Scour around submarine pipelines remains a largely complex and not yet fully understood problem. In this study, wave-induced scour around submarine pipelines was investigated. Since various physical processes occur during the development of a scour hole, the effects of each process were considered by employing several nondimensional parameters. To find the effective parameters on equilibrium scour depth, the correlation between independent parameters (e.g. Keulegan–Carpenter number) and dependent parameter (nondimensional scour depth) were determined using different experimental data. Then, an Artificial Neural Network (ANNs) approach was used to develop a more accurate model for prediction of wave-induced scour depth around submarine pipelines. ANN models with different input parameters including gap to diameter ratio, Keulegan–Carpenter number, pipe Reynolds number, Shields number, sediment Reynolds number and boundary layer Reynolds number were trained and evaluated to find the best predictor model. To develop the ANN models, both holdout and tenfold cross-validation methods were used. In addition, an existing empirical method was examined. Results show that the empirical method has a significant error in the prediction of scour depth for the cases with an initial gap between pipe and seabed. It is also indicated that the ANN models outperform the empirical method in terms of prediction capability.