J.O. Ehiorobo

In this study, the potential of Ikpoba river dam being used as a multipurpose dam was evaluated. Before the evaluation, the flow regime behaviour of the river was modelled and predicted using adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) in MATLAB software. The river daily discharge, temperature and precipitation data sets from 1991 to 1995 were used for the prediction. In applying ANFIS using hybrid algorithm, five different models: model-1, model-2, model-3, model-4 and model-5 were created using 1995 data sets as the target outputs in all the five models. Only discharge data sets for 1994; 1994 and 1993; 1994, 1993 and 1992; 1994, 1993, 1992 and 19991 were used as the input data sets for model-1 to model-4 respectively. Model-5 was created by indexing monthly temperature and precipitation into model-4 to see the effect of climate change on the models. ANN was also applied to the same models as created with ANFIS. In ANN, three training algorithms; Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG) and Bayesian Regularization (BR) were used. Five performance evaluation criteria namely coefficient of correlation (R), coefficient of determination (R2), mean square error (MSE), modelling efficiency (E) and index of agreement (IOA) were used for comparative analysis.The results of both ANFIS and ANN using the five performance evaluation criteria (R, R2, MSE, E and IOA) showed that model-5 (when the effect of climate change was incorporated) performed better than the other four models. The training phase in model-5 of ANFIS showed an over-estimation of 0.043% of the observed target output sets while an over-estimation of 0.044% was observed in the testing phase. The training phase in model-5 of ANN (LM) showed an over-estimation of 0.11% of the observed target output sets while an over-estimation of 0.14% was observed in the testing phase. The training phase in model-5 of ANN (SCG) showed an over-estimation of 0.21% of the observed target output sets while an over-estimation of 0.31% was observed in the testing phase. The training phase in model-5 of ANN (BR) showed an over-estimation of 0.17% of the observed target output sets while an over-estimation of 0.19% was observed in the testing phase. It was therefore concluded that ANFIS performed better than ANN in all the five models and that ANN (LM) performed best followed by ANN (BR) and ANN (SCG) in the ANN models. When the potential of Ikpoba dam being used as a multipurpose dam was evaluated, it was discovered that the dam with ultimate water pumping capacity of 160 x 106 liters/day could also be utilized to produce 5.26MW of power monthly (with discharge of 31.9m3/s) using a hydropower plant. The annual volume of water in the reservoir available for this hydropower scheme is 0.523 x 106m3