bearing capacity of shallow foundations on cohesionless soils: a random forest based approach

Determining the ultimate bearing capacity (ubc) is vital for design of shallow foundations. recently, soft computing methods (i.e. artificial neural networks and support vector machines) have been used for this purpose. in this paper, random forest (rf) is utilized as a treebased ensemble classifier for predicting the ubc of shallow foundations on cohesionless soils. the inputs of model are width of footing (b), depth of footing (d), footing geometry (l/b), unit weight of sand (γ) and internal friction angle (ϕ). a set of 112 load tests data were used to calibrate and test the developed rfbased model. the used data set consists of 47 fullscale observations and 65 smallscale laboratory footing load tests. to demonstrate the efficiency of proposed rfbased model, the results are compared with some popular classical formulas that are most commonly used for determining the ubc. the results show the efficiency and capabilities of the proposed rfbased model as a practical tool in evaluating the ubc of shallow foundations in a fast and accurate way.