Discharge predicted in compound channels using adaptive neuro-fuzzy inference system (ANFIS)

Abstract Some hydraulic structures and phenomena, including compound channels, must be studied in relation to open channel flow. Despite the fact that primary watersheds share a similar degree of roughness, estimating discharge composite channels with mainstreams flood plains has proved tricky. The flow for different roughness plain been studied, results computed experimentally using horizontal division level have compared those predicted dimensional analysis an adaptive neuro-fuzzy inference system. show good agreement between experimental numerical calculation according root-mean-square error, MARE, R 2 , SI, Nash–Sutcliffe efficiency, percentage error not exceeding ±5%.