Landslide susceptibility mapping using ensemble fuzzy clustering: A case study in ponorogo, east java, Indonesia

Abstract

Landslide susceptibility maps are vital for natural disaster mitigation activities. It can be a basic information to make appropriate mitigation plan. In the present study, we propose ensemble fuzzy clustering to produce the landslide susceptibility map for Ponorogo. The mapping process is based on five factors which play a dominant role in the occurrence of landslide. The factors are rainfall, land use, slope angle, geology, and elevation. As a result, from 316 areas in Ponorogo, 202 areas were mapped in very low level, 94 areas in medium level and 20 areas in the high level of vulnerability. Finally, the validation of landslide susceptibility map was carried out using Pearson's chi-square test. The chi-square value shows higher value than the critical value. It shows that the model has good accuracy in predicting the landslide susceptibility in Ponorogo. The map was visualized on web-based to make it easier to use and can be used for mitigation activities.