A novel grey multivariate model for forecasting landslide displacement. (August 2021)

• Record Type: Journal Article
• Authors: Li, S.H.; Zhu, L.; Wu, Y.; Lei, X.Q.
• Is Part Of: Engineering applications of artificial intelligence. Volume 103(2021)
• Publication Date: 2021-08
• Subjects: Landslide displacement -- Forecast -- Grey multivariate prediction model -- Hausdorff derivative -- Particle swarm optimization algorithm; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2021.104297
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Forecasting landslide displacement is an important issue in engineering geology. In this field, it is difficult to accurately forecast the displacement of the step point of a step-type landslide. In this study, a novel grey multivariate model is proposed for forecasting landslide displacement. The proposed model transforms the original sequence by using the Hausdorff derivative operator, determines the model parameters by using the particle swarm optimization algorithm, and uses the trapezoidal integral formula to calculate the predicted value. Two numerical examples show that the average absolute relative error and mean squared error of the proposed model are smaller than those of the recursive discrete multivariate grey model and the multivariable grey model with structure compatibility. The proposed model is used to forecast the displacement of the Bazimen landslide in the Three Gorges Reservoir area of China. The previous month's displacement, precipitation, and change in the reservoir water level are used as input variables. The results show that the performance of the proposed model is superior to that of the extreme learning machine model. This paper provides an effective method for forecasting displacement of the step point of a step-type landslide.