Improving streamflow prediction using a new hybrid ELM model combined with hybrid particle swarm optimization and grey wolf optimization

Accurate runoff estimation is crucial for optimal reservoir operation and irrigation purposes. In this study, a novel hybrid method is proposed for monthly runoff prediction in Mangla watershed in northern Pakistan by integrating particle swarm optimization (PSO) and grey wolf optimization (GWO) with extreme learning machine (ELM) as ELM-PSOGWO. The proposed method was compared with the standalone ELM, hybrid of ELM-PSO, and binary hybrid PSOGSA (hybrid of PSO with gravitational search algorithm) methods. Monthly precipitation and runoff data were used as inputs to the models to examine their accuracy in terms of different statistical indexes. Test results showed that the proposed ELM-PSOGWO provided more accurate results than the standalone ELM, hybrid ELM-PSO, ELM-GWO nd binary hybrid PSOGSA methods in monthly runoff prediction. ELM-PSOGWO reduced the RMSE in prediction of ELM, ELM-PSO, ELM-GWO and ELM-PSOGSA by 38.2, 22.8, 22.4 and 16.7%, respectively. The PSO and GWO based ELM models also performed better than standalone ELM models, with an improvement in RMSE by 19.9 to 20.3%, respectively. Results also showed that adding precipitation as input enhanced the prediction accuracy of models. ELM-PSOGWO was also able to provide more precise estimates of peak runoff with the lowest absolute mean relative error compared to other methods. The results indicate the potential of ELM-PSOGWO model to be recommended for monthly runoff prediction. • ELM-PSOGWO is compared with the ELM, ELM-PSO, ELM-GWO and ELM-PSOGSA methods. • ELM-PSOGWO method found more successful than the other benchmarked models. • ELM-PSOGWO method also provided the lowest AMRE in peak streamflow estimation. • ELM-PSOGWO significantly improved the RMSE of ELM, ELM-PSO, ELM-GWO and ELM-PSOGSA.