A NEW ARTIFICIAL NEURAL NETWORK MODEL FOR THE PREDICTION OF THE RAINFALL-RUNOFF RELATIONSHIP FOR LA CHARTREUX SPRING, FRANCE

Abstract

The prediction of a rainfall-runoff relationship includes complex processes in karstic aquifer systems. In this study, an artificial neural network (ANN) model is utilized in order to simulate the rainfall -runoff relationships of La Chartreux spring in the karstic region Cahors, Southern France. Since numerical models are thought to be insufficient, the present study will contribute to the improvement of rainfall-discharge prediction models by using ANNs in MATLAB software. The model has been conducted with a feed forward and back propagation algorithm. The model is improved by the Levenberg-Marquardt algorithm in order to generalize the complex and non-linear rainfall-runoff issues. The meteorological data was obtained from meteorological stations in the region including eight years of rainfall and discharge data between 1976 and 1983. Model performance has been evaluated with respect to statistical error measures (root mean square error (RMSE), and correlation coefficient square (R-2). This study confirmed that artificial neural networks are capable of predicting rainfall-runoff relationships depending on the data quality, neural network properties, and data variability.