Landslide Early Warning Model Based on the Coupling of Limit Learning Machine and Entropy Method
Ning Zhang, Qing Li, Chuangjiang Li, Yongbo He · Journal of Physics Conference Series · 2019
Monitoring and early warning are the means and methods to reduce landslide hazards. Traditional landslide monitoring methods are single, and the accuracy of statistical prediction model and deterministic prediction model are low. Aiming at this situation, a landslide warning model is proposed to comprehensively monitor the landslide impact factor and combine the Extreme Learning Machine with the Entropy method. The experimental results show that the results obtained by this method are consistent with the actual situation, and the predicted values are basically consistent with the measured values; the accuracy is 97.21%, which is higher than BP neural network; provide a feasible method for landslide warning model.