Article(id=1241794072386539583, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1241794070289387562, articleNumber=null, orderNo=null, doi=10.13197/j.eeed.2025.0509, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1728403200000, receivedDateStr=2024-10-09, revisedDate=1730822400000, revisedDateStr=2024-11-06, acceptedDate=null, acceptedDateStr=null, onlineDate=1773996378274, onlineDateStr=2026-03-20, pubDate=1761062400000, pubDateStr=2025-10-22, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773996378274, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773996378274, creator=13701087609, updateTime=1773996378274, updator=13701087609, issue=Issue{id=1241794070289387562, tenantId=1146029695717560320, journalId=1241701559352995854, year='2025', volume='45', issue='5', pageStart='1', pageEnd='227', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1773996377775, creator=13701087609, updateTime=1773996935444, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241796409465307627, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1241794070289387562, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241796409465307628, tenantId=1146029695717560320, journalId=1241701559352995854, issueId=1241794070289387562, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=88, endPage=99, ext={EN=ArticleExt(id=1241794073120542804, articleId=1241794072386539583, tenantId=1146029695717560320, journalId=1241701559352995854, language=EN, title=Selection of ground motion parameters based on machine learning and damage data from the Great East Japan Earthquake, columnId=1241794071602200899, journalTitle=Earthquake Engineering and Engineering Dynamics, columnName=Research Paper, runingTitle=null, highlight=null, articleAbstract=

Ground motion parameters quantify the intensity of ground motion and their impact on building structures, making the selection of appropriate parameters crucial for pre-earthquake seismic design and post-earthquake damage assessment. Ground motion parameters and structural seismic responses are often statistically related through traditional correlation analysis and regression methods. However, data are mostly sourced from numerical simulations, which makes it difficult to capture the true nonlinear mapping relationship between the two. Therefore, this paper collected and organized nearly 1.28 million actual damage records from the Great East Japan Earthquake on March 11, 2011, and the complex mapping relationship between ground motion parameters and building damage levels was established based on four machine learning classification models, namely, XGBoost (eXtreme gradient boosting), RF(random forest), LightGBM (light gradient boosting machine), and CatBoost (categorical boosting). The SMOTE oversampling and Bayesian hyperparameter optimization algorithms were introduced to optimize the model, and the optimal combination of seven ground motion parameters was selected using two methods for evaluating feature importance. The results indicate that the XGBoost algorithm performs the best, with an overall accuracy of 71.39% on the test set. The optimal combination of ground motion parameters includs PGA, Td, VSI, PGD, PGV/PGA, PGV, and Sa. The amplitude, spectrum, and duration parameters of the ground motion show a strong correlation with post-earthquake building damage, while the cumulative energy parameters exhibit a weaker correlation. Finally, an earthquake loss prediction model based on the XGBoost algorithm was established using actual damage data from three earthquakes in New Zealand, validating the completeness, reliability, and regional generalization capability of the selected parameter combination. The research results can provide a theoretical basis and engineering reference for the seismic design of buildings and earthquake risk assessment.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Sui LI, Zifa WANG, Dengke ZHAO, Zhaodong WANG, Zhaoyan LI), CN=ArticleExt(id=1241794080024367432, articleId=1241794072386539583, tenantId=1146029695717560320, journalId=1241701559352995854, language=CN, title=基于机器学习和东日本大地震破坏数据的地震动参数筛选, columnId=1241786728458031995, journalTitle=地震工程与工程振动, columnName=研究论文, runingTitle=null, highlight=null, articleAbstract=

地震动参数量化了地面运动的强度及其对建筑结构的影响程度,选取合理的参数对震前抗震设计与震后震害评估具有重要意义。地震动参数和结构地震反应间的统计关系常通过传统的相关性分析和回归方法建立,且数据多来源于数值模拟,难以捕捉两者间真实的非线性映射关系。为此,该文收集整理了2011年3月11日东日本大地震后近128万条房屋实际震害数据,基于XGBoost(eXtreme cradient boosting)、随机森林(random forest, RF)、LightGBM(light gradient boosting machine)和CatBoost(categorical boosting)共4种机器学习分类模型建立地震动参数与建筑破坏等级之间的复杂映射关系。引入SMOTE过采样和贝叶斯超参数优化法对模型进行优化,结合2种重要性评价方法选出包含7个参数的最优地震动参数组合。结果表明:XGBoost算法表现最佳,在测试集上的整体准确率可以达到71.39%;最优地震动参数组合为峰值地面加速度(peak ground acceleration, PGA)、TdVSI、峰值地面位移(peak ground displacement, PGD)、峰值地面速度(peak ground velocity, PGV)、PGV/PGA、谱加速度Sa;地震动幅值、频谱及持时参数与震后建筑损失的相关性较强,而累积能量参数与其相关性较弱。最后,通过新西兰3次地震的实际震害数据建立基于XGBoost算法的地震损失预测模型,验证了所选参数组合的完备性、可靠性和地区泛化性能。研究成果能够为建筑抗震设计及地震风险评估等工作提供一定的理论依据和工程参考。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
王自法(1965—),男,研究员,博士,主要从事巨灾风险相关研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=GGvByREuuSYhf9brw4JFYQ==, magXml=jYTR0FyuHm9EfH0AAk4pog==, pdfUrl=null, pdf=dZb2bvebDUb+N0xiH6PCTw==, pdfFileSize=2821020, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=P36KVTfTRQPBdD5E+/zwEQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=r+Odrdpxnc4sOdGPScTUMQ==, mapNumber=null, authorCompany=null, fund=null, authors=

李遂(2001—),女,硕士研究生,主要从事地震动参数和损失间相关性研究。E-mail:

, authorsList=李遂, 王自法, 赵登科, 王昭栋, 李兆焱)}, authors=[Author(id=1241802937698160973, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ls1295950841@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241802937786241370, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802937698160973, language=EN, stringName=Sui LI, firstName=Sui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241802937903681894, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802937698160973, language=CN, stringName=李遂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.河南大学建筑工程学院,河南开封475004, bio={"content":"

李遂(2001—),女,硕士研究生,主要从事地震动参数和损失间相关性研究。E-mail:

