The bed surface of alluvial rivers is rarely plane and takes different geometric configurations called bed forms. Bed forms are created by the movement of riverbed sediments, especially during floods. The interaction between the flow and bed form is very complex. The flow intensity controls bed forms, and the bed form significantly affects the properties of the flow (such as depth, velocity, and flow resistance). The Manning roughness coefficient is one of the most important flow resistance coefficients, which significantly affects the bed form shape and geometry. This study aimed to estimate the Manning roughness coefficient in rivers with bed forms, using soft computing models, including multilayer perceptron artificial neural network (MLPNN), group method of data handling (GMDH), support vector machine (SVM) model, and genetic programming model (GP). To this end, the energy grade line (Sf), flow Froude number (Fr), y/d50, ∆/d50, ∆\λ, and ∆/y were used as the input variables, and the Manning roughness coefficient was used as the output variable. The results showed that all the test models have acceptable accuracy, while the SVM model showed the highest level of accuracy with the coefficient of determination R2=0.99 in the verification stage. The sensitivity analysis of SVM and MLPNN models and the structural analysis of GMDH and GP models indicated that the most important parameters affecting the Manning roughness coefficient are Fr, Sf, ∆\λ.