Improving artificial intelligence models accuracy for monthly streamflow forecasting using grey Wolf optimization (GWO) algorithm

Monthly streamflow forecasting is required for short- and long-term water resources management especially in extreme events such as flood and drought. Therefore, there is need to develop a reliable and precise model for streamflow forecasting. The precision of Artificial Intelligence (AI) models can be improved by using hybrid AI models which consist of coupled models. Therefore, the chief aim of this study is to propose efficient hybrid system by integrating Grey Wolf Optimization (GWO) algorithm with Artificial Intelligence (AI) models. 130 years of monthly historical natural streamflow data will be used to evaluate the performance of the proposed modelling technique. Quantitative performance indicators will be introduced to evaluate the validity of the integrated models; in addition to that, comprehensive analysis will be conducted between the predicted and the observed streamflow. The results show the integrated AI with GWO outperform the standard AI methods and can make better forecasting during training and testing phases for the monthly inflow in all input cases. This finding reveals the superiority of GWO meta-heuristic algorithm in improving the accuracy of the standard AI in forecasting the monthly inflow.