[Objective] To quickly and accurately obtain the effective soil thickness in a region, evaluate its spatial distribution characteristics and identify the influencing factors, which is of considerable importance for vegetation growth, soil conservation and food security. [Methods] Taking the Xin'an River Basin as the research area, combining field survey data, topography, lithology, and climate and other soil-forming factors, the Empirical Bayesian Kriging Regression Prediction (EBKRP) and Random Forest (RF) algorithms were used to obtain the effective soil thickness inversion results. The relationship between this data and environmental variables was also analysed. [Results] ①The average effective soil thickness in the region is 0.2-0.3 m, with higher soil thickness in basins and plains where urban construction is concentrated and human activities are intensive, and lower soil thickness in hilly and mountainous areas. ②From the three accuracy evaluation indicators of MAE (Mean Absolute Error), R2 (Coefficient of Determination) and RMSE (Root Mean Square Error), the prediction results of RF algorithm are significantly better than those of EBKRP algorithm, and it can better display the spatial heterogeneity distribution characteristics of soil thickness, improving the effect of soil thickness digital mapping to a certain extent. The effective soil thickness estimation is greatly influenced by topography and climate variables, which account for 46.77% and 18.78% of the variable importance, respectively. [Conclusion] The RF algorithm is an effective method for inverting regional effective soil thickness, overcoming the characteristics of spatial heterogeneity of soil thickness. Furthermore, it is more accurate and has higher resolution compared to models with limited sampling.