Application of Artificial Neural Networks for Predicting Water Quality

In the Gaza Strip the maximum amount of the drinking water is produced through small private desalination plants. The present book is concerned with using artificial neural network (ANN) technique to forecast and predict the next week concentrations of total dissolved solids (TDS), chloride, nitrate and magnesium of the product water quality in the reverse osmosis desalination plants in the Gaza Strip. Multilayer perceptron (MLP) and radial basis function (RBF) neural networks were trained and developed with reference to product water parameters including: water temperature, pressure, pH and conductivity to predict TDS, chloride and nitrate next week values. MLP and RBF neural networks were trained and developed with reference to three water quality parameters including pressure, chloride and conductivity to predict magnesium concentrations. The prediction results showed that both types of neural networks are good for predicting TDS, chloride and nitrate levels and satisfactory for predicting magnesium.Results of both developed networks were compared with the statistical model and found that ANN predictions are better than the conventional methods.

Autorentext

Authors have experience in projects managing and coordination in the field of water quality assessment and water quality modeling using artificial neural network, in addition to consultation and evaluation of research works/ reviewing research papers in international journals and editorial board member of many international journals.