JWSS - Journal of Water and Soil Science

In regard to wide piers, the pile group rather than single pile is used frequently to bear the loading of the structure in a particular arrangement; piles group composed of only one column of piles in the flow direction has a great effect on supporting the bridge deck. In this study, local scour at a single column arrangement of the piles group made up of four rows of piles characterized by different piles spacing was studied for clear-water conditions with two flow discharges of 20 and 35 l/s (the effect of increasing the flow depth with the same flow intensity). The results indicated that an increase in the flow depth not only greatly enhanced the scour depth and the width of the scour hole. Besides, the investigation of the relative flow depth on scour extent showed the need for revision in deep water conditions, as reported in the literature. The results of the pile group experiments revealed the noticeable impacts of piles spacing on the local scour. The bigger pile spacing caused a feeble interaction of wake-horseshoe vortices, leading to a decrease of the scour depth; the separate view of the scour holes was generated at individual piles. Finally, the results were compared with commonly used comprehensive models. The findings of this study can be applied for the appropriate selection and positioning for the countermeasure of the scour at bridge piers.

Scour is a major challenge in river engineering, as it causes bridge failures during flood events and leads to significant economic losses. This study aims to estimate the normalized scour depth (Dse/Dp) around pile groups by examining relevant hydrodynamic and geometric parameters. A dataset comprising 299 laboratory measurements collected from various sources was assembled and divided into training and testing subsets. As machine learning inputs, several models were employed, including Artificial Neural Networks (ANN), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), and a meta-ensemble learning model (Stacking). Hyperparameter tuning was performed using the Grid search method to achieve optimal regression performance. Model performance evaluation indicated that the ANN and SVR models achieved coefficients of determination of R² = 0.87 and R² = 0.91, respectively. The XGBoost model outperformed these approaches, yielding R² = 0.94 with an RMSE of approximately 0.28. Ultimately, the stacking ensemble model, by integrating the outputs of the base learners, demonstrated the highest predictive accuracy with R² = 0.96 and an RMSE of 0.11, representing an improvement of approximately 15% compared to ANN and 7% compared to XGBoost. Overall, the findings highlight that ensemble machine learning models—particularly the Stacking approach—provide a robust and efficient framework for predicting scour depth around pile groups and for capturing the complex flow behaviors in hydraulic systems.