Study on the Combination of S-growth Curves Based on Ultra-Wideband Displacement Ranging for Predicting Landslides

In order to improve the prediction accuracy of landslide deformation prediction, a combination prediction method based on S-shaped growth curve is adopted to combine the Verhulst model and Pearl model, which are commonly used in landslide early warning and forecasting, with optimal weights, and the combination prediction model is applied to the UWB-based displacement ranging and deformation dataset for validation studies to realize the prediction of slope displacement changes. The results show that the Verhulst model is better than the Pearl model in the single prediction model, but the Pearl model is better in the fitting effect, while the combined prediction model based on the optimal weights can make full use of the advantages of the single prediction model, and can effectively improve the accuracy of the landslide deformation prediction. The combination prediction model based on optimal weights can fully utilize the advantages of a single prediction model and effectively improve the accuracy of landslide deformation prediction. The combination prediction model based on optimal weights can make full use of the advantages of a single prediction model and can effectively improve the accuracy of landslide deformation prediction.