Fuzzy c-means clustering for landslide mapping in Malang regency

Closed

Dhoriva Urwatul Wutsqa, Amelia Septi Aryani, Sri Andayani, Kismiantini

2020 Journal of Advanced Research in Dynamical and Control Systems Vol. 12 Issue 7 Special Issue Article Cited by 0 Quartile

Abstract

A landslide is a geological event in which land movements occur such as falling rocks or large lumps of soil. Landslides are one of the natural disasters that often occur in Indonesia. Potential landslides mainly occur in hilly areas of tropical wet areas such as Malang Regency. The purpose of this paper is to create a landslide vulnerability map in Malang Regency using the fuzzy C-means (FCM) method. This work uses data available at the Central Statistics Agency, Malang regency. We use 3 parameters to cluster 33 districts in Malang regency, including land slope, soil type, and land use. Two cluster validity indices, namely Xie-Beni index and partition coefficient index to determine the optimum number of clusters. The result shows that both indices reach optimum at two clusters. The map of the clustering result is presented. The cluster involves 8 districts indicates prone landslides regions since it is dominated by regions with a slope above 15%, latosols type, and the rice fields, settlements, and farmland usage. While 25 other districts lead to not prone landslide regions with respect to the land slope and soil type, but they are categorized as landslide prone regions regarding the land use. © 2020, Institute of Advanced Scientific Research, Inc.. All rights reserved.

Affiliations

Department of Statistics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Yogyakarta, Yogyakarta, Indonesia; Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Yogyakarta, Yogyakarta, Indonesia