Hybrid model outperformed individual models in predicting droughts in a semi-arid region of Bangladesh

Abstract

Drought is one of the most significant repercussions of climate change. Worldwide droughts affect food security and ecological productivity. Bangladesh has faced a series of droughts over the past few decades, with significant economic and environmental consequences. The north-western region of Bangladesh is the most affected by drought because of its geographical location and semi-arid climate. With the increasing frequency and severity of droughts, rapid and reliable drought information is essential for agro-ecological production and food security. Using the Standardized Precipitation Index (SPI) and three models (Auto Regressive Moving Average (ARMA), PROPHET, and ARMA-Generalized Autoregressive Conditional Heteroskedasticity (ARMA-GARCH)), we assessed the trends of drought in the five meteorological stations (Bogra, Dinajpur, Ishwardi, Rajshahi, and Rangpur) in the north-western region of Bangladesh for the period 1980–2019. Results show that the SPI trends were significant for Dinajpur and Ishwardi stations but insignificant for the other three stations (Bogra, Rajshahi, and Rangpur). Among the three models, the hybrid model (ARMA-GARCH) outperformed the individual models (ARMA and PROPHET), which suggests that the ARMA-GARCH model could be utilized to predict droughts as it showed higher accuracy than that of individual models. This study provides empirical evidence of (i) the intensification of drier climates in the north-western region of Bangladesh over the 40 years, which has practical implications for introducing climate adaptive practices in agriculture and other livelihood sectors, and (ii) the better performance of a hybrid model compared to individual models in predicting drought, which is of great significance for government decision-making.