Applicability of ANN Model and CPSOCGSA Algorithm for Multi-Time Step Ahead River Streamflow Forecasting

Accurate streamflow prediction is significant when developing water resource management and planning, forecasting floods, mitigating flood damage. This research developed a novel methodology that involves data pre-processing an artificial neural network (ANN) optimised with the coefficient-based particle swarm optimisation chaotic gravitational search algorithm (CPSOCGSA-ANN) to forecast monthly streamflow. The of Tigris River at Amarah City, Iraq, from 2010 2020, were used build evaluate suggested methodology. performance CPSOCGSA was compared slim mold (SMA) marine predator (MPA). principal findings this are effectively improves quality determines optimum predictor scenario. hybrid CPSOCGSA-ANN outperformed both SMA-ANN MPA-ANN algorithms. offered accurate results coefficient determination 0.91, 100% scattered between agreement limits Bland–Altman diagram. represent further step toward models in hydrology applications.