Evaluation of species distribution model algorithms for fine-scale container-breeding mosquito risk prediction

Abstract

The present work evaluates the use of species distribution model (SDM) algorithms to classify high densities of small container-breeding Aedes mosquitoes (Diptera: Culicidae) on a fine scale in the Bermuda Islands. Weekly ovitrap data collected by the Department of Health, Bermuda for the years 2006 and 2007 were used for the models. The models evaluated included the algorithms Bioclim, Domain, GARP (genetic algorithm for rule-set prediction), logistic regression and MaxEnt (maximum entropy). Models were evaluated according to performance and robustness. The area under the receiver operating characteristic curve was used to evaluate each model's performance, and robustness was assessed according to the spatial correlation between classification risks for the two datasets. Relative to the other algorithms, logistic regression was the best and MaxEnt the second best model for classifying high-risk areas. We describe the importance of covariables for these two models and discuss the utility of SDMs in vector control efforts and the potential for the development of scripts that automate the task of creating risk assessment maps.