Spatiotemporal Landslide Susceptibility Mapping Incorporating the Effects of Heavy Rainfall: A Case Study of the Heavy Rainfall in August 2021 in Kitakyushu, Fukuoka, Japan

Landslide represents an increasing menace causing huge casualties and economic losses, rainfall is a predominant factor inducing landslides. susceptibility assessment (LSA) commonly used effective method to prevent landslide risk, however, the LSA does not analyze impact of on landslides which significant non-negligible. Therefore, spatiotemporal considering effect proposed improve accuracy applicability. In this study, influencing factors are selected using chi-square test, out-of-bag error multicollinearity test. The spatial thus obtained random forest (RF) model, deep belief networks model support vector machine, compared receiver operating characteristic curve seed cell area index determine optimal result. According heavy characteristics in study area, period divided into four stages, employed generate (RI) maps stages. LSAs by coupling various RI verified warning map. results demonstrate that RF temporal data peak stage. It can predict where rainfall-induced likely occur risk.