The application of artificial neural network (ANN) coupled with other models or optimization algorithms in runoff prediction is gradually increasing. The systematic review and summary are given from 4 aspects: the coupling of ANN models with physical models, the combination of multiple ANN models, the integration of decomposition techniques with machine learning methods and the incorporation of ANN models with intelligent optimization algorithms. The reasons for the improvement in the prediction accuracy and the advantages of each method are analyzed. Furthermore, the present research challenges and future prospects are discussed, which can provide support for runoff prediction and water resources management.