Streamflow Prediction of Karuvannur River Basin Using ANFIS, ANN and MNLR Models. (2016)

• Record Type: Journal Article
• Authors: Anusree, K.; Varghese, K.O.
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 101
• Page End: 108
• Publication Date: 2016
• Subjects: Neural networks -- Fuzzy inference system -- Multiple Nonlinear Regression -- Hydrological modeling.; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.015
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: For the planning, design and management of water resources systems, streamflow forecasting is important. The use of artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS) and multiple nonlinear regression (MNLR) for predicting daily flow at the outlet of Karuvannur river basin, located in Thrissur district, is presented in this study. Precipitation data from nine raingauge stations were used to develop the models. Input vectors for simulations included different combinations of antecedent precipitation and flows, with different time lags. Performances of the models were evaluated with the RMSE and Nash-Sutcliffe model efficiency values. The results showed that ANFIS model predicts daily flow more accurately compared to ANN and MNLR models. Furthermore, ANFIS model with an input combination of antecedent flow with one day time lag and antecedent rainfall with three and four day time lags, is better than all other cases considered here. Therefore by using the ANFIS model with these 3 inputs we can forecast the daily discharge of Karuvannur river basin with a better accuracy.