• 1 Institute of Structural Mechanics, Bauhaus Universität Weimar, Weimar, Germany
  • 2 Department of Computer, Gorgan Branch, Islamic Azad University, Gorgan, Iran
  • 3 Department of Civil Engineering, Faculty of Engineering & Built Environment, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia
  • 4 School of the Built Environment, Oxford Brookes University, Oxford, United Kingdom
PLoS One, 2020;15(4):e0229731.
PMID: 32271780 DOI: 10.1371/journal.pone.0229731


Shear stress comprises basic information for predicting the average depth velocity and discharge in channels. With knowledge of the percentage of shear force carried by walls (%SFw) it is possible to more accurately estimate shear stress values. The %SFw, non-dimension wall shear stress ([Formula: see text]) and non-dimension bed shear stress ([Formula: see text]) in smooth rectangular channels were predicted by a three methods, the Bayesian Regularized Neural Network (BRNN), the Radial Basis Function (RBF), and the Modified Structure-Radial Basis Function (MS-RBF). For this aim, eight data series of research experimental results in smooth rectangular channels were used. The results of the new method of MS-RBF were compared with those of a simple RBF and BRNN methods and the best model was selected for modeling each predicted parameters. The MS-RBF model with RMSE of 3.073, 0.0366 and 0.0354 for %SFw, [Formula: see text] and [Formula: see text] respectively, demonstrated better performance than those of the RBF and BRNN models. The results of MS-RBF model were compared with three other proposed equations by researchers for trapezoidal channels and rectangular ducts. The results showed that the MS-RBF model performance in estimating %SFw, [Formula: see text] and [Formula: see text] is superior than those of presented equations by researchers.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.