Dataset and machine learning models for post-earthquake residual vertical load-carrying capacity (VLCC) assessment of RC bridge bents

This upload includes the collected dataset and trained machine learning models (based on Matlab platform) for post-earthquake residual vertical load-carrying capacity (VLCC) assessment of reinforced concrete (RC) single-column and double-column bridge bents. The input variables (features) are structural parameters of bridge bents. The output variables (labels) are post-earthquake residual vertical load-carrying capacity (VLCC) of laterally damaged RC bridge bents corresponding to an inelastic index (II) of 0.5 and 1.0. The dataset contains 860 post-earthquake residual VLCC results gathered by conducting cyclic pushover analyses and pushdown analyses for randomly sampled bridge bents. Machine learning models are developed using three popular machine learning algorithms, i.e., support vector regression (SVR), artificial neural network (ANN), and regression tree ensembles (RTE).