Prediction of roughness coefficient of a meandering open channel flow using Neuro-Fuzzy Inference System

Almost all the natural water resource channels meander. Accurate estimation of discharge capacity in a meander open channel is important from river engineering point of view. It helps the practitioners to provide essential information regarding flood mitigation, construction of hydraulic structures and prediction of sediment loads so as to plan for effective preventive measures. Reliable estimation of discharge capacity of a natural channel depends on selection of proper value of roughness in terms of Manning's n. Evaluation of Manning's n for a meandering channel is a complex procedure because of its dependence on many geometrical, hydraulic and surface parameters of the channel. Experimental investigation concerning the variation of roughness coefficient of meandering channels with flow depth, aspect ratio, slope and sinuosity are presented in this paper. An effort has been made to predict the roughness co-efficient of a meandering channel based on ANFIS. The results are compared with well established methods available in the literature. Statistical error analysis is also carried out to know the degree of accuracy of the models. Finally the present model is found to give better results as compared to others. It is concluded that, in practice ANFIS model can be used as a suitable and effective method to predict the non-linear relationship between roughness coefficient and the non-dimensional factors affecting it.