Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logic regression models

Iswar Das Das, A. Stein, N. Kerle, Vinay K. Dadhwal

Research output: Contribution to journalArticleAcademicpeer-review

57 Citations (Scopus)

Abstract

Landslide susceptibility mapping (LSM) along road corridors in the Indian Himalayas is an essential exercise that helps planners and decision makers in determining the severity of probable slope failure areas. Logistic regression is commonly applied for this purpose, as it is a robust and straightforward technique that is relatively easy to handle. Ordinary logistic regression as a data-driven technique, however, does not allow inclusion of prior information. This study presents Bayesian logistic regression (BLR) for landslide susceptibility assessment along road corridors. The methodology is tested in a landslide-prone area in the Bhagirathi river valley in the Indian Himalayas. Parameter estimates from BLR are compared with those obtained from ordinary logistic regression. By means of iterative Markov Chain Monte Carlo simulation, BLR provides a rich set of results on parameter estimation. We assessed model performance by the receiver operator characteristics curve analysis, and validated the model using 50% of the landslide cells kept apart for testing and validation. The study concludes that BLR performs better in posterior parameter estimation in general and the uncertainty estimation in particular.
Original languageEnglish
Pages (from-to)116-125
Number of pages10
JournalGeomorphology
Volume179
DOIs
Publication statusPublished - 2012

Fingerprint

landslide
logistics
road
slope failure
Markov chain
corridor
valley
methodology
river
simulation

Keywords

  • ITC-ISI-JOURNAL-ARTICLE

Cite this

@article{b6fdf949f36742f9a51fc848ba3704fc,
title = "Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logic regression models",
abstract = "Landslide susceptibility mapping (LSM) along road corridors in the Indian Himalayas is an essential exercise that helps planners and decision makers in determining the severity of probable slope failure areas. Logistic regression is commonly applied for this purpose, as it is a robust and straightforward technique that is relatively easy to handle. Ordinary logistic regression as a data-driven technique, however, does not allow inclusion of prior information. This study presents Bayesian logistic regression (BLR) for landslide susceptibility assessment along road corridors. The methodology is tested in a landslide-prone area in the Bhagirathi river valley in the Indian Himalayas. Parameter estimates from BLR are compared with those obtained from ordinary logistic regression. By means of iterative Markov Chain Monte Carlo simulation, BLR provides a rich set of results on parameter estimation. We assessed model performance by the receiver operator characteristics curve analysis, and validated the model using 50{\%} of the landslide cells kept apart for testing and validation. The study concludes that BLR performs better in posterior parameter estimation in general and the uncertainty estimation in particular.",
keywords = "ITC-ISI-JOURNAL-ARTICLE",
author = "Das, {Iswar Das} and A. Stein and N. Kerle and Dadhwal, {Vinay K.}",
year = "2012",
doi = "10.1016/j.geomorph.2012.08.004",
language = "English",
volume = "179",
pages = "116--125",
journal = "Geomorphology",
issn = "0169-555X",
publisher = "Elsevier",

}

Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logic regression models. / Das, Iswar Das; Stein, A.; Kerle, N.; Dadhwal, Vinay K.

In: Geomorphology, Vol. 179, 2012, p. 116-125.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Landslide susceptibility mapping along road corridors in the Indian Himalayas using Bayesian logic regression models

AU - Das, Iswar Das

AU - Stein, A.

AU - Kerle, N.

AU - Dadhwal, Vinay K.

PY - 2012

Y1 - 2012

N2 - Landslide susceptibility mapping (LSM) along road corridors in the Indian Himalayas is an essential exercise that helps planners and decision makers in determining the severity of probable slope failure areas. Logistic regression is commonly applied for this purpose, as it is a robust and straightforward technique that is relatively easy to handle. Ordinary logistic regression as a data-driven technique, however, does not allow inclusion of prior information. This study presents Bayesian logistic regression (BLR) for landslide susceptibility assessment along road corridors. The methodology is tested in a landslide-prone area in the Bhagirathi river valley in the Indian Himalayas. Parameter estimates from BLR are compared with those obtained from ordinary logistic regression. By means of iterative Markov Chain Monte Carlo simulation, BLR provides a rich set of results on parameter estimation. We assessed model performance by the receiver operator characteristics curve analysis, and validated the model using 50% of the landslide cells kept apart for testing and validation. The study concludes that BLR performs better in posterior parameter estimation in general and the uncertainty estimation in particular.

AB - Landslide susceptibility mapping (LSM) along road corridors in the Indian Himalayas is an essential exercise that helps planners and decision makers in determining the severity of probable slope failure areas. Logistic regression is commonly applied for this purpose, as it is a robust and straightforward technique that is relatively easy to handle. Ordinary logistic regression as a data-driven technique, however, does not allow inclusion of prior information. This study presents Bayesian logistic regression (BLR) for landslide susceptibility assessment along road corridors. The methodology is tested in a landslide-prone area in the Bhagirathi river valley in the Indian Himalayas. Parameter estimates from BLR are compared with those obtained from ordinary logistic regression. By means of iterative Markov Chain Monte Carlo simulation, BLR provides a rich set of results on parameter estimation. We assessed model performance by the receiver operator characteristics curve analysis, and validated the model using 50% of the landslide cells kept apart for testing and validation. The study concludes that BLR performs better in posterior parameter estimation in general and the uncertainty estimation in particular.

KW - ITC-ISI-JOURNAL-ARTICLE

UR - https://ezproxy2.utwente.nl/login?url=http://dx.doi.org/10.1016/j.geomorph.2012.08.004

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2012/isi/kerle_lan.pdf

U2 - 10.1016/j.geomorph.2012.08.004

DO - 10.1016/j.geomorph.2012.08.004

M3 - Article

VL - 179

SP - 116

EP - 125

JO - Geomorphology

JF - Geomorphology

SN - 0169-555X

ER -