Reducing Leaf-Level Hyperspectral Data to 22 Components of Biochemical and Biophysical Bands Optimizes Tree Species Discrimination

The high dimensionality of hyperspectral data constitutes a challenge for species classification. This study assessed 1) whether tree species classification can be optimized with the selection of bands which relate to known plant properties and 2) whether a partial least square (PLS) transformation improve species classification above principal component analysis (PCA). Leaf spectra between 400 and 2500 nm were measured for six evergreen tree species in the spring of 2011, in the KwaZulu-Natal Province of South Africa. Twenty-two bands which relate to pigment, foliage biomass, nutrients, and leaf structural components were selected from the hyperspectral data set. The 2100 bands of 1 nm were resampled to 421 bands at 5 nm spectral resolution, ensuring the number of variables are less than the number of samples. The random forest (RF) classification algorithm was used to assess the accuracy for both PCA and PLS transformations on the 421 and 22 bands. The accuracy of individual species classes was calculated as the average of ten iterations, for each data reduction option. The three 22-band models resulted in comparable accuracies to the 421-band classifications (OA of 84 ± 4.9% for untransformed, 78 ± 5% for PCA, and 84 ± 4% for PLS) and no significant differences between the 421 and 22-band models (p > 0.4). The optimized PLS model (22 bands, 8 components) showed a 6% (p <; 0.01) increase in accuracy above the optimized PCA model (22 bands, 3 components). Reducing hyperspectral data to bands which relate to plant properties, and the use of PLS for data transformation, optimizes species classification.