Uplift capacity of suction caisson in clay using multivariate adaptive regression spline

This study adopts Multivariate Adaptive Regression Spline (MARS) model for determination of uplift capacity (Q) of suction caisson in clay. MARS is a non-parametric adaptive regression procedure. The model inputs included the L/d (L is the embedded length of the caisson and d is the diameter of caisson), undrained shear strength of soil at the depth of the caisson tip (su), D/L (D is the depth of the load application point from the soil surface), inclined angle (θ) and load rate parameter (Tk). The output of MARS is Q. The results of MARS are compared with Artificial Neural Network (ANN) and Finite Element Method (FEM). An equation has been presented from the developed MARS. The results show the strong potential of MARS to be applied to uplift capacity of suction caisson in clay.

► Multivariate Adaptive Regression Spline successfully applied for prediction of uplift capacity of suction caisson in clay.
► The developed MARS outperforms the Artificial Neural Network model.
► User can use the developed equation for prediction of uplift capacity of suction caisson in clay.