Providing a robust and reliable predictive model for river sediment discharge is an essential task for several environmental and geomorphological perspectives, including water quality, riverbed engineering sustainability, and aquatic habitats. In this research, a new hybrid intelligent approach based on the support vector regression model approach has been developed to predict river sediment discharge. For this purpose, in this research, two optimization algorithms including firefly and gray wolf were used to model the sediment discharge of the river. In order to model, the statistics and information of the Kashkan river hydrometric station located in Lorestan province were used as a case study in 7 combined scenarios of input parameters in 1403-1373. In order to evaluate the performance of the models, the evaluation criteria of correlation coefficient, root mean square error, average absolute value of error, and Nash Sutcliffe coefficient were used. The results showed that the combined scenarios in the studied models improved the performance of the model. Also, the results of the evaluation criteria showed that the support vector regression model-firefly has a correlation coefficient of 0.970, the root mean error rate (ton/day) is 0.145, the mean absolute error value (ton/day) is 0.080 and the coefficient Nash Sutcliffe has 0.980 in the validation stage. In total, the results showed that the use of intelligent models based on the support vector regression approach can be an effective approach in the sustainability of river engineering.