This short article describes one of the latest advancements of a monitoring/inspection technique for the estimation of localized longitudinal stress in continuous welded rails (CWR). The technique is based on the use of vibration measurements and machine learning (ML). A finite element analysis is conducted to model the relationship between the boundary conditions and the longitudinal stress of any given CWR to the vibration characteristics of the rail. The results of the numerical analysis are used to train a ML algorithm that is then tested using field data obtained by an array of accelerometers polled on the track of interest. The proposed technique was tested in the field. A commercial FEM software was used to model the rail track as a short rail segment repeated indefinitely and under varying boundary conditions and stress. A ML model was developed to infer the rail neutral temperature and the local resistance of rails to vertical and lateral displacement. The results of the experiments demonstrated that the success of the technique is dependent on the accuracy of the model and the ability to properly label the modes of the detected frequencies. This study builds upon previous research conducted at the University of Pittsburgh and the interested reader is referred to previous publications from the authors for more details about the proposed technique.