Parviz, L., Kholghi, M., Hoorfar, A. (2010). A Comparison of the Efficiency of Parameter Estimation Methods in the Context of Streamflow Forecasting. , 12(1), 47-60.
L. Parviz; M. Kholghi; A. Hoorfar. "A Comparison of the Efficiency of Parameter Estimation Methods in the Context of Streamflow Forecasting". , 12, 1, 2010, 47-60.
Parviz, L., Kholghi, M., Hoorfar, A. (2010). 'A Comparison of the Efficiency of Parameter Estimation Methods in the Context of Streamflow Forecasting', , 12(1), pp. 47-60.
Parviz, L., Kholghi, M., Hoorfar, A. A Comparison of the Efficiency of Parameter Estimation Methods in the Context of Streamflow Forecasting. , 2010; 12(1): 47-60.

A Comparison of the Efficiency of Parameter Estimation Methods in the Context of Streamflow Forecasting

Journal of Agricultural Science and Technology
Article 5, Volume 12, Issue 1, 2010, Pages 47-60    PDF (328.36 K)
Authors
L. Parviz; M. Kholghi* ; A. Hoorfar
Department of Irrigation and Reclamation Engineering, College of Soil and Water Engineering, Campus of Agriculture and Natural Resources, University of Tehran, Karaj, Islamic Republic of Iran.
Abstract
The forecasting of hydrological variables, such as streamflow, plays an important role in water resource planning and management. Recently, the development of stochastic models is regarded as a major step for this purpose. Streamflow forecasting using the ARIMA model can be conducted when unknown parameters are estimated correctly because parameter estimation is one of the crucial steps in modeling process. The main objective of this research is to explore the performance of parameter estimation methods in the ARIMA model. In this study, four parameter estimation methods have been used: (i) autocorrelation function based on model parameters; (ii) conditional likelihood; (iii) unconditional likelihood; and (iv) genetic algorithm. Streamflow data of Ouromieh River basin situated in Northwest Iran has been selected as a case study for this research. The results of these four parameter estimation methods have been compared using RMSE, RME, SE, MAE and minimizing the sum squares of error. This research indicates that the genetic algorithm and unconditional likelihood methods are, respectively, more appropriate in comparison with other methods but, due to the complexity of the model, genetic algorithm has high convergence to a global optimum.
Keywords
ARIMA model; Conditional likelihood; forecasting; genetic algorithm; Parameter estimation
Statistics
Article View: 139
PDF Download: 92
Statistics
Number of Journals45
Number of Issues2,171
Number of Articles24,674
Article View24,447,944
PDF Download17,555,105