"}, bioImg=null, bioContent=

李遂(2001—),女,硕士研究生,主要从事地震动参数和损失间相关性研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241802937261953303, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=1., ext=[AuthorCompanyExt(id=1241802937282924830, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China), AuthorCompanyExt(id=1241802937291313437, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河南大学建筑工程学院,河南开封475004)])]), Author(id=1241802938029511026, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zifa@iem.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241802939585597831, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802938029511026, language=EN, stringName=Zifa WANG, firstName=Zifa, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, 1, address=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241802939724009873, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802938029511026, language=CN, stringName=王自法, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, 1, address=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080
1.河南大学建筑工程学院,河南开封475004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241802937396171050, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=2., ext=[AuthorCompanyExt(id=1241802937400365354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China), AuthorCompanyExt(id=1241802937408753963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937534583095, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=3., ext=[AuthorCompanyExt(id=1241802937547166010, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China), AuthorCompanyExt(id=1241802937576526139, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937261953303, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=1., ext=[AuthorCompanyExt(id=1241802937282924830, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China), AuthorCompanyExt(id=1241802937291313437, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河南大学建筑工程学院,河南开封475004)])]), Author(id=1241802939849839008, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241802940034388403, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802939849839008, language=EN, stringName=Dengke ZHAO, firstName=Dengke, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241802940181189057, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802939849839008, language=CN, stringName=赵登科, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241802937396171050, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=2., ext=[AuthorCompanyExt(id=1241802937400365354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China), AuthorCompanyExt(id=1241802937408753963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937534583095, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=3., ext=[AuthorCompanyExt(id=1241802937547166010, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China), AuthorCompanyExt(id=1241802937576526139, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080)])]), Author(id=1241802940449624529, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241802940579647970, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802940449624529, language=EN, stringName=Zhaodong WANG, firstName=Zhaodong, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241802940734837234, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802940449624529, language=CN, stringName=王昭栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241802937396171050, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=2., ext=[AuthorCompanyExt(id=1241802937400365354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China), AuthorCompanyExt(id=1241802937408753963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937534583095, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=3., ext=[AuthorCompanyExt(id=1241802937547166010, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China), AuthorCompanyExt(id=1241802937576526139, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080)])]), Author(id=1241802940860666369, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241802940994884116, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802940860666369, language=EN, stringName=Zhaoyan LI, firstName=Zhaoyan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241802941095547425, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, authorId=1241802940860666369, language=CN, stringName=李兆焱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241802937396171050, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=2., ext=[AuthorCompanyExt(id=1241802937400365354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China), AuthorCompanyExt(id=1241802937408753963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937534583095, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=3., ext=[AuthorCompanyExt(id=1241802937547166010, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China), AuthorCompanyExt(id=1241802937576526139, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080)])])], keywords=[Keyword(id=1241802941334622792, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, orderNo=1, keyword=earthquake loss data), Keyword(id=1241802941452063320, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1241802941556920931, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, orderNo=3, keyword=building damage level), Keyword(id=1241802941682750062, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, orderNo=4, keyword=optimal ground motion parameter combination), Keyword(id=1241802941779219065, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, orderNo=5, keyword=feature importance), Keyword(id=1241802941967962761, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, orderNo=1, keyword=地震损失数据), Keyword(id=1241802942068626067, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1241802942173483674, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, orderNo=3, keyword=建筑破坏等级), Keyword(id=1241802942278341289, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, orderNo=4, keyword=最优地震动参数组合), Keyword(id=1241802942404170423, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, orderNo=5, keyword=特征重要性)], refs=[Reference(id=1241802949899391124, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=24, pageEnd=28, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=BURATTI N, journalName=null, refType=null, unstructuredReference=BURATTI N. A comparison of the performances of various ground-motion intensity measures[C]∥Proceedings of the 15th World Conference on Earthquake Engineering, Lisbon, Portugal: Sociedade Portuguesa de Engenharia Sismica, 2012: 24-28., articleTitle=A comparison of the performances of various ground-motion intensity measures, refAbstract=null), Reference(id=1241802950012637341, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2024, volume=56, issue=1, pageStart=54, pageEnd=62, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=刘巴黎, 胡进军, 谢礼立, journalName=哈尔滨工业大学学报, refType=null, unstructuredReference=刘巴黎,胡进军,谢礼立.基于弹性网络回归的地震动参数排序与比选[J].哈尔滨工业大学学报, 2024, 56(1): 54-62., articleTitle=基于弹性网络回归的地震动参数排序与比选, refAbstract=null), Reference(id=1241802950134272171, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2024, volume=56, issue=1, pageStart=54, pageEnd=62, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=LIU Bali, HU Jinjun, XIE Lili, journalName=Journal of Harbin Institute of Technology, refType=null, unstructuredReference=LIU Bali, HU Jinjun, XIE Lili. Ranking and comparison of ground motion parameters based on elastic net regression[J]. Journal of Harbin Institute of Technology, 2024, 56(1): 54-62. (in Chinese), articleTitle=Ranking and comparison of ground motion parameters based on elastic net regression, refAbstract=null), Reference(id=1241802950272684215, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=11, pageStart=216, pageEnd=225, 235, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=吴梓楠, 韩小雷, 马建峰, journalName=建筑结构学报, refType=null, unstructuredReference=吴梓楠,韩小雷,马建峰,.基于机器学习的地震动强度指标敏感性分析与破坏势评估[J].建筑结构学报, 2023, 44(11): 216-225, 235., articleTitle=基于机器学习的地震动强度指标敏感性分析与破坏势评估, refAbstract=null), Reference(id=1241802950394319041, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=11, pageStart=216, pageEnd=225, 235, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=WU Zinan, HAN Xiaolei, MA Jianfeng, journalName=Journal of Building Structures, refType=null, unstructuredReference=WU Zinan, HAN Xiaolei, MA Jianfeng, et al. Sensitivity analysis of ground motion intensity measures and evaluation of potential damage based on machine learning[J]. Journal of Building Structures, 2023, 44(11): 216-225, 235. (in Chinese), articleTitle=Sensitivity analysis of ground motion intensity measures and evaluation of potential damage based on machine learning, refAbstract=null), Reference(id=1241802950528536783, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2007, volume=39, issue=4, pageStart=505, pageEnd=509, 560, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=李爽, 谢礼立, 郝敏, journalName=哈尔滨工业大学学报, refType=null, unstructuredReference=李爽,谢礼立,郝敏.地震动参数及结构整体破坏相关性研究[J].哈尔滨工业大学学报, 2007, 39(4): 505-509, 560., articleTitle=地震动参数及结构整体破坏相关性研究, refAbstract=null), Reference(id=1241802950650171613, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2007, volume=39, issue=4, pageStart=505, pageEnd=509, 560, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=LI Shuang, XIE Lili, HAO Min, journalName=Journal of Harbin Institute of Technology, refType=null, unstructuredReference=LI Shuang, XIE Lili, HAO Min. Correlation between seismic ground motion parameters and their relationship with overall damage to structure[J]. Journal of Harbin Institute of Technology, 2007, 39(4): 505-509, 560. (in Chinese), articleTitle=Correlation between seismic ground motion parameters and their relationship with overall damage to structure, refAbstract=null), Reference(id=1241802950796972260, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2020, volume=132, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=PINZóN L A, VARGAS-ALZATE Y F, PUJADES L G, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=PINZóN L A, VARGAS-ALZATE Y F, PUJADES L G, et al. A drift-correlated ground motion intensity measure: Application to steel frame buildings[J]. Soil Dynamics and Earthquake Engineering, 2020, 132: 106096., articleTitle=A drift-correlated ground motion intensity measure: Application to steel frame buildings, refAbstract=null), Reference(id=1241802950906024173, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2015, volume=82, issue=null, pageStart=151, pageEnd=167, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=KOSTINAKIS K, ATHANATOPOULOU A, MORFIDIS K, journalName=Engineering Structures, refType=null, unstructuredReference=KOSTINAKIS K, ATHANATOPOULOU A, MORFIDIS K. Correlation between ground motion intensity measures and seismic damage of 3D R/C buildings[J]. Engineering Structures, 2015, 82: 151-167., articleTitle=Correlation between ground motion intensity measures and seismic damage of 3D R/C buildings, refAbstract=null), Reference(id=1241802951019270394, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=4, pageStart=9, pageEnd=22, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=叶列平, 马千里, 缪志伟, journalName=地震工程与工程振动, refType=null, unstructuredReference=叶列平,马千里,缪志伟.结构抗震分析用地震动强度指标的研究[J].地震工程与工程振动, 2009, 29(4): 9-22., articleTitle=结构抗震分析用地震动强度指标的研究, refAbstract=null), Reference(id=1241802951149293831, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=4, pageStart=9, pageEnd=22, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=YE Lieping, MA Qianli, MIAO Zhiwei, journalName=Journal of Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=YE Lieping, MA Qianli, MIAO Zhiwei. Study on earthquake intensities for seismic analysis of structures[J]. Journal of Earthquake Engineering and Engineering Dynamics, 2009, 29(4): 9-22. (in Chinese), articleTitle=Study on earthquake intensities for seismic analysis of structures, refAbstract=null), Reference(id=1241802951266734356, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=3, pageStart=105, pageEnd=112, 144, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=陈健云, 李静, 韩进财, journalName=振动与冲击, refType=null, unstructuredReference=陈健云,李静,韩进财,.地震动强度指标与框架结构响应的相关性研究[J].振动与冲击, 2017, 36(3): 105-112, 144., articleTitle=地震动强度指标与框架结构响应的相关性研究, refAbstract=null), Reference(id=1241802951417729317, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=3, pageStart=105, pageEnd=112, 144, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=CHEN Jianyun, LI Jing, HAN Jincai, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=CHEN Jianyun, LI Jing, HAN Jincai, et al. Correlation between ground motionintensity indexes and seismic responses of frame structures[J]. Journal of Vibration and Shock, 2017, 36(3): 105-112, 144. (in Chinese), articleTitle=Correlation between ground motionintensity indexes and seismic responses of frame structures, refAbstract=null), Reference(id=1241802951547752754, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2020, volume=24, issue=11, pageStart=1747, pageEnd=1770, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=LIU T T, YU X H, LU D G, journalName=Journal of Earthquake Engineering, refType=null, unstructuredReference=LIU T T, YU X H, LU D G. An approach to develop compound intensity measures for prediction of damage potential of earthquake records using canonical correlation analysis[J]. Journal of Earthquake Engineering, 2020, 24(11): 1747-1770., articleTitle=An approach to develop compound intensity measures for prediction of damage potential of earthquake records using canonical correlation analysis, refAbstract=null), Reference(id=1241802952642466107, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=15, issue=7, pageStart=3083, pageEnd=3101, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=OZMEN H B, journalName=Bulletin of Earthquake Engineering, refType=null, unstructuredReference=OZMEN H B. Developing hybrid parameters for measuring damage potential of earthquake records: Case for RC building stock[J]. Bulletin of Earthquake Engineering, 2017, 15(7): 3083-3101., articleTitle=Developing hybrid parameters for measuring damage potential of earthquake records: Case for RC building stock, refAbstract=null), Reference(id=1241802952751518029, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2013, volume=11, issue=2, pageStart=365, pageEnd=384, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=GEHL P, SEYEDI D M, DOUGLAS J, journalName=Bulletin of Earthquake Engineering, refType=null, unstructuredReference=GEHL P, SEYEDI D M, DOUGLAS J. Vector-valued fragility functions for seismic risk evaluation[J]. Bulletin of Earthquake Engineering, 2013, 11(2): 365-384., articleTitle=Vector-valued fragility functions for seismic risk evaluation, refAbstract=null), Reference(id=1241802952847987032, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=10, pageStart=140, pageEnd=151, 172, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=胡进军, 刘巴黎, 谢礼立, journalName=工程力学, refType=null, unstructuredReference=胡进军,刘巴黎,谢礼立.基于因子分析的地震动特征提取及潜在破坏势评估[J].工程力学, 2022, 39(10): 140-151, 172., articleTitle=基于因子分析的地震动特征提取及潜在破坏势评估, refAbstract=null), Reference(id=1241802953019953510, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=10, pageStart=140, pageEnd=151, 172, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=HU Jinjun, LIU Bali, XIE Lili, journalName=Engineering Mechanics, refType=null, unstructuredReference=HU Jinjun, LIU Bali, XIE Lili. Factor analysis-based ground motion feature extraction and the measurement of the potential structural damage[J]. Engineering Mechanics, 2022, 39(10): 140-151, 172. (in Chinese), articleTitle=Factor analysis-based ground motion feature extraction and the measurement of the potential structural damage, refAbstract=null), Reference(id=1241802953149976943, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2007, volume=23, issue=2, pageStart=357, pageEnd=392, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=LUCO N, CORNELL C A, journalName=Earthquake Spectra, refType=null, unstructuredReference=LUCO N, CORNELL C A. Structure-specific scalar intensity measures for near-source and ordinary earthquake ground motions[J]. Earthquake Spectra, 2007, 23(2): 357-392., articleTitle=Structure-specific scalar intensity measures for near-source and ordinary earthquake ground motions, refAbstract=null), Reference(id=1241802953271611769, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2018, volume=35, issue=8, pageStart=122, pageEnd=129, 137, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=刘亭亭, 于晓辉, 吕大刚, journalName=工程力学, refType=null, unstructuredReference=刘亭亭,于晓辉,吕大刚.地震动多元强度参数主成分与结构损伤的相关性分析[J].工程力学, 2018, 35(8): 122-129, 137., articleTitle=地震动多元强度参数主成分与结构损伤的相关性分析, refAbstract=null), Reference(id=1241802953405829512, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2018, volume=35, issue=8, pageStart=122, pageEnd=129, 137, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=LIU Tingting, YU Xiaohui, LV Dagang, journalName=Engineering Mechanics, refType=null, unstructuredReference=LIU Tingting, YU Xiaohui, LV Dagang. Analysis of correlation between principal components of multivariate earthquake intensity measures and structural damage[J]. Engineering Mechanics, 2018, 35(8): 122-129, 137. (in Chinese), articleTitle=Analysis of correlation between principal components of multivariate earthquake intensity measures and structural damage, refAbstract=null), Reference(id=1241802953527464341, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2019, volume=125, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=LIU T T, LU D G, YU X H, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=LIU T T, LU D G, YU X H. Development of a compound intensity measure using partial least-squares regression and its statistical evaluation based on probabilistic seismic demand analysis[J]. Soil Dynamics and Earthquake Engineering, 2019, 125: 105725., articleTitle=Development of a compound intensity measure using partial least-squares regression and its statistical evaluation based on probabilistic seismic demand analysis, refAbstract=null), Reference(id=1241802953640710556, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2019, volume=52, issue=1, pageStart=27, pageEnd=36, 107, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=刘亭亭, 于晓辉, 吕大刚, journalName=土木工程学报, refType=null, unstructuredReference=刘亭亭,于晓辉,吕大刚.RC框架基于典型相关分析的地震动多元破坏势评估[J].