Hybrid machine learning-enabled multivariate bridge-specific seismic vulnerability and resilience assessment of UHPC bridges

Abstract

Efficient seismic vulnerability and resilience assessment is essential for ultra-high-performance concrete (UHPC) bridges, given their distinctive mechanical and structural properties. However, existing single-parameter-based probabilistic seismic demand (PSD) models overlook critical bridge‐specific characteristics and uncertainties. Besides, studies on seismic vulnerability and resilience assessment of UHPC bridges are scarce. Thus, this study proposes a hybrid machine learning (ML)-enabled multivariate bridge-specific seismic vulnerability and resilience assessment framework for UHPC bridges. Key design parameters and associated uncertainties are identified, and a Latin Hypercube Sampling (LHS) technique is employed to establish a representative UHPC bridge database, which is used to develop a hybrid ML model-based multivariate PSD model. A comparative analysis with the conventional PSD model, as well as widely used ML algorithms, demonstrated that the proposed PSD model achieves the highest predictive performance, characterized by the highest coefficient of determination and lowest prediction errors. Additionally, SHapley Additive exPlanation (SHAP) analysis is used to investigate the effect of different parameters on the PSD of UHPC bridges. The results of SHAP show the peak ground acceleration (PGA) as the most important factor, followed by bridge span and column diameter. The hybrid ML-enabled multi-variate bridge-specific fragility analysis results are used to investigate the functionality recovery and resilience of the bridge, which demonstrate the reduction in the residual functionality and overall bridge resilience with the increase in the ground motion intensity.