Considering the importance of scouring in the design of BRIDGEs, nowadays, to increase the accuracy of scour depth estimation, artificial neural networks are used. In this research, a model for estimating scour depth around the BRIDGE pier GROUP was used by a new method called support vector machine. In this method, the statistical parameters of RMSE, R 2, DC, were used to evaluate the performance of the models. The results showed that using compounds of the sedimentary and hydraulic parameters in the support vector data model provided better results in estimation of scour depth. For example, in tripod mode, the assessment criteria values for the scenario 1 (hydraulic parameters), were R 2 = 0. 9914, DC = 0. 9758 and RMSE= 0. 0576, and for scenario two (hydraulic and sediment parameters), were to R 2 = 0. 9924, DC = 0. 9803 and RMSE = 0. 0529, which indicated better performance of the support vector machine in the second scenario. Finally, non-linear equations were presented for calculating the scour depth around the INCLINED Single and GROUP PIERS.