Developing an expert group method of data handling system for predicting the geometry of a stable channel with a gravel bed

Predicting the geometry of channels and alluvial rivers is of primary importance in river engineering science. Appropriately designing channels and predicting stable river cross-sections can decrease costs and prevent the destruction of installations and agricultural land by rivers. Consequently, researchers have applied different empirical and regression methods to achieve relations for predicting stable channel and river geometry. In this study, Group Method of Data Handling] GMDH) models are used to predict three geometric variables of stable channels, namely width (w), depth (h) and slope (s). The effect of different input parameters, such discharge (Q), median grain size (d(50)) and the Shields parameter (tau*) on the GMDH models is assessed with regard to predicting stable channel geometry. The results indicate that the GMDH model with mean absolute percentage error (MAPE) of 5.53%, 4.05% and 4.89% for channel width, depth and slope prediction respectively, exhibits good accuracy. Moreover, a comparison of the GMDH models with previous theoretical equations (based on regression analysis) indicates the superiority of GMDH model performance, with error reductions of one-fifth, one-eighth and one-sixth compared with the regression equations for channel width, depth and slope prediction, respectively. Copyright (C) 2016 John Wiley & Sons, Ltd.