Landslide Susceptibility Mapping Using Feature Fusion-Based CPCNN-ML in Lantau Island, Hong Kong

Abstract

Landslide susceptibility mapping (LSM) is an effective way to predict spatial probability of landslide occurrence. Existing convolutional neural network (CNN)-based methods apply self-built CNN with simple structure, which failed to reach CNN's full potential on high-level feature extraction, meanwhile ignored the use of numerical predisposing factors. For the purpose of exploring feature fusion based CNN models with greater reliability in LSM, this study proposes an ensemble model based on channel-expanded pre-trained CNN and traditional machine learning model (CPCNN-ML). In CPCNN-ML, pre-trained CNN with mature structure is modified to excavate high-level features of multichannel predisposing factor layers. LSM result is generated by traditional machine learning (ML) model based on hybrid feature of high-level features and numerical predisposing factors. Lantau Island, Hong Kong is selected as study area; temporal landslide inventory is used for model training and evaluation. Experimental results show that CPCNN-ML has ability to predict landslide occurrence with high reliability, especially the CPCNN-ML based on random forest. Contrast experiments with self-built CNN and traditional ML models further embody the superiority of CPCNN-ML. It is worth noting that coastal regions are newly identified landslide-prone regions compared with previous research. This finding is of great reference value for Hong Kong authorities to formulate appropriate disaster prevention and mitigation policies.