Assessment of Lateral Displacements using Neuro-Fuzzy Group Method of Data Handling Systems

Lateral spreading is one of the most destructive effects of liquefaction. Liquefaction is known as one of the major causes of ground failure related to earthquake. This phenomenon is likely to occur when the rate of earthquake-induced excess pore water pressure buildup exceeds the rate of drainage. Estimation of the hazard of lateral spreading requires characterization of subsurface conditions. In this study, neuro-fuzzy group method of data handling (NF-GMDH) is utilized for assessment of lateral displacement in both ground slope and free face conditions. The NF-GMDH approach is improved using particle swarm optimization (PSO) algorithm. The comprehensive database used for the development of the model was obtained from different earthquakes. Contributions of the variables influencing the lateral displacement of soil are evaluated through a sensitivity analysis. Performance of the NF-GMDH-PSO models are compared with those yielded using empirical equations in terms of error indicators parameters and the advantages of the proposed models over the conventional method are discussed.