RESERVOIR WATER QUALITY MODELLING : USING ARTIFICIAL NEURAL NETWORK AND MULTIPLE LINEAR REGRESSION TOOL

Water Quality modelling is increasingly recognized as a useful tool for acquiring valuable information for optimal water quality management. Water quality assessment can be defined as the evaluation of the biological chemical and physical properties of water in reference to natural quality human health effects and intended use. Traditional reports on water quality typically consist of complex variable-by-variable and water body-by-body statistical summaries. This type of information is of value to water quality experts but may not be meaningful to know about the state of their local water bodies and for managers and policy makers who require concise information about these water bodies.  The study of quality of water at the reservoir is important because on this reservoir water various or more than 70% of water supply schemes in the basin and about 20 lacs people depend for their daily usage. Problems of environmental pollution have caused severe stress on human society and economic progress. Pollution in the reservoir is continuously increasing due to urbanization industrialization. Recently a neural network has been found to excel in environment system that is complex non- linear and uncertain.