Landslides susceptibility assessment and risk mapping using logistic regression and geographical information system

Faten Syaira Buslima, Rohayu Che Omar, Rasyikin Roslan, Intan Nor Zuliana Baharuddin, Badariah Solemon, Warishah Abdul Wahab, Vignesvaran Gunasagaran

Research output: Contribution to specialist publicationArticle

Abstract

Rapid development in the agriculture sector, land clearing, and construction have a great impact on the surface and soils structure especially in the mountainous area, for example, Cameron Highlands. These activities coupled with natural triggering factors like aspect of slope, elevation, geology, angle of slope, curvature, and rainfall may lead to serious geological hazard such as landslides. Cameron Highlands is one of the regions that is known to be susceptible to landslides. A study was carried out to classify susceptible areas and guide to the risk management. In this study, Logistics Regression (LR) using Geographical Information System (GIS) was applied to assess the susceptibility of landslides at Cameron Highlands. Ten (10) landslide contributing factors are taking into consideration including elevation, aspect, geology, slope, curvature, land use, distance from the fault, distance from drainage and road as well as rainfall. Based on the result, the LR approach obtained 82.5% landslides prediction accuracy and considered as a good result for the prediction. With the right information and updates from the landslides susceptibility map, it will assist the local authority in mitigating, treating and controlling this natural hazard at an early stage before any landslide happen.

Original languageEnglish
Pages3308-3315
Number of pages8
Volume81
Specialist publicationTest Engineering and Management
Publication statusPublished - 16 Dec 2019

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Mechanics of Materials
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Landslides susceptibility assessment and risk mapping using logistic regression and geographical information system'. Together they form a unique fingerprint.

  • Cite this

    Buslima, F. S., Omar, R. C., Roslan, R., Baharuddin, I. N. Z., Solemon, B., Wahab, W. A., & Gunasagaran, V. (2019). Landslides susceptibility assessment and risk mapping using logistic regression and geographical information system. Test Engineering and Management, 81, 3308-3315.