Group method of data handling to predict scour depth around vertical piles under regular waves

This paper presents a new application of the group method of data handling (gmdh), to predictpile scour depth exposed to waves. the gmdh network was developed using the levenbergmarquardt(lm) method in the training stage for scour prediction. scour depth due to regular waves was modeledas a function of five dimensionless parameters, including pile reynolds number, grain reynolds number,sediment number, keulegancarpenter number, and shields parameter. the testing results of the gmdh-lm were compared with those obtained using the adaptive neuro-fuzzy inference system (anfis), radialbasis function-neural network (rbf-nn), and empirical equations. in particular, the gmdh-lm providedthe most accurate prediction of scour depth compared to other models. also, the keulegancarpenternumber has been determined as the most effective parameter on scour depth through a sensitivityanalysis. the gmdh-lm was utilized successfully to investigate the influence of the pile cross sectionand keulegancarpenter number on scour depth.