%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.15.52.46
%2 sid.inpe.br/marte2/2017/10.27.15.52.47
%@isbn 978-85-17-00088-1
%F 59750
%T Utilização de regressão linear em séries temporais landsat-5 na identificação de desmatamento no município de São Miguel do Araguaia-GO entre 2002 e 2011
%D 2017
%A Oliveira, Bernard Silva de,
%A Carvalho, Helber de,
%A Miyashita, Priscila Midori,
%A Alves, Raissa Daher,
%A Cristóvão, Carlos Antônio de Melo,
%@electronicmailaddress bernard-so@segplan.go.gov.br
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%B Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)
%C Santos
%8 28-31 maio 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 6655-6662
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The Cerrado Biome has suffered intense degradation in the last decades. The State of Goiás, a component of the biome, had its vegetation affected by degradations motivated by agriculture and pasture, with an emphasis on the economic aspect. The use of satellite data associated with Geographic Information Systems has positive experiences in the monitoring of deforestation, and for this reason it is adopted in national research institutions. From this, this work aims to identify areas in the municipality of São Miguel do Araguaia-GO that have undergone deforestation between 2002 and 2011 by means of linear regression in NDVI temporal images of the TM sensor on board the Landsat-5 satellite. The adopted method applies a linear regression in the temporal images of NDVI, extracting the slope of each value of the pixel in relation to the posterior year. Three slope values were defined: 5, 10 and 15 degrees, representing the degrees of sensitivity of the vegetation cover change. It was verified that the value of 5º obtained greater sensitivity of alteration of the vegetation cover of low to high tree density. In the validation, this method obtained an overall precision of 83.13%, 72.18%, 50.9%, 47.62% respectively between 2008 and 2011 done in the value of 5º of slope. In the comparison with another mapping method, such as the Brazilian Biome Deforestation Monitoring Project (PMDBBS), it was verified that the overall accuracy was 66.67% and the Kappa index of 0.3, being therefore suitable for the detection of tree changes. The proposal may be relevant to accompany the transformations in a biome like the Cerrado, which has a great diversity of forest cover.
%9 Degradação de florestas
%@language pt
%3 59750.pdf