Prediction of SWCC using artificial intelligent systems: A comparative study

doi:10.1016/j.scient.2011.09.002

Scientia Iranica

Volume 18, Issue 5, October 2011, Pages 1002-1008

https://doi.org/10.1016/j.scient.2011.09.002 Get rights and content

Under a Creative Commons license

open access

Abstract

The significance of the Soil Water Characteristic Curve (SWCC) or soil retention curve in understanding the unsaturated soils behavior such as shear strength, volume change and permeability has resulted in many attempts for its prediction. In this regard, the authors had previously developed two models, namely. Genetic-Based Neural Network (GBNN) and Genetic Programming (GP). These two models have identical set of input parameters. These parameters include void ratio, initial water content, clay fraction, silt content and logarithm of suction normalized with respect to air pressure. In this paper, performance of these two models is further investigated using additional test data. For this purpose, soil samples from 14 different locations in Shiraz city in the Fars province of Iran are tested and their SWCCs are established, using a pressure plate apparatus. Next, the results are used to demonstrate the suitability of the previously proposed models and to evaluate relative importance of the input parameters. Assessment of the results indicates that predictions from GBNN model have relatively higher accuracy as compared to GP model.

Keywords

Unsaturated soils

Soil suction

Soil Water Characteristic Curve (SWCC)

Geotechnical models

Computer models

Numerical models

Cited by (0)

Ali Johari is Assistant professor at Shiraz University of Technology, Civil and Environmental Engineering Department. He has been a faculty member of this University since 2009. He graduated from Shiraz University in 1995 with a B.Sc. Degree and received his Master Degree from the university in 1999. He was granted a Ph.D. Degree from Shiraz University in 2006, and was a Post-Doctoral researcher at Exeter University in 2008. He is currently is a research staff of the Computational Geomechanics Group of this university. As a faculty member of Civil and Environmental Engineering Department of Shiraz University of technology, he has been teaching geotechnical courses at graduate levels and supervising numerous geotechnical students at M.S. level. He has also consulted and supervised numerous geotechnical projects.

Ghassem Habibagahi, professor of Civil Engineering, has been a faculty member of Shiraz University since 1990. He graduated from Shiraz University in 1982 with a B.Sc. Degree and received his Master Degree from McGill University in 1985. He was granted a Ph.D. Degree from University of Montreal. As a faculty member of Civil Engineering Department, he has been teaching geotechnical courses at undergraduate and graduate levels and supervising numerous geotechnical students at M.S. and Ph.D. levels. He has been a member of Unsaturated Soils Committee (TC106) of ISSMFE (International Society for Soil Mechanics and Foundation Engineering) since 2008, and has published more than 2026 papers in peer reviewed journals. He has also consulted and supervised numerous geotechnical projects.

Arsalan Ghahramani is professor at Shiraz University, Department of Civil Engineering. He received his Bachelor of Engineering from American University of Beirut, and his Master of Engineering and Ph.D. from Princeton University in 1967. He has been at Shiraz University since then, and has been effective in the Advanced Soil mechanics lab and the Ph.D. program at the department of civil engineering. His research area is the development of zero extension line method. His consulting includes panel of review of several large dams in Iran, and design of foundation of Milad tower in Tehran and the design of Lali bridge caisson foundation in Lali.