Abstract
A serious earthquake could trigger thousands of landslides and produce some slopes more sensitive to slide in future. Landslides could threaten human’s lives and properties, and thus mapping the post-earthquake landslide susceptibility is very valuable for a rapid response to landslide disasters in terms of relief resource allocation and posterior earthquake reconstruction. Previous researchers have proposed many methods to map landslide susceptibility but seldom considered the spatial structure information of the factors that influence a slide. In this study, we first developed a U-net like model suitable for mapping post-earthquake landslide susceptibility. The post-earthquake high spatial airborne images were used for producing a landslide inventory. Pre-earthquake Landsat TM (Thematic Mapper) images and the influencing factors such as digital elevation model (DEM), slope, aspect, multi-scale topographic position index (mTPI), lithology, fault, road network, streams network, and macroseismic intensity (MI) were prepared as the input layers of the model. Application of the model to the heavy-hit area of the destructive 2008 Wenchuan earthquake resulted in a high validation accuracy (precision 0.77, recall 0.90, F1 score 0.83, and AUC 0.90). The performance of this U-net like model was also compared with those of traditional logistic regression (LR) and support vector machine (SVM) models on both the model area and independent testing area with the former being stronger than the two traditional models. The U-net like model introduced in this paper provides us the inspiration that balancing the environmental influence of a pixel itself and its surrounding pixels to perform a better landslide susceptibility mapping (LSM) task is useful and feasible when using remote sensing and GIS technology.
Highlights
Serious earthquakes, those that occurred in mountainous regions can trigger thousands of landslides because of unfavorable geomorphic environments [1]
The multi-scale topographic position index (mTPI) can be used to distinguishes ridges from valleys which contribute to the landslide occurrence
In very short time after a serious earthquake, the U.S Geological Survey (USGS) can produce a series of earthquake products such as macroseismic intensity (MI), peak ground acceleration (PGA), and peak ground velocity (PGV) maps [55,56]
Summary
Those that occurred in mountainous regions can trigger thousands of landslides because of unfavorable geomorphic environments [1]. Machine learning methods such as support vector machine (SVM) [22], decision tree (DT) [23], random forest (RF) [24,25], and artificial neural networks (ANN) [26] have been more popular in the recent years because of their ability of modeling the complex nonlinear relationship between landslides and the influencing factors These machine learning methods perform better in LSM than the heuristic and statistical methods. An U-net like model architecture for post-earthquake LSM was built and discussed to perform better results; the model was trained, validated, and tested on the data collected in a heavy-hit area of the destructive 2008 Wenchuan earthquake; results from the U-net like model were compared with those from traditional LR and SVM models to evaluate their performance
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
