Onur Coskun, Rafet Aktepe, Alper Aldemir, Ali Erhan Yilmaz, Murat Durmaz, Burcu Guldur Erkal, Engin Tunali
{"title":"利用机器学习确定砌体建筑群的地震风险优先次序","authors":"Onur Coskun, Rafet Aktepe, Alper Aldemir, Ali Erhan Yilmaz, Murat Durmaz, Burcu Guldur Erkal, Engin Tunali","doi":"10.1002/eqe.4227","DOIUrl":null,"url":null,"abstract":"<p>The seismic risk mitigation plans are vital since vulnerable structures are prone to partial or total collapse under the effect of future major earthquake events. Therefore, vulnerable structures in large building stocks should be determined using robust and accurate methods to prevent loss of lives and property. In the current state-of-the-art, the risk states (i.e., whether risky or not) of structures completely depend on the experience of the reconnaissance team of engineers, which could not result in standardized decisions. In this study, machine learning has been integrated into the decision-making algorithm to classify more precise and reliable seismic risk states of masonry buildings, categorizing them into up to four risk categories. For this purpose, a large database, including 12 features and detailed seismic risk analysis results of 4356 masonry buildings, is formed. Firstly, the input variables are preprocessed using feature engineering methods. Then, several machine learning algorithms are utilized to produce a network to estimate the risk state of masonry buildings in association with the risk states obtained from the detailed analysis results. As a result of the analysis of these algorithms, the correct prediction percentages for the testing database of the proposed method for two, three, and four risk states classification are predicted as approximately 87.5%, 86.6%, and 79.0%, respectively. This new approach makes it possible to produce risk color maps of large building stocks and reduce the number of buildings that require immediate action.</p>","PeriodicalId":11390,"journal":{"name":"Earthquake Engineering & Structural Dynamics","volume":"53 14","pages":"4432-4450"},"PeriodicalIF":4.3000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eqe.4227","citationCount":"0","resultStr":"{\"title\":\"Seismic risk prioritization of masonry building stocks using machine learning\",\"authors\":\"Onur Coskun, Rafet Aktepe, Alper Aldemir, Ali Erhan Yilmaz, Murat Durmaz, Burcu Guldur Erkal, Engin Tunali\",\"doi\":\"10.1002/eqe.4227\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>The seismic risk mitigation plans are vital since vulnerable structures are prone to partial or total collapse under the effect of future major earthquake events. Therefore, vulnerable structures in large building stocks should be determined using robust and accurate methods to prevent loss of lives and property. In the current state-of-the-art, the risk states (i.e., whether risky or not) of structures completely depend on the experience of the reconnaissance team of engineers, which could not result in standardized decisions. In this study, machine learning has been integrated into the decision-making algorithm to classify more precise and reliable seismic risk states of masonry buildings, categorizing them into up to four risk categories. For this purpose, a large database, including 12 features and detailed seismic risk analysis results of 4356 masonry buildings, is formed. Firstly, the input variables are preprocessed using feature engineering methods. Then, several machine learning algorithms are utilized to produce a network to estimate the risk state of masonry buildings in association with the risk states obtained from the detailed analysis results. As a result of the analysis of these algorithms, the correct prediction percentages for the testing database of the proposed method for two, three, and four risk states classification are predicted as approximately 87.5%, 86.6%, and 79.0%, respectively. This new approach makes it possible to produce risk color maps of large building stocks and reduce the number of buildings that require immediate action.</p>\",\"PeriodicalId\":11390,\"journal\":{\"name\":\"Earthquake Engineering & Structural Dynamics\",\"volume\":\"53 14\",\"pages\":\"4432-4450\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eqe.4227\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Earthquake Engineering & Structural Dynamics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/eqe.4227\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Earthquake Engineering & Structural Dynamics","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/eqe.4227","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
Seismic risk prioritization of masonry building stocks using machine learning
The seismic risk mitigation plans are vital since vulnerable structures are prone to partial or total collapse under the effect of future major earthquake events. Therefore, vulnerable structures in large building stocks should be determined using robust and accurate methods to prevent loss of lives and property. In the current state-of-the-art, the risk states (i.e., whether risky or not) of structures completely depend on the experience of the reconnaissance team of engineers, which could not result in standardized decisions. In this study, machine learning has been integrated into the decision-making algorithm to classify more precise and reliable seismic risk states of masonry buildings, categorizing them into up to four risk categories. For this purpose, a large database, including 12 features and detailed seismic risk analysis results of 4356 masonry buildings, is formed. Firstly, the input variables are preprocessed using feature engineering methods. Then, several machine learning algorithms are utilized to produce a network to estimate the risk state of masonry buildings in association with the risk states obtained from the detailed analysis results. As a result of the analysis of these algorithms, the correct prediction percentages for the testing database of the proposed method for two, three, and four risk states classification are predicted as approximately 87.5%, 86.6%, and 79.0%, respectively. This new approach makes it possible to produce risk color maps of large building stocks and reduce the number of buildings that require immediate action.
期刊介绍:
Earthquake Engineering and Structural Dynamics provides a forum for the publication of papers on several aspects of engineering related to earthquakes. The problems in this field, and their solutions, are international in character and require knowledge of several traditional disciplines; the Journal will reflect this. Papers that may be relevant but do not emphasize earthquake engineering and related structural dynamics are not suitable for the Journal. Relevant topics include the following:
ground motions for analysis and design
geotechnical earthquake engineering
probabilistic and deterministic methods of dynamic analysis
experimental behaviour of structures
seismic protective systems
system identification
risk assessment
seismic code requirements
methods for earthquake-resistant design and retrofit of structures.