Surrogate learning for scoured bridges for capacity prediction with climate-scenario deep uncertainties
No Thumbnail Available
Authors
Meeting name
Sponsors
Date
Journal Title
Format
Subject
Abstract
Waterway bridges are among the most vulnerable components of transportation infrastructure due to scour—the erosion of soil around foundations caused by flowing water—a risk expected to grow under climate-driven increases in flood intensity. Traditional fragility models often assume a fixed structural capacity, overlooking how scour alters soil–foundation–structure interaction (SFSI) and degrades performance.This study develops a computationally efficient surrogate-learning framework, trained on nonlinear pushover analyses, to predict yield-level transverse capacities—base shear, deck displacement, base moment, and column rotation—collectively expressed as a capacity tuple. To incorporate deep uncertainty arising from future IPCC climate-scenario trajectories, we employ a credal-set approach that yields upper and lower bounds on capacity predictions. The resulting method enables rapid, risk-informed evaluation of scour-critical bridges, supporting practical decision-making under uncertain future hydraulic hazards.
Table of Contents
Introduction -- Literature review and background -- Bridge modeling and scour hazard simulation -- Nonlinear pushover analysis and capacity tuple extraction -- Conclusions and future work
DOI
PubMed ID
Degree
M.S. (Master of Science)