Forest Classification: Data-Analytical Experiments on Vertical Forest Layering and Flattened Data

Warning

This publication doesn't include Institute of Computer Science. It includes Faculty of Science. Official publication website can be found on muni.cz.

Authors	MUCINA Ladislav TICHÝ Lubomír
Year of publication	2018
Type	Chapter of a book
MU Faculty or unit	Faculty of Science
Citation
Description	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.
Related projects:	Next generation expert systems for vegetation classification on a continental scale