Do all roads lead to Rome? A comparison of knowledge-based, data-driven, and physics-based surrogate models for performance-based early design

•The relative capabilities knowledge-based, machine learning-based, and mechanistic surrogate models are compared to estimate the life-cycle seismic loss of concrete frame buildings based on their geometry and design parameters.•Two scenarios of incomplete (early design) and complete (design develop...

Full description

Saved in:
Bibliographic Details
Published in:Engineering structures Vol. 286; p. 116098
Main Authors: Zaker Esteghamati, Mohsen, Flint, Madeleine M.
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.07.2023
Subjects:
Data-driven models
Early design
Knowledge-based models
Performance-based earthquake engineering
Physics-based models
Surrogate modeling
Early design
Performance-based earthquake engineering
Physics-based models
Data-driven models
Surrogate modeling
Knowledge-based models
ISSN:0141-0296, 1873-7323
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•The relative capabilities knowledge-based, machine learning-based, and mechanistic surrogate models are compared to estimate the life-cycle seismic loss of concrete frame buildings based on their geometry and design parameters.•Two scenarios of incomplete (early design) and complete (design development) design information are considered to evaluate the impact of design data availability on surrogate models’ prediction.•A sequential framework is proposed to implement surrogate models with lower fidelity in earlier stages of design exploration, where each prior model guide parametrization of the posterior model.•Data-driven models are a versatile tool to demarcate seismic loss under incomplete design data. Mechanistic surrogate models can better extract the relationship between design parameters and seismic loss as the scale of analysis shrinks. A performance-based early design must assess the life cycle performance of a sizable design space at low computational cost and limited data. This paper evaluates the relative capabilities of three surrogate modeling approaches to estimate seismic loss under complete and incomplete design information scenarios. Three surrogate models of knowledge-based (i.e., from prior published assessments), data-driven (i.e., support vector machine trained on a simulation-based building inventory), and physics-based (i.e., equivalent single-degree-of-freedom systems) are systematically used to estimate bounds on direct seismic loss for four hypothetical concrete office construction projects in Charleston, South Carolina. Subsequently, a framework is presented that implements these surrogate models as a sequence to explore design alternatives consistent with divergence-convergence cycles of early design exploration. The results show that all different surrogate models provide reasonable accuracy for the complete design information case, whereas data-driven models provided higher accuracy than the other models. For incomplete design information, the data-driven models demarcated the performance space and estimated the same median loss values as detailed loss analysis. In contrast, physics-based surrogate models were more accurate in capturing the relationship between loss and design parameters for smaller sets of design alternatives. Nevertheless, all different surrogate modeling techniques were inadequate to capture loss variability between different designs of the same geometry.
ISSN:0141-0296
1873-7323
DOI:10.1016/j.engstruct.2023.116098