Employing a genetic algorithm and grey wolf optimizer for optimizing RF models to evaluate soil liquefaction potential

Among the research hotspots in geological/geotechnical engineering, research on the prediction of soil liquefaction potential is still limited. In this research, several machine-learning methods were developed to evaluate the liquefaction potential of soil using random forest (RF) as the base model. The parameters of the RF model were optimized using two optimization algorithms, namely, the grey wolf optimizer (GWO) and genetic algorithm (GA). In the experiment, three in situ databases based on the standard penetration test (SPT), shear wave velocity test (SWVT) and cone penetration test (CPT) were considered and used to investigate the applicability of GA-RF and GWO-RF models. For comparison purposes, a single RF model was also constructed to predict soil liquefaction. The developed models in this study were evaluated using four metrics, i.e., accuracy, recall, precision and F1-score (F1). Furthermore, receiver operating characteristic and precision-recall curves were also proposed for evaluation purposes. The results showed that the developed GA-RF and GWO-RF models can improve the performance of the original classifier. By comparing the two hybrid models, it was found that the GWO-RF performs better on two databases, i.e., CPT and SPT, while in the case of the SWVT database, the GA-RF has better performance. Considering a variety of metrics, the two hybrid models can be employed as powerful techniques to estimate soil liquefaction potential and may be feasible tools to assist technicians in making correct decisions. By implementing sensitivity analysis, the impact of each model predictor on soil liquefaction was evaluated, and the most influential parameters were identified.