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 density of small container Aedes mosquitoes at a fine scale, in the Bermuda islands. Weekly ovitrap data collected by the Health Department of Bermuda (UK) for the years 2006 and 2007 were used for the models. The models evaluated included the following algorithms: Bioclim, Domain, GARP, logistic regression, and MaxEnt. Models were evaluated according to performance and robustness. The area Receiver Operating Characteristic (ROC) curve was used to evaluate each model’s performance, and robustness was assessed considering the spatial correlation between classification risks for the two datasets. Relative to the other algorithms, logistic regression was the best model for classifying high risk areas, and the maximum entropy approach (MaxEnt) presented the second best performance. We report the importance of covariables for these two models, and discuss the utility of SDMs for vector control efforts and the potential for the development of scripts that automate the task of creating risk assessment maps.

Comparing Selections of Environmental Variables for Ecological Studies: A Focus on Terrain Attributes

“…When used, bathymetry and two of the backscatter derivatives (Q1 and Q2) contributed the most to the models, with a respective average of 39.2%, 25.4% and 19.6% for the 15 models that used them. Bathymetry contributed less to the models that include local mean as input, resulting from the high collinearity between these two variables; when two variables are correlated, MaxEnt is known to assign a more important percentage contribution to one of the two and a lower one to the other [28]. Consequently, local mean is a surrogate of bathymetry and appears as an important variable, with an average contribution of 51.2% for the 12 models that include it.…”

“…Such a model is too specific to the training data and less generalizable. A diagnostic of the input variables contribution to the different models was also performed based on the results from the jackknife procedure, in order to identify the loss or gain in explanatory power as each variable is removed from the models or used alone [28]. Finally, a spatial comparison of the models was performed to evaluate the consequences of variable selection on the model outputs.…”

Habitat suitability and protection status of four species of amphibians in the Dominican Republic

“…SDMs have been used at length for the evaluation of species habitat and determination of species geographic ranges, in order to facilitate conservation planning and resource management (Carroll, Dunk, & Moilanen, 2010;Corbal an, Tognelli, Scolaro, & RoigJuñent, 2011;Ferrier, 2002;Leathwick et al, 2008;Loiselle et al, 2003); and for the evaluation of invasive species' spread and diseases mapping (Jim enez-Valverde et al, 2011;Khatchikian, Sangermano, Kendell, & Livdahl, 2011;MachadoeMachado, 2012;Shatz, Rogan, Sangermano, Ogneva-Himmelberger, & Chen, 2013;V aclavík & Meentemeyer, 2009). The maximum entropy (Maxent) species distribution modeling method (Phillips, Anderson, & Schapire, 2006); is a use-availability species distribution model that needs species presence and background (environmental availability) data to extract and project species responses to environmental gradients.…”

Mapping of Aedes albopictus Abundance at a Local Scale in Italy

“…albopictus based on occurrence data, i.e., presence only or presence-absence data, and have produced suitability maps at a global scale that do not fit well with the scale at which surveillance and control measures may be implemented [7,12]. On the contrary, maps at a local scale should be promoted to stakeholders and policy makers [7,13]. The identification of areas highly infested by Ae.…”