Accurate forecasting of annual runoff is necessary for water resources management. However, a runoff series consists of complex nonlinear and non-stationary characteristics, which makes forecasting difficult. To contribute towards improved prediction accuracy, a novel hybrid model based on the empirical mode decomposition (EMD) for annual runoff forecasting is proposed and applied in this paper. Firstly, the original annual runoff series is decomposed into a limited number of intrinsic mode functions (IMFs) and one trend term based on the EMD, which makes the series stationary. Secondly, it will be forecasted by a least squares support vector machine (LSSVM) when the IMF component possesses chaotic characteristics, and simulated by a polynomial method when it does not. In addition, the reserved trend term is predicted by a Gray Model. Finally, the ensemble forecast for the original runoff series is formulated by combining the prediction results of the modeled IMFs and the trend term. Qualified rate (QR), root mean square errors (RMSE), mean absolute relative errors (MARE), and mean absolute errors (MAE) are used as the comparison criteria. The results reveal that the EMD-based chaotic LSSVM (EMD-CLSSVM) hybrid model is a superior alternative to the CLSSVM hybrid model for forecasting annual runoff at Shangjingyou station, reducing the RMSE, MARE, and MAE by 39%, 28.6%, and 25.6%, respectively. To further illustrate the stability and representativeness of the EMD-CLSSVM hybrid model, runoff data at three additional sites, Zhaishang, Fenhe reservoir, and Lancun stations, were applied to verify the model. The results show that the EMD-CLSSVM hybrid model proved its applicability with high prediction precision. This approach may be used in similar hydrological conditions.
Due to climate change and human activities over the last fifty years, the spring flow volume of karst groundwater has sharply diminished in China. Climate change is one of the critical factors that initiates a series of karst hydrogeologic and water ecological environmental problems, because the precipitation shows a decreasing trend while the temperature shows an increasing trend. The Jinci Spring is one of the largest, most famous springs in northern China. This study employed data from the Taiyuan Meteorological Station and ten precipitation stations in and around the Jinci Spring region as well as the runoff data gathered from two hydrological monitoring stations during 1960-2012. The sliding average method and the Mann-Kendall test were used to analyze the variation tendency of precipitation, temperature, and land evaporation in this area. Finally, the following were calculated: the varying pattern of the karst groundwater recharge amount and the response of the recharge amount to precipitation, land evaporation, and river runoff by quantitative analysis. The results indicated that the precipitation and land evaporation amount decreased at first and then subsequently increased. Likewise, the variation trend of the karst groundwater recharge amount in the spring region was roughly consistent with the precipitation variation pattern. In contrast, the temperature displayed an increasing trend. The climate change resulted in a reduction of the karst groundwater recharge amount, and it had the greatest influence in the 1990s, which caused the karst groundwater recharge amount to decrease 26.75 mm as compared to that of the 1960s (about 39.68% lower than that of the 1960s). The Jinci Spring had zero flow during this period. The reduction in precipitation was one of main factors that caused the cutoff of the Jinci Spring.
A multilevel thresholding algorithm for histogram-based image segmentation is presented in this paper. The proposed algorithm introduces an adaptive adjustment strategy of the rotation angle and a cooperative learning strategy into quantum genetic algorithm (called IQGA). An adaptive adjustment strategy of the quantum rotation which is introduced in this study helps improving the convergence speed, search ability, and stability. Cooperative learning enhances the search ability in the high-dimensional solution space by splitting a high-dimensional vector into several one-dimensional vectors. The experimental results demonstrate good performance of the IQGA in solving multilevel thresholding segmentation problem by compared with QGA, GA and PSO.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.