Abstract: The purpose of this paper is to explore the relationship between the distribution of field songs in Hubei and the geographic environment in which the field songs are nurtured, with a view to providing new ideas and methods for empirical research on regional music． This study takes Hubei Tiange as the research object, selects 1248 sample data sets of Tiange, uses Geographic Information System (GIS) to build a database of the distribution of the preliminary selected Tiange and the influencing factors of the music elements, and constructs an analytical model of the system of influencing factors of the Tiange based on the Random Forest and Shapley Additive exPlanations (SHAP) interpretable algorithms, and evaluates the validity of the model through the Receiver Operating Characteristic (ROC) curve, to analyze the distribution of the Tiange, the relationship between the music elements and the geographic environment． And analyze the relationship between the distribution of Tian songs, music elements and geographic environment． The results of the study show that: (1) the model of the influence factor system of field songs constructed based on the random forest has a good prediction effect, and its Area Under the Curve (AUC) value is 0.82; (2) the ranking of the importance of the influence factors of the generation of the field songs and the music elements shows that the multi-year average rainfall and the multi-year average temperature are the main factors of the cultivation of the field songs in Hubei． Its Random Forest and SHAP algorithms can predict the distribution pattern of Hubei Tiange to a certain extent, which is of great significance to the study of regional music culture and geographic correlation．