River Discharge Prediction at Kinta River using Multi Quadric Radial Basis Function

In recent years, data evaluation approaches such as artificial neural network (ANN) techniques are being increasingly used for river flow forecasting. For efficient management of water resources, accurate and reliable flow prediction is extremely important. Additionally, it is also true for effective flood risk management. In general, streamflow prediction models when incorporated within flood forecasting systems serve as tools for early warning systems so as to reduce flood damages on one hand and may also result in considerable economic and social benefits. The specific objective of this study is to develop Multi-Quadric Basis function Neural Network model for the prediction of river discharge at Kinta River and to evaluate the performance of the Multi-Quadric basis function model using different statistical performances measures. The ANNs model for this study is developed in MATLAB software. To measure the performance of the model, four criteria performances, including a coefficient of determination (R2), the sum squared error (RSE), the mean square error (MSE), and the root mean square error (RMSE) are used. The results of this study could be used to help local and national government plan for the future and develop appropriate to the local environmental conditions new infrastructure to protect the lives and property of the people of Perak.