Calculation of the bearing capacity of shallow foundations on rock masses is usually addressed either using empirical equations, analytical solutions, or numerical models. While the empirical laws are limited to the particular conditions and local geology of the data and the application of analytical solutions is complex and limited by its simplified assumptions, numerical models offer a reliable solution for the task but require more computational effort. This research presents an artificial neural network (ANN) solution to predict the bearing capacity due to general shear failure more simply and straightforwardly, obtained from FLAC numerical calculations based on the Hoek and Brown criterion, reproducing more realistic configurations than those offered by empirical or analytical solutions. The inputs included in the proposed ANN are rock type, uniaxial compressive strength, geological strength index, foundation width, dilatancy, bidimensional or axisymmetric problem, the roughness of the foundation-rock contact, and consideration or not of the self-weight of the rock mass. The predictions from the ANN model are in very good agreement with the numerical results, proving that it can be successfully employed to provide a very accurate assessment of the bearing capacity in a simpler and more accessible way than the existing methods.

The theoretical basis for evaluating shear strength in rock joints is presented and used to derive an equation that governs the relationship between tangential and normal stress on the joint during situations of slippage between the joint faces. The dependent variables include geometric dilatancy, the instantaneous friction angle, and a parameter that considers joint surface roughness. The effect roughness is studied, and the aforementioned formula is used to analyse joints under different conditions. A mathematical expression is deduced that explains Barton's value for the joint roughness coefficient (JRC) according to the roughness geometry. In particular, when the Hoek and Brown failure criterion is used for a rock in the contact with the surface roughness plane, it is possible to determine the shear strength of the joint as a function of the relationship between the uniaxial compressive strength of the wall with the normal stress acting on the wall. Finally, theoretical results obtained for the geometry of a three-dimensional joint are compared with those of the Barton's formulatio