A major concern in design of foundations is to achieve a precise estimation of bearing capacity of underlying soil or rock mass. The present study proposes a new design equation for the prediction of the bearing capacity of shallow foundations on rock masses utilizing artificial neural networks (ANNs). The bearing capacity is formulated in terms of rock mass rating (RMR), unconfined compressive strength of rock, ratio of joint spacing to foundation width, and angle of internal friction for the rock mass. Further, a conventional calculation procedure is proposed based on the fixed connection weights and bias factors of the best ANN structure. A comprehensive database of rock socket, centrifuge rock socket, plate load, and large-scaled footing load test results is used for the model development. Sensitivity and parametric analyses are conducted and discussed. The results clearly demonstrate the acceptable performance of the derived model for estimating the bearing capacity of shallow foundations. The proposed prediction equation has a notably better performance than the traditional equations.

Keywords