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

TL;DR

This paper introduces an explainable machine learning-based surrogate modeling approach to efficiently solve inverse seismic design problems, optimizing structural properties for minimal seismic loss.

Contribution

It develops a novel methodology integrating explainable ML models with genetic algorithms to directly derive optimal design parameters for seismic performance-based design.

Findings

High surrogate model accuracy (R2 > 90%) across diverse building types.

Effective optimization of structural properties for seismic loss reduction.

Method successfully applied to steel and concrete frames in different cities.

Abstract

This study presents a methodology to treat performance-based seismic design as an inverse engineering problem, where design parameters are directly derived to achieve specific performance objectives. By implementing explainable machine learning models, this methodology directly maps design variables and performance metrics, tackling computational inefficiencies of performance-based design. The resultant machine learning 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., R2> 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.