Millions of dollars are being spent worldwide on the repair and maintenance of sewer networks and wastewater treatment plants. The production and emission of hydrogen sulphide has been identified as a major cause of corrosion and odour problems in sewer networks. Accurate prediction of sulphide build-up in a sewer system helps engineers and asset managers to appropriately formulate strategies for optimal sewer management and reliability analysis. This paper presents a novel methodology to model and predict the sulphide build-up for steady state condition in filled sewer pipes. The proposed model is developed using a novel data-driven technique called evolutionary polynomial regression (EPR) and it involves the most effective parameters in the sulphide build-up problem. EPR is a hybrid technique, combining genetic algorithm and least square. It is shown that the proposed model can provide a better prediction for the sulphide build-up as compared with conventional models.