DOI QR코드

DOI QR Code

Prediction of Landslide Probability around Railway using Decision Tree Model

Decision Tree model을 이용한 철도 주변 산사태 발생가능성 예측

  • Yun, Jung-Mann (Department of Construction Information System, ShinAnsan University) ;
  • Song, Young-Suk (Geologic Environment Division, Korea Institute of Geoscience and Mineral Resources) ;
  • Bak, Gueon Jun (Hanshin Engineering and Construction Co.) ;
  • You, Seung-Kyong (Department of Civil Engineering, Myongji College)
  • Received : 2017.11.17
  • Accepted : 2017.12.14
  • Published : 2017.12.30

Abstract

In this study, the prediction of landslide probability was performed to the study area located in ${\bigcirc}{\bigcirc}$ area of Muan-gun, Jeonnam Province around Honam railway using the computer program SHAPP ver 1.0 developed by a decision tree model. The soil samples were collected at total 8 points, and soil tests were performed to measure soil properties. The thematic maps of soil properties such as coefficient of permeability and void ratio were made on the basis of soil test results. The slope angle analysis of topography was performed using a digital map. As the prediction result of landslide probability, 435 cells among total 15,552 cells were predicted to be in the event of landslides. Therefore, the predicted area of occurring landslides may be $43,500m^2$ because the analyzed cell size was $10m{\times}10m$.

본 연구에서는 Decision Tree model을 기반으로 개발된 산사태 예측프로그램 SHAPP ver 1.0을 이용하여 전라남도 무안군 ${\bigcirc}{\bigcirc}$지역의 호남선 철도 주변에 대한 산사태 발생예측을 실시하였다. 이를 위하여 먼저 대상지역의 총 8개소에서 토층시료를 채취하고, 이에 대한 토질시험을 실시하였다. 대상지역에 대한 토질시험결과를 토대로 투수계수와 간극비에 대한 주제도를 작성하고 수치지형도를 이용하여 지형의 경사분석을 실시하였다. 이를 이용하여 산사태 발생예측을 실시한 결과 총 15,552개의 해석셀 가운데 435개의 셀에서 산사태가 발생될 것으로 예측되었다. 이때 해석셀의 크기는 $10m{\times}10m$이므로 산사태 발생예상 면적은 $43,500m^2$으로 나타났다.

Keywords

References

  1. Brand, E. W. (1981), "Some thoughts on rainfall-induced slope failures", Proc. 10th International Conference on Soil Mechanics Foundation Engineering, Stockholm, The Netherlands, pp.373-376.
  2. Das, B. M. (1990), Principles of geotechnical engineering, PWS-KENT, Boston.
  3. Hong, W. P., Kim, W. Y., Song, Y. S., and Lim, S. G. (2004), "Prediction of landslide using artificial neural network model", Journal of the Korean Geotechnical Society, Vol.20, No.4, pp.67-75. (In Korean)
  4. Kim, W. Y., Chae, B. G., Kim, K. S., Cho, Y. C., Choi, Y. S., Lee, C. O., Lee, C. W., Kim, G. Y., Kim, J. H., and Kim, J. M. (2003), Prediction and mitigation of landslide hazards, Ministry of Science and Technology, KR-03-(T)-03, 339p. (In Korean)
  5. Korean Geotechnical Society (2011), Report on the causes investigation and restoration measures of Mt. Woomyeon landslide, KGS11-250, 262p. (In Korean)
  6. Olivier, M. Bell, F. G., and Jemy, C. A. (1994), "The effect of rainfall on slope failure, with examples from the Greater Durban area", Proc. 7th International Conference on IAEG. Vol.3, pp.1629-1636.
  7. Song, Y. S., Cho, Y. C., Seo, Y. S., and Ahn, S. R. (2009), "Development and its application of computer program for slope hazards prediction using decision tree model", Journal of the Korean Society of Civil Engineers, Vol.29, No.2C, pp.59-69. (In Korean)