Tecomella undulata under threat: The impact of climate change on the distribution of a valuable tree species using a machine learning model

PLOS One | https://doi.org/10.1371/journal.pone.0326609 July 9, 2025 5 / 18 To prevent model overfitting and multicollinearity between variables, we calculated the variance inflation factor (VIF) between the bioclimatic variables and DEM. We used the usdm package [43] and a threshold of 0.8 was set for VIF and removed highly correlated variables [44]. The remaining seven variables were Mean Diurnal Range (BIO2), Isothermal- ity (BIO3), Temperature Seasonality (BIO4), Mean Temperature of Wettest Quarter (BIO8), Mean Temperature of Driest Quarter (BIO9), Precipitation of Driest Month (BIO14), Precipitation Seasonality (BIO15), Precipitation of Coldest Quarter (BIO19) and DEM. Fig 1. The study area and occurrence points of Desert teak. Map was generated using QGIS 3.4.1 (https://www.qgis.org). https://doi.org/10.1371/journal.pone.0326609.g001