Design of a Hybrid ANFIS–PSO Model to Estimate Sediment Transport in Open Channels

Abstract

In the present study, a new hybrid evolutionary method is presented for estimating the minimum densimetric Froude number required for sediment transport with no solid substance deposition in channel pipes. This method is based on a combination of particle swarm optimization (PSO) algorithm with adaptive neuro-fuzzy inference system (ANFIS). The PSO algorithm is utilized for optimization of fuzzy membership function value. Three different sets of data measured at different times as well as a vast range of parameters are used to test and train the suggested models. The results of ANFIS–PSO (R2 = 0.976, RMSE = 0.260, MAPE = 5.743, BIAS = − 0.004, SI = 0.059) are compared with the results of ANFIS (R2 = 0.929, RMSE = 0.452, MAPE = 9.107, BIAS = − 0.077, SI = 0.101) and regression-based equations obtained from the literature.