Artificial neural network modeling of the water quality index for Kinta River (Malaysia) using water quality variables as predictors

This article describes design and application of feed-forward, fully-connected, three-layer perceptron neural network model for computing the water quality index (WQI)1Abbreviations: AAE, average absolute error; ANN, artificial neural network; FA, factor analysis; MAE, mean absolute error; MSE, mean squared error; Nh, number of hidden neurons; PFA, principal factor analysis; QP, quick propagation (Quickprop); r, correlation coefficient; R2, coefficient of determination; SEM, standard error of the mean; SSE, sum of squared errors; WQ, water quality; WQI, water quality index; WQV, water quality variable. Kinta River (Malaysia). The modeling efforts showed that the optimal network architecture was 23-34-1 and that the best WQI predictions were associated with the quick propagation (QP) training algorithm; a learning rate of 0.06; and a QP coefficient of 1.75. The WQI predictions of this model had significant, positive, very high correlation (r = 0.977, p < 0.01) with the measured WQI values, implying that the model predictions explain around 95.4% of the variation in the measured WQI values. proach presented in this article offers useful and powerful alternative to WQI computation and prediction, especially in the case of WQI calculation methods which involve lengthy computations and use of various sub-index formulae for each value, or range of values, of the constituent water quality variables.