Abstract
Landslide represents an increasing menace causing huge casualties and economic losses, and rainfall is a predominant factor inducing landslides. Landslide susceptibility assessment (LSA) is a commonly used and effective method to prevent landslide risk, however, the LSA does not analyze the impact of the rainfall on landslides which is significant and non-negligible. Therefore, the spatiotemporal LSA considering the inducing effect of rainfall is proposed to improve accuracy and applicability. In this study, the influencing factors are selected using the chi-square test, out-of-bag error and multicollinearity test. The spatial LSA are thus obtained using the random forest (RF) model, deep belief networks model and support vector machine, and compared using receiver operating characteristic curve and seed cell area index to determine the optimal assessment result. According to the heavy rainfall characteristics in the study area, the rainfall period is divided into four stages, and the effective rainfall model is employed to generate the rainfall impact (RI) maps of the four stages. The spatiotemporal LSAs are obtained by coupling the optimal spatial LSA and various RI maps and verified using the landslide warning map. The results demonstrate that the optimal spatiotemporal LSA is obtained using the spatial LSA of the RF model and temporal LSA of the rainfall data in the peak stage. It can predict the area where rainfall-induced landslides are likely to occur and prevent landslide risk.
Highlights
Landslides are one of the most common geo-hazards on Earth and result in considerable damage to life and property [1,2]
Based on the heavy rainfall data in August of the study area, the heavy rainfall period is divided into four stages, and the rainfall impact (RI) maps of the four stages are generated using Effective Rainfall Model (ERM)
receiver operating characteristic (ROC) curves, area under the curve (AUC) and seed cell area index (SCAI) to determine that the random forest (RF) model is the optimal model for the spatial landslide susceptibility mapping (LSM) in the study area
Summary
Landslides are one of the most common geo-hazards on Earth and result in considerable damage to life and property [1,2]. It is critical to accurately evaluate landslide-prone areas to effectively determine the locations and times of landslides [3]. Landslide susceptibility assessment (LSA) is an effective risk management measure to prevent landslides and reduce landslide risk [4]. Rainfall-induced landslides are a typical cascading geo-hazard and are attracting the increasing attention of many researchers [5,6]. Rainfall-induced landslides commonly occur after heavy rainfall and may develop into potentially catastrophic movements [7,8]. Heavy rainfall or prolonged rainfall may result in the increase of pore-water pressure and the significant decrease of friction force, which causes slope instability [9,10,11]. In addition to analyzing the spatial LSA using the environmental condition factors, it is necessary to analyze the temporal LSA using the rainfall data to illustrate the impact of heavy rainfall on landslides, which ensures the availability and accuracy of LSA [12,13,14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
