Predicting the liquefaction potential of soil layers in Tabriz city via artificial neural network analysis

Abstract Soil liquefaction is a phenomenon through which saturated soil completely loses its strength and hardness behaves the same as liquid due to severe stress it entails. This can be caused by earthquakes or sudden changes in conditions. Many empirical approaches have been proposed for predicting potential of liquefaction, each includes advantages disadvantages. In this paper, novel prediction approach based on an artificial neural network (ANN) adequately predict specific range properties. To end, whole set 100 data collected calculate via Tabriz, Iran. Then, results are utilized training ANN, considered option first time Tabriz. The achieved configuration ANN 10 other sets validation purposes. According obtained results, well-trained capable error values less than 5%, represents reliability approach.