Forecasting the precipitation which is one of the most important meteorological variables is very important for planning and management of the water resources. Accurate precipitation prediction is one of the most difficult tasks in the meteorology because the complex physical processes involved and the variability of the precipitation is highly dependent on small scale processes and local geography. Especially the daily precipitation forecasting is one of the most challenging works and very important for the flood and drought analyses.Artificial Neural Networks (ANN) are a useful tool to identify this relation. ANN approach is extensively used in the water resources literature in recently years. Artificial neural networks which is a black-box model, is used successfully in the modeling of non-stationary and complex variables. Black-box models are divided generally as linear and nonlinear and in particular artificial neural networks method is used in the modeling of nonlinear system behavior. The artificial neural networks have some advantages, such as easily applied, not needing much data. However the accuracy of model predictions is very subjective and highly dependent on user’s ability, knowledge and understanding of the model. Especially, the input selecting is one of the most important phases in any ANN modeling study Because of this, wavelet transformation is used for increase of user ability and success of artificial neural networks. The wavelet transform, which can produce a good local representation of the signal in both the time and frequency domains, provides considerable information about the structure of the physical process to be modeled and has positive effects on the ANN modeling ability. Because of these reasons, coupling wavelets with the ANN can provide significant advantages on predicting.This study aims to predict the daily precipitation data of three belong to Turkish meteorological stations by applying the ANN methods and discrete wavelet transform. For this reason, the original time series were decomposed into a certain number of sub-time series using the wavelet transform. Then, the suitable sub time series constituted the inputs of the ANN and the resulting model was applied to forecast the original time series. The sub time series decomposed by discrete wavelet transform from the original time series provide detailed information about the data structure and its periodicity. Behavior of each sub-series is different. For the selection of dominant sub-series, the correlation coefficients between the decomposed wavelet sub-series and the observed precipitation time series are computed. The selection of dominant sub-series becomes effective on the output data improving ANN model’s performance.In this study, the wavelet transforms and the ANN has been applied to estimate the daily precipitation. The meteorological data belong to the three station were investigated for this study. These are the daily mean temperature, the daily maximum temperature, the daily minimum temperature, the daily total specific humidity, the daily total evaporation and the daily total precipitation. Each of the meteorological data considered as input for the ANN model was decomposed into the wavelet sub-series by Discrete Wavelet Transform (DWT). Then, ANN configuration is constructed with appropriate wavelet sub series as input and the original precipitation time series as output. So, different wavelet-ANN models were prepared for each station. Precipitation estimation was applied with the two different algorithms of the artificial neural networks. Employment of the Feed Forward Back Propagation (FFBP) in the precipitation estimation is compared with the Radial Basis Function (RBF) performances. The results were also compared with linear regression model. As a result, it was seen that the wavelet-feed forward back propagation method provided the best estimation performance. Results indicate that the wavelet-ANN model estimations were superior to the ones obtained by the multi linear regression model. The wavelet-ANN models have provided a good fit with the observed data, especially for the time series which have zero precipitation in the summer months. It was seen that the ANN-wavelet method provided very successful estimation performance. This study is the first application to the daily precipitation estimations using the wavelet sub-series of the various meteorological variables in the water resources literature. The wavelet-ANN method is especially convenient in variables having non-linear dynamics such as predicting of precipitation data.