Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation

Weiguo Jiang, Pingzeng Rao, Ran Cao, Zhenghong Tang, Kun Chen

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Geological disasters not only cause economic losses and ecological destruction, but also seriously threaten human survival. Selecting an appropriate method to evaluate susceptibility to geological disasters is an important part of geological disaster research. The aims of this study are to explore the accuracy and reliability of multi-regression methods for geological disaster susceptibility evaluation, including Logistic Regression (LR), Spatial Autoregression (SAR), Geographical Weighted Regression (GWR), and Support Vector Regression (SVR), all of which have been widely discussed in the literature. In this study, we selected Yunnan Province of China as the research site and collected data on typical geological disaster events and the associated hazards that occurred within the study area to construct a corresponding index system for geological disaster assessment. Four methods were used to model and evaluate geological disaster susceptibility. The predictive capabilities of the methods were verified using the receiver operating characteristic (ROC) curve and the success rate curve. Lastly, spatial accuracy validation was introduced to improve the results of the evaluation, which was demonstrated by the spatial receiver operating characteristic (SROC) curve and the spatial success rate (SSR) curve. The results suggest that: 1) these methods are all valid with respect to the SROC and SSR curves, and the spatial accuracy validation method improved their modelling results and accuracy, such that the area under the curve (AUC) values of the ROC curves increased by about 3%–13% and the AUC of the success rate curve values increased by 15%–20%; 2) the evaluation accuracies of LR, SAR, GWR, and SVR were 0.8325, 0.8393, 0.8370 and 0.8539, which proved the four statistical regression methods all have good evaluation capability for geological disaster susceptibility evaluation and the evaluation results of SVR are more reasonable than others; 3) according to the evaluation results of SVR, the central-southern Yunnan Province are the highest susceptibility areas and the lowest susceptibility is mainly located in the central and northern parts of the study area.

Original languageEnglish (US)
Pages (from-to)439-462
Number of pages24
JournalJournal of Geographical Sciences
Volume27
Issue number4
DOIs
StatePublished - Apr 1 2017

Fingerprint

logistics
geological disaster
evaluation
method
hazard
rate
economics
modeling
province
loss
index

Keywords

  • Yunnan Province
  • geographical weighted regression
  • geological disaster susceptibility
  • multi-regression methods
  • spatial accuracy validation
  • support vector regression

ASJC Scopus subject areas

  • Earth and Planetary Sciences (miscellaneous)

Cite this

Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation. / Jiang, Weiguo; Rao, Pingzeng; Cao, Ran; Tang, Zhenghong; Chen, Kun.

In: Journal of Geographical Sciences, Vol. 27, No. 4, 01.04.2017, p. 439-462.

Research output: Contribution to journalArticle

@article{ef07fa8fc7dc4faeab37be9378db08a1,
title = "Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation",
abstract = "Geological disasters not only cause economic losses and ecological destruction, but also seriously threaten human survival. Selecting an appropriate method to evaluate susceptibility to geological disasters is an important part of geological disaster research. The aims of this study are to explore the accuracy and reliability of multi-regression methods for geological disaster susceptibility evaluation, including Logistic Regression (LR), Spatial Autoregression (SAR), Geographical Weighted Regression (GWR), and Support Vector Regression (SVR), all of which have been widely discussed in the literature. In this study, we selected Yunnan Province of China as the research site and collected data on typical geological disaster events and the associated hazards that occurred within the study area to construct a corresponding index system for geological disaster assessment. Four methods were used to model and evaluate geological disaster susceptibility. The predictive capabilities of the methods were verified using the receiver operating characteristic (ROC) curve and the success rate curve. Lastly, spatial accuracy validation was introduced to improve the results of the evaluation, which was demonstrated by the spatial receiver operating characteristic (SROC) curve and the spatial success rate (SSR) curve. The results suggest that: 1) these methods are all valid with respect to the SROC and SSR curves, and the spatial accuracy validation method improved their modelling results and accuracy, such that the area under the curve (AUC) values of the ROC curves increased by about 3{\%}–13{\%} and the AUC of the success rate curve values increased by 15{\%}–20{\%}; 2) the evaluation accuracies of LR, SAR, GWR, and SVR were 0.8325, 0.8393, 0.8370 and 0.8539, which proved the four statistical regression methods all have good evaluation capability for geological disaster susceptibility evaluation and the evaluation results of SVR are more reasonable than others; 3) according to the evaluation results of SVR, the central-southern Yunnan Province are the highest susceptibility areas and the lowest susceptibility is mainly located in the central and northern parts of the study area.",
keywords = "Yunnan Province, geographical weighted regression, geological disaster susceptibility, multi-regression methods, spatial accuracy validation, support vector regression",
author = "Weiguo Jiang and Pingzeng Rao and Ran Cao and Zhenghong Tang and Kun Chen",
year = "2017",
month = "4",
day = "1",
doi = "10.1007/s11442-017-1386-4",
language = "English (US)",
volume = "27",
pages = "439--462",
journal = "Journal of Geographical Sciences",
issn = "1009-637X",
publisher = "Science in China Press",
number = "4",

