Date of Award
5-1-2025
Degree Name
Master of Science
Department
Civil Engineering
First Advisor
Tezcan, Jale
Abstract
Support Vector Machine (SVM) is used to create ground motion models for the prediction of Horizontal component, vertical component and V/H ratio using 11,546 ground motion records obtained from the “Next Generation and the duration of Ground-Motion Attenuation Models” project. The predictor set considered in this research consists of the moment magnitude, dip angle, rake angle, depth to the top of fault rupture, Joyner Boore distance, closest distance to the ruptured fault area, and the shear wave velocity in the top 30 m of the site. SVM employs a kernel function to convert the data into a high-dimensional feature space, where linear modeling is carried out to address the difficulty associated with high nonlinear datasets. SVM was reasonably capable for prediction of both the horizontal and vertical component. However, prediction of V/H ratio was not accurate. The results illustrate SVM’s potential as a viable alternative to traditional ground motion prediction equations (GMPEs).
Access
This thesis is only available for download to the SIUC community. Current SIUC affiliates may also access this paper off campus by searching Dissertations & Theses @ Southern Illinois University Carbondale from ProQuest. Others should contact the interlibrary loan department of your local library or contact ProQuest's Dissertation Express service.