Table 2 Predictive models from machine learning (RF, SVM, and BRT), regression (GAM and GLM), and profile (bioclim) methods and their short description and common pieces of literature that have used these models in modelling invasive species distribution

Random Forest (RF)

RF (Breiman 2001), a combination of tree predictors, is the most commonly used machine learning algorithm (Abdi 2020). It is an effective method for predicting species richness and density (Kosicki 2020).

Früh et al. (2018); Mi et al. (2017); Ng et al. (2018); West et al. (2017)

Support Vector Machine (SVM)

SVM (Cortes and Vapnik 1995) is characterized by its ability to generalize features. It can be used for classification and regression-based studies.

Abdi (2020); Früh et al. (2018); Ng et al. (2016)

Boosted Regression Trees (BRT)

Like RF, BRT is based on a combination of a relatively small number of trees to increase the performance of predictive variables (Elith et al. 2008). It has also the capacity to process several predictors at high predictive accuracy (Gu et al. 2019).

Guisan et al. (2007); West et al. (2017)

Generalized Additive Model (GAM)

GAM is a popular regression model and is extensively used in ecological studies for modelling non-normal distributions (Ravindra et al. 2019).

Guisan et al. (2007); Soultan and Safi (2017)

Generalized Linear Model (GLM)

GLM can process and manage non-linear data structures. Its flexibility makes it better suited for ecological-based studies (Guisan et al. 2002).

Guisan et al. (2007); Soultan and Safi (2017); West et al. (2017)

Bioclim

Bioclim was the earliest SDM package used in many ecological studies including invasive species prediction (Booth et al. 2014).

Guisan et al. (2007); Hernandez et al. (2006); Reiss et al. (2011)