Intelligent Modeling of Monthly flow Time Series into Vahdat dam in sanandaj city

آب و خاک

Article 20, Volume 23, Issue 1, March 2009   

Document Type: Research Article

DOI: 10.22067/jsw.v0i0.1552

Authors

P. Fathi^{* 1}; Y. Mohammadi²; M. Homaee³

¹Dept. of Water Engineering, University of Kurdistan, Sanandaj

²University of Tarbiat Modares

³Dept. of Soil Science, University of Tarbiat Modares

Abstract

Abstract
Prediction of input flow into water resources is regarded as one of the most important issues in optimum planning and management in producing electro-water energy and optimum allocation of water into different consumption sources. Different parameters affect on input discharge into dams. Climate variables including temperature and rainfall have the most effect on input runoff rate to water resource in dry and semi-dry regions like Iran. A suitable monthly runoff-rainfall model is a strong tool to consider the climate changes effect on accessibility of water to produce electro-water energy. The investigations have shown that the relation between runoff rate and effective variables is non-linear and complicated. Artificial Neural Networks due to their unique properties have a tremendous capability in non-linear relations simulation. Artificial Neural Networks establish a great change in analyzing dynamic systems behavior in different water-science engineering. In this paper it has been attempted to design static network to recover the non-linear relations between dependant and independent variables, so that the intelligent discharge estimation of average monthly input to Vahdat dam can be done by its help. In addition, by designing and extension of dynamic neural network model based on times series performance, the amount of the monthly input discharge to the dam was predicted. Considering the capability of Artificial Neural Networks, these networks were used for modeling the rivers monthly discharge non-linear time series. Analysis of time series having two major goals; random mechanism understanding or modeling and future series value prediction was done base on previous ones. Also, the performance of the designed models was evaluated by comparing results of the static and dynamic neural network. The results of the investigation showed that there is a good conformity between the predicted values given by combined neural network and observed data. Furthermore, the results showed that the time series dynamic neural network model predict the monthly discharge more accurate than static model.

Keywords: monthly average discharge, Artificial Neural Networks, time series