Landslide susceptibility prediction based on a semi-supervised multiple-layer perceptron model
- PDF / 2,290,365 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 240 Views
Faming Huang I Zhongshan Cao I Shui-Hua Jiang I Chuangbing Zhou I Jinsong Huang I Zizheng Guo
Landslide susceptibility prediction based on a semi-supervised multiple-layer perceptron model
Abstract Conventional supervised and unsupervised machine learning models used for landslide susceptibility prediction (LSP) have many drawbacks, such as an insufficient number of recorded landslide samples, and the subjective and random selection of non-landslide samples. To overcome these drawbacks, a semisupervised multiple-layer perceptron (SSMLP) is innovatively proposed with several processes: (1) an initial landslide susceptibility map (LSM) is produced using the multiple-layer perceptron (MLP) based on the original recorded landslide samples and related environmental factors; (2) the initial LSM is respectively classified into five areas with very high, high, moderate, low and very low susceptible levels; (3) some reasonable grid units from the areas with very high susceptible level are selected as new landslide samples to expand the original landslide samples; (4) reasonable non-landslide samples are selected from the areas with very low susceptible level; and (5) the expanded landslide samples, reasonable selected non-landslide samples and related environmental factors are put into the MLP once again to predict the final LSM. The Xunwu County of Jiangxi Province in China is selected as the study area. Conventional supervised machine learning (i.e. MLP) and unsupervised machine learning (i.e. K-means clustering model) are selected for comparisons. The comparative results indicate that the SSMLP model has a considerably higher LSP performance than the MLP and K-means clustering in Xunwu County. The SSMLP model successfully addresses the drawbacks existed in the conventional machine learning for LSP. Keywords Landslide susceptibility prediction . Supervised machine learning . Unsupervised machine learning . Semisupervised machine learning . Multiple-layer perceptron . Kmeans clustering Introduction Landslides lead to serious casualties and large economic losses around the world. It is significant to implement the regional landslide susceptibility prediction (LSP) and to guide landslide disaster prevention and mitigation projects (Jiang et al. 2018; Pham et al. 2017; Yu and Lu 2018; Zhu et al. 2018). The modelling processes of LSP involve several important issues, including the acquisition of recorded landslide and non-landslide samples, the extraction of landslide-related environmental factors and the selection of the LSP model. Many types of probabilistic, heuristic, deterministic, conventional statistical and machine learning models have been proposed for LSP, and it is a crucial step to select an appropriate model (Marjanović et al. 2011). According to Huang et al. (2020a), Pham et al. (2017) and Zhu et al. (2018), compared with other types of models, machine learning models can more accurately reflect the nonlinear relationships between landslide susceptibility indexes (LSIs) and environmental factors and have a highe
Data Loading...
