Mapping environmental variation in lowland Amazonian rainforests using remote sensing and floristic data

Abstract

This article describes a method for detailed mapping of ecological variation in a tropical rainforest based on field inventory of pteridophytes (ferns and lycophytes) and remote sensing using Landsat Enhanced Thematic Mapper Plus (ETM+) imagery. Previously known soil cation optima of the pteridophyte species were first used in calibration, i.e. to infer soil cation concentrations for sites on the basis of their pteridophyte species com- position. Multiple linear regression based on spectral reflectance values in the Landsat image was then used to derive an equation that allowed the prediction of these cali- brated soil values for unvisited sites in the study area. The predictive accuracy turned out to be high: the mean absolute error, as estimated by leave-one-out cross-validation, was just 7% of the total range of calibrated soil values. This method for detailed map- ping of natural environmental variability in lowland tropical rainforest has applications for land-use planning, such as wildlife management, forestry, biodiversity conservation, and payments for carbon sequestration.