Anzeige
Erschienen in:
2021 | OriginalPaper | Buchkapitel
Support Vector Machine for Evaluation of Liquefaction Potential Using SPT Data
verfasst von : Dev Kumar Pradhan, Suvendu Kumar Sasmal, Vamsi Alla, Rabi Narayan Behera
Erschienen in: Local Site Effects and Ground Failures
Verlag: Springer Singapore
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
The geotechnical engineers usually have difficulties in resolving complicated problems that involve a number of influencing parameters. Sometimes, it is also complicated to describe a problem mathematically. This study aims for an alternative algorithm known as Support Vector Machine (SVM), which can be used to solve the classification-type problem. In this study, liquefaction potential is analysed using influencing parameters viz. the Standard Penetration Test (SPT) values, different soil parameters, and depth of water table taken from a borehole database of a certain depth. This borehole database was prepared by collecting borehole data of different sites located in different parts of the country. A deterministic approach has been used to evaluate the liquefaction potential and it is expressed in the form of factor of safety (FS). The SVM model developed using the dataset of the liquefaction potential evaluated from a deterministic approach showed an overall accuracy of 96.8%.