•  
  •  
 

Abstract

This study presents a support vector machine (SVM)-based approach for predicting earthquake liquefaction. The SVM model database includes five indexes: earthquake magnitude, total overburden pressure, effective overburden pressure, qc values from cone penetration tests (CPT), and peak ground acceleration. The proposed model was trained and tested on a dataset comprising 466 field liquefaction performance records and CPT measurements. A grid search method with k-fold cross-validation was also used to verify the feasibility. Compared with an artificial neural network (ANN)–based method, the SVM-based method has the advantage of increased accuracy and simpler operation. Experimental results show that the proposed SVM approach can increase the classification accuracy rate to a standard of 98.71%.

Download
COinS