土木工程学报, 2019, 52(1): 27-36, 107., articleTitle=RC框架基于典型相关分析的地震动多元破坏势评估, refAbstract=null), Reference(id=1241802953720402340, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2019, volume=52, issue=1, pageStart=27, pageEnd=36, 107, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=LIU Tingting, YU Xiaohui, LU Dagang, journalName=China Civil Engineering Journal, refType=null, unstructuredReference=LIU Tingting, YU Xiaohui, LU Dagang. Multivariate damage potential estimation of earthquake ground motions for RC frames based on canonical correlation analysis[J]. China Civil Engineering Journal, 2019, 52(1): 27-36, 107. (in Chinese), articleTitle=Multivariate damage potential estimation of earthquake ground motions for RC frames based on canonical correlation analysis, refAbstract=null), Reference(id=1241802953829454256, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=8, pageStart=4259, pageEnd=4279, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=XU Y J, LU X Z, TIAN Y, journalName=Journal of Earthquake Engineering, refType=null, unstructuredReference=XU Y J, LU X Z, TIAN Y, et al. Real-time seismic damage prediction and comparison of various ground motion intensity measures based on machine learning[J]. Journal of Earthquake Engineering, 2022, 26(8): 4259-4279., articleTitle=Real-time seismic damage prediction and comparison of various ground motion intensity measures based on machine learning, refAbstract=null), Reference(id=1241802953896563129, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2022, volume=152, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=YAN Y X, XIA Y, YANG J P, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=YAN Y X, XIA Y, YANG J P, et al. Optimal selection of scalar and vector-valued seismic intensity measures based on Gaussian Process Regression[J]. Soil Dynamics and Earthquake Engineering, 2022, 152: 106961., articleTitle=Optimal selection of scalar and vector-valued seismic intensity measures based on Gaussian Process Regression, refAbstract=null), Reference(id=1241802954072723913, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2024, volume=177, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=DANG H T, WANG Z F, ZHAO D K, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=DANG H T, WANG Z F, ZHAO D K, et al. Ground motion prediction model for shallow crustal earthquakes in Japan based on XGBoost with Bayesian optimization[J]. Soil Dynamics and Earthquake Engineering, 2024, 177: 108391., articleTitle=Ground motion prediction model for shallow crustal earthquakes in Japan based on XGBoost with Bayesian optimization, refAbstract=null), Reference(id=1241802954194358741, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=3, pageStart=428, pageEnd=439, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=ZHAO D K, WANG Z F, WANG J M, journalName=International Journal of Disaster Risk Science, refType=null, unstructuredReference=ZHAO D K, WANG Z F, WANG J M, et al. A rapid estimation method for post-earthquake building losses[J]. International Journal of Disaster Risk Science, 2023, 14(3): 428-439., articleTitle=A rapid estimation method for post-earthquake building losses, refAbstract=null), Reference(id=1241802954311799264, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2019, volume=118, issue=null, pageStart=98, pageEnd=110, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=PODILI B, RAGHUKANTH S T G, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=PODILI B, RAGHUKANTH S T G. Ground motion prediction equations for higher order parameters[J]. Soil Dynamics and Earthquake Engineering, 2019, 118: 98-110., articleTitle=Ground motion prediction equations for higher order parameters, refAbstract=null), Reference(id=1241802954404073963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2008, volume=28, issue=3, pageStart=198, pageEnd=211, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=MORASCA P, ZOLEZZI F, SPALLAROSSA D, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=MORASCA P, ZOLEZZI F, SPALLAROSSA D, et al. Ground motion models for the Molise Region (southern Italy)[J]. Soil Dynamics and Earthquake Engineering, 2008, 28(3): 198-211., articleTitle=Ground motion models for the Molise Region (southern Italy), refAbstract=null), Reference(id=1241802954504737268, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2015, volume=13, issue=null, pageStart=1587, pageEnd=1612, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=CAUZZI C, FACCIOLI E, VANINI M, journalName=Bulletin of Earthquake Engineering, refType=null, unstructuredReference=CAUZZI C, FACCIOLI E, VANINI M, et al. Updated predictive equations for broadband (0.01~10 s) horizontal response spectra and peak ground motions, based on a global dataset of digital acceleration records[J]. Bulletin of Earthquake Engineering, 2015, 13: 1587-1612., articleTitle=Updated predictive equations for broadband (0.01~10 s) horizontal response spectra and peak ground motions, based on a global dataset of digital acceleration records, refAbstract=null), Reference(id=1241802954592817660, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=GUPTA A K, journalName=Response spectrum method in seismic analysis and design of structures, refType=null, unstructuredReference=GUPTA A K. Response spectrum method in seismic analysis and design of structures[M]. New York: Routledge, 2017., articleTitle=null, refAbstract=null), Reference(id=1241802954735424011, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2007, volume=97, issue=5, pageStart=1379, pageEnd=1395, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=WALD D J, ALLEN T I, journalName=Bulletin of the Seismological Society of America, refType=null, unstructuredReference=WALD D J, ALLEN T I. Topographic slope as a proxy for seismic site conditions and amplification[J]. Bulletin of the Seismological Society of America, 2007, 97(5): 1379-1395., articleTitle=Topographic slope as a proxy for seismic site conditions and amplification, refAbstract=null), Reference(id=1241802954873836053, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=1997, volume=13, issue=4, pageStart=605, pageEnd=621, url=null, language=null, rfNumber=[26], rfOrder=33, authorNames=MCCORMACK T C, RAD F N, journalName=Earthquake Spectra, refType=null, unstructuredReference=MCCORMACK T C, RAD F N. An earthquake loss estimation methodology for buildings based on ATC-13 and ATC-21[J]. Earthquake Spectra, 1997, 13(4): 605-621., articleTitle=An earthquake loss estimation methodology for buildings based on ATC-13 and ATC-21, refAbstract=null), Reference(id=1241802955020636707, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=785, pageEnd=794, url=null, language=null, rfNumber=[27], rfOrder=34, authorNames=CHEN T Q, GUESTRIN C, journalName=null, refType=null, unstructuredReference=CHEN T Q, GUESTRIN C. XGBoost: A scalable tree boosting system[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. New York: ACM, 2016: 785-794., articleTitle=XGBoost: A scalable tree boosting system, refAbstract=null), Reference(id=1241802955163243054, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=null, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=[28], rfOrder=35, authorNames=BREIMAN L, journalName=Machine Learning, refType=null, unstructuredReference=BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32., articleTitle=Random forests, refAbstract=null), Reference(id=1241802955322626621, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=3149, pageEnd=3157, url=null, language=null, rfNumber=[29], rfOrder=36, authorNames=KE G L, MENG Q, FINLEY T, journalName=null, refType=null, unstructuredReference=KE G L, MENG Q, FINLEY T, et al. LightGBM: A highly efficient gradient boosting decision tree[C]∥Proceedings of Advances in Neural Information Processing Systems. Long Beach, CA, USA: Neural Information Processing Systems Foundation, 2017: 3149-3157., articleTitle=LightGBM: A highly efficient gradient boosting decision tree, refAbstract=null), Reference(id=1241802955477815882, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=6639, pageEnd=6649, url=null, language=null, rfNumber=[30], rfOrder=37, authorNames=PROKHORENKOVA L, GUSEV G, VOROBEV A, journalName=null, refType=null, unstructuredReference=PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features[C]∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2018: 6639-6649., articleTitle=CatBoost: unbiased boosting with categorical features, refAbstract=null), Reference(id=1241802955599450704, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2011, volume=3, issue=1, pageStart=4, pageEnd=21, url=null, language=null, rfNumber=[31], rfOrder=38, authorNames=NGUYEN H M, COOPER E W, KAMEI K, journalName=International Journal of Knowledge Engineering and Soft Data Paradigms, refType=null, unstructuredReference=NGUYEN H M, COOPER E W, KAMEI K. Borderline over-sampling for imbalanced data classification[J]. International Journal of Knowledge Engineering and Soft Data Paradigms, 2011, 3(1): 4-21., articleTitle=Borderline over-sampling for imbalanced data classification, refAbstract=null), Reference(id=1241802955729474142, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2002, volume=16, issue=null, pageStart=321, pageEnd=357, url=null, language=null, rfNumber=[32], rfOrder=39, authorNames=CHAWLA N V, BOWYER K W, HALL L O, journalName=Journal of Artificial Intelligence Research, refType=null, unstructuredReference=CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: Synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357., articleTitle=SMOTE: Synthetic minority over-sampling technique, refAbstract=null), Reference(id=1241802955880469099, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=7, pageStart=5633, pageEnd=5644, url=null, language=null, rfNumber=[33], rfOrder=40, authorNames=SUN Y T, DING S F, ZHANG Z C, journalName=Soft Computing, refType=null, unstructuredReference=SUN Y T, DING S F, ZHANG Z C, et al. An improved grid search algorithm to optimize SVR for prediction[J]. Soft Computing, 2021, 25(7): 5633-5644., articleTitle=An improved grid search algorithm to optimize SVR for prediction, refAbstract=null), Reference(id=1241802955993715317, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2012, volume=13, issue=2, pageStart=281, pageEnd=305, url=null, language=null, rfNumber=[34], rfOrder=41, authorNames=BERGSTRA J, BENGIO Y, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=BERGSTRA J, BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13(2): 281-305., articleTitle=Random search for hyper-parameter optimization, refAbstract=null), Reference(id=1241802956253762177, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2012, volume=25, issue=null, pageStart=2951, pageEnd=2959, url=null, language=null, rfNumber=[35], rfOrder=42, authorNames=SNOEK J, LAROCHELLE H, ADAMS R P, journalName=null, refType=null, unstructuredReference=SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms[C]∥Proceedings of Advances in Neural Information Processing Systems. New York, USA: Curran Associates Inc, 2012, 25: 2951-2959., articleTitle=Practical bayesian optimization of machine learning algorithms, refAbstract=null), Reference(id=1241802956350231178, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2020, volume=36, issue=1, pageStart=183, pageEnd=208, url=null, language=null, rfNumber=[36], rfOrder=43, authorNames=MANGALATHU S, SUN H, NWEKE C C, journalName=Earthquake Spectra, refType=null, unstructuredReference=MANGALATHU S, SUN H, NWEKE C C, et al. Classifying earthquake damage to buildings using machine learning[J]. Earthquake Spectra, 2020, 36(1): 183-208., articleTitle=Classifying earthquake damage to buildings using machine learning, refAbstract=null), Reference(id=1241802956459283096, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2010, volume=26, issue=10, pageStart=1340, pageEnd=1347, url=null, language=null, rfNumber=[37], rfOrder=44, authorNames=ALTMANN A, TOLO I L, SANDER O, journalName=Bioinformatics, refType=null, unstructuredReference=ALTMANN A, TOLO I L, SANDER O, et al. Permutation importance: A corrected feature importance measure[J]. Bioinformatics, 2010, 26(10): 1340-1347., articleTitle=Permutation importance: A corrected feature importance measure, refAbstract=null), Reference(id=1241802956576723617, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2017, volume=30, issue=null, pageStart=4765, pageEnd=4774, url=null, language=null, rfNumber=[38], rfOrder=45, authorNames=LUNDBERG S M, LEE S-I, journalName=null, refType=null, unstructuredReference=LUNDBERG S M, LEE S-I. A unified approach to interpreting model predictions[C]∥Proceedings of Advances in Neural Information Processing Systems, New York, USA: Curran Associates Inc, 2017, 30: 4765-4774., articleTitle=A unified approach to interpreting model predictions, refAbstract=null), Reference(id=1241802956702552745, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=1990, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[39], rfOrder=46, authorNames=周锡元, 王广军, 苏经宇, journalName=场地·地基·设计地震, refType=null, unstructuredReference=周锡元,王广军,苏经宇.场地·地基·设计地震[M].北京:地震出版社, 1990., articleTitle=null, refAbstract=null), Reference(id=1241802956840964788, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=1990, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[39], rfOrder=47, authorNames=ZHOU Xiyuan, WANG Guangjun, SU Jingyu, journalName=Site·Foundation·Design earthquake, refType=null, unstructuredReference=ZHOU Xiyuan, WANG Guangjun, SU Jingyu. Site·Foundation·Design earthquake[M]. Beijing: Seismological Press, 1990. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1241802957004542661, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2006, volume=28, issue=4, pageStart=495, pageEnd=502, url=null, language=null, rfNumber=[40], rfOrder=48, authorNames=AMANAT K M, HOQUE E, journalName=Engineering Structures, refType=null, unstructuredReference=AMANAT K M, HOQUE E. A rationale for determining the natural period of RC building frames having infill[J]. Engineering Structures, 2006, 28(4): 495-502., articleTitle=A rationale for determining the natural period of RC building frames having infill, refAbstract=null), Reference(id=1241802957277172440, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=5, pageStart=186, pageEnd=195, url=null, language=null, rfNumber=[41], rfOrder=49, authorNames=刘渊, 王自法, 赵登科, journalName=地震工程与工程振动, refType=null, unstructuredReference=刘渊,王自法,赵登科.基于新西兰详细地震破坏数据的建筑物构件损失分析[J].地震工程与工程振动, 2021, 41(5): 186-195., articleTitle=基于新西兰详细地震破坏数据的建筑物构件损失分析, refAbstract=null), Reference(id=1241802957407195876, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=5, pageStart=186, pageEnd=195, url=null, language=null, rfNumber=[41], rfOrder=50, authorNames=LIU Yuan, WANG Zifa, ZHAO Dengke, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=LIU Yuan, WANG Zifa, ZHAO Dengke. Building component level loss analysis based on detailed earthquake loss data in New Zealand[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(5): 186-195. (in Chinese), articleTitle=Building component level loss analysis based on detailed earthquake loss data in New Zealand, refAbstract=null), Reference(id=1241802957524636397, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=84, pageEnd=95, url=null, language=null, rfNumber=[42], rfOrder=51, authorNames=赵登科, 王自法, 刘渊, journalName=地震工程与工程振动, refType=null, unstructuredReference=赵登科,王自法,刘渊,.基于新西兰实际震害资料的地震损失不确定性分析[J].地震工程与工程振动, 2021, 41(2): 84-95., articleTitle=基于新西兰实际震害资料的地震损失不确定性分析, refAbstract=null), Reference(id=1241802957625299699, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=2, pageStart=84, pageEnd=95, url=null, language=null, rfNumber=[42], rfOrder=52, authorNames=ZHAO Dengke, WANG Zifa, LIU Yuan, journalName=Earthquake Engineering and Engineering Dynamics, refType=null, unstructuredReference=ZHAO Dengke, WANG Zifa, LIU Yuan, et al. Earthquake loss uncertainty based on detailed loss data in New Zealand[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(2): 84-95. (in Chinese), articleTitle=Earthquake loss uncertainty based on detailed loss data in New Zealand, refAbstract=null)], funds=[Fund(id=1241802949358325848, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, awardId=52378544; 52378543, language=CN, fundingSource=国家自然科学基金面上项目(52378544; 52378543), fundOrder=null, country=null), Fund(id=1241802949488349282, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, awardId=2023YFC3805203, language=CN, fundingSource=国家重点研发计划项目(2023YFC3805203), fundOrder=null, country=null), Fund(id=1241802949660315766, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, awardId=2021B09; 2023A01, language=CN, fundingSource=中国地震局工程力学研究所基本科研业务费专项资助项目(2021B09; 2023A01), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241802937261953303, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=1., ext=[AuthorCompanyExt(id=1241802937282924830, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China), AuthorCompanyExt(id=1241802937291313437, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937261953303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河南大学建筑工程学院,河南开封475004)]), AuthorCompany(id=1241802937396171050, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=2., ext=[AuthorCompanyExt(id=1241802937400365354, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China), AuthorCompanyExt(id=1241802937408753963, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937396171050, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080)]), AuthorCompany(id=1241802937534583095, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, xref=3., ext=[AuthorCompanyExt(id=1241802937547166010, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China), AuthorCompanyExt(id=1241802937576526139, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, companyId=1241802937534583095, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080)])], figs=[ArticleFig(id=1241802944065114839, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 1, caption=Research technical roadmap, figureFileSmall=nVN9A167dElvJHHvrzPk2w==, figureFileBig=RMHeqz37lCxAMrXMch2SHg==, tableContent=null), ArticleFig(id=1241802944216109795, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图1, caption=研究技术路线图, figureFileSmall=nVN9A167dElvJHHvrzPk2w==, figureFileBig=RMHeqz37lCxAMrXMch2SHg==, tableContent=null), ArticleFig(id=1241802944379687669, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 2, caption=Confusion matrix of XGBoost model, figureFileSmall=fYIWbYjNTylH/EWldASO4A==, figureFileBig=0TR3KMvsxktanOBWrRiD7A==, tableContent=null), ArticleFig(id=1241802944501322493, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图2, caption=XGBoost模型混淆矩阵, figureFileSmall=fYIWbYjNTylH/EWldASO4A==, figureFileBig=0TR3KMvsxktanOBWrRiD7A==, tableContent=null), ArticleFig(id=1241802944622957319, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 3, caption=Weighted feature importance ranking, figureFileSmall=6WsWAgH7h7A/thUZaKxN9Q==, figureFileBig=PxcgmNlxPcIkkEOK3ySEKw==, tableContent=null), ArticleFig(id=1241802944740397843, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图3, caption=加权特征重要性排序, figureFileSmall=6WsWAgH7h7A/thUZaKxN9Q==, figureFileBig=PxcgmNlxPcIkkEOK3ySEKw==, tableContent=null), ArticleFig(id=1241802944845255453, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 4, caption=Curves of model accuracy changing with the number of features in feature set H, figureFileSmall=PDoxuRJ+zHg0BpQZ0JJRFQ==, figureFileBig=XANi2Sg9uG2HAVV8NDWWeg==, tableContent=null), ArticleFig(id=1241802944979473197, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图4, caption=模型精度随特征集合H中特征数量的变化曲线, figureFileSmall=PDoxuRJ+zHg0BpQZ0JJRFQ==, figureFileBig=XANi2Sg9uG2HAVV8NDWWeg==, tableContent=null), ArticleFig(id=1241802945105302329, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 5, caption=Weighted feature importance ranking in New Zealand, figureFileSmall=8Cd/0xgEN0uAoVst/5mbEA==, figureFileBig=gv62FmElH9Jp3hc/cLbYyQ==, tableContent=null), ArticleFig(id=1241802945205965636, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图5, caption=新西兰加权特征重要性排序, figureFileSmall=8Cd/0xgEN0uAoVst/5mbEA==, figureFileBig=gv62FmElH9Jp3hc/cLbYyQ==, tableContent=null), ArticleFig(id=1241802945348571986, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Fig. 6, caption=Curves of model accuracy changing with the number of IMs in set H2, figureFileSmall=Dq5av6Cm0BqcKNQOTOiv+g==, figureFileBig=B1bBLR9nANn22dmvP1UjKw==, tableContent=null), ArticleFig(id=1241802945470206818, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=图6, caption=模型精度随集合H2中IMs数量的变化曲线, figureFileSmall=Dq5av6Cm0BqcKNQOTOiv+g==, figureFileBig=B1bBLR9nANn22dmvP1UjKw==, tableContent=null), ArticleFig(id=1241802945596035955, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 1, caption=

