ABOVEGROUND BIOMASS ESTIMATION IN THE BRAZILIAN AMAZON USING COMBINED LIDAR AND HYPERSPECTRAL DATA

Active Light Detection And Ranging (LiDAR) and passive Hyperspectral Imaging (HSI) remote sensing provide complementary information that can be combined to improve the estimation of vegetation properties, such as aboveground biomass (AGB). Thus, the main objective of this study is to evaluate the combined use of LiDAR and HSI data for estimating AGB in the Brazilian Amazon, by using six regression methods, a high range of remote sensing metrics, and feature selection. To assess the prediction ability of the remote sensing data, single and combined LiDAR and HSI metrics were regressed against AGB from 147 sample plots across the Brazilian Amazon Biome. Overall, the results showed a similar model performance for both LiDAR and HSI single datasets, and for the regression methods used. However, the combination of LiDAR and HSI data improved the AGB estimation accuracy.