Water surface profile prediction in non-prismatic compound channel using support vector machine (SVM)

Abstract

The process of estimating the level of water surface in two-stage waterways is a crucial aspect in the design of flood control and diversion structures. Human activities carried out along the course of rivers, such as agricultural and construction operation, have the potential to modify the geometry of floodplains, leading to the formation of compound channels with non-prismatic floodplains, thus possibly exhibiting convergent, divergent, or skewed characteristics. In the current investigation, the Support Vector Machine (SVM) technique is employed to approximate the water surface profile of compound channels featuring narrowing floodplains. Some models are constructed by utilizing significant experimental data obtained from both contemporary and previous investigations. Water surface profiles in these channels can be estimated through the utilization of non-dimensional geometric and flow parameters, including: converging angle, width ratio, relative depth, aspect ratio, relative distance, and bed slope. The results of this study indicate that the SVM-generated water surface profile exhibits a high degree of concordance with both the empirical data and the findings from previous research, as evidenced by its R2 value of 0.99, RMSE value of 0.0199, and MAPE value of 1.263. The findings of this study based on statistical analysis demonstrate that the SVM model developed is dependable and suitable for applications in this particular domain, exhibiting superior performance in forecasting water surface profiles.