The surface topography of milled workpieces often defines their performance. One example is blades in turbine engines, where the topography defines the flow losses. This type of complex goods is often machined by ball end mills, either for manufacture or repair. The literature offers various model types to predict the surface topography in order to design a machining process without prior experiment. The most accurate models use the real kinematics of the process and blend the tool with the workpiece. But this type of surface prediction ignores the differences between the reality and the simulation due to vibrations, tool chipping etc. This paper presents a combined approach using the kinematic topography from the machining simulation and adds a stochastic topography based on empirical data. It could be shown, that the usage of the stochastic topography greatly affects the flow losses and thus cannot be ignored.