Forecasting of Meteorological Drought Using Machine Learning Algorithm

Abstract

Drought forecasting is one of the crucial tools for the water management system, and understanding the different climatic variables affecting the occurrences of drought is a major scientific challenge. In this study, drought forecasting is done for the Peninsular region of India using different machine learning algorithms. A meteorological drought index known as Standardized Precipitation Index (SPI) which is dependent on the precipitation is taken into account for analysis. The SPI with a different timescale for 3-, 6-, 9-, 12-month were calculated from 1958–2017 for 60 years. SPI is a function of precipitation and the trend of rainfall followed may be found to be similar in some regions. Two different models, GA-ANFIS and GRNN were compared in this study. The results obtained from the statistical performance assessment of the models were compared with each other. For different timescale, there is a variation in its evaluation metrics. Comparing the performance assessment of the two different models, it is noticeable that the performance assessment of the statistics of the GA-ANFIS model outperformed GRNN model. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.