A novel liquefaction study for fine-grained soil using PCA-based hybrid soft computing models

Earthquake-induced liquefaction is an unpredicted phenomenon that causes catastrophic damages and devastation to the environment, structures, and human life. The assessment of soil liquefaction behavior is a decisive work for geotechnical engineers especially during the designing phase of any civil engineering projects. These decisions implicate tedious and costly experimental procedures and extensive evaluation. Considering these facts, the present study aims to simplify the process of evaluating soil's liquefaction behavior in a broader domain involving the least experimental datasets. Three PCA (principal component analysis)-based advanced hybrid computational models, namely PCA-ANN, PCA-ANFIS, and PCA-ELM were developed to predict the liquefaction behavior of soils. The dimension reduction technique, i.e. PCA, was used to avoid the multicollinearity effect during the course of the development of the said models. Geotechnical parameters, namely plasticity index, SPT blow count, water content to liquid limit ratio, bulk density, total stress, effective stress, and fine content along with other seismic input variables, such as the ratio of peak ground acceleration and acceleration due to gravity, and magnitude of an earthquake were used to develop the predictive models. The predictive accuracy of the proposed models was evaluated via several fitness parameters. In the end, the best predictive model was determined using a novel tool called Rank Analysis. Based on the results, it has been established that the PCA-ELM hybrid computational model can be considered as a new alternative tool to assist geotechnical engineers in the task of assessing the liquefaction potential of soil during the preliminary design stage in any engineering project.