Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning

This dataset supports the study “Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning”It includes (1) the numerical dataset of bridge and seismic hazard parameters, together with seismic risks for four damage states, and (2) trained Backpropagation Neural Network (BPNN) models developed using the H2O machine learning platform. This dataset supports the study “Rapid Lifetime Seismic Risk and Economic Loss Estimation of Aging RC Highway Bridge Portfolios Leveraging Machine Learning”It contains the input-output data used for model training and testing, as well as the trainedBackpropagation Neural Network (BPNN) models for seismic risk prediction. 1. Corroded Bridge Seismic Risk Dataset.xlsx This Excel file includes the numerical dataset used in the study.It contains bridge geometric, material, and corrosion level parameters and two seismic hazard parameters, together with the seismic risk for four damage states. Input parameters: number of spans, span length, number of columns per bent, column diameter and height, concrete strength, reinforcement yield strength, longitudinal and transverse reinforcement ratios, axial load ratios, corrosion levels of longitudinal and transverse reinforcements, and seismic hazard decay rate k and scaling factor k0. Output data: siesmic risks corresponding to Slight, Moderate, Extensive, and Complete damage states under combined corrosion-seismic conditions. 2. Corroded Bridge Seismic Risk BPNN.zip This compressed file contains all trained Backpropagation Neural Network (BPNN) models developed using the H2O machine learning platform.It includes 40 model files corresponding to the four seismic damage states (Slight, Moderate, Extensive, and Complete), each with 10 independently trained models for ensemble prediction.