Preliminary Study of Landslide Susceptibility Modeling with Random Forest Algorithm Using R (Case Study: the Cisangkuy Sub-watershed)

• Published in: IOP conference series. Earth and environmental science 2021-12, Vol.936 (1), p.12015
• Main Authors: Sukristiyanti, S, Wikantika, K, Sadisun, I A, Yayusman, L F, Soebowo, E
• Format: Article
• Language: English
• Subjects: Algorithms; Cell size; Geological hazards; Hazard mitigation; Landslides; Landslides & mudslides; Mitigation; Spatial data; Spatial discrimination; Spatial resolution; Susceptibility; Watersheds
• ISSN: 1755-1307; 1755-1315
• DOI: 10.1088/1755-1315/936/1/012015

Landslide susceptibility mapping is an initial measure in the landslide hazard mitigation. This study aims to evaluate landslide susceptibility in the Cisangkuy Sub-watershed, a part of Bandung Basin. Twenty-seven landslide variables were involved in this modeling derived from various data sources. As a target, 25 landslide polygons obtained through a visual interpretation of Google Earth timeseries images and 33 landslide points obtained from a field survey and an official landslide report, were used as landslide inventory data. All spatial data were prepared in the same cell size referring to the highest spatial resolution of data involved in this modeling, i.e., 8.34 m. Fifty-eight (58) landslide locations covering an area of 0.87 Ha are equivalent to 1040 cells in the raster format. In total, 2040 samples consisting of landslides and non-landslides with the same ratio, were trained using random forest algorithm. Non-landslides were sampled randomly from landslide-free cells. This modeling was executed using R environment. In this study, the result was two labels, susceptible and non-susceptible. This model provided an excellent performance, its accuracy reached 98.56%. This research needs an improvement to provide a probability that has a range of 0 to 1 to show the level of landslide susceptibility.