Generalized Regression Neural Networks with K-Fold Cross-Validation for Displacement of Landslide Forecasting

摘要

This paper proposes a generalized regression neural networks (GRNNS) with K-fold cross-validation (GRNNSK) for predicting the displacement of landslide. Furthermore, correlation analysis is a fundamental analysis to find the potential input variables for a forecast model. Pearson cross-correlation coefficients (PCC) and mutual information (MI) are applied in the paper. Test on the case study of Liangshuijing (LSJ) landslide in the Three Gorges reservoir in China demonstrate the effectiveness of the proposed approach.