Seismic site amplification prediction- an integrated Bayesian optimisation explainable machine learning approach

This study presents machine learning (ML) models for predicting average seismic site amplification, a key factor in seismic hazard assessment. Utilizing data from Japan’s KiK-Net strong-motion network, several algorithms were developed, including Gaussian Process Regression (GPR), Least Median Square Regression (LMSR), Sequential Minimal Optimization Regression (SMOR), K-star (K*), M5 Rules, Alternative Modeling Trees (AMT), and Regression Tree Ensemble (RTE). Input features included shear wave velocity profiles, peak ground acceleration at the rock, and ground motion duration. Models were optimized using Bayesian tuning and k-fold cross-validation. Among all models, the RTE model exhibited superior performance, achieving the lowest Root Relative Square Error (RRSE) values of 0.125 and 0.568, and Mean Squared Logarithmic Error (MSLE) values of 0.005 and 0.058 in the training and testing sets, respectively. It also showed MSLE reductions of 83.4% and 60% compared to LMSR and traditional 1D equivalent linear analysis. Shapley Additive explanations and partial dependence plots were used to interpret model behavior, revealing key variable impacts and increasing model transparency. The results highlight the capability of ML—particularly RTE—in improving the accuracy and efficiency of seismic site response predictions, demonstrating strong potential for advancing geotechnical engineering applications.