In this paper, a hybrid experimental/numerical methodology for the assessment of railwayinduced ground-borne noise and vibration in buildings based on experimental measurement in the ground surface is presented. This methodology is specifically designed for the prediction of railway-induced vibration in buildings to be constructed close to operative railway infrastructures. A set of virtual forces applied in the ground, as a model of the incident wave field induced by the railway infrastructure, are obtained from vibration experimental measurements in the surface of the ground close to the future building foundation. These virtual forces can be subsequently applied on a model of the building/soil system to obtain a prediction of the vibration that will be induced by the existing railway track to the studied building. In the present work, this methodology is presented and validated numerically by a two-dimensional example and a two-and-a-half-dimensional one. The proposed hybrid model simplifies the usual numerical procedure for these problems, since a model of the railway infrastructure is not longer required. Moreover, it reduces the uncertainty of the prediction due to the use of experimental measurements of the particular site to be studied. In addition, it provides a higher accuracy and flexibility than empirical models based on experimental transmissibility functions between the ground surface and the building