A Decision Tree model for sediment transport modeling

Sediment transport in open channels such as urban drainage systems plays a crucial role in hydraulic capacity of the channel. This study, investigates the bed load sediment transport in sewer pipes with particular reference to the non-deposition condition in clean bed channels. Four data sets available in the literature covering wide ranges of pipe size, sediment size and sediment volumetric concentration have been utilized through applying Decision Tree (DT) technique for modeling. The developed model have been compared with conventional regression models available in the literature. The model performance indicators, showed that DT model outperforms conventional regression models. It is concluded that conventional regression models generally overestimate particle Froude number for non-deposition condition of sediment transport, while DT outputs are close to their measured counterparts.

Keywords:

decision tree , open channel , sediment transport , self-cleansing