predicting sediment transport rate under vegetation cover using group method of data handling and new optimization algorithms

Developing vegetation cover is one of the practical solutions to alleviate the sediment transfer rate. predicting the sediment transfer rate in the presence of cover vegetation is a complicated necessary issue for designers due to the complex interaction between sediments and cover vegetation. this study intends to predict the sediment transfer rate (str) by employing soft computing models based on an experimental study. the primary innovations in this study were the introduction of new and optimized versions of the group method of data handling (gmdh) for predicting sediment transport rate, the use of a new inclusive multiple model for predicting sediment transport rate, and the investigation of the effects of various parameters on the sediment transport rate, such as vegetation cover density. this study used an inclusive multiple model (imm) as an ensemble model to predict sediment transport in the presence of cover vegetation. initially, the sediment transport rate was predicted using the individual gmdh models. these outputs were then used to create the final outputs by inserting them into the gmdh model as an ensemble model at the next level. the honey badger algorithm (hba), the rat swarm optimization algorithm (rsoa), the sine cosine algorithm (sca), and the particle swarm optimization algorithm (psoa) were used to train the gmdh model. the diameter of the sediments, the diameter of the stems, the density of vegetation cover, the wave height, the wave velocity, the cover height, and the wave force were used as inputs to the models. the imm’s mean absolute error (mae) was 0.145 m3/s, while the maes for gmdh-hba, gmdh-rsoa, gmdh-sca, gmdh-psoa, and gmdh in the testing level were 0.176 m3/s, 0.312 m3/s, 0.367 m3/s, 0.498 m3/s, and 0.612 m3/s, respectively. the nash–sutcliffe coefficient (nse) of imm, gmdh-hba, gmdh-rsoa, gmdh-sca, gmdh-psoa, and ghmdh were 0.95 0.93, 0.89, 0.86, 0.82, and 0.76, respectively. additionally, this study demonstrated that vegetation cover decreased sediment transport rate by 90%. the overall results indicated that the imm and gmdh-hba models could accurately predict sediment transport rates.