NF-GMDH-Based self-organized systems to predict bridge pier scour depth under debris flow effects

Existence of debris structures inevitably ascends the rate of scour process around bridge piers and flow area not only lead into remarkable deviation of flow but also increase the velocity around bridge piers. A myriad of experimental and field studies to understand effective parameters on the scour depth with debris effects were conducted. To reach permissible values of the scour depth for the practical uses, relationships extracted in previous investigations suffer from lack of generalization for experimental data ranges. In this way, neuro-fuzzy group method of data handling (NF-GMDH)-based self-organized models is applied to evaluate the pier scour depth. In this study, NF-GMDH network is implemented using evolutionary algorithms listed particle swarm optimization (PSO), gravitational search algorithm (GSA), and genetic algorithm (GA). In all, 243 experimental datasets including a wide range of input and output parameters to develop the proposed models were compiled from various literature. The efficiency of NF-GMDH networks for training and testing stages was perused. NF-GMDH-PSO model provided the scour depth with more precise predictions (root mean squared error (RMSE)=0.388 and scatter index (SI)=0.343) in comparison with NF-GMDH-GA (RMSE=0.402 and SI=0.361) and NF-GMDH-GSA (RMSE=0.456 and SI=0.407) networks. In addition, blockage ratio (A) was taken into account as the most sumptuous parameter with utmost level of effectiveness using the sensitivity analysis.