Monthly streamflow forecasting plays an important role in water resources management, especially for dam operation. In this paper, an approach of model fusion technique named selected model fusion (SMF) is applied and assessed under two strategies of model selection in order to improve the accuracy of streamflow forecasting. The two strategies of SMF are: fusion of the outputs of best individual forecasting models (IFMs) selected by dendrogram analysis (S1), and fusion of the best outputs of all IFMs resulting from an ordered selection algorithm (S2). In both strategies, five data-driven models including: artificial neural network, generalized regression neural network, least square-support vector regression, K-nearest neighbor regression, and multiple linear regression with optimized structure are performed as IFMs. The SMF strategies are applied for forecasting the monthly inflow to Karkheh reservoir, Iran, owning various patterns between predictor and predicted variables in different months. Results show that applying SMF approach based on both strategies results in more accurate forecasts in comparison with fusion of all IFMs outputs (S3), as the benchmark. However, comparison of the two SMF strategies reveals that the implementation of strategy (S2) considerably improves the accuracy of forecasts than strategy (S1) as well as the best IFM results (S4) in all months.
In this study, it has been investigated whether the SSTs of Mediterranean Sea and Persian Gulf and combination of them are applicable and effective variables as predictors for operational streamflow forecasting, regionally, in Karkheh basin or not. For this goal, the singular value decomposition (SVD) method has been used to determine the effective nodes of Mediterranean Sea and Persian Gulf on the climate of the subbasins of this basin and to produce the most correlated time series of SST with the streamflow of each subbasin. In this research, the best predictors have been detected from several combinations of the appropriate predictors based on the cross-validation analysis for the results of the Generalized Regression Neural-Network model. Results show that autumn SST of Mediterranean Sea and Persian Gulf is prominently effective variables for forecasting the streamflow in all subbasins of Karkheh basin in April and May, respectively. Summer SST of Persian Gulf has been detected as an effective predictor for streamflow forecasting in April and May in snowy regions. Moreover, the results demonstrate that the combination of Mediterranean Sea SST and Persian Gulf SST affects the streamflow in almost all the regions of the basin in April, while the streamflow in May is affected only by Persian Gulf SST. In addition, the north and west regions of Karkheh basin (Garsha and Seimareh subbasins) as well as the east and south regions of this basin (Tang Mashooreh and Karkheh subbasins) have similar pattern of the best predictors for operational streamflow forecasting in all the spring months.
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.