An evolutionary based approach for assessment of earthquake-induced soil liquefaction and lateral displacement

M. Rezania, A. Faramarzi, A. A. Javadi

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

Prediction of liquefaction and the resulting lateral displacement is a complex engineering problem due to heterogeneous nature of soils and participation of a large number of factors involved. In this paper new models are developed, based on evolutionary polynomial regression (EPR), for assessment of liquefaction potential and lateral spreading. The models developed for liquefaction and lateral spreading are compared to those obtained from neural network and linear regression based techniques. It is shown that the developed models are able to learn the complex relationship between either of these problems and their contributing factors in the form of a function with high level of accuracy (mostly in excess of 90%). The results of the EPR model developed for the liquefaction determination are used to find a novel 3-D boundary surface that discriminates between the cases of occurrence and non-occurrence of liquefaction. The developed boundary surface is employed to calculate the factor of safety against liquefaction occurrence.
LanguageEnglish
Pages142-153
Number of pages12
JournalEngineering Applications of Artificial Intelligence
Volume24
Issue number1
DOIs
Publication statusPublished - Feb 2011

Fingerprint

Soil liquefaction
Liquefaction
Earthquakes
Polynomials
Linear regression
Neural networks
Soils

Keywords

  • CPT
  • lateral displacement
  • spread
  • liquefaction
  • prediction
  • resistance
  • artificial neural networks
  • earthquake
  • regression
  • cone penetration test
  • evolutionary regression

Cite this

@article{d61ca21a5c4a469dae0c88c2ed3a5a2e,
title = "An evolutionary based approach for assessment of earthquake-induced soil liquefaction and lateral displacement",
abstract = "Prediction of liquefaction and the resulting lateral displacement is a complex engineering problem due to heterogeneous nature of soils and participation of a large number of factors involved. In this paper new models are developed, based on evolutionary polynomial regression (EPR), for assessment of liquefaction potential and lateral spreading. The models developed for liquefaction and lateral spreading are compared to those obtained from neural network and linear regression based techniques. It is shown that the developed models are able to learn the complex relationship between either of these problems and their contributing factors in the form of a function with high level of accuracy (mostly in excess of 90{\%}). The results of the EPR model developed for the liquefaction determination are used to find a novel 3-D boundary surface that discriminates between the cases of occurrence and non-occurrence of liquefaction. The developed boundary surface is employed to calculate the factor of safety against liquefaction occurrence.",
keywords = "CPT, lateral displacement, spread, liquefaction, prediction, resistance, artificial neural networks, earthquake, regression, cone penetration test, evolutionary regression",
author = "M. Rezania and A. Faramarzi and Javadi, {A. A.}",
year = "2011",
month = "2",
doi = "10.1016/j.engappai.2010.09.010",
language = "English",
volume = "24",
pages = "142--153",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
number = "1",

}

An evolutionary based approach for assessment of earthquake-induced soil liquefaction and lateral displacement. / Rezania, M.; Faramarzi, A.; Javadi, A. A.

In: Engineering Applications of Artificial Intelligence , Vol. 24, No. 1, 02.2011, p. 142-153.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An evolutionary based approach for assessment of earthquake-induced soil liquefaction and lateral displacement

AU - Rezania, M.

AU - Faramarzi, A.

AU - Javadi, A. A.

PY - 2011/2

Y1 - 2011/2

N2 - Prediction of liquefaction and the resulting lateral displacement is a complex engineering problem due to heterogeneous nature of soils and participation of a large number of factors involved. In this paper new models are developed, based on evolutionary polynomial regression (EPR), for assessment of liquefaction potential and lateral spreading. The models developed for liquefaction and lateral spreading are compared to those obtained from neural network and linear regression based techniques. It is shown that the developed models are able to learn the complex relationship between either of these problems and their contributing factors in the form of a function with high level of accuracy (mostly in excess of 90%). The results of the EPR model developed for the liquefaction determination are used to find a novel 3-D boundary surface that discriminates between the cases of occurrence and non-occurrence of liquefaction. The developed boundary surface is employed to calculate the factor of safety against liquefaction occurrence.

AB - Prediction of liquefaction and the resulting lateral displacement is a complex engineering problem due to heterogeneous nature of soils and participation of a large number of factors involved. In this paper new models are developed, based on evolutionary polynomial regression (EPR), for assessment of liquefaction potential and lateral spreading. The models developed for liquefaction and lateral spreading are compared to those obtained from neural network and linear regression based techniques. It is shown that the developed models are able to learn the complex relationship between either of these problems and their contributing factors in the form of a function with high level of accuracy (mostly in excess of 90%). The results of the EPR model developed for the liquefaction determination are used to find a novel 3-D boundary surface that discriminates between the cases of occurrence and non-occurrence of liquefaction. The developed boundary surface is employed to calculate the factor of safety against liquefaction occurrence.

KW - CPT

KW - lateral displacement

KW - spread

KW - liquefaction

KW - prediction

KW - resistance

KW - artificial neural networks

KW - earthquake

KW - regression

KW - cone penetration test

KW - evolutionary regression

UR - http://www.scopus.com/inward/record.url?scp=78649656808&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2010.09.010

DO - 10.1016/j.engappai.2010.09.010

M3 - Article

VL - 24

SP - 142

EP - 153

JO - Engineering Applications of Artificial Intelligence

T2 - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

IS - 1

ER -