Lateral spreading and flow failure are amongst the most destructive effects of liquefaction. Estimation of the peril of lateral spreading requires characterization of subsurface conditions, principally soil density, fine content, groundwater conditions, site topography and seismic characteristics. In this paper a GMDH-type neural network and particle swarm optimization is developed for prediction of liquefaction induced lateral displacements. Using this method, a new model was proposed that is suitable for predicting the liquefaction induced lateral displacements. The proposed model was tested before the requested calculation. The data set which is contains 250 data points of liquefaction-induced lateral ground spreading case histories from eighteen different earthquakes was divided into two parts: 70% were used as training and 30% were used as a test set, which were randomly extracted from the database. After initially testing on the input_output process, the predicted values were compared with experimental values to evaluate the performance of the group method of data handling neural network method.
Jirdehi, Reza A.; Mamoudan, Hamidreza T.; and Sarkaleh, Hossein H.
Applying GMDH-type Neural Network and Particle warm Optimization for Prediction of Liquefaction Induced Lateral Displacements,
Applications and Applied Mathematics: An International Journal (AAM), Vol. 9,
2, Article 6.
Available at: https://digitalcommons.pvamu.edu/aam/vol9/iss2/6