Back-propagation neural network for assessment of highway slope failure in Taiwan

T. L. Lee, Hung-Ming Lin, D. S. Jeng, Y. P. Lu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The highway slope failure during typhoons and earthquakes is a major geotechnical engineering problem in Taiwan. Intensive studies have been carried out in recent years. However, conventional investigations for determining slope failure have focused on the linear relationships between the dominant factors, such as slope angle, slope height, material, construction, rainfall, earthquake and etc., although it should be a complicated nonlinear relationship. In this paper, a back-propagation neural network is proposed as an assessment tool for the slope failure. On-site slope failure data at the A-Li-San Highway in southern Taiwan are used to test the performance of the artificial neural network model. The numerical results demonstrate the effectiveness of the artificial neural network in the evaluation of slope failure potential with five major factors, such as slope gradient angle, slope height, cumulative precipitation, surface acceleration and strength of material.

Original languageEnglish
Pages (from-to)121-128
Number of pages8
JournalGeotechnical Engineering
Volume39
Issue number3
Publication statusPublished - 2008 Sep 1

Fingerprint

back propagation
slope failure
Backpropagation
road
Neural networks
Earthquakes
slope angle
Geotechnical engineering
artificial neural network
Strength of materials
Rain
earthquake
geotechnical engineering
rainfall

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Geotechnical Engineering and Engineering Geology

Cite this

Lee, T. L. ; Lin, Hung-Ming ; Jeng, D. S. ; Lu, Y. P. / Back-propagation neural network for assessment of highway slope failure in Taiwan. In: Geotechnical Engineering. 2008 ; Vol. 39, No. 3. pp. 121-128.
@article{17a50ced474a4290ac292f8f4cde4bce,
title = "Back-propagation neural network for assessment of highway slope failure in Taiwan",
abstract = "The highway slope failure during typhoons and earthquakes is a major geotechnical engineering problem in Taiwan. Intensive studies have been carried out in recent years. However, conventional investigations for determining slope failure have focused on the linear relationships between the dominant factors, such as slope angle, slope height, material, construction, rainfall, earthquake and etc., although it should be a complicated nonlinear relationship. In this paper, a back-propagation neural network is proposed as an assessment tool for the slope failure. On-site slope failure data at the A-Li-San Highway in southern Taiwan are used to test the performance of the artificial neural network model. The numerical results demonstrate the effectiveness of the artificial neural network in the evaluation of slope failure potential with five major factors, such as slope gradient angle, slope height, cumulative precipitation, surface acceleration and strength of material.",
author = "Lee, {T. L.} and Hung-Ming Lin and Jeng, {D. S.} and Lu, {Y. P.}",
year = "2008",
month = "9",
day = "1",
language = "English",
volume = "39",
pages = "121--128",
journal = "Geotechnical Engineering",
issn = "0046-5828",
publisher = "Southeast Asian Geotechnical Society",
number = "3",

}

Back-propagation neural network for assessment of highway slope failure in Taiwan. / Lee, T. L.; Lin, Hung-Ming; Jeng, D. S.; Lu, Y. P.

In: Geotechnical Engineering, Vol. 39, No. 3, 01.09.2008, p. 121-128.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Back-propagation neural network for assessment of highway slope failure in Taiwan

AU - Lee, T. L.

AU - Lin, Hung-Ming

AU - Jeng, D. S.

AU - Lu, Y. P.

PY - 2008/9/1

Y1 - 2008/9/1

N2 - The highway slope failure during typhoons and earthquakes is a major geotechnical engineering problem in Taiwan. Intensive studies have been carried out in recent years. However, conventional investigations for determining slope failure have focused on the linear relationships between the dominant factors, such as slope angle, slope height, material, construction, rainfall, earthquake and etc., although it should be a complicated nonlinear relationship. In this paper, a back-propagation neural network is proposed as an assessment tool for the slope failure. On-site slope failure data at the A-Li-San Highway in southern Taiwan are used to test the performance of the artificial neural network model. The numerical results demonstrate the effectiveness of the artificial neural network in the evaluation of slope failure potential with five major factors, such as slope gradient angle, slope height, cumulative precipitation, surface acceleration and strength of material.

AB - The highway slope failure during typhoons and earthquakes is a major geotechnical engineering problem in Taiwan. Intensive studies have been carried out in recent years. However, conventional investigations for determining slope failure have focused on the linear relationships between the dominant factors, such as slope angle, slope height, material, construction, rainfall, earthquake and etc., although it should be a complicated nonlinear relationship. In this paper, a back-propagation neural network is proposed as an assessment tool for the slope failure. On-site slope failure data at the A-Li-San Highway in southern Taiwan are used to test the performance of the artificial neural network model. The numerical results demonstrate the effectiveness of the artificial neural network in the evaluation of slope failure potential with five major factors, such as slope gradient angle, slope height, cumulative precipitation, surface acceleration and strength of material.

UR - http://www.scopus.com/inward/record.url?scp=67649547253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649547253&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:67649547253

VL - 39

SP - 121

EP - 128

JO - Geotechnical Engineering

JF - Geotechnical Engineering

SN - 0046-5828

IS - 3

ER -