An application of different artificial intelligences techniques for water quality prediction

Artificial Intelligence (AI) is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared with other classical modelling techniques. In this study, different techniques of AI have been investigated in prediction of water quality parameters including: multi-layer perceptron neural networks (MLP-ANN), ensemble neural networks (E-ANN) and support vector machine (SVM). The parameters were investigated in terms of the following: the dissolved oxygen (DO), biochemical oxygen demand (BOD) and chemical oxygen demand (COD). To assess the effect of input parameters on the model, the sensitivity analysis was adopted. To evaluate the performance of the proposed model, three statistical indexes were used, namely; correlation coefficient (CC), mean square error (MSE) and correlation of efficiency (CE). The principle aim of this study is to develop a computationally efficient and robust approach for predicting water quality parameters which could reduce the cost and labour for measuring these parameters. This research concentrates on the Johor river in Johor State, Malaysia where the dynamics of river water quality are significantly altered.