Physical and artificial intelligence-based hybrid models for rainfall-runoff-sediment process modelling

This study evaluates the performance of the Hydrologic Engineering Center-Hydrologic Modelling System (HEC-HMS), Hydrologiska Byrans Vattenbalansavdelning (HBV), Soil and Water Assessment Tool (SWAT), feedforward neural network (FFNN), adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR) and multilinear regression (MLR) for modelling the rainfall-runoff-sediment process in Katar catchment, Ethiopia. Afterward, neural network ensemble (NE), weighted average ensemble (WE) and simple average ensemble (SE) techniques were developed to improve the performance of single models. The performance of the models was evaluated using Nash-Sutcliffe efficiency (NSE), root mean square error (RMSE) and mean absolute error (MAE). The results show that the ANFIS model outperformed the other single models for rainfall-runoff-sediment modelling. Moreover, the integration of artificial intelligence and physically-based models resulted in improved performance, with the NE technique demonstrating better accuracy by improving individual models by 5.8-27.6% for rainfall-runoff and 3.59-37.9% for suspended sediment load modelling in the validation phase.

Automated summary

This study evaluates the performance of multiple models for rainfall-runoff-sediment process in Katar catchment, Ethiopia. The results show that the ANFIS model outperformed other single models, and the integration of artificial intelligence and physically-based models improved the accuracy. The NE technique demonstrated better accuracy by improving individual models by 5.8-27.6% for rainfall-runoff and 3.59-37.9% for suspended sediment load.