Monthly Streamflow Forecasting Using ELM-IPSO Based on Phase Space Reconstruction
- PDF / 932,682 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 91 Downloads / 173 Views
Monthly Streamflow Forecasting Using ELM-IPSO Based on Phase Space Reconstruction Yan Jiang 1 & Xin Bao 1,2 & Shaonan Hao 1 & Hongtao Zhao 1 & Xuyong Li 1 & Xianing Wu 3 Received: 24 May 2019 / Accepted: 21 July 2020/ # Springer Nature B.V. 2020
Abstract
We have developed a hybrid model that integrates chaos theory and an extreme learning machine with optimal parameters selected using an improved particle swarm optimization (ELM-IPSO) for monthly runoff analysis and prediction. Monthly streamflow data covering a period of 55 years from Daiying hydrological station in the Chaohe River basin in northern China were used for the study. The Lyapunov exponent, the correlation dimension method, and the nonlinear prediction method were used to characterize the streamflow data. With the time series of the reconstructed phase space matrix as input variables, an improved particle swarm optimization was used to improve the performance of the extreme learning machine. Finally, the optimal chaotic ensemble learning model for monthly streamflow prediction was obtained. The accuracy of the predictions of the streamflow series (linear correlation coefficient of about 0.89 and efficiency coefficient of about 0.78) indicate the validity of our approach for predicting streamflow dynamics. The developed method had a higher prediction accuracy compared with an auto-regression method, an artificial neural network, an extreme learning machine with genetic algorithm and with PSO algorithm, suggesting that ELM-IPSO is an efficient method for monthly streamflow prediction. Keywords Streamflow prediction . Chaohe River basin . Chaotic dynamic characteristics . Phase space reconstruction . Extreme learning machine . Improved particle swarm optimization algorithm
* Yan Jiang [email protected]
1
State Key Laboratory of Urban and Regional Ecology, Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences, Beijing 100085, China
2
University of Chinese Academy of Sciences, Beijing 100049, China
3
PowerChina Resources Limited, Beijing 100044, China
Jiang Y. et al.
1 Introduction Flood control, drought relief, and the optimal utilization of water resources require accurate prediction of streamflow. However, the hydrological process is extremely complex and difficult to predict, especially in the medium and long term because of human impact, changing climatic conditions, and the geographical environment (Vicente-Guillén et al. 2012). A large number of researchers are devoted to understanding the dynamics of rainfall-runoff process (Bradford et al. 1991; Duan et al. 1992; Huang et al. 2014). In the past, the hydrological process was regarded as stochastic (Sivakumar et al. 2001). With the rapid development of nonlinear science, nonlinear time series analysis has brought a significant method revolution. The “science of chaos” has found applications in almost all the natural sciences, including hydrological sciences (Islam and Sivakumar 2002). Even simple deterministic systems can display complex or chaotic behavior. It i
Data Loading...
