Rainfall Forecast by Integrated Model ARMA-ARCH for West of Urmia Lake Catchment basin

Forecasting rainfall situation has paramount importance for water resources engineering. In this field, linear time series models are widely used in hydrology. Models of ARMA family have always had weaknesses which can be solved by integration of ARMA linear time series models with nonlinear time series models such as ARCH. In economy, the sequence of error variance in one model of errors’ size in previous time periods is the main assumption for Autoregressive conditional heteroscedastic models (Engle, 1982). At first, models of ARCH family for time series were used in financial and economic problems. In problems related to hydrology, ARCH models have been studied less.