Towards using explainable data-driven surrogate models for treating performance-based seismic design as an inverse engineering problem

This study presents a methodology to treat performance-based seismic design (PBSD) as an inverse engineering problem, where design parameters are directly derived to achieve specific performance objectives (POs). By implementing explainable machine learning (ML) models, this methodology directly maps design variables and performance metrics, thereby tackling the computational inefficiencies associated with performance-based design. The resultant ML model is integrated as an evaluation function into a genetic optimization algorithm to solve the inverse problem. The developed methodology is then applied to two different inventories of steel and concrete moment frames in Los Angeles and Charleston to obtain sectional properties of frame members that minimize expected annualized seismic loss in terms of repair costs. The results show high accuracy of the surrogate models (e.g. R 2 > 90%) across a diverse set of building types, geometries, seismic design and site hazard, where the optimization algorithm could identify the optimum values of members’ properties for a fixed set of geometric variables, consistent with engineering principles. This article is part of the theme issue ‘Frontiers of applied inverse problems in science and engineering’.