| Summary: | Black box models are one of the most common hydrologicalmodels in order to make predictions of hydrological variables such asprecipitation and stream flow. In this study, performance of a combined modelwhich consists of wavelet transformation, genetic algorithm and artificialneural network (WGANN) were tested forprediction of monthly precipitation by using North Atlantic Oscillation (NAO)index, Southern Oscillation (SO) index and precipitation data as input in themodel. The case study was carried out for Antalya which is located in Mediterraneanregion of Turkey. As a result, it was attained that WGANN model performed moresuccessful than usual artificial neural network (ANN), multiple linearregression (MLR) and genetic algorithm-artificial neural network (GANN) models.
|
|---|