Determination of Uplift Capacity of Suction Caisson Using Gaussian Process Regression, Minimax Probability Machine Regression and Extreme Learning Machine

This article employs Gaussian process regression (GPR), minimax probability machine regression (MPMR) and extreme learning machine (ELM) for prediction of uplift capacity (–) of suction caisson. This study uses GPR, MPMR and ELM as regression techniques. 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) have been adopted as inputs of GPR, MPMR and ELM models. The output of GPR, MPMR and ELM is P. The results of GPR, MPMR and ELM have been compared with the artificial neural network (ANN) model. The developed models have also been used to determine the effect of each input on P. This study shows that the developed GPR, MPMR and ELM are robust models for prediction of P of suction caisson.