This case study presents the verification of two surface subsidence prediction models for longwall mining at depths greater than 400 m. The surface subsidence points were surveyed and compared for both models. The first model uses empirical calculations to predict the surface subsidence. This method is reliable for predicting surface subsidence at shallower depths. At present, however, coal mining has progressed to great depths. The second model is the 2-dimensional finite element method to predict surface subsidence. In contrast to the first method, this method is based on the regional parameters and uses the rock mass properties to evaluate surface subsidence for multi-seams at any depth. Results show that the finite element method gives a better approximation of the measured surface subsidence than the Knothe method. The maximum surface subsidence, which was determined by the FEM method, was used to adjust the extraction coefficient in the Knothe's method. The predicted value differs from the measured value by 8 %. The slope of the predicted subsidence trough was within the range of 2‒8 % from the surveyed subsidence. This case study proposes a procedure for using both models to successfully predict the surface subsidence.