Landslide displacement prediction model based on multisource monitoring data fusion

Abstract

This study presents a displacement prediction model that integrating various monitoring data sources to comprehensive landslide monitoring information utilization. The research focuses on the landslide in Lingwan Village, utilizing Ridge Regression (RR) to integrate diverse monitoring data. The fused displacement data undergo decomposition into trend and periodic terms using the Smoothness Priors Approach (SPA). The Autoregressive Integrated Moving Average (ARIMA) model predicts trend and periodic term displacements separately, which are then combined to forecast the overall landslide surface displacement accurately. The RR model demonstrates a strong correlation coefficient of 0.998, indicating high predictive ability. Trend term displacement prediction outperformed periodic term prediction, especially during the rainy season. The RR-SPA-ARIMA model has an average absolute error of 1.73 mm, a mean bias error of −0.08 mm, and a root mean square error of 1.87 mm. The model demonstrates high prediction accuracy.