Prediction of landslide movement is an efficient approach in the reduction in landslide risk. However, it is also a tough task due to the scientific challenges in forecasting a sophisticated natural disaster. This paper proposes a VMD-MIC-M-KELM (variational mode decomposition-maximum information coefficient-multi-kernel extreme learning machine) technique for prediction of landslide movements. The original displacement is first decomposed into a predefined number of components by VMD. Then, the triggers of each component are selected based on MIC between subseries and influencing factors. The decomposed terms are predicted by M-KELM respectively via k-fold cross-validation. Finally, predicted total displacement is achieved by summing up all forecasting subseries. A case study of Miaodian landslide (China) is presented for validation of the developed model. The verification results demonstrate the higher ability of the approach to forecast monthly displacement for periods up to 12 months as compared to the Poly-KELM and SVR models. Thus, improved monthly predictions may be achieved with constantly updated datasets from the monitoring system, which would offer reliable information for early warning of landslide.