A liquefaction-induced settlement assessment is considered one of the major challenges in geotechnical earthquake engineering. This paper presents random forest (RF) and reduced error pruning tree (REP Tree) models for predicting settlement caused by liquefaction. Standard penetration test (SPT) data were obtained for five separate borehole sites near the Pohang Earthquake epicenter. The data used in this study comprise of four features, namely depth, unit weight, corrected SPT blow count and cyclic stress ratio. The available data is divided into two parts: training set (80%) and test set (20%). The output of the RF and REP Tree models is evaluated using statistical parameters including coefficient of correlation (r), mean absolute error (MAE), and root mean squared error (RMSE). The applications for the aforementioned approach for predicting the liquefaction-induced settlement are compared and discussed. The analysis of statistical metrics for the evaluating liquefaction-induced settlement dataset demonstrates that the RF achieved comparatively better and reliable results.
Part of the book: Natural Hazards
The paper develops a framework to analyze the interactions among seismic soil liquefaction significant factors using the interpretive structural model (ISM) approach based on cone penetration test. To identify the contextual relationships among the significant factors, systematic literature review approach was used bearing in mind the selection principle. Since multiple factors influence seismic soil liquefaction, determining all factors in soil liquefaction would be extremely difficult, as even a few seismic soil liquefaction factors are not easy to deal with. This study highlighted two main characteristics of seismic soil liquefaction factors. First, the seismic soil liquefaction factors–peak ground acceleration F2 (amax), equivalent clean sand penetration resistance F5 (qc1Ncs), and thickness of soil layer F11 (Ts) influenced soil liquefaction directly and were located at level 2 (top level) in the ISM model, meaning they require additional seismic soil liquefaction factors except thickness of soil layer F11 (Ts) to collaboratively impact on soil liquefaction potential. The multilevel hierarchy reveals that depth of soil deposit F10 (Ds) is formed the base of ISM hierarchy. Secondly, Matrice d’impacts croisés multiplication appliqués à un classement (MICMAC) analysis has been employed for evaluating these identified factors in accordance with driving power and dependence power. Factors with a higher driving power should be given special consideration. Autonomous soil liquefaction factors have no reliance on other soil liquefaction factors and interfere less. In order to identify the significant factors that affect seismic soil liquefaction susceptibility, the model built in this study clearly illustrates the complex relationships between factors and demonstrates the direct and indirect relationships.
Part of the book: Earthquakes