Displacement prediction model of landslide based on a modified ensemble empirical mode decomposition and extreme learning machine

• Published in: Natural hazards (Dordrecht) 2013-03, Vol.66 (2), p.759-771
• Main Authors: Lian, Cheng, Zeng, Zhigang, Yao, Wei, Tang, Huiming
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Canyons; China (People's Republic); Civil Engineering; Data structures; Decomposition; Deformation; Displacement; Earth and Environmental Science; Earth Sciences; Earth, ocean, space; Elm; Empirical analysis; Engineering and environment geology. Geothermics; Ensemble forecasting; Environmental Management; Exact sciences and technology; Geophysics/Geodesy; Geotechnical Engineering & Applied Earth Sciences; High frequency; Hydrogeology; Landslides; Learning; Learning algorithms; Machine learning; Mathematical models; Measurement; Natural Hazards; Natural hazards: prediction, damages, etc; Neural networks; Nonlinear systems; Original Paper; Prediction models; Reservoirs; Time series
• ISSN: 0921-030X; 1573-0840
• DOI: 10.1007/s11069-012-0517-6

In this paper, an M–EEMD–ELM model (modified ensemble empirical mode decomposition (EEMD)-based extreme learning machine (ELM) ensemble learning paradigm) is proposed for landslide displacement prediction. The nonlinear original surface displacement deformation monitoring time series of landslide is first decomposed into a limited number of intrinsic mode functions (IMFs) and one residual series using EEMD technique for a deep insight into the data structure. Then, these sub-series except the high frequency are forecasted, respectively, by establishing appropriate ELM models. At last, the prediction results of the modeled IMFs and residual series are summed to formulate an ensemble forecast for the original landslide displacement series. A case study of Baishuihe landslide in the Three Gorges reservoir area of China is presented to illustrate the capability and merit of our model. Empirical results reveal that the prediction using M–EEMD–ELM model is consistently better than basic artificial neural networks (ANNs) and unmodified EEMD–ELM in terms of the same measurements.