3.1 MaxEnt model evaluation
Table S1 . Evaluation results of MaxEnt model under different parameter settings.
The MaxEnt model was used to simulate the potential distribution area of PWD in China. When the model is the default parameter, RM = 1, FC of operation are H and L; and RM = 0.5, FC = LQHPT, delta, and AICc = 0, the model is optimal (Table S1). Therefore, FC = LQHPT and RM = 0.5 were set as modeling parameters (Fig.2). The optimized parameters were used to remodel and simulate the suitable area of PWD in China. The model was repeated 10 times, and the training data of AUC were 0.940, indicating that the prediction results of the MaxEnt model were accurate (Fig.S1).
Fig. 2. Evaluation metriies of MaxEnt model generated by ENMeval
Fig.S1. ROC response curve under the MaxEnt model.