Application of Artificial Neural Networks for the Prediction of Water Quality Variables in the Nile Delta英文文献资料.docVIP

Journal of Water Resource and Protection, 2012, 4, 388-394 /10.4236/jwarp.2012.46044 Published Online June 2012 (http://www.SciRP.org/journal/jwarp) Application of Artificial Neural Networks for the Prediction of Water Quality Variables in the Nile Delta Bahaa Mohamed Khalil , Ayman Georges Awadallah , Hussein Karaman , Ashraf El-Sayed 1 2 3 3 1 Faculty of Engineering Mataria, Helwan University, Cairo, Egypt Faculty of Engineering, Fayoum University, Fayoum, Egypt 2 3 Drainage Research Institute, National Water Research Center, Cairo, Egypt Email: aawadallah@ Received March 3, 2012; revised April 2, 2012; accepted May 2, 2012 ABSTRACT The quality of a water body is usually characterized by sets of physical, chemical, and biological parameters, which are mutually interrelated. Since August 1997, monthly records of 33 parameters, monitored at 102 locations on the Nile Delta drainage system, are stored in a National Database operated by the Drainage Research Institute (DRI). Correlation patterns may be found between water quantity and water quality parameters at the same location, or among water qual- ity parameters within a monitoring location or among locations. Serial correlation is also detected in water quality vari- ables. Through the investigation of the level of information redundancy, assessment and redesign of water quality monitoring network aim to improve the overall network efficiency and cost effectiveness. In this study, the potential of the Artificial Neural Network (ANN) on simulating interrelation between water quality parameters is examined. Several ANN inputs, structures and training possibilities are assessed and the best ANN model and modeling procedure is se- lected. The prediction capabilities of the ANN are compared with the linear regre