TEL:886-2-2367-8532
FAX:886-2-2368-6732

Full-text available
   < Previous vol/No | Next vol/No >
Vol.46, No.4, PP.197-251
Content:   PDF( 0.11MB )

Editorial Scope and Editorial Board:  PDF( 0.26MB )

1
The Maximum Impact Force from a Rock-fall for Rock-Shed Slab Design
46(4):197-204
Chia-Ming Lo[1]* Kai-Jie Chang[2]
* Corresponding Author. E-mail : ppb428@yahoo.com.tw
Show preview   |   PDF( 3.89MB )   |  
2
Three-Dimensional Numerical Analyses of the Mechanical Behaviors of Retaining Shear Piles Stabilized Slope
46(4):205-212
Der-Guey Lin Wei-Hsiang Chen* Sheng-Hsien Wang
* Corresponding Author. E-mail : cws271641@yahoo.com.tw
Show preview   |   PDF( 2.86MB )   |  
3
A GIS-based Comparative Study of the use of A Logistic Regression, the Instability Index Method and A Support Vector Machine for Landslide Susceptibility Analysis
46(4):213-222
Hsun-Chuan Chan[1]* Po-An Chen[1][2] Yu-Ting Wen[1]
* Corresponding Author. E-mail : hcchan@ nchu.edu.tw
Show preview   |   PDF( 2.56MB )   |  
A GIS-based Comparative Study of the use of A Logistic Regression, the Instability Index Method and A Support Vector Machine for Landslide Susceptibility Analysis
Close
Hsun-Chuan Chan[1]* Po-An Chen[1][2] Yu-Ting Wen[1]

Abstract
This study uses the inventories for landslides that were established by the Central Geological Survey for landslide data. A logistic regression, the Instability index method and a Support vector machine (SVM) are used to establish landslide susceptibility models and to produce landslide susceptibility maps for the upstream areas of Jing-Shan River. Ten causative factors for landslides are selected similarly to previous studies. A selection procedure is then used to reduce the number of factors. The receiver operating characteristic curve is used to evaluate the accuracy of the model results. The Logistic regression and the Instability index method both show that the roughness of the terrain is a critical factor for the susceptibility value. The instability index method can lead to possible underestimation around the river and the number of factor classifications can impact the results. SVM establishes the model by classifying the landslide data. The landslide susceptibility values are not reliant on particular factors.Therefore, the results for the model prediction are not influenced by the weights of the factors. The landslide susceptibilities are classified into four groups: low, medium, medium-high and high. SVM and Logistic regression are superior to the Instability index method because they identify landslides in medium-high and high susceptibility areas.The analysis of the area under the curve (AUC) gives an AUC value of 0.825 using SVM, 0.721 using logistic regression and 0.718 using the instability index method. This demonstrates that SVM is the best method to assess landslide risk in the research areas.
Key Words : Logistic regression, instability index, support vector machine, landslide susceptibility.
〔1〕Department of Soil and Water Conservation, National Chung Hsing University, Taichung, Taiwan.
〔2〕Taichung Branch of Soil and Water Conservation Bureau, Council of Agriculture, Executive Yuan.
* Corresponding Author. E-mail : hcchan@ nchu.edu.tw
Received: 2015/04/30
Revised: 2015/05/22
Accepted: 2015/08/27
4
The Mechanism of Landslides Caused by Typhoon Soudelor in Northern Taiwan
46(4):223-232
Lun-Wei Wei [1]* Wei-Kai Huang[1] Chuen-Ming Huang[1] Ching-Fang Lee[1] Sheng-Chi Lin[2] Chung-Chi Chi [3]
* Corresponding Author. E-mail : lwwei@sinotech.org.tw
Show preview   |   PDF( 19MB )   |  
5
The Effect of Free Over-fall by Upstream and Downstream Channel Bed Slopes on Impact Position
46(4):233-238
Jie-Hui Huang Chun-Hsien Hsieh Jen-Yan Chen*
* Corresponding Author. E-mail : jychen@dragon.nchu.edu.tw
Show preview   |   PDF( 0.65MB )   |  
6
A 3-D Numerical Simulation of the Flow Field around a Porous Cylinder
46(4):239-251
Shao-Hua Marko Hsu[1] Wei-Bang Hsin[1]* Pi-Fang Hung[2]
* Corresponding Author. E-mail : jasonshin9@hotmail.com
Show preview   |   PDF( 6.61MB )   |  
   Copyright © 2011 Chinese Soil And Water Conservation Society   MAP    
Address:2FL, No.8, Lane 113, Xiamen St., Zhongzheng Dist., Taipei City 100, Taiwan (R.O.C.)