Distribution of building damage levels according to ATC-13

, figureFileSmall=null, figureFileBig=null, tableContent=
建筑破坏未破坏轻微破坏中等破坏严重破坏毁坏总数量/条
等级标准 rD=0 rD∈(0,10%] rD∈(10%,30%] rD∈(30%,60%] rD∈(60%,100%]
样本数量88800815749017210031937293261278861
), ArticleFig(id=1241802945747030915, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表1, caption=

依据ATC-13划分的建筑破坏等级数据分布

, figureFileSmall=null, figureFileBig=null, tableContent=
建筑破坏未破坏轻微破坏中等破坏严重破坏毁坏总数量/条
等级标准 rD=0 rD∈(0,10%] rD∈(10%,30%] rD∈(30%,60%] rD∈(60%,100%]
样本数量88800815749017210031937293261278861
), ArticleFig(id=1241802945843499917, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 2, caption=

Feature explanation of the model

, figureFileSmall=null, figureFileBig=null, tableContent=
编号类别特征特征解释计算方式和来源
1地震信息峰值地面加速度PGA=max|at)|地震动空间插值方法
2峰值地面速度PGV=max|vt)|
3峰值地面位移PGD=max|dt)|
4谱加速度 Sa=SaT
5谱速度 Sv=SvT
6谱位移 Sd=SdT
7Arias强度
8特征强度
9重要持时 Td=t2-t1
10均方根加速度
11累积绝对速度
12加速度谱强度
13速度谱强度
14峰值比PGV/PGA
15震中距目标建筑到震中的地面距离Haversine公式
16建筑物信息建筑年代建筑物建造年代数据库
17外墙类型外墙材料类型
18结构类型建筑物结构类型
19柱子类型柱子材料类型
20屋顶类型屋顶材料类型
21用途分类建筑物使用用途
22层数建筑物层数
23场地信息 VS30地下30 m深度内的等效剪切波速USGS
), ArticleFig(id=1241802946250347431, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表2, caption=

模型的特征解释

, figureFileSmall=null, figureFileBig=null, tableContent=
编号类别特征特征解释计算方式和来源
1地震信息峰值地面加速度PGA=max|at)|地震动空间插值方法
2峰值地面速度PGV=max|vt)|
3峰值地面位移PGD=max|dt)|
4谱加速度 Sa=SaT
5谱速度 Sv=SvT
6谱位移 Sd=SdT
7Arias强度
8特征强度
9重要持时 Td=t2-t1
10均方根加速度
11累积绝对速度
12加速度谱强度
13速度谱强度
14峰值比PGV/PGA
15震中距目标建筑到震中的地面距离Haversine公式
16建筑物信息建筑年代建筑物建造年代数据库
17外墙类型外墙材料类型
18结构类型建筑物结构类型
19柱子类型柱子材料类型
20屋顶类型屋顶材料类型
21用途分类建筑物使用用途
22层数建筑物层数
23场地信息 VS30地下30 m深度内的等效剪切波速USGS
), ArticleFig(id=1241802946355205046, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 3, caption=

Optimal hyperparameters of four models based on Bayesian optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数名称最优取值模型超参数名称最优取值
XGBoostn_estimators624.000LightGBMn_estimators564.000
max_depth20.000max_depth11.000
gamma0.040reg_lambda5.210
reg_lambda27.536reg_alpha9.344
reg_alpha42.131learning_rate0.858
learning_rate0.546num_leaves50.000
Random Forestn_estimators898.000CatBoostdepth14.000
max_depth64.000iterations152.000
min_samples_split20.000learning_rate0.966
min_samples_leaf16.00012_leaf_reg47.502
), ArticleFig(id=1241802946460062658, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表3, caption=

基于贝叶斯优化后的4种模型最优超参数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数名称最优取值模型超参数名称最优取值
XGBoostn_estimators624.000LightGBMn_estimators564.000
max_depth20.000max_depth11.000
gamma0.040reg_lambda5.210
reg_lambda27.536reg_alpha9.344
reg_alpha42.131learning_rate0.858
learning_rate0.546num_leaves50.000
Random Forestn_estimators898.000CatBoostdepth14.000
max_depth64.000iterations152.000
min_samples_split20.000learning_rate0.966
min_samples_leaf16.00012_leaf_reg47.502
), ArticleFig(id=1241802946627834834, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 4, caption=

Evaluation index of model

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标计算公式评价标准
整体准确率 OA、R、P、F1∈[0,1]
指标数值越大,模型性能越好
召回率
精确率
F1值
), ArticleFig(id=1241802946841744365, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表4, caption=

模型评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标计算公式评价标准
整体准确率 OA、R、P、F1∈[0,1]
指标数值越大,模型性能越好
召回率
精确率
F1值
), ArticleFig(id=1241802946996933633, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 5, caption=

Comparison of model performance

, figureFileSmall=null, figureFileBig=null, tableContent=
模型召回率精确率F1值准确率模型召回率精确率F1值准确率
XGBoost0.6010.4980.5350.714LightGBM0.6070.4850.5230.697
RF0.6090.4930.5310.703CatBoost0.5990.4800.5170.695
), ArticleFig(id=1241802948540436492, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表5, caption=

模型性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型召回率精确率F1值准确率模型召回率精确率F1值准确率
XGBoost0.6010.4980.5350.714LightGBM0.6070.4850.5230.697
RF0.6090.4930.5310.703CatBoost0.5990.4800.5170.695
), ArticleFig(id=1241802948695625754, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 6, caption=

Comparison of the results of permutation importance and SHAP importance

, figureFileSmall=null, figureFileBig=null, tableContent=
特征PFI排名SHAP排名特征PFI排名SHAP排名
震中距1.00011.0001CAV0.083140.11313
PGA0.48020.6902 ASI0.087130.10015
Td0.47830.4084 Sd0.066180.11512
VSI0.32850.4983 Arms0.067170.09616
PGD0.31060.3595 Sv0.081150.07218
VS300.38040.2826 Ia0.038200.08617
屋顶类型0.28670.2278用途分类0.071160.02120
建筑年代0.26480.2377外墙类型0.048190.00621
PGV/PGA0.16690.1709 Ic0.018210.03019
PGV0.126110.12711柱子类型0.004220.00023
层数0.098120.14510结构类型0.000230.00222
Sa0.130100.10414
), ArticleFig(id=1241802948800483367, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表6, caption=

置换重要性和SHAP重要性结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
特征PFI排名SHAP排名特征PFI排名SHAP排名
震中距1.00011.0001CAV0.083140.11313
PGA0.48020.6902 ASI0.087130.10015
Td0.47830.4084 Sd0.066180.11512
VSI0.32850.4983 Arms0.067170.09616
PGD0.31060.3595 Sv0.081150.07218
VS300.38040.2826 Ia0.038200.08617
屋顶类型0.28670.2278用途分类0.071160.02120
建筑年代0.26480.2377外墙类型0.048190.00621
PGV/PGA0.16690.1709 Ic0.018210.03019
PGV0.126110.12711柱子类型0.004220.00023
层数0.098120.14510结构类型0.000230.00222
Sa0.130100.10414
), ArticleFig(id=1241802948943089712, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=EN, label=Table 7, caption=

Basic information and distribution of damaged buildings of three earthquakes in New Zealand

