Machine Learning for Landslide Susceptibility Mapping Using Phyton in Sigi Biromaru Area (Near Palu), Central Sulawesi, Indonesia

Abstract

Sigi Biromaru is near Palu City; both experienced the Palu earthquake on 28 September 2018. Unlike Palu City, a flat area, Sigi Biromaru is hilly, so it experienced landslides after the big earthquake. This study performed landslide susceptibility mapping for Sigi Biromaru using a machine learning method, namely random forest. Nine parameters were used, i.e., altitude, slope, lithology, peak ground acceleration, land cover, river density, lineament density, rainfall, and aspect. The total data points were 530, half landslide samples and the other half non-landslide samples. We used 70% of the data points to train the model and the rest to evaluate the model. The landslide susceptibility map produced by random forest with no hyperparameter tuning has an area under the curve (AUC) of 0.94 for the success rate and 0.91 for the predictive rate. This study used a novel method in which the non-landslide locations represent the safe zone area, sampled randomly from the lowest class of landslide susceptibility area based on a bivariate statistical model. This study is highly recommended for the initial phase of landslide hazard mitigation.