OBJECTIVE To explore the potential geographic distribution of Pinellia Ternata (Thunb.) Breit. in Gansu province, clarify its habitat requirements, and provide a theoretical basis for rational cultivation.

METHODS Based on 100 geographic distribution points of Pinellia Ternata (Thunb.) Breit. and 39 environmental variables (including 19 bioclimatic variables, 17 soil variables and 3 topographic variables), the maximum entropy model(MaxEnt) and ArcGIS geographic information system software were used to make the habitat suitable for its evaluation and classification of suitable areas, the result of Jackknife test was used to evaluate the environmental variables that affect the habitat of Pinellia Ternata (Thunb.) Breit., the area under the ROC curve(AUC) was used to evaluate the degree of reliability of the prediction results.

RESULTS The AUC was 0.993, indicating that the prediction results of the MaxEnt model were reliable. Monthly average daily temperature difference, isotherm, standard deviation of seasonal variation of temperature, annual precipitation, the wettest month precipitation, the driest month precipitation, the driest season precipitation, the coldest season precipitation and altitude were the main environmental variables affecting the growth of Pinellia Ternata (Thunb.) Breit.. The suitable areas for Pinellia Ternata (Thunb.) Breit. in Gansu were mainly concentrated in Longnan, Tianshui and Pingliang, where the areas of high, medium and low suitable areas were 16 180.4, 15 413.96, 21 204.84 km², respectively.

CONCLUSION The research results can provide a theoretical reference for the protection and standardized cultivation of Pinellia Ternata (Thunb.) Breit. resources.