Prediction of suspended sediment load in Sungai Semenyih using extreme learning machines and metaheuristic optimization approach

Suspended sediment load (SSL) refers to sediment particles, such as silt and clay, that are suspended in water. It plays a critical role in hydrology and water quality management, influencing factors such as water quality, river erosion, sedimentation rates, dam operations, and aquatic ecosystems. Therefore, accurate prediction and monitoring of SSL is crucial for efficient water resources and environmental management. The study aims to enhance SSL prediction performance by integrating Extreme Learning Machines (ELM) with metaheuristic optimizations. The selected metaheuristic optimizations, namely Particle Swarm Optimization (PSO), Henry Gas Solubility Optimization (HGSO), Electromagnetic Field Optimization (EFO), and Nuclear Reaction Optimization (NRO), are systematically employed in ELM models for predicting SSL in Sungai Semenyih, Selangor, for a period from 2015 to 2018. The results show that the ELM-HGSO model slightly better performs than the other optimized models, achieving a Willmott Index (WI) of 0.9986, a Confidence Index (CI) of 0.996, a Mean Absolute Percentage Error (MAPE) of 0.058, a Nash-Sutcliffe Efficiency (NSE) of 0.994, and a Root Mean Square Error (RMSE) of 4.082. The ELM-HGSO model improves NSE by approximately 10 % compared to the standalone ELM model. The Taylor diagram further confirms that ELM-HGSO best fits the observed data for both training and test datasets. This study concludes that ELM-HGSO is the most suitable model for SSL prediction in the study area. The findings are expected to advance SSL prediction research, contributing to improved water management and sustainable infrastructure development.