Development of a Hybrid SG-ARIMA-LSTM Model for Improved Meteorological Drought Forecasting Using the Standardized Precipitation Index in the KwaZulu Natal Province, South Africa.

Abstract

Abstract Drought is a significant natural hazard that has devastating effects on both human life and water resources. Monitoring and predicting drought are essential for the efficient management of water resources thereby reducing its effects. Designing a consistent drought prediction model based on the dynamic relationship between the drought index and its prior values remains difficult due to nonstationarity and nonlinearity. This study investigates the combined strengths of the Savitzky-Golay (SG) filter, Autoregressive Integrated Moving Average (ARIMA), and Long Short-Term Memory (LSTM) to test a new method of a hybrid model's ability to accurately forecast future droughts in uMkhanyakude district, South Africa using SPI index as a drought assessment. The Standardized Precipitation Index (SPI) was computed for 6-, 9- and 12-month timescales using monthly rainfall data from 1980 to 2023 (528 monthly observations) for a 44-year period. The performance of the models is evaluated using three statistical measures, namely root mean square error (RMSE), directional symmetry (DS) and coefficient of determination ( R 2 ). The results reveal the SG-ARIMA-LSTM hybrid model as an efficient tool, outperforms the individual models, SG-ARIMA, SG-LSTM and ARIMA-LSTM in forecasting across all timescales with the improved RMSE ranging between 0.2056 – 0.3011 for SPI-6, 0.1051 – 0.2064 for SPI-9 and 0.0525 – 0.0854 for SPI-12 and the R 2 ranges between 0.9392 – 0.9624 for SPI-6, 0.9724 – 0.9865 for SPI-9 and 0.9904 – 0.9969 for SPI-12. The SG-ARIMA-LSTM-based approach proposed herein could be adopted to forecast the drought with reasonable accuracy.