Comparison of fuzzy inference algorithms for stream flow prediction

Fuzzy logic is, inter alia, a simple and flexible approach of modelling that can be used in river basins where adequate hydrological data are unavailable. In order to improve the real-time forecasting of floods, this paper proposes a Takagi–Sugeno fuzzy inference system termed as flood model Sugeno. A total of 12 input parameters were used to develop two fuzzy flood models—Mamdani and Sugeno. Whereas Sugeno FIS performed exceptionally well in predicting the river discharge, the Mamdani FIS failed to deliver the accurate results. The river Jhelum flowing through the Kashmir Valley in the northern Himalayas, India, was hit in September 2014 by a major flood and has been chosen as the case study to apply the fuzzy flood models. With a total of 24 rules in the rule base and five levels of linguistic variables, the flood model Sugeno predicted the river discharge with Nash–Sutcliffe model efficiency of 0.887, coefficient of correlation (R2) of 90.74%, mean square error of 0.00122, root mean square error of 0.0349, mean absolute error of 0.0139 and combined accuracy of 0.0466. The efficiencies of the developed model show acceptable levels according to the tested performance indicators implying the potential of establishing a flood forecasting system using the developed model.