Evaluating models to assess the distribution of Buxus balearica in southern Spain

Abstract

Question: Which is the best model to predict the habitat distribution of Buxus balearica Lam. in southern Spain? Location: Málaga and Granada, Spain, across an area of 38 180 km2. Methods: Prediction models based on 17 environmental variables were tested. Six methods were compared: multivariate adaptive regression spline (MARS), maximum entropy approach to modelling species' distributions (Maxent), two generic algorithms based on environmental metrics dissimilarity (BIOCLIM and DOMAIN), Genetic Algorithm for Rule‐set Prediction (GARP), and supervised learning methods based on generalized linear classifiers (support vector machines, SVMs). To test the predictive power of the models we used the Kappa index. Results: Maxent most accurately predicted the habitat distribution of B. balearica, followed by MARS models. The other models tested yielded lower accuracy values. A comparison of the predictive power of the models revealed that climate variables made the highest contributions among the environmental variables studied. The variables that made the lowest contributions were the insolation models. To examine the sensitivity of the models to a reduction in the number of variables, a test showed that accuracy of over 0.90 was maintained by applying just three climatic variables (spring rainfall, mean temperature of the warmest month, and mean temperature of the coldest month). Maps derived from the algorithms of all models tested coincided well with the known distribution of the species. Conclusions: Model habitat prediction is a preliminary step towards highlighting areas of high habitat suitability of B. balearica. These data support the results of previous research, which show that MaxEnt is the best technique for modelling species distributions with small sample sizes.

Current and potential distribution areas for Nothofagus alessandrii, an endangeredtree species from central Chile

“…Therefore, it is advisable to compare the efficiency and accuracy of the proposed model with others (e.g., MARS or CART models) (Navarro-Cerrillo et al, 2011). These models should be evaluated using more detailed information about N. alessandrii habitat.…”

“…To achieve these objectives, high-quality spatial information about land cover is necessary (Felicísimo, 2003;Navarro-Cerrillo et al, 2011). Predictive models are important tools that provide information that can be used for species conservation (Pearce and Ferrier, 2000).…”

“…These models can be used to achieve objectives such as biodiversity conservation and reduced fragmentation of forests by facilitating decision-making for conservation planning and restoration management (Navarro-Cerrillo et al, 2006). One example of a predictive model is a map of potential species distributions, which are theoretical zones defined by a hypotheticodeductive process (Navarro-Cerrillo et al, 2011) that are created by combining the use of GIS with multivariate mathematical models. The models can be generated through diverse techniques such as logistic regression, non-parametric classification and regression trees (CART) or multivariate adaptative regression splines (MARS) (Felicísimo, 2003).…”

Using ecological niche modeling to predict the distributions of two endangered amphibian species in aquatic breeding sites

“…Maxent, unlike other distributional modeling techniques, uses only presence and background data instead of presence and absence data. This method has been shown to perform well in comparison with alternative approaches (Elith et al, 2006;Hernandez et al, 2008;Navarro Cerrillo et al, 2011) and may remain effective even when the number of sites in which presence has been recorded is quite low (Hernandez et al, 2006;Papeş & Gaubert, 2007;Pearson et al, 2007;Wisz et al, 2008;Costa et al, 2010). Both Pearson et al (2007) and Hernandez et al (2006) suggest that reliable predictions with Maxent can be attained even when the number of sites in which presence is recorded is\10, and this presents positive implications for the scope of applying Maxent for predicting endangered species' distributions.…”

High probability areas for ASF infection in China along the Russian and Korean borders

“…MaxEnt has become the SDM tool of choice for animal distribution studies, including wild boar (Bosch, Mardones, Pérez, Torre, & Muñoz, ), bear (van Gils et al, ) and anthrax (Abdrakhmanov et al., ). Furthermore, MaxEnt provided a robust response independently of a number of selected variables of 5 or lower (Navarro‐Cerrillo, Hernández‐Bermejo, & Hernández‐Clemente, ; van Gils et al, ). Early MaxEnt studies did neither consider spatial autocorrelation of presence point data nor multi‐collinearity of environmental predictor variables.…”