A decision tree approach modelling functional group abundance in a pasture ecosystem

Decision tree, one of the data mining approaches, was used to model the relative abundance of five functional groups of plant species, namely high fertility response grasses (HFRG), low fertility tolerance grasses (LFTG), legume, moss and flatweeds in a New Zealand hill-pasture ecosystem using aboveground biomass. The model outputs were integrated with a geographic information system (GIS) to map and validate the predictions on a pasture. The decision tree models clearly revealed the interactions between the functional groups and environmental and management factors, and also indicated the relative importance of these factors in influencing the functional group abundance. Soil Olsen P was the most significant factor influencing the abundance of LFTG and moss, while soil bulk density, slope and annual P fertiliser input were the most significant factors influencing the abundance of legume, HFRG and flatweeds, respectively. Generally, slope and soil Olsen P were the two key factors underlying the patterns of abundance for these five functional groups. For the five functional groups studied, there was an overall predictive accuracy of 75%. Modelling functional group abundance simplified the investigation of the complex interrelationship between species and environment in a pasture ecosystem. The integration of the decision tree with GIS in this study provides a platform to investigate community structure and functional composition for a pasture over space, and thus can be applied as a tool in pasture management.