Classification Trees and Spatial Autocorrelation

I'm currently trying to model species presence / absence data (N = 523) that were collected over a geographic area and are possibly spatially autocorrelated. Samples come from preferential sites (sea level > 1200 m, obligatory presence of permanent waterbodies, etc). My main goal is to infere on environmental factors determining the occurrence rate of several (amphibian) species and to rule out spatial autocorrelation.

Use of Classification Trees to Investigate Traits of Invasive Species

Which traits make an alien species invasive?
Due to what traits an alien species becomes established in a foreign flora?


This kind of questions could be analysed by the use of recursive partitioning and classification trees..
(the below example also includes some useful data manipulation techniques)...