基于卷积神经网络的液化预测模型及可解释性分析

Convolutional neural network-based liquefaction prediction model and interpretability analysis

常规液化判别方法通常是半经验方法,存在人为因素干扰,成功率及均衡性不佳。现有的机器学习方法缺乏足够的样本支撑,存在一定的局限性。通过整合液化数据集,选取修正标准贯击数、细粒含量、土层深度、地下水位深度、总上覆应力、有效上覆应力、门槛加速度、循环剪应力比、剪切波速、震级与地表峰值加速度11个液化特征建立卷积神经网络(convolutional neural network,简称CNN)模型。引入边界合成少数过采样技术消除不平衡数据集的影响。将CNN模型与随机森林模型、逻辑回归模型、支持向量机模型、极致梯度提升模型和规范方法进行对比,并结合沙普利加性解释(SHapley Additive exPlanations,简称SHAP)分析输入特征对预测结果的影响趋势。结果表明,CNN模型准确率达92.58%,各项指标均优于其他4种机器学习模型和规范方法。对SHAP结果分析可知,修正标贯击数小于15的土层液化概率较高,循环剪应力比CSR小于0.25的土层更不易液化。各因素的影响规律均符合现有认知,预测模型合理可靠。

Conventional methods for liquefaction discrimination are often semi-empirical,prone to human factors,with low success rates and balance.Moreover,current machine learning approaches lack ample sample support and have specific limitations.Through the integration of liquefaction datasets,11 features were chosen:corrected standard penetration test blow count,fine content,soil layer depth,groundwater table depth,total overburden stress,effective overburden stress,threshold acceleration,cyclic shear stress ratio,shear wave velocity,earthquake magnitude,and peak ground acceleration.A convolutional neural network(CNN)model was established.The Borderline SMOTE technique was introduced to address the issue of imbalanced datasets.The CNN model was compared against random forest,logistic regression,support vector machine,extreme gradient boosting models,and methods specified in Chinese codes.Furthermore,the SHapley Additive exPlanations(SHAP)algorithm was utilized to examine the influence trends of input features on the prediction outcomes.The results demonstrated that the CNN model attained an accuracy of 92.58%,outperforming all metrics of the four machine learning models and the method specified in Chinese codes.Examination of the SHAP results unveiled that soil layers with corrected standard penetration blow numbers below 15 exhibited a higher liquefaction probability,whereas layers with cyclic stress ratios under 0.25 were less prone to liquefaction.The influence patterns of each factor align with current understanding,indicating the prediction model’s credibility and reliability.