}

TY - JOUR

T1 - Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation

AU - Jiang, Weiguo

AU - Rao, Pingzeng

AU - Cao, Ran

AU - Tang, Zhenghong

AU - Chen, Kun

PY - 2017/4/1

Y1 - 2017/4/1

N2 - Geological disasters not only cause economic losses and ecological destruction, but also seriously threaten human survival. Selecting an appropriate method to evaluate susceptibility to geological disasters is an important part of geological disaster research. The aims of this study are to explore the accuracy and reliability of multi-regression methods for geological disaster susceptibility evaluation, including Logistic Regression (LR), Spatial Autoregression (SAR), Geographical Weighted Regression (GWR), and Support Vector Regression (SVR), all of which have been widely discussed in the literature. In this study, we selected Yunnan Province of China as the research site and collected data on typical geological disaster events and the associated hazards that occurred within the study area to construct a corresponding index system for geological disaster assessment. Four methods were used to model and evaluate geological disaster susceptibility. The predictive capabilities of the methods were verified using the receiver operating characteristic (ROC) curve and the success rate curve. Lastly, spatial accuracy validation was introduced to improve the results of the evaluation, which was demonstrated by the spatial receiver operating characteristic (SROC) curve and the spatial success rate (SSR) curve. The results suggest that: 1) these methods are all valid with respect to the SROC and SSR curves, and the spatial accuracy validation method improved their modelling results and accuracy, such that the area under the curve (AUC) values of the ROC curves increased by about 3%–13% and the AUC of the success rate curve values increased by 15%–20%; 2) the evaluation accuracies of LR, SAR, GWR, and SVR were 0.8325, 0.8393, 0.8370 and 0.8539, which proved the four statistical regression methods all have good evaluation capability for geological disaster susceptibility evaluation and the evaluation results of SVR are more reasonable than others; 3) according to the evaluation results of SVR, the central-southern Yunnan Province are the highest susceptibility areas and the lowest susceptibility is mainly located in the central and northern parts of the study area.

AB - Geological disasters not only cause economic losses and ecological destruction, but also seriously threaten human survival. Selecting an appropriate method to evaluate susceptibility to geological disasters is an important part of geological disaster research. The aims of this study are to explore the accuracy and reliability of multi-regression methods for geological disaster susceptibility evaluation, including Logistic Regression (LR), Spatial Autoregression (SAR), Geographical Weighted Regression (GWR), and Support Vector Regression (SVR), all of which have been widely discussed in the literature. In this study, we selected Yunnan Province of China as the research site and collected data on typical geological disaster events and the associated hazards that occurred within the study area to construct a corresponding index system for geological disaster assessment. Four methods were used to model and evaluate geological disaster susceptibility. The predictive capabilities of the methods were verified using the receiver operating characteristic (ROC) curve and the success rate curve. Lastly, spatial accuracy validation was introduced to improve the results of the evaluation, which was demonstrated by the spatial receiver operating characteristic (SROC) curve and the spatial success rate (SSR) curve. The results suggest that: 1) these methods are all valid with respect to the SROC and SSR curves, and the spatial accuracy validation method improved their modelling results and accuracy, such that the area under the curve (AUC) values of the ROC curves increased by about 3%–13% and the AUC of the success rate curve values increased by 15%–20%; 2) the evaluation accuracies of LR, SAR, GWR, and SVR were 0.8325, 0.8393, 0.8370 and 0.8539, which proved the four statistical regression methods all have good evaluation capability for geological disaster susceptibility evaluation and the evaluation results of SVR are more reasonable than others; 3) according to the evaluation results of SVR, the central-southern Yunnan Province are the highest susceptibility areas and the lowest susceptibility is mainly located in the central and northern parts of the study area.

KW - Yunnan Province

KW - geographical weighted regression

KW - geological disaster susceptibility

KW - multi-regression methods

KW - spatial accuracy validation

KW - support vector regression

UR - http://www.scopus.com/inward/record.url?scp=85008462107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85008462107&partnerID=8YFLogxK

U2 - 10.1007/s11442-017-1386-4

DO - 10.1007/s11442-017-1386-4

M3 - Article

VL - 27

SP - 439

EP - 462

JO - Journal of Geographical Sciences

JF - Journal of Geographical Sciences

SN - 1009-637X

IS - 4

ER -