Anfis-based Approach to Scour Prediction at the Grade Control Structures

An assessment of maximum scour depth downstream of grade control structure is essential 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). The alternative recent approaches such as artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) have also been reported to provide better solutions in cases where the available data is incomplete or ambiguous by nature. An attempt has, therefore, been made herein to develop an ANFIS model along with the ANN models for the prediction of scour depth at the grade control structures on the bed of non-uniform sediments using the sizeable amount of data and make the comparative study for the performance of ANFIS model over the RM and ANN models for the scour depth prediction at the grade control structures. The performance of the ANFIS model was found to the best among the various prediction models under considerations. Salient features of the present study are presented herein.