Assessment of earthquake-induced slope deformation of earth dams using soft computing techniques

Evaluating behavior of earth dams under dynamic loads is one of the most important problems associated with the initial design of such massive structures. This study focuses on prediction of deformation of earth dams due to earthquake shaking. A total number of 103 real cases of deformation in earth dams due to earthquakes that has occurred over the past years were gathered and analyzed. Using soft computing methods, including feed-forward back-propagation and radial basis function based neural networks, two models were developed to predict slope deformations in earth dams under variant earthquake shaking. Earthquake magnitude (Mw), yield acceleration ratio (ay/amax), and fundamental period ratio (Td/Tp) were considered as the most important factors contributing to the level of deformation in earth dams. Subsequently, a sensitivity analysis was conducted to assess the performance of the proposed model under various conditions. Finally, the accuracy of the developed soft computing model was compared with the conventional relationships and models to estimate seismic deformations of earth dams. The results demonstrate that the developed neural model can provide accurate predictions in comparison to the available practical charts and recommendations.