Table 1. Boosted regression tree model.

Summary of the relative contributions (%) of predictor variables (tree and shrub species abundance) developed with cross validation on data using 1400 trees, tree complexity of 2 and learning rate of 0.004.

Variable	Relative influence (%)
Xanthorrhoea johnsonii	38.3
Corymbia trachyphloia	27.4
Allocasuarina torulosa	15.5
Elaeocarpus reticulatus	11.2
Eucalyptus montivaga	7.6