Abstract
Annual runoff forecasting remains a difficult task due to its complicated non-stationary characteristics. To solve this difficulty and improve the prediction accuracy, this paper proposes a novel hybrid model for annual runoff forecasting. This model is based on the ensemble empirical mode decomposition (EEMD) and Auto-Regressive (AR). And it is suitable for non-stationary time series. The proposed model is tested using the annual runoff data from four hydrologic stations in the upper reaches of the Fenhe River basin in China. The non-stationary original annual runoff time series is first decomposed into a limited number of intrinsic mode functions (IMFs) and one trend term using EEMD technique for making the time series stationary. Then, these IMFs are forecasted by establishing corresponding optimum AR models only stationary processes, and trend term is predicted by quadratic polynomial equation. At last, the prediction results of the modeled IMFs and trend term are summed to formulate an ensemble forecast for the original runoff series. The performance of the EEMD-AR hybrid model is compared with EMD-AR and single AR models. Results indicate that EEMD-AR hybrid model gives better accuracy in predicting annual runoff in the study area when compared to other models.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
