Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings

This paper aims to investigate the feasibility of machine learning methods for the vulnerability assessment of buildings and structures. Traditionally, the seismic performance of buildings and structures is determined through a non-linear time–history analysis, which is an accurate but time-consumin...

Full description

Saved in:
Bibliographic Details
Main Author: Sung Hei Luk
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/14/2395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849734026838933504
author Sung Hei Luk
author_facet Sung Hei Luk
author_sort Sung Hei Luk
collection DOAJ
description This paper aims to investigate the feasibility of machine learning methods for the vulnerability assessment of buildings and structures. Traditionally, the seismic performance of buildings and structures is determined through a non-linear time–history analysis, which is an accurate but time-consuming process. As an alternative, structural responses of buildings under earthquakes can be obtained using well-trained machine learning models. In the current study, machine learning models for the damage classification of RC buildings are developed using the datasets generated from numerous incremental dynamic analyses. A variety of earthquake and structural parameters are considered as input parameters, while damage levels based on the maximum inter-story drift ratio are selected as the output. The performance and effectiveness of several machine learning algorithms, including ensemble methods and artificial neural networks, are investigated. The importance of different input parameters is studied. The results reveal that well-prepared machine learning models are also capable of predicting damage levels with an adequate level of accuracy and minimal computational effort. In this study, the XGBoost method generally outperforms the other algorithms, with the highest accuracy and generalizability. Simplified prediction models are also developed for preliminary estimation using the selected input parameters for practical usage.
format Article
id doaj-art-43342398767d44a6b87d67b9c4b63b2b
institution DOAJ
issn 2075-5309
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-43342398767d44a6b87d67b9c4b63b2b2025-08-20T03:07:54ZengMDPI AGBuildings2075-53092025-07-011514239510.3390/buildings15142395Machine Learning-Based Methods for the Seismic Damage Classification of RC BuildingsSung Hei Luk0Department of Construction, Environment and Engineering, Technological and Higher Education Institute of Hong Kong, Hong Kong, ChinaThis paper aims to investigate the feasibility of machine learning methods for the vulnerability assessment of buildings and structures. Traditionally, the seismic performance of buildings and structures is determined through a non-linear time–history analysis, which is an accurate but time-consuming process. As an alternative, structural responses of buildings under earthquakes can be obtained using well-trained machine learning models. In the current study, machine learning models for the damage classification of RC buildings are developed using the datasets generated from numerous incremental dynamic analyses. A variety of earthquake and structural parameters are considered as input parameters, while damage levels based on the maximum inter-story drift ratio are selected as the output. The performance and effectiveness of several machine learning algorithms, including ensemble methods and artificial neural networks, are investigated. The importance of different input parameters is studied. The results reveal that well-prepared machine learning models are also capable of predicting damage levels with an adequate level of accuracy and minimal computational effort. In this study, the XGBoost method generally outperforms the other algorithms, with the highest accuracy and generalizability. Simplified prediction models are also developed for preliminary estimation using the selected input parameters for practical usage.https://www.mdpi.com/2075-5309/15/14/2395structural assessmentmachine learningreinforced concreteearthquake engineering
spellingShingle Sung Hei Luk
Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
Buildings
structural assessment
machine learning
reinforced concrete
earthquake engineering
title Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
title_full Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
title_fullStr Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
title_full_unstemmed Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
title_short Machine Learning-Based Methods for the Seismic Damage Classification of RC Buildings
title_sort machine learning based methods for the seismic damage classification of rc buildings
topic structural assessment
machine learning
reinforced concrete
earthquake engineering
url https://www.mdpi.com/2075-5309/15/14/2395
work_keys_str_mv AT sungheiluk machinelearningbasedmethodsfortheseismicdamageclassificationofrcbuildings