A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping

A. Xing Zhu, Yamin Miao, Rongxun Wang, Tongxin Zhu, Yongcui Deng, Junzhi Liu, Lin Yang, Cheng Zhi Qin, Haoyuan Hong

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

In this study, an expert knowledge-based model, a logistic regression model, and an artificial neural network model were compared for their accuracy and portability in landslide susceptibility mapping. Two study areas (the Kaixian and the Three Gorges areas in China) were selected for this comparison based on their well-known, high landslide hazard. To evaluate the performance of these models and to minimize the impact of the particularity of a study area on model performance, cross-applications of three models between the two study areas were conducted. When the Kaixian area was used as a model development area, prediction accuracy for the expert knowledge-based model, the logistic regression model, and the artificial neural network model were 71.5%, 81.0% and 100.0%, respectively. The high prediction accuracy of the two data-driven models were expected because the observed landslide occurrence used in training the models were also used to validate their respective performance, while the expert knowledge-based model did not use these observations for training. The perfect accuracy for the neural network model can also be attributed to its over-prediction of the susceptibility. When breaking the susceptibility into four classes: very low susceptibility (0–0.25), low susceptibility (0.25–0.5), high susceptibility (0.5–0.75), and very high susceptibility (0.75–1), the observed landslide density at the very high susceptibility level is 0.303/km2, 0.212/km2, and 0.195/km2 for the expert knowledge-based model, the logistic regression model, and the artificial neural network model, respectively. This suggests that the expert knowledge-based model was much better than the other two data-driven models at evaluating landslide occurrence in very high susceptibility areas. When the three models developed in the Kaixian area were applied in the Three Gorges area without any changes, their prediction accuracy dropped to 44.8% for the logistic regression model and 81.6% for the artificial neural network model, while the expert knowledge-based model maintained its initial accuracy level of 82.8%. The landslide density for the very high susceptibility areas in the Three Georges area was 0.275/km2, 0.082/km2, and 0.060/km2 for the expert knowledge-based model, the logistic model, and the artificial neural network model, respectively. These results indicate that the expert knowledge-based model is more effective at predicting areas with very high susceptibility. When the Three Gorges area was used as a model development area and the Kaixian area was used as the model application area, similar results were obtained. Results from the two experiments show that the performance of the logistic regression model and artificial neural network model is not as stable as the expert knowledge-based model when transferred to a new area. This suggests that the expert knowledge-based model is more suitable for landslide susceptibility mapping over large areas.

Original languageEnglish (US)
Pages (from-to)317-327
Number of pages11
JournalCatena
Volume166
DOIs
StatePublished - Jul 1 2018
Externally publishedYes

Fingerprint

landslide
comparative study
artificial neural network
logistics
gorge
prediction

Keywords

  • Artificial neural network
  • Data-driven models
  • Expert knowledge-based model
  • GIS
  • Landslide susceptibility
  • Logistic regression

Cite this

A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping. / Zhu, A. Xing; Miao, Yamin; Wang, Rongxun; Zhu, Tongxin; Deng, Yongcui; Liu, Junzhi; Yang, Lin; Qin, Cheng Zhi; Hong, Haoyuan.

In: Catena, Vol. 166, 01.07.2018, p. 317-327.

