Predicting Max Scour Depths near Two-Pier Groups Using Ensemble Machine-Learning Models and Visualizing Feature Importance with Partial Dependence Plots and SHAP

Abstract

Assessing scour depth (Sd) near side-by-side, tandem, and eccentric bridge piers is crucial for designing resilient structures. Researchers employed soft computing techniques to enhance Sd prediction models, focusing on ensemble machine learning (ML) methods for isolated piers. However, this research is limited on such two-pier groups, which necessitates a detailed study of how pier spacing and positioning collectively affect Sd predictions. A thorough examination is needed to analyze scouring patterns and the collective two-pier impact on estimating Sd using ensemble ML models. This study employs two ensemble ML models, random forest (RF) and extreme gradient boosting (XGBoost), to collectively predict circular two-pier Sd. Input parameters such as flow characteristics, sediment properties, time, pier gaps, and flow skew angle are rigorously evaluated to assess their combined impact on Sd. Partial dependence plots (PDP) and SHapley Additive exPlanations (SHAP) are used to visualize feature importance and effects on predicting Sd after training ML models, providing insights into individual features’ influence on predictions. Performance indicators [coefficient of determination (R2), mean absolute error, and root mean squared error] assess the ML models’ performance. Results demonstrate that XGBoost outperformed RF in training and testing phases with random search cross validation (CV) optimization for both piers. However, RF excelled over XGBoost in training using grid search CV and random search CV for both piers. Flow intensity was identified as the most influential variable, making the phenomenon highly vulnerable during model training with SFS and SHAP. Using ensemble ML models with detailed parameter evaluations and visualizations, engineers can predict Sd more effectively, thus enhancing scouring pattern understanding to design resilient structures. The practical application of this study shows where new bridges are needed next to old bridges for traffic in rapidly populating cities. Bridge piers are placed side-by-side, in tandem, or eccentrically. Scour depth can increase or decrease due to dynamic interference if these piers are not studied properly. This study examines how interference impacts scour depth in various positions and estimates it using an ensemble ML model. This ensemble model accurately predicts scour depth around such interfering piers, which outperforms the classic model. Partial dependence plots show how parameters affect scour depth, considering interference effects. The model shows how interference impacts the scour depth for designing such piers. This model can be used to analyze the impact of such two-pier configurations after integrating the field data for studying field installation effects. Experts and practitioners can utilize the model to improve bridge placements by predicting how pier interference affects scour depth, thus enhancing safety in the design process.