In this study, a machine learning method, i.e. genetic programming (GP), is employed to obtain a simplified statistical model to describe the variation of soil suction in drying cycles using five selected influential parameters. The data used for model development was recorded by an in-situ experiment. The image processing technology is used to quantify several tree canopy parameters. Based on four accuracy metrics, i.e. root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R), and relative error, the performance of the proposed GP model was evaluated. The results indicate that the model can give a reasonable estimation for the spatiotemporal variations of soil suction around a tree with acceptable errors. Global sensitivity analysis for the statistical model obtained using limited data of a specific region demonstrates the drying time as the most influential variable and the initial soil suction as the second most influential variable for the soil suction variations. A case study was conducted using a set of assumed input variable values and validated that the simplified GP model can be used to estimate and predict the spatiotemporal variations of soil suction in rooted soil at a certain range.