Seismic ground response prediction based on multilayer perceptron

Abstract

Earthquake disasters can cause enormous social and economic damage, and therefore the sustainability of infrastructure requires the mitigation of earthquake consequences. In seismic design of infrastructures, it is essential to estimate the response of the site during earthquake. Geotechnical engineers have developed quantitative methods for analyzing the seismic ground response. This study proposes a multilayer perceptron (MLP) model to evaluate the seismic response of the surface based on the seismic motion at the bedrock (or 100 m level), and compares its performance with that of a conventional model. A total of 6 sites, with 100 earthquake events at each site, were selected from the Kiban Kyoshin Network (KiK-net) and used as datasets. The acceleration response spectra were calculated from the predicted and measured (baseline) acceleration histories and compared. The proposed MLP model predicted the magnitudes of response and the natural periods where the response amplifies closely with the measured ground motions (baseline). The MLP model outperformed the conventional model for seismic ground response analysis. However, the proposed model did not perform as well for earthquakes whose response spectra exceed 2g due to a deficiency in large earthquake measurements in the training datasets.