Improving multi-month hydrological drought forecasting in a tropical region using hybridized extreme learning machine model with Beluga Whale Optimization algorithm

Climate change has increased drought frequency globally, which harms the environment, agriculture, and water resources. This study explores the capacity of a hybrid model based on the integration of extreme learning machine (ELM) with a novel meta-heuristic algorithm called Beluga Whale Optimization (BWO) for drought forecasting within tropical region. The forecasting adopted for the standardized streamflow index (SSI) for several time scales (SSI-1, SSI-3, SS1-6, SSI-9, SSI-12, and SSI-24) over Selangor state, Malaysia. The drought calculation was based on 58 years of stream flow data (1961 to 2018) obtained from two hydrological stations, S3615412 and S3414421. The ELM-BWO model was validated with standalone models including Gradient boosting regression (GBR) and classical ELM in addition to the hybridization of ELM with genetic algorithm (GA). The inputs were nominated by using partial autocorrelation function (PACF) at 5% significance level. The research finding reveals that the ELM-BWO model used for the first in hydrological drought forecasting, outperforms other models and provides the narrowest uncertainty bounds. The proposed ELM-BWO model accuracy was demonstrated by the decreased metric of root mean square error (RMSE) values across different drought timescales (e.g., SSI-9 by 12.65% to 78.74%). In addition, the model obtains the highest correlation coefficient (0.9777 and 0.9944) and Wilmot index values (0.9882 and 0.9971) for both stations. The ELM-BWO model can be used to form a dependable expert intelligent system for anticipating hydrological drought at multiple time scales, making decisions about appropriate measures to deal with hydrological drought at the studied stations, and supporting sustainable water resource management.