Standalone and ensemble-based machine learning techniques for particle Froude number prediction in a sewer system

The hydraulic capacity of a channel is impacted due to sediment deposition in urban drainage and sewer system. As a result, the self-cleansing mechanism is a widely used phenomena in urban drainage and sewer systems. In this context, the prediction of particle Froude number plays an important role in the design of the sewer system. This study investigates the performance of multiple standalone and ensemble machine learning techniques for the prediction of particle Froude number with reference to non-deposition with deposited bed. Five datasets available in the literature comprising of wide ranges of the volumetric sediment concentration (C_v), dimensional grain size of particles (D_gr), sediment median size (d), hydraulic radius (R), pipe friction factor (λ) have been utilized in this study. For standalone techniques, we made use of a decision tree regressor (DecisionTreeRegressor), multilayer perceptron regressor (MLPRegressor), while for ensemble approach extreme gradient boosting regressor (XGBRegressor), extra trees regressor (ExtraTreesRegressor) have been utilized. To evaluate the proposed models, several performance metrics have been used such as correlation coefficient (CC), Nash–Sutcliffe efficiency (NSE), root mean square error (RMSE), and R². Results indicate that ensemble techniques are more accurate as compared to the standalone methods and empirical equations. Among the proposed models, ExtraTreesRegressor provides the highest prediction (CC = 0.978, NSE = 0.957, RMSE = 0.208, and R² = 0.957) followed by XGBRegressor, MLPRegressor, and DecisionTreeRegressor for the prediction of particle Froude number.