Application of adaptive neuro fuzzy inference system (Anfis) in River Kaduna discharge forecasting

Abstract

The study and understanding of the amount of water that would be discharged by a stream in the future is of crucial importance to the water resources development, planning and management of any area. This is so because, stream flow data are very important for many areas of water engineering. The data used for this research include the monthly rainfall data for Kaduna town, Zaria and Jos, temperature data for Kaduna town, relative humidity for Kaduna town and the stage height data for the studied river and the discharge data. All the data used span the period 1975-2004 (30 years). These parameters are non-linear, stochastic (random) and uncertain in nature. Adaptive Neuro-Fuzzy based Inference System (ANFIS), an integrated system, comprising of Fuzzy Logic and Neural Network was used to model the discharge forecast, because it can address and solve problems related to non-linearity, randomness and uncertainty of data. The ANFIS-based model developed uses 70% of data for training and 30% for checking; subsequently validation data of the variables were used to predict the discharge and test the model developed. From the analysis carried out on the ANFIS-based model; Root Mean Square Error (RMSE) found to be 107.62. The analysis shows high level of accuracy with regards to the ANFIS-based model developed in forecasting the river discharge especially with a correlation (r) value of 86%. © Maxwell Scientific Organization, 2012.