Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network

Y. Li, G. Chen, C. Tang, G. Zhou, L. Zheng

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

A GIS-based method for the assessment of landslide susceptibility in a selected area of Qingchuan County in China is proposed by using the back-propagation Artificial Neural Network model (ANN). Landslide inventory was derived from field investigation and aerial photo interpretation. 473 landslides occurred before the Wenchuan earthquake (which were thought as rainfall-induced landslides (RIL) in this study), and 885 earthquake-induced landslides (EIL) were recorded into the landslide inventory map. To understand the different impacts of rainfall and earthquake on landslide occurrence, we first compared the variations between landslide spatial distribution and conditioning factors. Then, we compared the weight variation of each conditioning factor derived by adjusting ANN structure and factors combination respectively. Last, the weight of each factor derived from the best prediction model was applied to the entire study area to produce landslide susceptibility maps. Results show that slope gradient has the highest weight for landslide susceptibility mapping for both RIL and EIL. The RIL model built with four different factors (slope gradient, elevation, slope height and distance to the stream) shows the best success rate of 93 %; the EIL model built with five different factors (slope gradient, elevation, slope height, distance to the stream and distance to the fault) has the best success rate of 98 %. Furthermore, the EIL data was used to verify the RIL model and the success rate is 92 %; the RIL data was used to verify the EIL model and the success rate is 53 %.

Original languageEnglish
Pages (from-to)2719-2729
Number of pages11
JournalNatural Hazards and Earth System Science
Volume12
Issue number8
DOIs
Publication statusPublished - Sep 21 2012

Fingerprint

artificial neural network
landslide
GIS
earthquake
rainfall
conditioning
back propagation

All Science Journal Classification (ASJC) codes

  • Earth and Planetary Sciences(all)

Cite this

Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network. / Li, Y.; Chen, G.; Tang, C.; Zhou, G.; Zheng, L.

In: Natural Hazards and Earth System Science, Vol. 12, No. 8, 21.09.2012, p. 2719-2729.

Research output: Contribution to journalArticle

@article{5f54aadbdbaa4e2cbe9df962d57c2e7f,
title = "Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network",
abstract = "A GIS-based method for the assessment of landslide susceptibility in a selected area of Qingchuan County in China is proposed by using the back-propagation Artificial Neural Network model (ANN). Landslide inventory was derived from field investigation and aerial photo interpretation. 473 landslides occurred before the Wenchuan earthquake (which were thought as rainfall-induced landslides (RIL) in this study), and 885 earthquake-induced landslides (EIL) were recorded into the landslide inventory map. To understand the different impacts of rainfall and earthquake on landslide occurrence, we first compared the variations between landslide spatial distribution and conditioning factors. Then, we compared the weight variation of each conditioning factor derived by adjusting ANN structure and factors combination respectively. Last, the weight of each factor derived from the best prediction model was applied to the entire study area to produce landslide susceptibility maps. Results show that slope gradient has the highest weight for landslide susceptibility mapping for both RIL and EIL. The RIL model built with four different factors (slope gradient, elevation, slope height and distance to the stream) shows the best success rate of 93 {\%}; the EIL model built with five different factors (slope gradient, elevation, slope height, distance to the stream and distance to the fault) has the best success rate of 98 {\%}. Furthermore, the EIL data was used to verify the RIL model and the success rate is 92 {\%}; the RIL data was used to verify the EIL model and the success rate is 53 {\%}.",
author = "Y. Li and G. Chen and C. Tang and G. Zhou and L. Zheng",
year = "2012",
month = "9",
day = "21",
doi = "10.5194/nhess-12-2719-2012",
language = "English",
volume = "12",
pages = "2719--2729",
journal = "Natural Hazards and Earth System Sciences",
issn = "1561-8633",
publisher = "European Geosciences Union",
number = "8",

}

TY - JOUR

T1 - Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network

AU - Li, Y.

AU - Chen, G.

AU - Tang, C.

AU - Zhou, G.

AU - Zheng, L.

PY - 2012/9/21

Y1 - 2012/9/21

N2 - A GIS-based method for the assessment of landslide susceptibility in a selected area of Qingchuan County in China is proposed by using the back-propagation Artificial Neural Network model (ANN). Landslide inventory was derived from field investigation and aerial photo interpretation. 473 landslides occurred before the Wenchuan earthquake (which were thought as rainfall-induced landslides (RIL) in this study), and 885 earthquake-induced landslides (EIL) were recorded into the landslide inventory map. To understand the different impacts of rainfall and earthquake on landslide occurrence, we first compared the variations between landslide spatial distribution and conditioning factors. Then, we compared the weight variation of each conditioning factor derived by adjusting ANN structure and factors combination respectively. Last, the weight of each factor derived from the best prediction model was applied to the entire study area to produce landslide susceptibility maps. Results show that slope gradient has the highest weight for landslide susceptibility mapping for both RIL and EIL. The RIL model built with four different factors (slope gradient, elevation, slope height and distance to the stream) shows the best success rate of 93 %; the EIL model built with five different factors (slope gradient, elevation, slope height, distance to the stream and distance to the fault) has the best success rate of 98 %. Furthermore, the EIL data was used to verify the RIL model and the success rate is 92 %; the RIL data was used to verify the EIL model and the success rate is 53 %.

AB - A GIS-based method for the assessment of landslide susceptibility in a selected area of Qingchuan County in China is proposed by using the back-propagation Artificial Neural Network model (ANN). Landslide inventory was derived from field investigation and aerial photo interpretation. 473 landslides occurred before the Wenchuan earthquake (which were thought as rainfall-induced landslides (RIL) in this study), and 885 earthquake-induced landslides (EIL) were recorded into the landslide inventory map. To understand the different impacts of rainfall and earthquake on landslide occurrence, we first compared the variations between landslide spatial distribution and conditioning factors. Then, we compared the weight variation of each conditioning factor derived by adjusting ANN structure and factors combination respectively. Last, the weight of each factor derived from the best prediction model was applied to the entire study area to produce landslide susceptibility maps. Results show that slope gradient has the highest weight for landslide susceptibility mapping for both RIL and EIL. The RIL model built with four different factors (slope gradient, elevation, slope height and distance to the stream) shows the best success rate of 93 %; the EIL model built with five different factors (slope gradient, elevation, slope height, distance to the stream and distance to the fault) has the best success rate of 98 %. Furthermore, the EIL data was used to verify the RIL model and the success rate is 92 %; the RIL data was used to verify the EIL model and the success rate is 53 %.

UR - http://www.scopus.com/inward/record.url?scp=84866312529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866312529&partnerID=8YFLogxK

U2 - 10.5194/nhess-12-2719-2012

DO - 10.5194/nhess-12-2719-2012

M3 - Article

AN - SCOPUS:84866312529

VL - 12

SP - 2719

EP - 2729

JO - Natural Hazards and Earth System Sciences

JF - Natural Hazards and Earth System Sciences

SN - 1561-8633

IS - 8

ER -