Data Mining Using NDVI Time Series Applied to Change Detection

Information about the land cover and land use of a region are fundamental in studies such as mapping of deforestation and forest degradation. Quantifying and monitoring woody cover distribution in semiarid regions is challenging, due to their scattered distribution. Data mining has been widely used in remote sensing data for information extraction of spectral and temporal data in the analysis of change detection. The main objective of this study was to characterize the land cover and land use over 2000-2010 time period for the Brazilian Caatinga seasonal biome using a temporal NDVI series and Geographic Object-Based Image Analysis. For each of the target years was obtained NDVI images derived from MODIS (MOD13Q1, at 250 m spatial and 16 day temporal scale) sensor during the dry season to predict wood cover in the municipality of Buriti dos Montes, in the state of Piauí, Northeast region of Brazil (H13V09 tile). The images were automatically pre-processed and in the GEOBIA approach was performed image segmentation, spatial and spectral attribute extraction and labelled according to the following legend: Tree Cover (TC) and Cropland/Grass (CG), to obtain a classification using the decision tree supervised algorithm. Our results showed that approach using GEOBIA presented Kappa Index of 0.58 and Global Accuracy (GA) of 0.81% and showed better accuracy for the Tree Cover. Finally, we recommend new studies using a higher spatial resolution data, as well as the addition of other parameters strongly related to vegetation of semiarid regions.