 This study examined a method to classify 7 tropical rainforest tree species from full range for 100 to 2500 nanometers, hyperspectral data collected at leaf, bark, and crown levels. The researchers developed metrics based on narrowband indices, derivative and absorption based techniques, and spectral mixture analysis. These metrics were then used to train a random forest classifier which achieved high accuracy rates when applied to both tissue and crown spectra. The study found that variation in tissue metrics was best explained by an axis of red absorption related to photosynthesis and another axis distinguishing bark water and other chemical absorptions. Additionally, the study noted that tree structure and phenology at the time of imaging affected the ability to distinguish between species. This article was authored by Dar A. Roberts and Matthew L. Clark.