Applications of artificial neural network in assessing waterquality: a case study

This is attributable to pollution due to human activities such as plunging of idols of deity and divinity in the festival season, surface runoff due to heavy rainfall, washing exercises and ‎sewage disposal everywhere in lakes. Water environment is a complex system where theological methods cannot meet the demands of water environment preservation. To demonstrate the usefulness of the Back Propagation Neural Network (BPNN), the Water Quality Index (WQI) has been used on the basis of physical-chemical parameters of different sources of water. Water from different sources like Gandhisagar, Ambazari and Futala lake revealed significant water pollution as compared to Gorewada lake. The WQI is continuously upgrading and the situation is becoming more alarming which demands some appropriate actions with an immediate effect to get it under control. In this study, an attempt was made to assess WQI using Multi-Layer Perceptrons (MLP) architecture. The feed forward back propagation algorithm has been chosen for training and testing the experimental data. The feed forward back propagation algorithm has been chosen for training and testing the experimental data. All the calculated WQI parameters in aforesaid lakes are observed to be at a medium level in rainy season, fairer in the autumn season and comparatively higher during the summer season.