N.M. Sebusang (Gaborone) and J. Ndiritu (South Africa)
Artificial neural network, data-based hydrologic modelling, trans-boundary flows
This paper presents an attempt to use Artificial Neural Networks (ANN) for the simulation of the Crocodile water resource system in the Mpumalanga province of South Africa and to use the model to assess the extent to which Kwena dam, the only major dam in the system could meet the required cross border flow to Mozambique. The modelling was confined to the low flow periods when the Kwena dam releases are most significant. The form of ANN model developed in this study is the standard error backpropagation run on a daily time scale. The model applied 32 inputs that comprised of four irrigation abstractions at Montrose, Tenbosch, Riverside and Karino; current and average daily rainfall totals for the previous 4 days at four rainfall stations; average daily temperature at Karino and Nelspruit; daily releases from Kwena dam; daily streamflow from the tributaries of Kaap, Elands and Sand rivers and the previous day’s flow at Tenbosch. The single output was the current day’s flow at Tenbosch. Data from a representative dry year and four release scenarios were used. The scenarios assumed that Kwena dam was 100%, 75%, 50% and 25% full at the beginning of the year and the water would be supplied at a constant rate to emptiness over a period of one year. It was found that increasing Kwena releases improved the cross border flows but the improvement in providing the 0.9m3 /s cross border flow requirement was minimal. For the scenario when the dam is initially 100% full, the requirement was met with an improvement of 11% over the observed flows.
Important Links:
Go Back
