Development of artificial neural networks to predict membrane fouling in an anoxic-aerobic membrane bioreactor treating domestic wastewater

•A set of ANNs is first developed to predict membrane fouling in AO-MBR.•An optimal set of parameters was identified to predict TMP using ANN efficiently.•High performances were reached (R2 = 0.850) for the developed ANN.•ANN model have shown high potential to predict membrane fouling. An artificial neural network (ANN) was first developed to predict the transmembrane pressure in an anoxic-aerobic membrane bioreactor (AO-MBR) treating domestic wastewater. A few studies about prediction of membrane fouling in MBRs using ANNs have been published so far, even though our recent work indicates that ANNs show a great potential for this application. In this study, 10 parameters linked to wastewater treatment and measured in the different parts of the AO-MBR system were used as the input variables of the ANN. The goal was to select the most relevant input parameters to predict the evolution of the transmembrane pressure based on the performances of the ANN. An ANN model was selected for its satisfying performances (R2 = 0.850). In conclusion, ANNs could be a valid method to predict membrane fouling in AO-MBR systems treating domestic wastewater.