An Alternative Method for Determination of Liquefaction Susceptibility of Soil

Abstract

This article focuses on the application of extreme learning machine (ELM) for prediction of liquefaction susceptibility of soil based on cone penetration test data. The determination of liquefaction susceptibility of soil has been taken as a classification problem. ELM predicts liquefaction susceptibility of soil based on earthquake magnitude (M), cone resistance (qc), mean grain size (D50), total vertical stress (σ0), effective vertical stress (σ′0), normalized peak horizontal acceleration at ground surface (α/g), cyclic stress ratio \(\left( {\frac{\tau }{{\sigma^{\prime}_{0} }}} \right)\). Six models have been developed. The results of ELM have been compared with the artificial neural network models. This study shows that the developed ELM is a potential robust method for solving different problems in geotechnical engineering.