Application of an artificial neural network in wastewater quality monitoring: prediction of water quality index
Water bodies have become more and more polluted owing to discharge of industrial waste. Therefore, it has been the chief concern of scientists, engineers and ecologists to decrease the water pollution level around the globe to maintain living viability and ecological balance. In this paper, the seasonal and positional variation of wastewater parameters in a natural flowing stream has been observed and an Artificial Neural Network (ANN) model is proposed to predict the water quality. Tolly's Canal was chosen as the purview of this case study. Wastewater and sediment samples were collected from Tolly's Canal and the River Ganges at different points and different seasons both at high and low tide conditions on a particular day. All the important water quality parameters were evaluated. To summarise and report river-water quality, a new term, 'Water Quality Index' (WQI), has been introduced. The WQI value is a dimensionless number ranging from 0 to 100 (best quality). In this study, the WQI is predicted by a simulative model using an ANN. This model has been developed for the assessment of the WQI and compared with the conventionally determined values of WQI. A Multilayer-Perceptron (MLP) network with a single hidden layer was used along with back-propagation algorithm. The results were found to be quite impressive. Thus, the ANN proved to be an efficient tool to assess the WQI of any sample.
Keywords: artificial neural networks, ANN, multilayer perceptron networks, water quality index, WQI, simulation models, parameter estimation, wastewater monitoring, quality monitoring, water pollution