No Detail Found!

Application of ANN for predicting water quality parameters in the Mediterranean Sea along Gaza-Palestine.

Author(s)
Hossam Adel Zaqoot Institute of Environmental Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Abdul Khalique Ansari Department of Chemical Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Mukhtiar Ali Unar Department of Computer Systems & Software Engineering, Mehran University of Engineering & Technology, Jamshoro, Pakistan
Abstract
Seawater pollution problems are gaining interest world wide because of their health impacts and other environmental issues. Intense human activities in areas surrounding enclosed and semi-enclosed seas such as the Mediterranean Sea always produce in the long term a strong environmental impact in the form of coastal and marine degradation. This paper is concerned with the use of ANNs (Artificial Neural Networks) MLP (Multilayer Perceptron) model for the prediction of pH and EC (Electrical Conductivity) in water quality parameters along Gaza city coast. MLP neural networks are trained and developed with reference to three major oceanographic parameters (water temperature, wind speed and turbidity) to predict the values of pH and EC; these parameters are considered as inputs of the neural network. The data collected comprised of four years and collected from nine locations along Gaza coastline. Results show that the model has high capability and accuracy in predicting both parameters. The network performance has been validated with different data sets and the results show satisfactory performance. Results of the developed model have been compared with multiple regression statistical model and found that MLP predictions are slightly better than the conventional methods. Prediction results prove that the proposed approach is suitable for modeling the water quality in the Mediterranean Sea along Gaza.
Publication Details
Page(s) 331-338
DOI DOI not available
Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 27, Issue: 3, Year: 2008

Request the full text from PASTIC

0

Citations

0

Downloads

48

Views