Hybridizing Artificial Intelligence Algorithms for Forecasting of Sediment Load with Multi-Objective Optimization

Forecasting of sediment load (SL) is essential for reservoir operations, design water resource structures, risk management, planning and preventing natural disasters in the river basin systems. Direct measurement SL difficult, labour intensive, expensive. The development an accurate reliable model forecasting required. Sediment transport highly non-linear influenced by a variety factors. using various conventional methods not because association complex phenomena. In this study, major key factors such as rock type (RT), relief (R), rainfall (RF), discharge (WD), temperature (T), catchment area (CA), are recognized developing one-step-ahead Mahanadi River (MR), which among India’s largest rivers. Artificial neural networks (ANN) conjunction with multi-objective genetic algorithm (ANN-MOGA)-based models were developed MR. ANN-MOGA was employed to optimize two competing objective functions (bias error variance) simultaneous optimization all associated ANN parameters. performances proposed novel finally compared other existing verify capability model. improved performance 12.81% 10.19% traditional AR MAR regression models, respectively. results suggested that hybrid outperform autoregressive multivariate models. Overall, intelligent techniques recommended rivers their relatively better simplicity application.