The objective of this study was to use a set of orthorectified IKONOS satellite data to estimate aerial biomass in a semideciduous seasonal forest fragment located in Viçosa, state of Minas Gerais, Brazil. Estimates of above ground biomass were obtained with allometric equations based on forest inventory data conducted in fifteen 1,000 m² (20 m × 50 m) parcels. These estimates were related to digital variables (reflectance of four spectral bands and 12 vegetation indices) extracted from digital images using Artificial Neural Network (ANN). The results showed that for the conditions of the study area, the use of ANN with only bands 1, 2, 3 and 4 of the IKONOS satellite as input variables was efficient to estimate the total aerial biomass, although the residual was even lower when 4 bands and 12 vegetation indices were used.
remote sensing; biophysical parameter; semideciduous forest