Climate change and water supply shortage are among the most critical issues around the globe. In this case, drought as a complicated and less realized phenomenon can lead to negative effects on several aspects of human life. Therefore, early forecasting of drought is essential for strategic planning and water supply management. In this study, a hybrid wavelet autoregressive integrated moving average (W-ARIMA) model is presented for drought forecasting to compare its ability over the traditional autoregressive integrated moving average (ARIMA) model using standardized precipitation index (SPI). To reach a better model for drought forecasting, wavelet transform is combined with the ARIMA model. Monthly precipitation data from January 1970 to December 2019 from Kabul are utilized in this experiment. SPI 3, SPI 6, SPI 9, and SPI 12 were then computed using these precipitation records. The objective of this study is to compare the accuracy of ARIMA and W-ARIMA for drought forecasting in Kabul, Afghanistan, based on the SPI. The empirical outcomes gave away that the proposed W-ARIMA model has acceptable proficiency based on statistical measurements such as root-mean-square error, mean absolute error, and mean absolute percentage error over individual ARIMA for drought prediction.
In this research article, a hybrid wavelet autoregressive integrated moving average (ARIMA) model is proposed for drought forecasting based on SPI. The proposed model showed significant excellency over the individual ARIMA model for drought forecasting according to statistical metrices.