The assessment of vegetation seasonal dynamics using multitemporal NDVI and EVI images derived from MODIS

The objectives of this work were to characterize seasonal dynamics of cerrado, deciduous and semideciduous forests in the north of Minas Gerais, Brazil. Time series of NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index) derived from MODIS (MODerate-resolution Imaging Spectroradiometer) sensor, were compared by analyzing temporal profiles and image classification results. The results showed that: (1) there is an agreement between vegetation indices and the monthly precipitation pattern; (2) deciduous forest showed the lowest values and the highest variation; (3) cerrado and the semideciduous forest presented higher values and lower variation; (4) according to the paired Student's test there was a significant difference between the NDVI and EVI values (5) the NDVI showed higher values than the EVI; (6) based on the classification accuracies the best vegetation index for mapping the vegetation classes in the study area was the NDVI, however both indices might be used to assess the vegetation seasonal dynamic; and (7) further research need to be carried out exploring the use of feature extraction algorithms to improve classification accuracy of cerrado, semideciduous and deciduous forests in Minas Gerais, Brazil.