Research on landslide sliding distance prediction model based on multiple nonlinear regression and BP neural network

Landslide disasters seriously threaten the safety of human life and property and have a certain impact on land resources. The landslide sliding distance directly indicates the impact and accumulation range size of landslides, which is an important parameter for estimating the affected area of landslides and assessing the potential risk of landslides and is also an indicator that needs to be focused on in landslide prevention and mitigation work. In order to predict the landslide hazard range more accurately and efficiently, this paper uses the theories of multivariate nonlinear regression and BP neural network to estimate the sliding distance of the landslide, respectively. And to study examples of landslides in the Tianshui region, the results show that both models can be used to predict landslide. Compared with the actual results, the BP neural network has a higher degree of fit and accuracy.