Preprints
https://doi.org/10.5194/nhess-2023-73
https://doi.org/10.5194/nhess-2023-73
08 Jun 2023
 | 08 Jun 2023
Status: this discussion paper is a preprint. It has been under review for the journal Natural Hazards and Earth System Sciences (NHESS). The manuscript was not accepted for further review after discussion.

Prediction of landslide induced debris’ severity using machine learning algorithms: a case of South Korea

Tuganishuri Jérémie, Chan-Young Yune, Gihong Kim, Seung Woo Lee, Manik Adhikari, and Sang-Guk Yum

Abstract. Rainfall-induced landslides frequently occur in the mountainous region of the Korean peninsula. The resulting landslide-induced debris causes extreme property damage, huge financial losses, and human deaths. To mitigate their effect different landslide susceptibility mapping is frequently used. However, these methods do identify regions with potential landslides but they do not quantify their severity. In this paper, multi-category ordered machine models, namely, proportional odd logistic regression (POLR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (EGB) methods, are proposed to fill the specified gap. Moreover, the exploratory data analysis on the landslide-induced debris dataset has been conducted to examine patterns and relationships between landslide-induced debris severity(size), causal factors(rainfall), and influencing factors. Findings revealed that cumulative three days’ rainfall and slope length were most responsible for the severity of landslide-originated debris severity and slopes between 20° to 40° were identified as the most vulnerable region. Furthermore, the predictive accuracy statistics were compared to assess the suitable model for debris severity for the Korean case. The RF and EGB ranked higher with an overall accuracy of 90.07 % and 86.09 % and kappa of 0.72 and 0.61 on the validation set, respectively. The findings of this research may be useful in the identification of high-risk zones for extreme rainfall-induced debris to elaborate mitigation and resilience policies, post-disaster rehabilitation planning, and land use management.

Tuganishuri Jérémie et al.

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2023-73', Anonymous Referee #1, 29 Jun 2023
    • AC1: 'Reply on RC1', Sang-Guk Yum, 01 Sep 2023
  • RC2: 'Comment on nhess-2023-73', Anonymous Referee #2, 17 Jul 2023
    • AC2: 'Reply on RC2', Sang-Guk Yum, 01 Sep 2023

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on nhess-2023-73', Anonymous Referee #1, 29 Jun 2023
    • AC1: 'Reply on RC1', Sang-Guk Yum, 01 Sep 2023
  • RC2: 'Comment on nhess-2023-73', Anonymous Referee #2, 17 Jul 2023
    • AC2: 'Reply on RC2', Sang-Guk Yum, 01 Sep 2023

Tuganishuri Jérémie et al.

Tuganishuri Jérémie et al.

Viewed

Total article views: 539 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
412 104 23 539 10 13
  • HTML: 412
  • PDF: 104
  • XML: 23
  • Total: 539
  • BibTeX: 10
  • EndNote: 13
Views and downloads (calculated since 08 Jun 2023)
Cumulative views and downloads (calculated since 08 Jun 2023)

Viewed (geographical distribution)

Total article views: 521 (including HTML, PDF, and XML) Thereof 521 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 15 Jan 2024
Download
Short summary
The prediction of the size of rainfall-induced debris in South Korea was analyzed. The model suitability was carried out and Random forest was the most suitable for the Size of debris prediction. The most contributing factor in the model was slope length and the most vulnerable region to higher frequency and severe debris was Gangwon province. The findings may be used for rainfall induced-debris prevention policies and post-disaster rehabilitation planning.
Altmetrics