, figureFileSmall=null, figureFileBig=null, tableContent=
事件时间震级/Mw震源深度/km构造分类震源位置破坏建筑分布
2010-09-047.211浅地壳地震43°32′S建筑数量/条57506
172°10′E
2010-02-226.25浅地壳地震43°35′S建筑数量/条42767
172°41′E
2011-06-136.07浅地壳地震43°35′S建筑数量/条15466
172°44′E
), ArticleFig(id=1241802949110861888, tenantId=1146029695717560320, journalId=1241701559352995854, articleId=1241794072386539583, language=CN, label=表7, caption=

新西兰3次地震基本信息及破坏建筑分布

, figureFileSmall=null, figureFileBig=null, tableContent=
事件时间震级/Mw震源深度/km构造分类震源位置破坏建筑分布
2010-09-047.211浅地壳地震43°32′S建筑数量/条57506
172°10′E
2010-02-226.25浅地壳地震43°35′S建筑数量/条42767
172°41′E
2011-06-136.07浅地壳地震43°35′S建筑数量/条15466
172°44′E
)], attaches=null, journal=Journal(id=1241699397025705997, delFlag=0, nameCn=地震工程与工程振动, nameEn=Earthquake Engineering and Engineering Dynamics, nameHistory1=null, nameHistory2=null, issn=1000-1301, eissn=null, cn=23-1157/P, coden=null, periodic=1, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=/vhigrb0Ie5dk9EvytPyQg==, journalPrice=null, startedYear=null, abbrevIsoEn=Earthquake Engineering and Engineering Dynamics, journalRemark=null, publicationField=null, createdTime=1773973805912, updatedTime=1773974475511, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=E, firstLetterEn=E, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=/vhigrb0Ie5dk9EvytPyQg==, picEn=mP4JjBszibypE3yTy4J1ag==, jcr=null, cjcr=null, exts=[JournalExt(id=1241702205619753886, language=CN, name=地震工程与工程振动, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1773974475531, updatedTime=1773974475531, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://dzgc.paperonce.org/#/Login, submissionEditorUrl=https://dzgc.paperonce.org/#/Login, submissionReviewUrl=https://dzgc.paperonce.org/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1241702205665891231, language=EN, name=Earthquake Engineering and Engineering Dynamics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1773974475542, updatedTime=1773974475542, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://dzgc.paperonce.org/#/Login, submissionEditorUrl=https://dzgc.paperonce.org/#/Login, submissionReviewUrl=https://dzgc.paperonce.org/#/Login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1241701559352995854, websiteList=[Website(id=1241702575498646432, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241701559352995854, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN, language=CN, createTime=1773974563717, createBy=18614031015, updateTime=1773974590635, updateBy=18614031015, name=地震工程与工程振动-中文, tplId=1146099689490845704, title=地震工程与工程振动, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241703043805270973, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=articleTextType, value=kx, createTime=1773974675370, updateTime=1773974675370, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043771716538, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=banner, value=null, createTime=1773974675362, updateTime=1773974675362, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043830436800, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=grayFlag, value=0, createTime=1773974675376, updateTime=1773974675376, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043759133625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=logo, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/file/pic?fileId=C6sfoMWhaI5iihfhixVjYQ==, createTime=1773974675359, updateTime=1773974675359, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043843019714, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=minRunFlag, value=0, createTime=1773974675379, updateTime=1773974675379, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043801076668, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/file/pic, createTime=1773974675369, updateTime=1773974675369, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043838825409, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=silenceFlag, value=0, createTime=1773974675378, updateTime=1773974675378, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043780105147, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773974675364, updateTime=1773974675364, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043813659582, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=themeColor, value=null, createTime=1773974675372, updateTime=1773974675372, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703043822048191, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575498646432, code=themeStyle, value=null, createTime=1773974675374, updateTime=1773974675374, creator=18614031015, updator=18614031015)]), Website(id=1241702575569949602, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241701559352995854, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN, language=EN, createTime=1773974563735, createBy=18614031015, updateTime=1773974605208, updateBy=18614031015, name=地震工程与工程振动-英文, tplId=1146101810881728533, title=Earthquake Engineering and Engineering Dynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241703068497138631, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=articleTextType, value=kx, createTime=1773974681257, updateTime=1773974681257, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068480361412, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=banner, value=null, createTime=1773974681253, updateTime=1773974681253, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068513915850, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=grayFlag, value=0, createTime=1773974681261, updateTime=1773974681261, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068471972803, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=logo, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/file/pic?fileId=C6sfoMWhaI5iihfhixVjYQ==, createTime=1773974681251, updateTime=1773974681251, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068530693068, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=minRunFlag, value=0, createTime=1773974681265, updateTime=1773974681265, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068492944326, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/file/pic, createTime=1773974681256, updateTime=1773974681256, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068522304459, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=silenceFlag, value=0, createTime=1773974681263, updateTime=1773974681263, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068484555717, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773974681254, updateTime=1773974681254, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068505527240, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=themeColor, value=null, createTime=1773974681259, updateTime=1773974681259, creator=18614031015, updator=18614031015), WebsiteProps(id=1241703068509721545, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241702575569949602, code=themeStyle, value=null, createTime=1773974681260, updateTime=1773974681260, creator=18614031015, updator=18614031015)])], journalTitle=地震工程与工程振动, weixinUrl=null, journalUrl=https://dzgc.paperonce.org/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Earthquake Engineering and Engineering Dynamics, journalPhotoCn=/vhigrb0Ie5dk9EvytPyQg==, journalPhotoEn=mP4JjBszibypE3yTy4J1ag==, journalFirstLetter=E, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/10.13197/j.eeed.2025.0509, detailUrlEn=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/10.13197/j.eeed.2025.0509, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/PDF/10.13197/j.eeed.2025.0509, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dzgcygczd/EN/PDF/10.13197/j.eeed.2025.0509, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于机器学习和东日本大地震破坏数据的地震动参数筛选
收藏切换
PDF下载
李遂 1 , 王自法 2, 3, 1 , 赵登科 2, 3 , 王昭栋 2, 3 , 李兆焱 2, 3
地震工程与工程振动 | 研究论文 2025,45(5): 88-99
收起
收藏切换
地震工程与工程振动 | 研究论文 2025, 45(5): 88-99
基于机器学习和东日本大地震破坏数据的地震动参数筛选
全屏
李遂1 , 王自法2, 3, 1 , 赵登科2, 3, 王昭栋2, 3, 李兆焱2, 3
作者信息
  • 1.河南大学建筑工程学院,河南开封475004
  • 2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
  • 3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080
  • 李遂(2001—),女,硕士研究生,主要从事地震动参数和损失间相关性研究。E-mail:

通讯作者:

王自法(1965—),男,研究员,博士,主要从事巨灾风险相关研究。E-mail:
Selection of ground motion parameters based on machine learning and damage data from the Great East Japan Earthquake
Sui LI1 , Zifa WANG2, 3, 1 , Dengke ZHAO2, 3, Zhaodong WANG2, 3, Zhaoyan LI2, 3
Affiliations
  • 1.School of Civil Engineering and Architecture, Henan University, Kaifeng 475004, China
  • 2.Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China
  • 3.Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management, Harbin 150080, China
出版时间: 2025-10-22 doi: 10.13197/j.eeed.2025.0509
文章导航
收藏切换

地震动参数量化了地面运动的强度及其对建筑结构的影响程度,选取合理的参数对震前抗震设计与震后震害评估具有重要意义。地震动参数和结构地震反应间的统计关系常通过传统的相关性分析和回归方法建立,且数据多来源于数值模拟,难以捕捉两者间真实的非线性映射关系。为此,该文收集整理了2011年3月11日东日本大地震后近128万条房屋实际震害数据,基于XGBoost(eXtreme cradient boosting)、随机森林(random forest, RF)、LightGBM(light gradient boosting machine)和CatBoost(categorical boosting)共4种机器学习分类模型建立地震动参数与建筑破坏等级之间的复杂映射关系。引入SMOTE过采样和贝叶斯超参数优化法对模型进行优化,结合2种重要性评价方法选出包含7个参数的最优地震动参数组合。结果表明:XGBoost算法表现最佳,在测试集上的整体准确率可以达到71.39%;最优地震动参数组合为峰值地面加速度(peak ground acceleration, PGA)、TdVSI、峰值地面位移(peak ground displacement, PGD)、峰值地面速度(peak ground velocity, PGV)、PGV/PGA、谱加速度Sa;地震动幅值、频谱及持时参数与震后建筑损失的相关性较强,而累积能量参数与其相关性较弱。最后,通过新西兰3次地震的实际震害数据建立基于XGBoost算法的地震损失预测模型,验证了所选参数组合的完备性、可靠性和地区泛化性能。研究成果能够为建筑抗震设计及地震风险评估等工作提供一定的理论依据和工程参考。

地震损失数据  /  机器学习  /  建筑破坏等级  /  最优地震动参数组合  /  特征重要性

Ground motion parameters quantify the intensity of ground motion and their impact on building structures, making the selection of appropriate parameters crucial for pre-earthquake seismic design and post-earthquake damage assessment. Ground motion parameters and structural seismic responses are often statistically related through traditional correlation analysis and regression methods. However, data are mostly sourced from numerical simulations, which makes it difficult to capture the true nonlinear mapping relationship between the two. Therefore, this paper collected and organized nearly 1.28 million actual damage records from the Great East Japan Earthquake on March 11, 2011, and the complex mapping relationship between ground motion parameters and building damage levels was established based on four machine learning classification models, namely, XGBoost (eXtreme gradient boosting), RF(random forest), LightGBM (light gradient boosting machine), and CatBoost (categorical boosting). The SMOTE oversampling and Bayesian hyperparameter optimization algorithms were introduced to optimize the model, and the optimal combination of seven ground motion parameters was selected using two methods for evaluating feature importance. The results indicate that the XGBoost algorithm performs the best, with an overall accuracy of 71.39% on the test set. The optimal combination of ground motion parameters includs PGA, Td, VSI, PGD, PGV/PGA, PGV, and Sa. The amplitude, spectrum, and duration parameters of the ground motion show a strong correlation with post-earthquake building damage, while the cumulative energy parameters exhibit a weaker correlation. Finally, an earthquake loss prediction model based on the XGBoost algorithm was established using actual damage data from three earthquakes in New Zealand, validating the completeness, reliability, and regional generalization capability of the selected parameter combination. The research results can provide a theoretical basis and engineering reference for the seismic design of buildings and earthquake risk assessment.

