Machine Learning-Based Seismic Damage Assessment Of Residential Buildings Considering Multiple Earthquake And Structure Uncertainties - Paper abstract

Aug 4, 2026

Wood-frame structures are used in almost 90% of residential buildings in the United States, making rapid and accurate seismic damage assessment essential. This research develops a machine-learning seismic classifier for 6,113 wood-frame buildings near the New Madrid Seismic Zone, using synthesized ground motions to represent potential earthquakes. A multilayer perceptron model is compared with existing fragility curves for the same building portfolio. Results show comparable performance for minor damage, while the MLP classifier outperforms fragility curves for moderate and severe damage, offering faster portfolio-scale prediction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Introduction

Missouri University of Science and Technology Scholars' Mine | Civil, Architectural and Environmental
Engineering Faculty Research & Creative Works | Civil, Architectural and Environmental Engineering | | --- | --- | | 01 Aug 2023
Machine Learning-Based Seismic Damage Assessment Of Residential Buildings Considering Multiple Earthquake And Structure Uncertainties
Xinzhe Yuan
Liujun Li
Missouri University of Science and Technology, [llpwc@mst.edu](llpwc@mst.edu)[ ](llpwc@mst.edu)Haibin Zhang
Yanping Zhu
[et. al. For a complete list of authors](et. al. For a complete list of authors), see [https://](https://)scholarsmine. mst. edu/civarc_ enveng_facwork/2517
Follow this and additional works at: [https://scholarsmine.mst.edu/civarc_enveng_facwork](https://scholarsmine.mst.edu/civarc_enveng_facwork)
Part of the Architectural Engineering Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, and the Structural Engineering Commons | | Recommended Citation X. Yuan et al., "Machine Learning-Based Seismic Damage Assessment Of Residential Buildings Considering Multiple Earthquake And Structure Uncertainties," Natural Hazards Review, vol. 24, no. 3, article no. 04023024, American Society of Civil Engineers, Aug 2023. The definitive version is available at [https://doi.org/10.1061/NHREFO.NHENG-1681](https://doi.org/10.1061/NHREFO.NHENG-1681) [This Article-Journal is brought to you for free and open access by Scholars](This Article-Journal is brought to you for free and open access by Scholars)' Mine. It has been accepted for inclusion in Civil, Architectural and Environmental Engineering Faculty Research & Creative Works by an authorized administrator of Scholars' Mine. This work is protected by U. S. Copyright Law. Unauthorized use including reproduction for redistribution requires the permission of the copyright holder. For more information, please contact [scholarsmine@mst.edu](scholarsmine@mst.edu). Downloaded on 06/06/23from ascelibrary .org by Missouri University of Science and Technology . Copyright ASCE . For personal use only; all rights reserved . Machine Learning-Based Seismic Damage Assessment of Residential Buildings Considering Multiple Earthquake and Structure Uncertainties Xinzhe Yuan, Ph. D.1 ; Liujun Li, Ph. D.2 ; Haibin Zhang, Ph. D.3 ; Yanping Zhu, Ph. D.4 ; Genda Chen, Ph. D. , P. E. , F.ASCE 5 ; and Cihan Dagli, Ph. D.6 Abstract: Wood-frame structures are used in almost 90% of residential buildings in the United States. It is thus imperative to rapidly and accurately assess the damage of wood-frame structures in the wake of an earthquake event. This study aims to develop a machine-learningbased seismic classifier for a portfolio of 6,113 wood-frame structures near the New Madrid Seismic Zone (NMSZ) in which synthesized ground motions are adopted to characterize potential earthquakes. This seismic classifier, based on a multilayer perceptron (MLP), is compared with existing fragility curves developed for the same wood-frame buildings near the NMSZ. This comparative study indicates that the MLP seismic classifier and fragility curves perform equally well when predicting minor damage. However, the MLP classifier is more accurate than the fragility curves in prediction of moderate and severe damage. Compared with the existing fragility curves with earthquake intensity measures as inputs, machine-learning-based seismic classifiers can incorporate multiple parameters of earthquakes and structures as input features, thus providing a promising tool for accurate seismic damage assessment in a portfolio scale. Once trained, the MLPclassifier can predict damage classes of the 6,113 structures within 0.07 s on a general-purpose computer. DOI: 10.1061/NHREFO. NHENG-1681. © 2023 American Society of Civil Engineers. Introduction Approximately 90% of the US residential buildings are constructed with lightweight wood-frame structures. These residenti

FAQs

What is the main objective of the study?

To develop a machine-learning-based seismic classifier that rapidly and accurately assesses damage for a large portfolio of wood-frame residential buildings.

What modeling approach is used in the proposed classifier?

A multilayer perceptron (MLP) is trained to predict seismic damage classes using synthesized ground motions and input features describing earthquakes and structures.

How does the MLP classifier perform compared with existing fragility curves?

The MLP and fragility curves perform equally well for predicting minor damage, but the MLP is more accurate for moderate and severe damage.

Aug 4, 2026

Upload by Emma Wilson