Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors

•Two algorithms: SVR and ANFIS were used for simulating aerobic granulation.•A modular model structure was adopted for the simulation.•The capability of failure prediction was discussed.•SVR had better predictions accuracy.•ANFIS had better generalization ability.