Selective ensemble deep bidirectional RVFLN for landslide displacement prediction

Landslide displacement prediction is a challenging and important subject in landslide research. To improve the prediction accuracy of and reduce disasters caused by landslides, we propose a selective ensemble deep bidirectional Random Vector Functional Link Network (sedb-RVFLN) for landslide displacement prediction in which each independent hidden layer is linked to a different output layer. In this paper, to reduce the number of hidden nodes without affecting the efficiency of network training, an incremental learning method is utilized to make some hidden nodes not randomly chosen. Moreover, we apply selected partial hidden layers instead of all hidden layers to construct a selective ensemble. The ensemble method adopted by sedb-RVFLN does not require training multiple independent networks, and the entire sedb-RVFLN only needs to be trained once. Finally, we conduct extensive experiments on real landslide datasets from the Huangdeng Hydropower Station in China to demonstrate the effectiveness of our model.