earthquake loss data  /  machine learning  /  building damage level  /  optimal ground motion parameter combination  /  feature importance
李遂, 王自法, 赵登科, 王昭栋, 李兆焱. 基于机器学习和东日本大地震破坏数据的地震动参数筛选. 地震工程与工程振动, 2025 , 45 (5) : 88 -99 . DOI: 10.13197/j.eeed.2025.0509
Sui LI, Zifa WANG, Dengke ZHAO, Zhaodong WANG, Zhaoyan LI. Selection of ground motion parameters based on machine learning and damage data from the Great East Japan Earthquake[J]. Earthquake Engineering and Engineering Dynamics, 2025 , 45 (5) : 88 -99 . DOI: 10.13197/j.eeed.2025.0509
强震地面运动十分复杂,地震动参数(intensity measure, IM)量化了地面运动的强度,是连接地震灾害和建筑破坏程度之间的关键参数[1]。因此,在地震工程中,寻找关键的地震动参数及其组合来描述地面运动对结构的破坏潜力是一个重要问题[2-3]
传统方法往往基于相关性评价或回归方法确定地震动参数与结构响应指标(damage measure, DM)之间的统计关系,并进一步筛选出最具相关特征的单一地震动参数[4]。近年来,许多专家学者围绕该方面做了大量研究[5-6]。现有研究已提出数十种地震动参数,能表征地震动破坏潜力的参数通常只有有限几个。单一强度指标如峰值地面加速度(peak ground acceleration, PGA)、峰值地面速度(peak ground velocity, PGV)和考虑结构基本周期的谱加速度(Sa),因其形式简单且物理意义明确而被广泛使用。叶列平等[7]基于皮尔逊相关性系数分析了33个地震动参数和结构峰值反应的线性相关性,指出已有的单一指标无法在各个周期内达到最佳效果;陈健云等[8]研究了13种常用地震动参数与框架结构地震反应的相关性,提出结构在线性和非线性反应阶段的峰值反应与地震动参数的相关性不同,建议选用多个参数来提高抗震性能评估的可靠性。综上,单一地震动参数无法准确描述地震对结构响应的影响,因此,有必要使用多元地震动参数或者找到最优的地震动参数组合。
为了综合考虑多个地震动参数的影响,已有学者通过对单一参数进行线性或指数形式的组合得到多元地震动参数[9-12]。LUCO等[13]考虑到结构非线性和高阶振型的影响,提出了与位移谱相关的组合型地震动参数;刘亭亭等[14-16]分别采用主成分分析、偏最小二乘法和典型相关性分析建立了多元地震动参数。与单个参数相比,多元参数与结构响应虽然在不同周期内整体相关性更强,但现有研究在组合方法上存在较大的主观性,并且对于如何构建最佳的组合型参数尚且缺乏系统讨论。此外,传统方法在拟合地震动参数和建筑破坏程度间的非线性关系时存在一定局限性,具有较大的改进空间。
机器学习作为一种有效的数据分析工具,在拟合非线性关系时更加灵活和准确,并且在参数选择上具有显著的优势,近年来其也被应用于地震动参数比选的研究中。XU等[17]基于机器学习方法建立了地震动参数和结构损伤状态之间的非线性映射关系,并迭代比选出几个关键指标;YAN等[18]提出了一种顺序浮动特征选择算法,可以从地震动参数候选集中找到最佳的参数组合,并验证了其有效性。相比于传统的相关性分析和多元回归方法,虽然基于机器学习方法的地震动参数筛选研究已经取得了一些成果,但仍存在以下不足:
1)由于缺乏实际震害资料,目前大多数研究的数据都来自数值模拟,并非实际的房屋震害数据,且采用的样本数据量有限,难以满足大数据样本的需求。
2)现有研究往往采用单一和经验性的结构响应指标(如最大层间位移、最大楼面速度和最大楼面加速度等)来判断结构的破坏状态,无法有效反映建筑物实际的破坏程度,进一步增加了地震动参数和结构损伤状态之间的不确定性。
3)目前的研究通常仅针对特定地区的单一结构类型进行建模和分析,缺乏区域和建筑结构类型泛化能力,无法验证所选取的最优指标是否具有普适性。
为了解决上述问题,本文整理了2011年3月11日东日本大地震中近128万栋建筑的实际震害资料。首先基于台站实际观测信息,利用地震动空间插值方法计算出建筑物处的14个地震动参数;随后基于机器学习模型建立地震动参数、建筑物信息和场地条件与建筑破坏等级之间的复杂非线性映射关系,并结合2种重要性评价方法迭代筛选出最有效的地震动参数组合;最后采用新西兰3次地震事件中共115739条建筑详细破坏数据进行验证,证明所选参数组合在新西兰地区的适用性和有效性。该研究能够为地震损失估计中地震动参数的选择提供参考,同时能够有效地帮助提高地震巨灾风险分析精度。
日本位于环太平洋地震带,是世界上发生地震频数最多的国家之一。2011年3月11日,日本东北海岸38°02′N,143°09′E的地区发生里氏9.0级特大地震,造成约2.8万人遇难,数百万栋建筑受损,给社会和经济带来了巨大冲击。美国再保险公司Validus收集了震后建筑物的详细破坏资料,包括建筑物的建筑年代、层数、结构类型、柱子类型和损失比等详细建筑特征与破坏信息。本文收集整理了此次地震中1278861栋建筑的详细破坏资料作为本研究的数据集。
地震发生后,各空间位置地震动强度一般用地震动预测方程(ground motion prediction equation, GMPE)获取。GMPE通过传统回归方法来拟合地震动的复杂衰减关系,因此预测结果与实际结果往往存在偏差[19]。本研究采用ZHAO等[20]提出的地震动参数的空间插值计算方法,该方法基于实际的台站观测记录,利用GMPE作为权重分别对空间距离和场地条件进行修正,最终空间插值得到台站附近每栋建筑物处的地震动参数。本文采用日本国家防灾科学技术研究所(National Research Institute for Earth Science and Disaster Resilience, NIED)提供的实际台站观测以及适用于日本地区的GMPE[21-23],获得了共14个广泛应用的地震动参数作为原始地震动参数集见第1.5节。需要说明的是,由于频谱参数中谱速度(Sv)和谱位移(Sd)也较为关键[24],且目前没有适用于日本地区SvSd的GMPE,因此上述2种地震动参数的GMPE分别采用MORASCA等[22]和CAUZZI等[23]提出的全球模型。建筑物的场地条件通过地下30 m深度内的等效剪切波速(VS30)判别,计算方法参考WALD等[25]
获得的数据集中一般包含缺失值、异常值和重复数据等问题,影响后续的模型训练,因此模型训练前需要进行数据预处理。本文基于Python语言中的Pandas、Numpy等数据处理工具对数据集进行以下预处理:
1)数据清理。剔除数据集中建筑年代、结构类型和屋顶类型等特征不明类数据;删除由地震外的其他灾害(如海啸、滑坡和火灾等)造成的建筑破坏数据。
2)模型算法的本质是数值运算,无法识别非数字信息,因此需要将建筑信息中的建筑年代、结构类型等文本信息利用Scikit-learn库提供的Label Encoder编码工具转换为整数,实现文本数值化。
3)数据集划分。采用机器学习领域最典型的“八二原则”对样本数据进行划分,即从震后建筑资料数据库中随机抽取80%数据(1023088条)作为训练集,剩余20%(255773条)作为测试集。
本文中建筑破坏程度信息由美国再保险公司Validus统计计算,它是由建筑物损失价值与建筑物总价值的比值计算得到,记为损失比(damage ratio, Dr)。参考美国应用技术协会所发布的地震震害评估标准ATC-13[26],根据rD将建筑物划分为4种破坏等级,(0,10%]为轻微破坏,(10%,30%]为中等破坏,(30%,60%]为严重破坏,(60%,100%]为毁坏。将未破坏建筑的破坏等级标记为0,其他四类按照破坏等级由小到大依次标记为1、2、3、4,标记的样本用于机器学习分类模型的训练。5种破坏等级的数据分布见表1
特征是机器学习模型的基本组成部分,选择和处理好特征可以显著提高模型的预测性能。地震发生后,建筑物的破坏是由强震地面运动、建筑结构和场地条件等因素之间相互复杂作用而造成的,因此特征选择要综合考虑以上影响因素。为了准确反映强震地面运动,研究采用在1.2节中计算得到的14个地震动参数,包括PGA、PGV和Sa等,以及震中距来描述地震动特性,这些选定的地震动参数涵盖了多种地震动信息,如振幅、频谱和累积能量等;结合数据库及现有研究中常用的建筑特征,最终确定建筑年代、屋顶类型等7个特征来代表建筑物信息;为了研究不同的场地类型对于建筑结构破坏的影响,引入VS30来代表不同的场地条件。综上所述,最终确定23个特征作为模型输入,各个特征的具体信息见表2
本研究的目的是得出与地震后建筑物损失相关性最强的地震动参数组合,从而为提高损失预测的准确性、优化抗震设计和制定防灾减灾措施提供依据和参考。本文研究路线见图1,具体包括:
1)收集2011年3月11日东日本大地震后实际震害资料,利用地震动空间插值方法计算每栋建筑处的14个地震动参数并为每栋建筑匹配VS30,形成较为完善的实际震害数据库。
2)对数据进行切片处理,指定模型输入特征及输出标签的类别。
3)按照8∶2的比例将数据集划分为训练集和测试集。
4)选用XGBboost(eXtreme cradient boosting)、随机森林(random forest, RF)、LightGBM(light gradient boosting machine)和CatBoost(categorical boosting)[27-30]共4种机器学习分类算法,调用函数并设置模型初始超参数,建立4种初始预测模型。
5)引入SMOTE过采样、贝叶斯超参数优化法后获得最优模型,对测试集进行预测并打分。
6)通过OA、P、R及F1指标对4种模型进行综合评估并获得最优预测模型。
7)利用最优预测模型对各输入特征进行重要性分析,迭代选出最优地震动参数组合,并进行结果分析。
8)通过新西兰震害数据对筛选得到的最优参数组合进行结果验证。
数据集收集整理完毕后,将1.5节中确定的23个特征及标签输入机器学习模型进行训练。虽然地震动参数之间可能存在较高的相关性,但本研究并未利用相关性对特征进行剔除,原因有:①相关性较高的参数之间仍包含固有信息的差异[17];②在地震动参数组合中,参数之间存在着复杂的相互作用,简单依据相关性剔除某些参数可能会忽略这些复杂关系和潜在影响。此外,由于不同的地震动参数及VS30的量纲和数据分布不同,为了消除这些影响,在建立模型之前,利用式(1)对数据集中的连续型特征进行归一化处理,以确保数据的等效性。
式中:Xi为某一特征中第i个样本数据;Xmax为该特征的最大值;Xmin为该特征的最小值。
由地震动衰减的客观规律可知,地震发生后影响场内未破坏和发生轻微破坏的建筑往往多于发生严重破坏的建筑,见表1,导致实际震害数据分布不均衡。NGUYEN等[31]的研究表明,训练数据的不均衡分布会降低分类器的预测性能。因此,有必要采用相关方法降低数据不均衡分布带来的不利影响,提升模型分类性能。现有研究中,非平衡数据的处理方法主要有过采样方法和欠采样方法。欠采样方法可能会导致过多数据丢失,从而破坏数据的原有特性,因此本研究不予采用。合成少数过采样技术(synthetic minority oversampling technique, SMOTE)[32]是一种著名的过采样方法,通过在邻近的少数类样本间进行线性插值来合成新的样本,从而达到数据平衡,该方法可以在一定程度上减少过拟合风险,同时保持类别分布的自然性。本研究采用SMOTE过采样方法处理数据不均衡问题。
超参数是影响机器学习模型性能的关键参数,通过优化获得适当的超参数可以防止过拟合和欠拟合,以此提升模型的泛化能力和预测精度。超参数优化方法有网格搜索、随机搜索和贝叶斯优化三大类。网格搜索法(grid search)[33]是通过穷举搜索的方式在给定的参数范围内遍历所有的参数组合,在测试集上精度最高的参数组合将作为最优超参数组合。但该方法在处理高维和大规模数据集时效率较低,且训练成本高。随机搜索(random search)[34]是在搜索范围内随机选择超参数组合来训练和评估模型,以找到最优的超参数组合。尽管计算效率高,但由于搜索过程没有针对性地探索参数空间,可能会错过某些最优解。贝叶斯优化(Bayesian optimization)[35]是一种基于贝叶斯概率论超参数调整方法,通过构建参数的后验概率分布来推断最优的超参数组合,该方法具有较高的运算效率,并且能够有效探索全局最优解,尤其适合于复杂的参数空间优化。因此,本研究采用贝叶斯优化方法选择最优超参数组合,4种模型筛选得到的最优关键超参数见表3,非关键参数采用默认数值。
本研究选取整体准确率OA、召回率R、精确率P、F1值作为模型的性能评估指标,具体计算公式见表4。准确率OA为模型正确预测目标的精度,即模型预测正确的样本个数占总样本数的比率。召回率R为模型正确分配实际标签的百分比,精确率P为模型正确分配预测标签的百分比。召回率R与精确率P在一定程度上存在权衡关系,通常使用F1值来平衡这2个指标并协助评估模型性能。
采用SMOTE过采样和贝叶斯优化对4种机器学习模型优化后各模型的评价指标见表5。对比4种模型得出:基于XGBoost算法模型的整体准确率和F1值最高,分别达到了0.714、0.535。因此,本研究选择训练完毕的XGBoost模型为最终的损失预测模型。
为了直观展示XGBboost模型在5个破坏标签上的分类表现,采用混淆矩阵(confusion matrix)来评估其分类性能,最终模型在测试集上的分类结果见图2。主对角线上的值分别表示模型对5种破坏等级的预测准确率,分别为80.05%、48.59%、51.54%、49.60%、70.57%。模型的整体准确率为71.39%。值得注意的是,模型可以较为准确地预测未破坏和发生毁坏的建筑物,这对灾后紧急救援具有重要意义。类别1、类别2、类别3的准确率较低,均在50.00%左右,主要是因为建筑物发生破坏之后,不同破坏程度之间的建筑物属性区别度较低,相邻破坏等级的建筑物容易出现匹配失误,但这在建筑破坏等级评估中是可以接受的,如果机器学习错误将实际标签分配到跨越2个及以上的标签就需要引起较大的关注[36]
XGBoost模型在训练的过程中可以检测各个特征对分类结果的影响。本研究采用置换特征重要性(permutation feature importance, PFI)[37]和沙普利可加性模型解释方法(SHapley Additive exPlanation, SHAP)[38]对模型进行解释。PFI算法基于已经训练好的模型,通过随机打乱测试集中某一变量的数据顺序,统计打乱前后模型精度下降的程度,精度下降越多,表明模型对该特征的依赖程度越大;SHAP是基于Shapley值的模型解释工具,该方法将传统方法与博弈论和局部解释联系起来用于解释各种黑箱模型,通过计算样本中每个特征的贡献,对模型进行解释, Shapley值表示具有特征归因可加性的线性模型,将模型的预测值转换为每个特征的归因值之和,明确了各个特征对模型的影响程度。为了更好地对比衡量2种方法下的特征重要度,对每种方法得到的重要性进行归一化处理,评价结果见表6
由于2种重要性评价方法的原理和评价指标不同,因此所得到的排序结果存在一定差异,但2种方法得到的特征排序基本一致。为了更加准确全面地评估各个特征对模型的贡献度,最终的特征重要性排序通过结合2种评价方法归一化后的加权特征重要性来确定,见图3
