Machine-learning models to predict P- and S-wave velocity profiles for Japan as an example

Wave velocity profiles are significant for various fields, including rock engineering, petroleum engineering, and earthquake engineering. However, direct measurements of wave velocities are often constrained by time, cost, and site conditions. If wave velocity measurements are unavailable, they need to be estimated based on other known proxies. This paper proposes machine learning (ML) approaches to predict the compression and shear wave velocities (VP and VS, respectively) in Japan. We utilize borehole databases from two seismograph networks of Japan: Kyoshin Network (K-NET) and Kiban Kyoshin Network (KiK-net). We consider various factors such as depth, N-value, density, slope angle, elevation, geology, soil/rock type, and site coordinates. We use three ML techniques: Gradient Boosting (GB), Random Forest (RF), and Artificial Neural Network (ANN) to develop predictive models for both VP and VS and evaluate the performances of the models based on root mean squared errors and the five-fold cross-validation method. The GB-based model provides the best estimation of VP and VS for both seismograph networks. Among the considered factors, the depth, standard penetration test (SPT) N-value, and density have the strongest influence on the wave velocity estimation for K-NET. For KiK-net, the depth and site longitude have the strongest influence. The study confirms the applicability of commonly used machine-learning techniques in predicting wave velocities, and implies that exploring additional factors will enhance the performance.