Abstract:
Landslide displacement prediction is an important basis of predicting landslide disasters. Most of the previous landslide displacement prediction models include time series prediction models, BP neural network prediction models, Gaussian fitting prediction models, and various other nonlinear prediction models. However, these landslide displacement prediction models lack the foundation of mechanical theory in the establishment and have no pertinence in the prediction and analysis of landslide displacement resulting from diverse mechanical properties. In this paper, a nonlinear prediction model of landslide creep displacement based on genetic optimization algorithm is proposed for the prediction of gravity creep landslide displacement. Using the cumulative horizontal displacement data from monitoring point J05 on the eastern side of the Lujiapo landslide as a case study, the test area and prediction area are delimited for model prediction analysis. The results of the new model are compared with those of Gaussian fitting model and BP neural network model. The results indicate that, in comparison to the traditional prediction models, the new model exhibits improved predictive performance, offering a certain engineering value and practical value.