Classificadores de SIG aplicados na análise temporal da bacia hidrográfica do Rio São Francisco Verdadeiro – Oeste do PR
The techniques of geoprocessing have become indispensable tools in the accomplishment of studies directed to the analysis of the use and coverage of the soil of watersheds. Using satellite images, these systems make it possible to carry out field surveys with a high degree of accuracy. Based on this...
Autor principal: | Amaral, Camila Zeni do |
---|---|
Formato: | Trabalho de Conclusão de Curso (Graduação) |
Idioma: | Português |
Publicado em: |
Universidade Tecnológica Federal do Paraná
2020
|
Assuntos: | |
Acesso em linha: |
http://repositorio.utfpr.edu.br/jspui/handle/1/12536 |
Tags: |
Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
|
Resumo: |
The techniques of geoprocessing have become indispensable tools in the accomplishment of studies directed to the analysis of the use and coverage of the soil of watersheds. Using satellite images, these systems make it possible to carry out field surveys with a high degree of accuracy. Based on this, this work has as main objective to evaluate the performance of Geographic Information System (GIS) classifiers applied in the temporal analysis of the São Francisco Verdadeiro River Basin, which is located in southern Brazil and west of the state of Paraná . Being considered a basin with area of 2,219,19 km², it has total or partial influence in 11 municipalities of the West of Paraná. Landsat images 5 and 8 of August 2005 and August of 2015 were used to map the use and cover of the soil, which were worked in the SPRING software, using the Maxver and Bhatacharya (Supervised) and Isoseg (Unsupervised). The evaluation of the classifications was based on the mathematical proof of the results from the automatic generation of the classification confusion matrix followed by the use of the Kappa Index. The three classifiers presented similar performance for both dates, however, the Bhattacharya classifier was more efficient. The results showed that in the interval between 2005 and 2015 there were no significant changes in the landscape configuration of the basin, confirming the agricultural profile of the region. |
---|