Research output: Contribution to journalArticle

Zhu, A. Xing ; Miao, Yamin ; Wang, Rongxun ; Zhu, Tongxin ; Deng, Yongcui ; Liu, Junzhi ; Yang, Lin ; Qin, Cheng Zhi ; Hong, Haoyuan. / A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping. In: Catena. 2018 ; Vol. 166. pp. 317-327.
@article{c0af47bf06ba49b3bb2426a1b16b8b01,
title = "A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping",
abstract = "In this study, an expert knowledge-based model, a logistic regression model, and an artificial neural network model were compared for their accuracy and portability in landslide susceptibility mapping. Two study areas (the Kaixian and the Three Gorges areas in China) were selected for this comparison based on their well-known, high landslide hazard. To evaluate the performance of these models and to minimize the impact of the particularity of a study area on model performance, cross-applications of three models between the two study areas were conducted. When the Kaixian area was used as a model development area, prediction accuracy for the expert knowledge-based model, the logistic regression model, and the artificial neural network model were 71.5{\%}, 81.0{\%} and 100.0{\%}, respectively. The high prediction accuracy of the two data-driven models were expected because the observed landslide occurrence used in training the models were also used to validate their respective performance, while the expert knowledge-based model did not use these observations for training. The perfect accuracy for the neural network model can also be attributed to its over-prediction of the susceptibility. When breaking the susceptibility into four classes: very low susceptibility (0–0.25), low susceptibility (0.25–0.5), high susceptibility (0.5–0.75), and very high susceptibility (0.75–1), the observed landslide density at the very high susceptibility level is 0.303/km2, 0.212/km2, and 0.195/km2 for the expert knowledge-based model, the logistic regression model, and the artificial neural network model, respectively. This suggests that the expert knowledge-based model was much better than the other two data-driven models at evaluating landslide occurrence in very high susceptibility areas. When the three models developed in the Kaixian area were applied in the Three Gorges area without any changes, their prediction accuracy dropped to 44.8{\%} for the logistic regression model and 81.6{\%} for the artificial neural network model, while the expert knowledge-based model maintained its initial accuracy level of 82.8{\%}. The landslide density for the very high susceptibility areas in the Three Georges area was 0.275/km2, 0.082/km2, and 0.060/km2 for the expert knowledge-based model, the logistic model, and the artificial neural network model, respectively. These results indicate that the expert knowledge-based model is more effective at predicting areas with very high susceptibility. When the Three Gorges area was used as a model development area and the Kaixian area was used as the model application area, similar results were obtained. Results from the two experiments show that the performance of the logistic regression model and artificial neural network model is not as stable as the expert knowledge-based model when transferred to a new area. This suggests that the expert knowledge-based model is more suitable for landslide susceptibility mapping over large areas.",
keywords = "Artificial neural network, Data-driven models, Expert knowledge-based model, GIS, Landslide susceptibility, Logistic regression",
author = "Zhu, {A. Xing} and Yamin Miao and Rongxun Wang and Tongxin Zhu and Yongcui Deng and Junzhi Liu and Lin Yang and Qin, {Cheng Zhi} and Haoyuan Hong",
year = "2018",
month = "7",
day = "1",
doi = "10.1016/j.catena.2018.04.003",
language = "English (US)",
volume = "166",
pages = "317--327",
journal = "Catena",
issn = "0341-8162",
publisher = "Elsevier",

