Identificação de áreas queimadas por meio de índices espectrais em regiões do cerrado tocantinense

Abstract

Obtaining information on burned areas has been studied and improved in the last decades, and the biggest question is to acquire consistent and detailed information about the occurrence of burnings in a simple and effective way. In view of this remote sensing is a very interesting tool because it allows obtaining information in large areas and difficult to access. The identification of the areas burned by orbital data is directly related to their spectral behavior. The objective of this work was to analyze the performance of spectral indices in the identification of burned area in OLI / Landsat-8 satellite images to three areas of tocantinense Cerrado. For this the indexes for the before and after fire images were calculated, using bands of red and near infrared: NDVI, MSAVI, SAVI, GEMI and bands of near infrared and short wave infrared: NBR, BAIMmod, MIRBImod, as well as to calculate the difference between pre and post-fire index: dNDVI, dMSAVI, dSAVI, dGEMI, dNBR, dBAIMmod and dMIRBImod. From these indices, six different compositions (RGB) were created and later they were segmented and classified in a supervised way and soon after the extraction of the area of interest. The results of this classification were validated with the reference data obtained through the visual interpretation of the image, where the methods showed a great similarity between them, has been a small difference in performance of methods in the areas estudieds, wuth percentage of accuracy ranging from 65,83 to 83,01% to area 1, to area 2 from 62,9 to 76,3% and in the area 3 from 85,54 a 92,46% and according Kappa value, the performance of methods is classified form very good to excellent.