Determination of Strain Energy for Triggering Liquefaction Based on Gaussian Process Regression

Authors

  • Jayaraman Karthikeyan VIT University
  • Pijush Samui VIT University

DOI:

https://doi.org/10.4186/ej.2013.17.4.71

Keywords:

Earthquake, liquefaction, Gaussian process regression, variance, artificial neural network.

Abstract

The determination of seismic liquefaction potential of soil is an imperative task in earthquake engineering. This article adopts Gaussian Process Regression (GPR) for determination of amount of strain energy required to induce liquefaction. Effective mean confining pressure (σ' mean), initial relative density after consolidation (Dr), percentage of fines content (FC), coefficient of uniformity (Cu), and mean grain size (D50) are considered as input of the GPR model. The developed GPR gives the variance of predicted output. The results of GPR have been compared with the Artificial Neural Network (ANN). The results of this article show the suitability of the proposed approach for determination of stain energy for triggering liquefaction.

Downloads

Download data is not yet available.

Author Biographies

Jayaraman Karthikeyan

Centre for Disaster Mitigation and Management, VIT University, Vellore 632014, India

Pijush Samui

Centre for Disaster Mitigation and Management, VIT University, Vellore 632014, India

Published

Vol 17 No 4, Mar 12, 2013

How to Cite

[1]
J. Karthikeyan and P. Samui, “Determination of Strain Energy for Triggering Liquefaction Based on Gaussian Process Regression”, Eng. J., vol. 17, no. 4, pp. 71-78, Mar. 2013.