期刊
NATURAL HAZARDS
卷 107, 期 2, 页码 1709-1729出版社
SPRINGER
DOI: 10.1007/s11069-021-04655-3
关键词
Step-type landslide; Displacement prediction; The Three Gorges Reservoir area; Intelligent water cycle algorithm; Extreme learning machine
资金
- Fundamental Research Funds for the Central Universities [2015XKMS035]
This study combines the water cycle algorithm and extreme learning machine to improve the prediction accuracy of step-wise landslides, determining the main influencing factors using gray relational grade analysis and using them as input items for the model. The results show that the model has a faster convergence rate and higher prediction accuracy compared to traditional back-propagation neural network and ELM models.
Landslides are one of the most destructive geological disasters and have been caused many casualties and economic losses every year in the world. The reservoir area formed by the world's largest hydropower project, Three Gorges Hydropower project of China, has become a natural testing ground for landslide prediction in the hope of reducing losses. In this paper, a new algorithm with strong optimization ability, the water cycle algorithm (WCA), is combined with the extreme learning machine (ELM) to improve the prediction accuracy of step-wise landslide. The gray relational grade analysis method was adopted to determine the main influencing factors of the landslide's periodic displacement. Then, the determined factors were used as the input items of the proposed WCA-ELM model, and the corresponding periodic displacement was used as the model output item. Taking the Liujiabao landslide in the Three Gorges Reservoir area as a case history, the proposed model was verified through a comparison with the measurements. The results showed that the model has a faster convergence rate and higher prediction accuracy than the traditional back-propagation neural network model and ELM-model. The water cycle algorithm is suitable for optimizing the accuracy of the extreme learning machine model in landslide prediction.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据