Evren Turhan, Mümine Kaya Keleş, Atakan Tantekin, Abdullah Emre Keleş
Adana Alparslan Türkeş Science and Technology University, Turkey
corresponding author’s e-mail:
Proper water resources planning and management is based on reliable hydrological data. Missing rainfall and runoff observation data, in particular, can cause serious risks in the planning of hydraulics structures. Hydrological modeling pro-cess is quitely complex. Therefore, using alternative estimation techniques to forecast missing data is reasonable. In this study, two data-driven techniques such as Artificial Neural Networks (ANN) and Data Mining were investigated in terms of availability in hydrology works. Feed Forward Back Propagation (FFBPNN) and Generalized Regression Neural Networks (GRNN) methods were performed on rainfall-runoff modeling for ANN. Besides, Hydrological drought analysis were exam-ined using data mining technique. The Seyhan Basin was preferred to carry out these techniques. It is thought that the appli-cation of different techniques in the same basin could make a great contribute to the present work. Consequently, it is seen that FFBPNN is the best model for ANN in terms of giving the highest R2 and lowest MSE values. Multilayer Perceptron (MLP) algorithm was used to predict the drought type according to limit values. This system has been applied to show the relationship between hydrological data and measure the prediction accuracy of the drought analysis. According to the ob-tained data mining results, MLP algorithm gives the best accuracy results as flow observation stations using SRI-3 month data.
artificial neural networks, drought analysis, data mining, Multilayer Perceptron, Seyhan Basin