Multivariate NARX neural network in prediction gaseous emissions within the influent chamber of wastewater treatment plants

Several potential problems associated with emissions such as odour nuisance may occur in sewer systems and wastewater treatment plants (WWTP). Improved understanding of prediction of emitted gases (e.g. hydrogen sulphide, H2S) is of great importance for better evaluation of such problems in WWTPs. The present paper provides a survey of the feasibility of utilising soft computing models in predicting emission factors (gaseous H2S) of based on five input parameters including the total dissolved sulphides, biochemical oxygen demand (BOD5), temperature, flow rate and pH. Multivariate nonlinear autoregressive exogenous (NARX) neural networks were developed and applied to predict weekly H2S in four WWTPS. Due to the nonlinearity nature of the H2S emission, the principle component analysis, and the average mutual information (AMI) method was employed to determine the effective independent parameters and the optimal time lags in state space for the H2S data. In addition to the NARX models, three standard regressive models (multiple linear regression model, stepwise regression and two-variate logarithmic regression model) were also applied to the same dataset for evaluating the capability and reliability of the developed NARX models. Based on several statistical measures (RMSE, MAPE, PCC, NSE & GRI), it was found that the NARX models were superior to the other applied models in predicting emitted H2S. Although the temperature and wastewater flow rate were found to be the most effective parameters for modelling H2S, but the results indeed showed that taking into account of all wastewater parameters would lead to more accurate H2S prediction.