Fig. 2 (a) Variable importance of seven environmental factors in modeling potential distributions of A. annua with 10 different species distribution models. (b) Response curves of BIO9 (mean temperature of driest quarter) for each algorithm in modeling potential distribution of A. annua. The 10 species distribution models were Artificial Neural Network (ANN), Classification Tree Analysis (CTA), Flexible Discriminant Analysis (FDA), Generalized Additive Model (GAM), Generalized Boosting Model (GBM), Generalized Linear Model (GLM), Multiple Adaptive Regression Splines (MARS), Maximum Entropy (MAXENT), Random Forests (RF) and Surface Range Envelop (SRE). The seven environmental factors were altitude (ALT), Mean Diurnal Range (Mean of monthly (max temp - min temp)) (BIO2), Mean Temperature of Wettest Quarter (BIO8), Mean Temperature of Driest Quarter (BIO9), Precipitation Seasonality (Coefficient of Variation) (BIO15), Precipitation of Warmest Quarter (BIO18), Precipitation of Coldest Quarter (BIO19).