Cracks in clayey soil cause a reduction in the seismic loading capacity which can lead to structural failures. Seismic acceleration is the primary cause of crack propagation and damage to the earth's structure. This study investigated the impact of the earthquake's epicenter distance on the embankment model with a pre-existing crack in the embankment's core. The research adopted the numerical modeling method of soil categorized as a no-tensile material to explain displacement in selected points of the model using the extended finite element method (XFEM). Artificial Neural Networks (ANNs) were used to predict displacement obtained by XFEM. It was observed that the failure pattern and the maximum displacement time of the model change with the associated distance of the earthquake's epicenter. The key study objective is to understand the model's failure mode and introduce a new classification in earthquake damage prediction.