Towards a time and cost effective approach to water quality index class prediction

The development of water quality prediction models is an important step towards better water quality management of rivers. The traditional method for computing WQI is always associated with errors due to the protracted analysis of the water quality parameters in addition to the great effort and time involved in gathering and analyzing water samples. In addition, the cost of identifying the magnitude of some of the parameters through experimental testing is very high. The water quality of rivers in Malaysia is ranked into five classes based on water quality index (WQI). WQI is function of six water quality parameters: ammoniac nitrogen (NH3-N), biochemical oxygen demand (BOD), chemical oxygen demand (COD), dissolved oxygen (DO), pH, and suspended solids (SS). In this research, the decision tree machine learning technique is used to predict the WQI for the Kiang River and its classification within a specific water quality class. Kiang River is one of the most polluted rivers in Malaysia. Modeling experiments are designed to test the prediction and classification accuracy of the model based on various scenarios composed of different water quality parameters. Results show that the proposed prediction model has a promising potential to predict the class of the WQI. Moreover, the proposed model offers a more efficient process and cost-effective approach for the computation and prediction of WQI.