Discussion of “Evaluation of Data-Driven and Empirical Models for the Estimation of Sediment Removal Efficiency in Settling Basins”

The discussers express their gratitude to the authors utilizing data-driven models including adaptive boost regressor (ADBR), extreme gradient boost regressor (XGBR), random forest (RF), and random tree (RT) to predict the sediment removal efficiency and compare their results with empirical models such as United States Bureau of Reclamation (USBR), Garde, Raju, Camp-Dobbins, and Sumer models.Through a systematic examination of publicly available data sources, a database of 328 experimental observations was compiled.Among the empirical models, the Salmasi model exhibited a higher degree of accuracy, followed by the USBR, Garde, Raju, Camp-Dobbins, and Sumer models.The data-driven models were ranked from best to worst as ADBR, XGBR, RF, and RT, respectively.Additionally, the most suitable range of input parameters was assessed using the best-performing data-driven model, ADBR.The discussers highlight relevant factors that warrant attention to enhance the original study's findings and further advance the field.