Spatial-temporal disaggregation of rainfall time series using wavelet-artificial neural network hybrid model

The need to simulate rainfall time series at different time scales for engineering purposes on the one hand and lack of recording such parameters in small scales because of administrative and economic problems, on the other hand, rainfall time series disaggregation to the desired scale is an essential topic in water resources engineering. In this study, for disaggregating the Tabriz and Sahand rain gauges time series, according to nonlinear characteristics of time scales, wavelet-artificial neural network (WANN) hybrid model is proposed. For this purpose, daily data of four rain gauges and monthly data of six rain gauges from Urmia Lake Basin for ten years were decomposed with wavelet transform and then using mutual information and correlation coefficient criteria, the subseries were ranked and dominant subseries were used as input of ANN model for disaggregating the monthly rainfall time series to the daily time series. Results obtained by the WANN disaggregation model were also compared with the results of ANN and conventional multiple linear regression models. The efficiency of the WANN model with regard to ANN and multiple linear regression models at validation stage for Tabriz rain gauge shows increase up to 8.5% and 33% and for Sahand rain gauge shows increase up to 13.7% and 26% respectively. It was concluded that hybrid WANN model can be considered as an accurate model to disaggregate the hydro-climatological time series.