Use of Geospatial Methods to Characterize Dispersion of the Emerald Ash Borer in Southern Ontario, Canada

Since the introduction of the Asian Emerald Ash Borer beetle (EAB, Agrilus planipennis) to Southern Ontario in 2002, the condition of all species of Ash trees (Fraxinus) in the province is currently at risk. In this research, the effects of positive spatial autocorrelation on the EAB data as a result of sampling bias was addressed by applying a filtering distance threshold. To analyze the impact of environmental and anthropogenic predictors on the distribution of the EAB, logistic regression, Random Forest (RF) and a hybrid of Random Forest and GLM known as the Random Generalized Linear Model (RGLM) were applied to EAB data from 2006-2012 across Ontario. Ultimately, three risk maps were created from the 2006-2012 EAB data to validate the prediction dataset from 2013. In terms of model transferability, RGLM had the best extrapolation accuracy (84%), followed by stepwise backward logistic regression (70%), and Random Forest (52%).