Drought Forecasting Using Tree Multi-Scale Model

Drought is one of the environmental phenomena which causes severe damage to human societies. To survey the climatic changes conditions, especially drought, drought indices were as a strong management tool. In addition to the drought index, drought forecasting using appropriate models may be appropriate in control and drought management. In this research, information concerning precipitation related to two basins located in Hamadan and Lorestan Province was used to calculate the SPI and EDI indices, which are among the most-widely used indices for monitoring drought. The calculated indices were employed as the input for the WM5 models that were used in predicting drought. In the best-case scenario, the coefficients of determination for the EDI index in the M5 model and in WM5 model were 0.95 and 0.99, respectively. Moreover, the coefficients of determination for the SPI index in the M5 model and in WM5 model, in the best-case scenario, were 0.90 and 0.95, respectively. This suggests indicated the use of the WM5 was superior to and enjoyed great accuracy compared to the M5 model. The reason for this superiority is that both short- and long-term changes in time series are monitored in WM5. Moreover, the WM5 is more capable than the M5 in monitoring the maximum values of time series.