Sustainable rehabilitation of corroded RC culverts using ECC and interpretable machine learning

Culverts are vital for managing subsurface water flow beneath transport infrastructure, especially in areas with poor drainage and low bearing capacity. Precast reinforced concrete (RC) box culverts are widely used for their structural efficiency and constructability; however, prolonged exposure to moisture and corrosive environments leads to significant deterioration, particularly reinforcement corrosion. This study introduces a novel strengthening strategy using Engineered Cementitious Composites (ECC), applied beneath the top slab—the most corrosion-prone zone. A series of 200 nonlinear finite element (FE) simulations were conducted to evaluate culvert performance across varying corrosion thicknesses and ECC configurations. Subsequently, six machine learning (ML) models XGBoost, AdaBoost, RF, SGD, kNN, and GEP were trained to predict ultimate load capacity using key geometric and material parameters. Explainable AI (XAI) techniques SHAP and Partial Dependence Plot (PDP) analyses were employed to interpret the ML outputs, revealing parameter sensitivities and physical relevance. Results showed that ECC effectively restores load capacity (up to 41 % increase) of corroded culverts and improves deformation behavior. Among the models, XGBoost yielded the highest predictive accuracy, while SHAP analysis confirmed culvert width, corrosion thickness, and ECC strength as dominant features. This integrated FEM-ML-XAI approach offers a data-driven, interpretable, and material-efficient solution for rehabilitating corroded culverts. This study contributes a novel combination of advanced materials and explainable AI, offering actionable insights for the sustainable and intelligent rehabilitation of deteriorated culverts in corrosion-prone environments.