ENM can simulate the potential distribution areas of species based on their actual geographical distribution data and related environmental variables. Currently, the primary algorithms of ENM include Generalized Linear Models (GLM), Gradient Boosting Machines (GBM), Classification Tree Analysis (CTA), Artificial Neural Networks (ANN), one Rectilinear Envelope Similar to BIOCLIM (SRE), Flexible Discriminant Analysis (FDA), Random Forests (RF), and Maximum Entropy Models (MaxEnt), among others. However, when predicting the potential distribution areas of species, a single algorithm model often lacks stability and exhibits relatively large biases. In contrast, ensemble model such as biomod2 (v4.2–5–2, https://CRAN.R–project.org/package=biomod2) R package built on multiple algorithms tend to perform better. Therefore, the species distribution models used in current species distribution studies are gradually shifting from single models to ensemble models (Araujo & New, 2007).