Implementation of machine learning classification models considering the optimum data ratio in predicting soil liquefaction susceptibility

Abstract Soil Liquefaction has a disastrous impact on structures and underground infrastructure. Therefore, an appropriate liquefaction vulnerability assessment strategy can help reduce the detrimental consequences of this hazard. In recent decades, machine learning has been studied more frequently to solve geotechnical issues, such as determining liquefaction susceptibility. Intending to improve the model’s learning ability to identify liquefaction vulnerability and to find the optimum training and testing data ratio, this research attempts to develop a machine learning model for liquefaction prediction utilizing relatively more varied data in different data ratios. In this study, liquefaction prediction models were developed using four supervised learning-based algorithms: Random Forest (RF), Naïve Bayes Classifier (NBC), Decision Tree (DT), and K-Nearest Neighbor (k-NN). Seven parameters were utilized to train the model using historical data on liquefaction. The model’s performance in predicting liquefaction was compared with various training and testing data ratios and validated using 5-fold cross-validation. The capability of the model was assessed using performance metrics. The results show that the RF model has the highest accuracy in predicting liquefaction among all the algorithms used. RF achieved an overall accuracy of 90.28%, followed by the k-NN (86.11%) and the DT (81.94%) on a training and testing data ratio of 80:20. The NBC algorithm obtained the highest accuracy of 78.44% on the 75:25 data ratio. In general, the machine learning approach is capable of predicting liquefaction susceptibility.