为了筛选出与震后建筑损失相关性最强的关键地震动参数组合,基于3.2节中加权后的特征重要性排序,采用前向特征搜索法逐步扩充特征集合H,将数据集按照8∶2的比例划分为训练集和测试集,分别用于训练XGBoost模型和评估集合H对建筑损失等级的预测精度。关键参数组合应尽可能以较少的数量准确反映震后建筑损失。本文认为,当通过前向特征搜索法获得参数组合对应的模型精度与全部特征对应的最终模型精度相差1.00%时,该参数组合即为可充分预测建筑破坏等级且包含全面地震动信息的最优地震动参数组合。
图3可知,震中距是影响建筑损失最主要的因素,因此以震中距为基础创建特征集合H0,根据特征重要性排序从前到后逐步在集合H0中加入特征,利用训练集样本构建模型,通过模型的整体准确率OA评估集合H0对测试集建筑损失的预测精度,结果见图4(a),其中不同颜色的图形代表不同类型的特征。其中,红色为地震动峰值参数;绿色为地震动频谱参数;黄色为地震动累积能量参数;蓝色为建筑物基本信息;黑色为震中距;紫色为地震动重要持时;浅蓝色为场地条件。
图4(a)中模型精度整体呈上升趋势,当集合H0具有2个及以上特征时,模型精度总体趋于稳定。当模型中加入12个参数时,整体准确率可以达到70.00%;相比之下,包含所有特征的模型准确率为71.39%,相差不到1.00%。表明选择前12个特征能够较好地保留关键信息,同时保持较高的模型准确率。所选12个特征分别是震中距、PGA、TdVSI、PGD、VS30、屋顶类型、建筑年代、PGV/PGA、PGV、层数、Sa。其中包含建筑物基本信息,场地条件,震中距以及7个地震动参数构成的组合。地震动参数数量居多,表明他们在联系地震动和建筑损失上起到了重要的桥梁作用。所选7个地震动参数的组合涵盖了振幅、频谱和持时3个地震动的关键要素。其中包含PGA、PGD、PGV这3个幅值参数;VSI、PGV/PGA、Sa这3个频谱参数;1个持时参数Td。由此可见,幅值和频谱参数对模型性能有着重要影响,而累积能量参数对模型的贡献有限。幅值参数物理含义明确且可以直接反应地震动的强弱,在抗震设计中广泛应用,3个幅值参数中PGA表现出最强的有效性,其次是PGD和PGV;频谱参数中包含积分型谱强度参数VSI,这一现象可以解释为:在地震中结构发生非线性变形会导致周期延长,而VSI考虑了较长周期范围内(0.1~2.5 s)的反应谱值,因此表现出较好的效果;地震动持时的排序仅次于震中距和PGA,其影响主要体现在非线性体系的最大反应和能量累积两个方面[39],实际地震发生之后,地震动持续时间越长,对建筑物造成潜在破坏的可能性越大,因此地震动持时需要引起重视。
模型精度随特征集合H1中地震动参数逐次递增的变化趋势见图4(b),其能更加准确地评估地震动参数对模型精度的影响。模型精度随着特征集合H1地震动参数数目的递增逐渐增加,说明地震动参数的加入能有效提升模型精度。当H1中仅包含建筑信息、场地信息及震中距时,模型精度仅为57.45%。加入PGA后,模型精度显著提升至68.33%,进一步增加至7个参数后,模型精度达到70.80%。当加入全部参数时,模型精度为71.39%,与包含7个参数的模型精度相差不到1.00%。以上结果说明PGA、TdVSI、PGD、PGV/PGA、PGV、Sa这7个参数为最优参数组合,即可以用较少的参数且较为准确地反映地震损伤。
为了进一步与单一地震动参数作对比,本文在初始特征集合H1的基础上分别增加PGA和Sa这2个广泛研究的地震动参数,训练后模型精度分别达到68.33%(PGA)和67.80%(Sa)。表明与单一地震动参数(PGA/Sa)相比,所选地震动参数组合可以弥补单一参数包含信息不足的问题,且能够更为全面地反映地震动特征。此外发现,上述过程中, PGA的结果优于Sa,可能是因为本研究在计算Sa时参考了AMANAT等[40]的研究,经验性地使用N/10估计房屋地自振周期(其中N为房屋层数),而建筑物进入非线性阶段后刚度会降低,使得获取可靠的自振周期变得困难,最终导致Sa的计算结果存在一定偏差,相反地, PGA反映的是地面运动地强度,能够更加直接地反映建筑物遭受的地震作用。
新西兰位于太平洋板块和澳大利亚板块交界处,2个板块的相互作用产生了显著的地质活动,导致地震频发[41]。新西兰地震委员会(Earthquake Commission, EQC)成立至今积累了大量详实的房屋震后损失资料。为了验证所选最优参数组合的有效性,基于新西兰造成损失建筑较多的3次地震事件共115739条详细震害数据,建立震后建筑损失预测模型。由于新西兰和日本数据库中记录的基本信息不同,因此所选特征也存在一定差异,考虑到3次地震事件基本信息不同,因此将震级和震源深度作为2个新增的输入特征。
目前尚未针对新西兰地区提出专门的GMPE,但新西兰与日本同处于太平洋板块的边缘,且均为狭长的岛国,因此采用基于日本观测数据得到的GMPE来计算新西兰地区的地震动参数是较为合理的选择,赵登科等[42]已经证明了日本地区的GMPE应用于新西兰地区的有效性。在计算14个地震动参数时,仍采用1.2节中适用于日本及其他地区的GMPE,结合震害详细资料最终确定29个影响因素作为XGBoost分类模型的输入特征,同样以ATC-13划分的破坏等级作为标签。3次地震事件的基本信息及破坏建筑分布情况见表7
在对XGBoost模型训练和优化后其整体精度约达到71.85%。结合FPI和SHAP这2种方法对模型进行解释并获取加权后的特征重要性评分,排序结果见图5。由图可知,排名靠前的7个地震动参数分别是PGA、PGD、SaVSITd、PGV/PGA、CAV。其中包含2个地震动幅值参数为PGA、PGD;3个频谱参数为SaVSI、PGV/PGA;1个地震动持时参数为Td;1个累积能量参数为CAV。这一结果与日本的研究发现相符,表明幅值、频谱和持时参数与震后建筑损失间存在关键联系,而累积能量参数只有1个且排序靠后,与损失间相关性较弱。此外,新西兰排序前7位的地震动参数和日本筛选出的最优参数组合整体上基本一致,7个参数中有6个相同,差异在于日本最优地震动参数组合中的PGV在新西兰的前7位参数中被CAV替代,而PGV在新西兰地震动参数中的排序为8,仅次于CAV。
为了验证所选地震动参数组合的有效性,基于建筑信息、场地信息等创建特征集合H2,初始模型精度56.53%。将3.3节中选出的地震动参数组合PGA、TdVSI、PGD、PGV/PGA、PGV、Sa依次加入模型并记录精度变化情况,见图6。当模型中包含最优参数组合时,精度为70.97%,与包含所有特征的最终模型精度仅相差0.88%,证明了最优参数组合的有效性。当在初始特征集合H2中分别增加单一参数PGA和Sa后,模型精度分别为68.07%、63.63%。由初始建筑物自振周期计算得到的Sa无法准确表征建筑物在非线性阶段的响应,而PGA直接反映了建筑物承受的地震强度,这造成了模型精度的差异。以上结果表明,最优参数组合比单一参数更具优势,同时涵盖了大部分关键地震动信息,显著降低了地震动维度。
综上所述,以新西兰3次地震震后建筑损失资料作为验证,建立建筑损失等级预测模型,并对29个输入特征进行重要性分析。将关键地震动参数与最优参数组合进行比较,结果显示2个地区筛选得到的关键参数基本一致,此外,包含最优参数组合的模型精度与最终模型精度相差不到1.00%。研究表明,所选参数组合具有较高的信息覆盖率,并验证了其信息完备性且具有良好的地区泛化性能。
本文基于2011年3月11日东日本大地震后大量详实的建筑损失数据,利用机器学习算法建立结构、场地及地震动特性与建筑破坏等级之间的非线性映射关系,并比选出关键地震动参数组合。以新西兰3次地震实际损失资料作为验证,证明了所选参数组合用于描述地震动信息的完备性和有效性,得出如下主要结论:
1)与传统利用数值模拟开展的研究不同,本研究利用大量详实的地震损失数据,采用机器学习方法从14个地震动参数中比选出影响地震动破坏势的关键参数组合。解决了单一参数包含地震信息不足和多元参数构建复杂的问题;极大地改善了现有同类研究中数据受限、地震动参数间的内在关联被忽视、采用的结构响应指标无法反映建筑真实破坏程度、所选参数缺乏足够区域及结构类型泛化能力的问题。
2)基于4种机器学习算法(XGBoost、RF、LightGBM、Catboost)建立震后建筑损失等级预测模型。采用SMOTE过采样和贝叶斯超参数优化法后,对比4种模型在测试集上的表现,结果表明XGBoost模型精度最高,整体准确率达到71.39%,其次是RF、LightGBM、CatBoost。
3)结合置换重要性和SHAP重要性2种评价方法对训练完毕的XGBoost模型进行特征重要性分析,利用前向特征搜索法选出7个和损失相关性最强的地震动参数组合,依次为PGA、TdVSI、PGD、PGV/PGA、PGV、Sa。结果表明幅值参数和频谱参数与损失的相关性最强,而累积能量参数与损失的相关性较弱;另外,地震动持时的重要性需要引起关注。
4)以新西兰3次地震实际损失资料作为验证,证明所选参数组合涵盖了较为全面的地震动信息且具有一定的地区和未知事件泛化能力。研究成果有助于准确评估地震动的破坏潜力,同时为震前优化建筑抗震设计、震后应急评估与恢复提供有力依据。
5)本文在进行地震动参数筛选时,主要关注地震动参数与震后建筑损失间的联系,但未考虑到地震动参数与震后建筑损失分布的随机性和离散性之间的统计关系。因此,未来的研究应综合考虑这些复杂多元因素,以提升对建筑物在地震中的风险识别和损伤评估。
  • 国家自然科学基金面上项目(52378544; 52378543)
  • 国家重点研发计划项目(2023YFC3805203)
  • 中国地震局工程力学研究所基本科研业务费专项资助项目(2021B09; 2023A01)
参考文献 引证文献
排序方式:
[1]
BURATTI N. A comparison of the performances of various ground-motion intensity measures[C]∥Proceedings of the 15th World Conference on Earthquake Engineering, Lisbon, Portugal: Sociedade Portuguesa de Engenharia Sismica, 2012: 24-28.
[2]
刘巴黎,胡进军,谢礼立.基于弹性网络回归的地震动参数排序与比选[J].哈尔滨工业大学学报, 2024, 56(1): 54-62.
LIU Bali, HU Jinjun, XIE Lili. Ranking and comparison of ground motion parameters based on elastic net regression[J]. Journal of Harbin Institute of Technology, 2024, 56(1): 54-62. (in Chinese)
[3]
吴梓楠,韩小雷,马建峰,.基于机器学习的地震动强度指标敏感性分析与破坏势评估[J].建筑结构学报, 2023, 44(11): 216-225, 235.
WU Zinan, HAN Xiaolei, MA Jianfeng, et al. Sensitivity analysis of ground motion intensity measures and evaluation of potential damage based on machine learning[J]. Journal of Building Structures, 2023, 44(11): 216-225, 235. (in Chinese)
[4]
李爽,谢礼立,郝敏.地震动参数及结构整体破坏相关性研究[J].哈尔滨工业大学学报, 2007, 39(4): 505-509, 560.
LI Shuang, XIE Lili, HAO Min. Correlation between seismic ground motion parameters and their relationship with overall damage to structure[J]. Journal of Harbin Institute of Technology, 2007, 39(4): 505-509, 560. (in Chinese)
[5]
PINZóN L A, VARGAS-ALZATE Y F, PUJADES L G, et al. A drift-correlated ground motion intensity measure: Application to steel frame buildings[J]. Soil Dynamics and Earthquake Engineering, 2020, 132: 106096.
[6]
KOSTINAKIS K, ATHANATOPOULOU A, MORFIDIS K. Correlation between ground motion intensity measures and seismic damage of 3D R/C buildings[J]. Engineering Structures, 2015, 82: 151-167.
[7]
叶列平,马千里,缪志伟.结构抗震分析用地震动强度指标的研究[J].地震工程与工程振动, 2009, 29(4): 9-22.
YE Lieping, MA Qianli, MIAO Zhiwei. Study on earthquake intensities for seismic analysis of structures[J]. Journal of Earthquake Engineering and Engineering Dynamics, 2009, 29(4): 9-22. (in Chinese)
[8]
陈健云,李静,韩进财,.地震动强度指标与框架结构响应的相关性研究[J].振动与冲击, 2017, 36(3): 105-112, 144.
CHEN Jianyun, LI Jing, HAN Jincai, et al. Correlation between ground motionintensity indexes and seismic responses of frame structures[J]. Journal of Vibration and Shock, 2017, 36(3): 105-112, 144. (in Chinese)
[9]
LIU T T, YU X H, LU D G. An approach to develop compound intensity measures for prediction of damage potential of earthquake records using canonical correlation analysis[J]. Journal of Earthquake Engineering, 2020, 24(11): 1747-1770.
[10]
OZMEN H B. Developing hybrid parameters for measuring damage potential of earthquake records: Case for RC building stock[J]. Bulletin of Earthquake Engineering, 2017, 15(7): 3083-3101.
[11]
