Applying various algorithms for species distribution modelling


Correspondence: Xinhai Li, Key Laboratory of the Zoological Systematics and Evolution, Institute of Zoology, Chinese Academy of Sciences, 1 Beichen West Road, Beijing 100101, China. Email:


Species distribution models have been used extensively in many fields, including climate change biology, landscape ecology and conservation biology. In the past 3 decades, a number of new models have been proposed, yet researchers still find it difficult to select appropriate models for data and objectives. In this review, we aim to provide insight into the prevailing species distribution models for newcomers in the field of modelling. We compared 11 popular models, including regression models (the generalized linear model, the generalized additive model, the multivariate adaptive regression splines model and hierarchical modelling), classification models (mixture discriminant analysis, the generalized boosting model, and classification and regression tree analysis) and complex models (artificial neural network, random forest, genetic algorithm for rule set production and maximum entropy approaches). Our objectives are: (i) to compare the strengths and weaknesses of the models, their characteristics and identify suitable situations for their use (in terms of data type and species–environment relationships) and (ii) to provide guidelines for model application, including 3 steps: model selection, model formulation and parameter estimation.