Abstract：In predicting landslide displacement using traditional ELM algorithm, the solution of ELM network output weight parameter is based on least square estimation, leading to poor resistance to gross error of ELM algorithm. To enhance the resistance to gross error of the ELM algorithm, generalized maximum likelihood estimation (M estimation) is integrated with it and M estimation-based Robust-ELM landslide deformation displacement prediction is proposed. Then, the model is applied to predicting the deformation time series data monitored at the Lianziya and Gushuwu landslides. The case studies show that the traditional ELM algorithm is sensitive to gross error in landslide data and has poor resistance to gross error. M estimation-based Robust-ELM algorithm can better resist single and multiple gross errors in landslide data and its prediction accuracy is high.
