Mixtures of airborne lidar-based approaches improve predictions of forest structure

Abstract

The most common method for modeling forest attributes with airborne lidar, the area-based approach, involves summarizing the point cloud of individual plots and relating this to attributes of interest. Tree- and voxel-based approaches have been considered as alternatives to the area-based approach but are rarely considered in an area-based context. We estimated three forest attributes (basal area, overstory biomass, and volume) across 1680 field plots in Arizona and New Mexico. Variables from the three lidar approaches (area, tree, and voxel) were created for each plot. Random forests were estimated using subsets of variables based on each individual lidar approach and mixtures of each approach. Boruta feature selection was performed on variable subsets, including the mixture of all lidar-approach predictors (KS-Boruta). A corrected paired t test was utilized to compare six validated models (area-Boruta, tree-Boruta, voxel-Boruta, KS-Boruta, KS-all, and ridge-all) for each forest attribute. Based on significant reductions in error (SMdAPE), basal area and biomass were best modeled with KS-Boruta, while volume was best modeled with KS-all. Analysis of variable importance shows that voxel-based predictors are critical for the prediction of the three forest attributes. This study highlights the importance of multiresolution voxel-based variables for modeling forest attributes in an area-based context.