}

TY - JOUR

T1 - A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping

AU - Zhu, A. Xing

AU - Miao, Yamin

AU - Wang, Rongxun

AU - Zhu, Tongxin

AU - Deng, Yongcui

AU - Liu, Junzhi

AU - Yang, Lin

AU - Qin, Cheng Zhi

AU - Hong, Haoyuan

PY - 2018/7/1

Y1 - 2018/7/1

N2 - In this study, an expert knowledge-based model, a logistic regression model, and an artificial neural network model were compared for their accuracy and portability in landslide susceptibility mapping. Two study areas (the Kaixian and the Three Gorges areas in China) were selected for this comparison based on their well-known, high landslide hazard. To evaluate the performance of these models and to minimize the impact of the particularity of a study area on model performance, cross-applications of three models between the two study areas were conducted. When the Kaixian area was used as a model development area, prediction accuracy for the expert knowledge-based model, the logistic regression model, and the artificial neural network model were 71.5%, 81.0% and 100.0%, respectively. The high prediction accuracy of the two data-driven models were expected because the observed landslide occurrence used in training the models were also used to validate their respective performance, while the expert knowledge-based model did not use these observations for training. The perfect accuracy for the neural network model can also be attributed to its over-prediction of the susceptibility. When breaking the susceptibility into four classes: very low susceptibility (0–0.25), low susceptibility (0.25–0.5), high susceptibility (0.5–0.75), and very high susceptibility (0.75–1), the observed landslide density at the very high susceptibility level is 0.303/km2, 0.212/km2, and 0.195/km2 for the expert knowledge-based model, the logistic regression model, and the artificial neural network model, respectively. This suggests that the expert knowledge-based model was much better than the other two data-driven models at evaluating landslide occurrence in very high susceptibility areas. When the three models developed in the Kaixian area were applied in the Three Gorges area without any changes, their prediction accuracy dropped to 44.8% for the logistic regression model and 81.6% for the artificial neural network model, while the expert knowledge-based model maintained its initial accuracy level of 82.8%. The landslide density for the very high susceptibility areas in the Three Georges area was 0.275/km2, 0.082/km2, and 0.060/km2 for the expert knowledge-based model, the logistic model, and the artificial neural network model, respectively. These results indicate that the expert knowledge-based model is more effective at predicting areas with very high susceptibility. When the Three Gorges area was used as a model development area and the Kaixian area was used as the model application area, similar results were obtained. Results from the two experiments show that the performance of the logistic regression model and artificial neural network model is not as stable as the expert knowledge-based model when transferred to a new area. This suggests that the expert knowledge-based model is more suitable for landslide susceptibility mapping over large areas.

AB - In this study, an expert knowledge-based model, a logistic regression model, and an artificial neural network model were compared for their accuracy and portability in landslide susceptibility mapping. Two study areas (the Kaixian and the Three Gorges areas in China) were selected for this comparison based on their well-known, high landslide hazard. To evaluate the performance of these models and to minimize the impact of the particularity of a study area on model performance, cross-applications of three models between the two study areas were conducted. When the Kaixian area was used as a model development area, prediction accuracy for the expert knowledge-based model, the logistic regression model, and the artificial neural network model were 71.5%, 81.0% and 100.0%, respectively. The high prediction accuracy of the two data-driven models were expected because the observed landslide occurrence used in training the models were also used to validate their respective performance, while the expert knowledge-based model did not use these observations for training. The perfect accuracy for the neural network model can also be attributed to its over-prediction of the susceptibility. When breaking the susceptibility into four classes: very low susceptibility (0–0.25), low susceptibility (0.25–0.5), high susceptibility (0.5–0.75), and very high susceptibility (0.75–1), the observed landslide density at the very high susceptibility level is 0.303/km2, 0.212/km2, and 0.195/km2 for the expert knowledge-based model, the logistic regression model, and the artificial neural network model, respectively. This suggests that the expert knowledge-based model was much better than the other two data-driven models at evaluating landslide occurrence in very high susceptibility areas. When the three models developed in the Kaixian area were applied in the Three Gorges area without any changes, their prediction accuracy dropped to 44.8% for the logistic regression model and 81.6% for the artificial neural network model, while the expert knowledge-based model maintained its initial accuracy level of 82.8%. The landslide density for the very high susceptibility areas in the Three Georges area was 0.275/km2, 0.082/km2, and 0.060/km2 for the expert knowledge-based model, the logistic model, and the artificial neural network model, respectively. These results indicate that the expert knowledge-based model is more effective at predicting areas with very high susceptibility. When the Three Gorges area was used as a model development area and the Kaixian area was used as the model application area, similar results were obtained. Results from the two experiments show that the performance of the logistic regression model and artificial neural network model is not as stable as the expert knowledge-based model when transferred to a new area. This suggests that the expert knowledge-based model is more suitable for landslide susceptibility mapping over large areas.

KW - Artificial neural network

KW - Data-driven models

KW - Expert knowledge-based model

KW - GIS

KW - Landslide susceptibility

KW - Logistic regression

UR - http://www.scopus.com/inward/record.url?scp=85056993341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056993341&partnerID=8YFLogxK

U2 - 10.1016/j.catena.2018.04.003

DO - 10.1016/j.catena.2018.04.003

M3 - Article

VL - 166

SP - 317

EP - 327

JO - Catena

JF - Catena

SN - 0341-8162

ER -