the scattering coefficient of three types of vegetation cover and of bare soil. A statistical model for radar data was developed that incorporates signal-fading and natural within-field variabilities. Estimates of the within-field and between-field coefficients of variation were obtained for each cover-type and compared with similar quantities derived from LANDSAT images of the same fields. The classification accuracy provided by LANDSAT alone, radar alone, and both sensors combined was investigated. The results indicate that the addition of radar to LANDSAT improves the classification accuracy by about 10; percentage-points when the classification is performed on a pixel basis and by about 15 points when performed on a field-average basis.
NASA 13.3 GHz airborne radar data from a soil moisture measurement analysis is used to investigate the statistical nature of the radar backscattering coefficient for bare ground and three different crop types, and to evaluate the crop classification rates using Landsat data alone or combined with the airborne survey. The scatterometer was a fan-beam Doppler system, VV polarized, and is considered only for 50 deg angles of incidence. A total of 36 fields were covered a week apart by the aircraft and Landsat, and Rayleigh statistics were used in the frequency averaging to eliminate fluctuations due to random fluctuations. Within-field variances were calculated for the Landsat and the radar data and used to design optimum crop classification procedures. The Landsat Band 4 readings were 67% accurate, and an increase in accuracy of 10% was achieved by the addition of the radar data.