Application of Machine Learning Models to Bridge Afflux Estimation

Bridges are essential structures that connect riverbanks and facilitate transportation. However, bridge piers abutments can disrupt the natural flow of rivers, causing a rise in water levels upstream bridge. The levels, known as backwater or afflux, threaten stability service bridges riverbanks. It is postulated applications estimation models with more precise afflux predictions enhance safety flood-prone areas. In this study, eight machine learning (ML) were developed to estimate utilizing 202 laboratory 66 field data. ML consist Support Vector Regression (SVR), Decision Tree Regressor (DTR), Random Forest (RFR), AdaBoost (ABR), Gradient Boost (GBR), eXtreme Boosting (XGBoost) for (XGBR), Gaussian Process (GPR), K-Nearest Neighbors (KNN). To best authors’ knowledge, first time these have been applied afflux. performance ML-based was compared those artificial neural networks (ANN), genetic programming (GP), explicit equations adopted from previous studies. results show most utilized study significantly accuracy estimations. Nevertheless, few models, like SVR ABR, did not good overall performance, suggesting right choice an model important.