Scour prediction at the control structures using adaptive neuro-fuzzy inference system

An assessment of maximum scour depth with reasonable accuracy at a grade control structure is of paramount importance for its proper planning, design and management. Most of the scour depth prediction formulae available in the literature have been developed based on the analysis of the laboratory/field data using the statistical method such as the regression method (RM). Conventional statistical analysis is generally replaced in many fields of engineering by the alternative approaches such as artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS). These recent techniques have been reported to provide better solutions in cases where the available data is incomplete or ambiguous by nature. An attempt has been made herein to develop an ANFIS model for the prediction of scour depth at the grade control structures on the bed of non-uniform sediments using the sizable amount of data and make the comparative study for the performance of ANFIS model over the RM model for the scour depth prediction at the grade control structures. It was found that the AFIS models performed better than the regression models.