GEHL P, SEYEDI D M, DOUGLAS J. Vector-valued fragility functions for seismic risk evaluation[J]. Bulletin of Earthquake Engineering, 2013, 11(2): 365-384.
[12]
胡进军,刘巴黎,谢礼立.基于因子分析的地震动特征提取及潜在破坏势评估[J].工程力学, 2022, 39(10): 140-151, 172.
HU Jinjun, LIU Bali, XIE Lili. Factor analysis-based ground motion feature extraction and the measurement of the potential structural damage[J]. Engineering Mechanics, 2022, 39(10): 140-151, 172. (in Chinese)
[13]
LUCO N, CORNELL C A. Structure-specific scalar intensity measures for near-source and ordinary earthquake ground motions[J]. Earthquake Spectra, 2007, 23(2): 357-392.
[14]
刘亭亭,于晓辉,吕大刚.地震动多元强度参数主成分与结构损伤的相关性分析[J].工程力学, 2018, 35(8): 122-129, 137.
LIU Tingting, YU Xiaohui, LV Dagang. Analysis of correlation between principal components of multivariate earthquake intensity measures and structural damage[J]. Engineering Mechanics, 2018, 35(8): 122-129, 137. (in Chinese)
[15]
LIU T T, LU D G, YU X H. Development of a compound intensity measure using partial least-squares regression and its statistical evaluation based on probabilistic seismic demand analysis[J]. Soil Dynamics and Earthquake Engineering, 2019, 125: 105725.
[16]
刘亭亭,于晓辉,吕大刚.RC框架基于典型相关分析的地震动多元破坏势评估[J].土木工程学报, 2019, 52(1): 27-36, 107.
LIU Tingting, YU Xiaohui, LU Dagang. Multivariate damage potential estimation of earthquake ground motions for RC frames based on canonical correlation analysis[J]. China Civil Engineering Journal, 2019, 52(1): 27-36, 107. (in Chinese)
[17]
XU Y J, LU X Z, TIAN Y, et al. Real-time seismic damage prediction and comparison of various ground motion intensity measures based on machine learning[J]. Journal of Earthquake Engineering, 2022, 26(8): 4259-4279.
[18]
YAN Y X, XIA Y, YANG J P, et al. Optimal selection of scalar and vector-valued seismic intensity measures based on Gaussian Process Regression[J]. Soil Dynamics and Earthquake Engineering, 2022, 152: 106961.
[19]
DANG H T, WANG Z F, ZHAO D K, et al. Ground motion prediction model for shallow crustal earthquakes in Japan based on XGBoost with Bayesian optimization[J]. Soil Dynamics and Earthquake Engineering, 2024, 177: 108391.
[20]
ZHAO D K, WANG Z F, WANG J M, et al. A rapid estimation method for post-earthquake building losses[J]. International Journal of Disaster Risk Science, 2023, 14(3): 428-439.
[21]
PODILI B, RAGHUKANTH S T G. Ground motion prediction equations for higher order parameters[J]. Soil Dynamics and Earthquake Engineering, 2019, 118: 98-110.
[22]
MORASCA P, ZOLEZZI F, SPALLAROSSA D, et al. Ground motion models for the Molise Region (southern Italy)[J]. Soil Dynamics and Earthquake Engineering, 2008, 28(3): 198-211.
[23]
CAUZZI C, FACCIOLI E, VANINI M, et al. Updated predictive equations for broadband (0.01~10 s) horizontal response spectra and peak ground motions, based on a global dataset of digital acceleration records[J]. Bulletin of Earthquake Engineering, 2015, 13: 1587-1612.
[24]
GUPTA A K. Response spectrum method in seismic analysis and design of structures[M]. New York: Routledge, 2017.
[25]
WALD D J, ALLEN T I. Topographic slope as a proxy for seismic site conditions and amplification[J]. Bulletin of the Seismological Society of America, 2007, 97(5): 1379-1395.
[26]
MCCORMACK T C, RAD F N. An earthquake loss estimation methodology for buildings based on ATC-13 and ATC-21[J]. Earthquake Spectra, 1997, 13(4): 605-621.
[27]
CHEN T Q, GUESTRIN C. XGBoost: A scalable tree boosting system[C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. New York: ACM, 2016: 785-794.
[28]
BREIMAN L. Random forests[J]. Machine Learning, 2001, 45: 5-32.
[29]
KE G L, MENG Q, FINLEY T, et al. LightGBM: A highly efficient gradient boosting decision tree[C]∥Proceedings of Advances in Neural Information Processing Systems. Long Beach, CA, USA: Neural Information Processing Systems Foundation, 2017: 3149-3157.
[30]
PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features[C]∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2018: 6639-6649.
[31]
NGUYEN H M, COOPER E W, KAMEI K. Borderline over-sampling for imbalanced data classification[J]. International Journal of Knowledge Engineering and Soft Data Paradigms, 2011, 3(1): 4-21.
[32]
CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: Synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357.
[33]
SUN Y T, DING S F, ZHANG Z C, et al. An improved grid search algorithm to optimize SVR for prediction[J]. Soft Computing, 2021, 25(7): 5633-5644.
[34]
BERGSTRA J, BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13(2): 281-305.
[35]
SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms[C]∥Proceedings of Advances in Neural Information Processing Systems. New York, USA: Curran Associates Inc, 2012, 25: 2951-2959.
[36]
MANGALATHU S, SUN H, NWEKE C C, et al. Classifying earthquake damage to buildings using machine learning[J]. Earthquake Spectra, 2020, 36(1): 183-208.
[37]
ALTMANN A, TOLO I L, SANDER O, et al. Permutation importance: A corrected feature importance measure[J]. Bioinformatics, 2010, 26(10): 1340-1347.
[38]
LUNDBERG S M, LEE S-I. A unified approach to interpreting model predictions[C]∥Proceedings of Advances in Neural Information Processing Systems, New York, USA: Curran Associates Inc, 2017, 30: 4765-4774.
[39]
周锡元,王广军,苏经宇.场地·地基·设计地震[M].北京:地震出版社, 1990.
ZHOU Xiyuan, WANG Guangjun, SU Jingyu. Site·Foundation·Design earthquake[M]. Beijing: Seismological Press, 1990. (in Chinese)
[40]
AMANAT K M, HOQUE E. A rationale for determining the natural period of RC building frames having infill[J]. Engineering Structures, 2006, 28(4): 495-502.
[41]
刘渊,王自法,赵登科.基于新西兰详细地震破坏数据的建筑物构件损失分析[J].地震工程与工程振动, 2021, 41(5): 186-195.
LIU Yuan, WANG Zifa, ZHAO Dengke. Building component level loss analysis based on detailed earthquake loss data in New Zealand[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(5): 186-195. (in Chinese)
[42]
赵登科,王自法,刘渊,.基于新西兰实际震害资料的地震损失不确定性分析[J].地震工程与工程振动, 2021, 41(2): 84-95.
ZHAO Dengke, WANG Zifa, LIU Yuan, et al. Earthquake loss uncertainty based on detailed loss data in New Zealand[J]. Earthquake Engineering and Engineering Dynamics, 2021, 41(2): 84-95. (in Chinese)
2025年第45卷第5期
PDF下载
72
33
引用本文
BibTeX
文章信息
doi: 10.13197/j.eeed.2025.0509
  • 接收时间:2024-10-09
  • 首发时间:2026-03-20
  • 出版时间:2025-10-22
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-09
  • 修回日期:2024-11-06
基金
国家自然科学基金面上项目(52378544; 52378543)
国家重点研发计划项目(2023YFC3805203)
中国地震局工程力学研究所基本科研业务费专项资助项目(2021B09; 2023A01)
作者信息
    1.河南大学建筑工程学院,河南开封475004
    2.中国地震局工程力学研究所地震工程与工程振动重点实验室,黑龙江哈尔滨150080
    3.地震灾害防治应急管理部重点实验室,黑龙江哈尔滨150080

通讯作者:

王自法(1965—),男,研究员,博士,主要从事巨灾风险相关研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dzgcygczd/CN/10.13197/j.eeed.2025.0509
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