An Overview of the Methodologies in Drought Forecasting

Drought has resulted in the massive destruction of lives, livestock and economy, locally and globally. Under the current circumstances, the dry weather conditions are prevalent leading to water stress resulting in imbalance of the ecosystem. The persistent dry weather eventually results in drought conditions, which indirectly affects the economy of the country. As a result, it has become imperative to assess and mitigate the effects of the droughts. With the advancements in the machine learning techniques, there has been a substantial improvement in the level of accuracy of the prediction of drought events. The motivation of this paper is to review those machine learning techniques such as Extreme Gradient Boost, ARIMA, Long ShortTerm Memory (LSTM), Random Forest used in forecasting drought events. Considering the extensively used drought indices, that is, the Standard Precipitation Index (SPI) and Standardized Precipitation Evaporation Index (SPEI) together with the various meteorological parameters, the influence of the climate variables on drought forecasts are given more importance in the present study. This study also includes review on single and hybrid models used for forecasting droughts. Further the gaps in the reviews have been identified by critically observing the studies in the research articles which will enhance the efficiency of the predictive models.