A native soil dwelling insect pest, the redheaded cockchafer (Adoryphorus couloni) (Burmeister) (RHC) is an important pest in the higher rainfall regions of south-eastern Australia. Due to the majority of its lifecycle spent underground feeding on the roots and soil organic matter the redheaded cockchafer is difficult to detect and control. The ability to predict the level of infestation and location of redheaded cockchafers in a field may give producers the option to use an endophyte containing pasture or biological control agent in areas where it is most needed. Previous research has determined that data collected from soil, plant and topographic ground surveys has the ability to predict third instar RHC larvae infestations. The aim of the current research was to use a digital elevation model (DEM) obtained from a government website to determine whether it can be used to create predictive models for RHC population densities and in turn risk maps.  If predictive models using data only obtained from the DEM could be produced this may be a suitable alternative to farmers scanning their property with soil and plant sensors. To develop a predictive model three supervised classification trees were produced using a combination of sensor derived environmental variables. These variables included elevation, slope and flow accumulation calculated from a digital elevation model and apparent soil electrical conductivity obtained from an EM38 survey. Soil electrical conductivity was investigated to see if increased the predictive ability of the supervised classification tree. The best model based on a nearest neighbour accuracy of 82% used all the topographic attributes (elevation, slope and flow accumulation) derived from the digital elevation model.