A Combined Weight of Evidence and Logistic Regression Method for Susceptibility Mapping of Earthquake-induced Landslides: A Case Study of the April 20, 2013 Lushan Earthquake, China

Suhua Zhou, Wei Wang, Guangqi Chen, Baochen Liu, Ligang Fang

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The M s 7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence (WoE) and Logistic Regression (LR) methods have been widely used for LSM (Landslide Susceptibility Mapping). However, limitations still exist. WoE is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and WoE for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used: 70% were random-selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic (ROC) curve. The results showed that the LR-WoE model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model (0.715 success and 0.722 predictive). It is therefore concluded that the combined method of WoE and LR can provide a promising level of accuracy for earthquake-induced landslide susceptibility mapping.

Original languageEnglish
Pages (from-to)511-524
Number of pages14
JournalActa Geologica Sinica
Volume90
Issue number2
DOIs
Publication statusPublished - Apr 1 2016

Fingerprint

landslide
logistics
earthquake
condition factor
Lushan earthquake 2013
method

All Science Journal Classification (ASJC) codes

  • Geology

Cite this

A Combined Weight of Evidence and Logistic Regression Method for Susceptibility Mapping of Earthquake-induced Landslides : A Case Study of the April 20, 2013 Lushan Earthquake, China. / Zhou, Suhua; Wang, Wei; Chen, Guangqi; Liu, Baochen; Fang, Ligang.

In: Acta Geologica Sinica, Vol. 90, No. 2, 01.04.2016, p. 511-524.

Research output: Contribution to journalArticle

@article{ec90949cff6d4af3a6a3fdf3543942d5,
title = "A Combined Weight of Evidence and Logistic Regression Method for Susceptibility Mapping of Earthquake-induced Landslides: A Case Study of the April 20, 2013 Lushan Earthquake, China",
abstract = "The M s 7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence (WoE) and Logistic Regression (LR) methods have been widely used for LSM (Landslide Susceptibility Mapping). However, limitations still exist. WoE is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and WoE for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used: 70{\%} were random-selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic (ROC) curve. The results showed that the LR-WoE model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model (0.715 success and 0.722 predictive). It is therefore concluded that the combined method of WoE and LR can provide a promising level of accuracy for earthquake-induced landslide susceptibility mapping.",
author = "Suhua Zhou and Wei Wang and Guangqi Chen and Baochen Liu and Ligang Fang",
year = "2016",
month = "4",
day = "1",
doi = "10.1111/1755-6724.12687",
language = "English",
volume = "90",
pages = "511--524",
journal = "Acta Geologica Sinica (English Edition)",
issn = "0001-5717",
publisher = "Science Press",
number = "2",

}

TY - JOUR

T1 - A Combined Weight of Evidence and Logistic Regression Method for Susceptibility Mapping of Earthquake-induced Landslides

T2 - A Case Study of the April 20, 2013 Lushan Earthquake, China

AU - Zhou, Suhua

AU - Wang, Wei

AU - Chen, Guangqi

AU - Liu, Baochen

AU - Fang, Ligang

PY - 2016/4/1

Y1 - 2016/4/1

N2 - The M s 7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence (WoE) and Logistic Regression (LR) methods have been widely used for LSM (Landslide Susceptibility Mapping). However, limitations still exist. WoE is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and WoE for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used: 70% were random-selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic (ROC) curve. The results showed that the LR-WoE model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model (0.715 success and 0.722 predictive). It is therefore concluded that the combined method of WoE and LR can provide a promising level of accuracy for earthquake-induced landslide susceptibility mapping.

AB - The M s 7.0 Lushan earthquake triggered a huge number of landslides. Landslide susceptibility mapping is of great importance. Weight of Evidence (WoE) and Logistic Regression (LR) methods have been widely used for LSM (Landslide Susceptibility Mapping). However, limitations still exist. WoE is capable of assessing the influence of different classes of each factor, but neglects the correlation between factors. LR is able to analyze the relationship among the factors while it is not capable of evaluating the influence of different classes. This paper proposes a combined method of LR and WoE for LSM, taking advantage of their individual merits and overcoming their limitations. An inventory of 1289 landslides was used: 70% were random-selected for training and the remaining for validation. 11 landslide condition factors were employed in the model and the result was validated using Receiver Operating Characteristic (ROC) curve. The results showed that the LR-WoE model had a better accuracy than the LR model, producing an area below the curve with values of 0.802 success and 0.791 predictive, higher than that of the LR model (0.715 success and 0.722 predictive). It is therefore concluded that the combined method of WoE and LR can provide a promising level of accuracy for earthquake-induced landslide susceptibility mapping.

UR - http://www.scopus.com/inward/record.url?scp=84964310795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964310795&partnerID=8YFLogxK

U2 - 10.1111/1755-6724.12687

DO - 10.1111/1755-6724.12687

M3 - Article

AN - SCOPUS:84964310795

VL - 90

SP - 511

EP - 524

JO - Acta Geologica Sinica (English Edition)

JF - Acta Geologica Sinica (English Edition)

SN - 0001-5717

IS - 2

ER -