Abstract
In this chapter, we test whether the structural completeness (data stratified into structural layers-tree, shrub, herbaceous, epiphytes) in species-rich subtropical forests impacts on classification outcome. We manipulated a well-structured (multi-layered) data set by successive removing structural layers. We have found that the herbaceous layer (E1) and the epiphytic synusia (E0) do not play an important role in classification of the subtropical forests. Besides obligatory sampling the tree layer, it appears that sampling the complete shrub layers (E2 alpha and E2 beta) layers is crucial, both for classification as well as for production of functional expert system.
