EVALUATION OF CLIMATE CHANGE IMPACT ON RUNOFF IN THE KAINJI LAKE BASIN USING ARTIFICIAL NEURAL NETWORK MODEL (ANN)

This paper presents an evaluation of the impacts of climate change on the runoff in the Kainji Lake basin. Hydro-meteorological data used include the minimum and maximum temperature, evaporation, precipitation, runoff and water level were subjected to artificial neural network (ANN) model. The model results revealed a positive relationship between the actual and forecasted runoff for all the selected locations and their correlation coefficient of 0.62, 0.57, 0.55 and 0.57 for Lokoja, Kaiji, Baro and Idah respectively. Runoff values were predicted for the stations and the mean annual predicted runoff were subjected to trend analysis in order to determine their variation. The percentage variations are estimated as -9.75%, +4.58%, -12.07% and - 6.48% for Lokoja, Kainji, Idah and Baro respectively. The trend analysis indicated that the runoff at Lokoja, Baro and Idah are negative while that of Kainji exhibit positive trend. This implies that there is tendency for runoff to decrease at Lokoja, Baro and Idah stations while increases at Kainji. The study revealed that climate change has positive impact on the reservoir inflow at Kainji damand subsequently assure more water for hydropower generation.