The prediction of the potential of soil liquefaction induced by the earthquake is a vital task in construction engineering and geotechnical engineering. To provide a possible solution to such problems, this paper proposes two support vector machine (SVM) models which are optimized by genetic algorithm (GA) and grey wolf optimizer (GWO) to predict the potential of soil liquefaction. Field observation data based on cone penetration test (CPT), standard penetration test (SPT) and shear wave velocity (V_S) test (SWVT) are employed to verify the reliability of the GA–SVM model and the GWO–SVM model, the numbers of input variables of these three field testing data sets are 6, 12 and 8, respectively, and the output result is the potential of soil liquefaction. To verify whether the two optimization algorithms GA and GWO have significantly improved the performance of SVM model, an unoptimized SVM model is served as a reference in this study. And five performance metrics, including classification accuracy rate (ACC), precision rate (PRE), recall rate (REC), F1 score (F1) and AUC are used to evaluate the classification performance of the three models. Results of the study confirm that when CPT-based, SPT-based and SWVT-based test sets are input into three classification models, the highest classification accuracy of 0.9825, 0.9032 and 0.9231, respectively, is achieved with GWO–SVM. And based on these three data sets, the values of AUC obtained by GWO–SVM are all higher than those obtained by GA–SVM. Further, by comparing the other metrics of the three classification models, it is found that the classification performance of the two hybrid models is very similar and significantly better than the SVM, which indicates that GWO–SVM, like GA–SVM, can also be used as a reliable model for predicting soil liquefaction potential.

地震引起的土壤液化潜力的预测是建筑工程和岩土工程中的一项重要任务。为了为此类问题提供可能的解决方案，本文提出了两种支持向量机 (SVM) 模型，它们通过遗传算法 (GA) 和灰狼优化器 (GWO) 进行优化，以预测土壤液化的潜力。基于锥入试验（CPT）、标准贯入试验（SPT）和横波速度（V _S）的现场观测数据)检验(SWVT)来验证GA-SVM模型和GWO-SVM模型的可靠性，这三个现场测试数据集的输入变量数分别为6、12和8，输出结果为土壤液化的潜力。为了验证GA和GWO两种优化算法是否显着提高了SVM模型的性能，本研究以未优化的SVM模型作为参考。五个性能指标包括分类准确率（ACC），准确率（PRE），召回率（REC），F1得分（F1）和AUC被用于评估这三个模型的分类性能。研究结果证实，当将基于CPT、基于SPT和基于SWVT的测试集输入三个分类模型时，最高分类准确率分别为0.9825、0.9032和0.9231，分别是用 GWO-SVM 实现的。并且基于这三个数据集，GWO-SVM 得到的 AUC 值都高于 GA-SVM 得到的值。此外，通过比较三个分类模型的其他指标，发现两个混合模型的分类性能非常相似，并且显着优于SVM，这表明GWO–SVM（如GA–SVM）也可以用作预测土壤液化潜力的可靠模型。