Evaluation of liquefaction-induced lateral displacement using a GMDH-type neural network optimized by genetic algorithm

Liquefaction-induced lateral spreading is known to be a significant type of damage for engineering structures. This research introduces an evolutionary algorithm by using a combination of the group method of data handling (GMDH)-type neural network and genetic algorithm for predicting liquefaction-induced lateral displacements. A new and comprehensive database containing 526 case histories from 18 significant earthquakes is compiled and analyzed to develop a new predictive model. Also, the developed equation evaluated the results of previously published experimental studies and showed an acceptable performance. The obtained results show a more accurate performance of the proposed model compared with previous models. Since the presented model has been developed based on numerous seismic events and site conditions, it is more general and reliable than other models.