A Prediction of Manning Coefficient in Compound Channels with Converged and Diverged Floodplains using GMDH Model

In the study of natural waterways, the use of formulas such as Manning's equation is prevalent for analyzing flow structure characteristics. Typically, floodplains exhibit greater roughness compared to the main river channel, which results in higher flow velocities within the main channel. This difference in velocity can lead to increased sedimentation potential within the floodplains. Therefore, accurately determining Manning's roughness coefficient for compound channels, particularly during flood events, is of significant interest to researchers. This study aims to model the Manning roughness coefficient in compound channels with both converging and diverging floodplains using advanced soft computing techniques. These techniques include a multi-layer artificial neural network (MLPNN), Group Method of Data Handling (GMDH), and the Neuro-Fuzzy Group Method of Data Handling (NF-GMDH). For the analysis, a dataset from 196 laboratory experiments was used, which was divided into training and testing subsets. Input variables included parameters such as longitudinal slope (S_o), relative hydraulic radius (R_r), relative depth (D_r), relative dimension of flow aspects (δ^*), and the convergent or divergent angle (θ) of the floodplain. The relative Manning roughness coefficient (n_r) was the output variable of interest. The results of the study showed that all the models performed well, with the MLPNN model achieving the highest accuracy, characterized by R² = 0.99, RMSE = 0.001, SI = 0.0015, and DDR = 0.0233 during the testing phase. Further analysis of the soft computing models indicated that the most critical parameters influencing the results were S_o, R_r, D_r, δ^*, and θ.