Abstract
Species distribution modelling (SDM) is a family of statistical methods where species occurrence/density/richness are combined with environmental predictors to create predictive spatial models of species distribution. However, it often turns out that due to complex multi-level interactions between predictors and the response function, different types of models can detect different numbers of important predictors and also vary in their predictive ability. This is why we decided to explore differences in the predictive power of two most common methods, such as the Generalised Additive Model (GAM) and the Random Forest (RF) on the example of the Great Spotted Woodpecker Dendrocopos major and the Great Grey Shrike Lanius excubitor, as well as on the taxonomic and functional species richness. For each of the two bird species’ densities and for two measurements of biodiversity, two sets of SDMs were generated: One based on the GAM, and the other on the RF. According to the out-of-bag, the Akaike Information Criterion (AIC) and an independent evaluation, we demonstrated that the GAM is the best method for predicting density of the Great Spotted Woodpecker and taxonomic species richness, whereas the RF has the lowest prediction error for the density of the Great Grey Shrike and functional species richness. It also becomes apparent that the GAM is responsive to taxonomic species richness and species with broad tolerance to environmental factors, i.e. the Great Spotted Woodpecker, while the RF detects more subtle relationships between density and environmental variables, rendering it more suitable for functional species richness and species with a narrow tolerance range to habitats factors, i.e. the Great Grey Shrike. Thus, effective predictive modelling of animal distribution requires considering several different analytical approaches to produce biologically realistic predictions.
Highlights
Predicting species distributions on the basis of species distribution modelling (SDM), often referred to as “predictive mapping”, has become a tool which is widely used in macroecological studies, research on niche evolution, interactions and co-evolution of species, and in planning conservation areas (Warren et al 2008; Esselman and Allan 2011; Drew et al 2011; Fourcade et al 2017)
Our results are consistent with both of the above conclusions, because we found that the Generalised Additive Model (GAM) was the best method for the Great Spotted Woodpecker density and bird species richness, whereas the Random Forest (RF) had the highest predictive power for the Great Grey Shrike and functional species richness
The study shows that the effectiveness of different Species Distribution Modelling methods depends on the ecology of the studied species
Summary
Predicting species distributions on the basis of species distribution modelling (SDM), often referred to as “predictive mapping”, has become a tool which is widely used in macroecological studies, research on niche evolution, interactions and co-evolution of species, and in planning conservation areas (Warren et al 2008; Esselman and Allan 2011; Drew et al 2011; Fourcade et al 2017). From the analytical point of view, the SDM is a group of statistical tools based on ecological niches theory, which describe non-linear relationships between species occurrence/density/richness and environmental layers in order to build statistical models which reflect processes that drive species distribution on a large geographical scale (Guisan and Zimmermann 2000; Elith and Leathwick 2009; Franklin 2010). Such models, projected in space or time, can predict species occurrence and density, range shifts under climate and habitat changes (Hijmans and Graham 2006), and evaluate biodiversity surrogates and estimate invasive species distribution (Jimenez-Valverde et al 2011). Predictive occurrence of the European grayling (Thymallus thymallus L.) was provided by a number of different predictors coming from different models (Fukuda et al 2013)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
