A predictive understanding of the environmental controls on forest distributions is essential for the conservation of biodiversity and management of landscapes in the tropics. This is particularly true now because of potentially rapid climate change. The floristic complexity of tropical forests and the lack or absence of data severely limits the applicability of modelling methods based on the ecology or distribution of individual species. Here we present an artificial neural network (ANN) model using the information available in the humid tropics of North Queensland: a structural classification of forest types, maps of the forest mosaic, and estimates of spatial environmental variables.
The ANN model characterizes the relative suitabilities of environments for 15 forest classes defined by their physiognomy and canopy structure. Inputs include seven climate variables, nine soil parent-material classes, and seven terrain variables. The data used to train the model consisted of a stratified random sample of 75000 points. Output of the model is used to measure the dissimilarity between the environment at each location and the environment that would be most suitable for the forest type that is mapped there.
The model is highly successful at distinguishing the relative suitability of environments for the forest classes with 75% of the region's forest mosaic accurately predicted by the model at a one hectare resolution. In contrast, a comparable maximum likelihood classification has an accuracy of only 38%. In the remaining 25% of the region the environments are quite dissimilar to what would be expected for the forest types present there. This is especially the case at boundaries between forest classes and for a transitional forest class. Areas mapped as this disturbed, transitional class are generally classified by the model as having environments suitable to the forest type they are most likely to become.
The approach has high potential for the analysis of climate change impacts as well as inferring vegetation patterns in the past and should be applicable wherever vegetation maps and spatial estimates of climate variables are available.