Fuzzy, ANN, and regression models to predict longitudinal dispersion coefficient in natural streams

Abstract

This study developed fuzzy, ANN, and regression-based models to predict longitudinal dispersion coefficient in natural streams from flow discharge data. 92 sets of field data were employed to calibrate and validate the models. 63 sets of data were used for the calibration while the remaining data were used for the validation of the models. The model-prediction results revealed the superiority of the developed models over the existing equations. The developed models predicted the measured data satisfactorily with minimum errors and maximum accuracy rates. The three models had comparable performances although the fuzzy model had the highest accuracy rate (79%) and lowest mean relative error (0.85).