No description available.

The Army National Guard Bureau has implemented a cooperative project with Utah State University to help with the use, display, and evaluation of environmental data for maintaining land condition. Camp Grayling, Michigan, is comprised of deciduous and evergreen forest types. Use of remote sensing for classification has been limited in this region due to the difficulty of species-level classification using single-date remote-sensing techniques . Also, remote sensing has traditionally focused on mapping homogenous zones rather than vegetation boundaries, while one of the concerns for land managers is the nature of vegetation edges (ecotones). This study analyzed each season and band from multiseasonal satellite imagery for their contribution to separating vegetation type and density classes. Then spectral reflectance values for each vegetation and density class were used in discriminant models that define vegetation cover types and densities. These models were then tested against points within 200 m of vegetation boundaries to determine the performance of the models at edges of vegetation types . The reflectance values for vegetation types on Landsat Thematic Mapper (TM), Landsat MultiSpectral Sensor (MSS), and Advanced Very High Resolution Radiometer (AVHRR) imagery were used. Single-band separability decreased with decreasing resolution of the remote sensing data, and the number of spectral bands that could separate means of vegetation and density cover classes was much greater than expected . Winter bands provided more separability than expected for density classes . A VHRR data were shown to provide very little separation and were not included in the discriminant analysis. In the evaluation of the discriminant models, both resubstitution and crossvalidation tests showed that TM and MSS were nearly equal in their ability to discriminate cover types and densities. At the vegetation boundary zones, classification accuracy increased with increasing distance from the edge. These results are encouraging for future classification and monitoring of ecotones using satellite imagery, as picture elements (pixels) of ecotones generally exhibit the characteristics of a mixing of the boundary vegetation types. Further investigation into fuzzy set classification and ecotone classification and monitoring appears warranted.

Made available in DSpace on 2017-07-21T14:19:37Z (GMT). No. of bitstreams: 1 Cristian Abreu.pdf: 2219271 bytes, checksum: 3d770700a8027fff9a36f6287c8c4e54 (MD5) Previous issue date: 2013-04-30 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / The objective of this study was investigate the use of parallel computing to reduce the response time of data mining in agriculture. For this purpose, a tool, called Fast Weka been defined and implemented. This tool allows running data mining algorithms and explore parallelism in multi-core computers with the use of threads and distributed systems employing peer-to-peer networks. The exploration of parallelism occurs through the data parallelism inherent to the process of cross-validation (folds). The tool was evaluated through experiments using artificial neural networks data mining algorithms applied to a data set of forest cover types. The multi-thread computing and computing on peer-to-peer networks allowed to reduce the response time of data mining activities. The best results were achieved when employed a multiple number of threads or pairs in the number of folds of cross validation. It was observed and efficiency of 87% when used 4 threads to 24 folds and 86% efficiency also in peer-to-peer networks using 24 folds with 11 pairs. / O objetivo deste trabalho foi investigar a utilização da computação paralela para reduzir o tempo de resposta da mineração de dados na agricultura. Para esse fim, uma ferramenta, chamada Fast Weka foi definida e implementada. Essa ferramenta permite executar algoritmos de mineração de dados e explorar o paralelismo em computadores multi-núcleos com uso de threads em sistemas distribuídos empregando redes peer-to-peer. A exploração do paralelismo ocorre por meio do paralelismo de dados inerente ao processo de validação cruzada (folds). A ferramenta foi avaliada por meio de experimentos de mineração de dados utilizando algoritmos de redes neurais artificiais aplicados em um conjunto de dados de tipos de coberturas florestais. A computação multi-thread e a computação em redes peer-to-peer permitiram reduzir o tempo de resposta das atividades de mineração de dados. Os melhores resultados foram obtidos quando empregados um número múltiplo de threads ou pares em relação ao número de folds da validação cruzada. Observou-se uma eficiência de 87% quando utilizadas 4 threads para 24 folds e 86% de eficiência, também, com 2 folds utilizando redes peer-to-peer co 11 pares.