The 3rd Badong International Geohazards Symposium (BIGS2021)

52 / 2021-11-15 10:35:46

Intelligent early warning of High-cut slope in the Resettlement area of the Three Gorges Reservoir area based on machine learning

high-cut slope; stability prediction; machine learning; classification algorithm; regression algorithm

Due to the construction of the Three Gorges project, a large number of high cut slopes have been formed in the resettlement area, which poses a threat to the life and property safety of people in mountainous areas. With the rapid development of big data technology in recent years, various machine learning algorithms are widely used in engineering practice. It is feasible and necessary to use a large number of high cut slope data to train the algorithm so as to predict the stability of high cut slope.

Taking Zigui County, Yichang City, Hubei Province as the research area, this paper carries out data extraction and data preprocessing for the characteristics of high cut slope, designs and studies the regional high cut slope prediction process based on machine learning classification algorithm and the monomer high cut slope prediction process based on machine learning regression algorithm and time series algorithm, Finally, the formulation of comprehensive evaluation rules and system development of high cut slope stability are completed.

Key Words: high-cut slope; stability prediction; machine learning; classification algorithm; regression algorithm