Article(id=1322941066751651957, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322940959071285581, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2024.08.369, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1722528000000, receivedDateStr=2024-08-02, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793343329370, onlineDateStr=2026-10-30, pubDate=1749916800000, pubDateStr=2025-06-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793343329370, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793343329370, creator=13701087609, updateTime=1793343329370, updator=13701087609, issue=Issue{id=1322940959071285581, tenantId=1146029695717560320, journalId=1281212831689347082, year='2025', volume='45', issue='6', pageStart='551', pageEnd='660', issueExtLink='null', onlineDate='null', pubDate='1749916800000', pubDateStr='2025-06-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793343303697, creator='13701087609', updateTime=1793343303697, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=654, endPage=660, ext={EN=ArticleExt(id=1322941066973950070, articleId=1322941066751651957, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=Machine Learning for Automated Detection and Classification of Microseismic Signals from Avalanche Rockfalls, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In this paper, based on microseismic monitoring data and 49 microseismic feature parameters of a marble mine in Perugia, central Italy, we compare and analyze the accuracy of three machine learning models, namely, neural networks, decision trees and random forests, in the automated classification of microseismic signals, and optimize the model parameters to improve the performance of the model through the grid searcher algorithm, with an emphasis on discussing the effects of the feature parameter selection and the size of the classification set on the classification results. The results show that the random forest classifier obtains the highest accuracy in microseismic signal classification, with 98.11% classification accuracy after optimization, meanwhile, by reducing some of the feature parameters with small weights, the efficiency of the classification computation is greatly improved and the accuracy decreases less, and the optimal allocation ratio of the training set to the test set is 8 ∶2.

, authors=Bin XIE1, Guishan GAO2, Zhiyong HUANG3, 4, Liang FENG5, *, authorsList=Bin XIE, Guishan GAO, Zhiyong HUANG, Liang FENG, authorCompany=null, correspAuthors=Liang FENG, authorNote=

XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., 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, fund=null), CN=ArticleExt(id=1322941069909962881, articleId=1322941066751651957, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=机器学习实现崩塌落石微震信号自动化检测和分类, columnId=1322506256904994864, journalTitle=大地测量与地球动力学, columnName=观测技术, runingTitle=null, highlight=null, articleAbstract=

基于意大利中部佩鲁贾市某大理石矿山微震监测数据和49个微震特征参数,对比分析神经网络、决策树和随机森林3种机器学习模型在微震信号自动化分类中的精度,通过网格搜索算法优化模型参数提高模型性能,讨论特征参数的选择和分类集的大小对分类结果的影响。结果表明,随机森林分类器在微震信号分类中获得的准确度最高,优化后分类准确度为98.11%,同时减少部分权重小的特征参数,分类计算效率大幅提高,准确度下降较少,训练集与测试集的最佳分配比例为8 ∶2。

, authors=谢斌1, 高桂山2, 黄志勇3, 4, 冯亮5, *, authorsList=谢斌, 高桂山, 黄志勇, 冯亮, authorCompany=null, correspAuthors=冯亮, authorNote=

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

, correspAuthorsNote=

冯亮,博士,副教授,主要从事地质灾害与环境地震学研究,E-mail:

FENG Liang, PhD, associate professor, majors in geological hazards and environmental seismology, E-mail:

, copyrightStatement=版权所有,未经授权,不得转载。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=PgC0obgdPK07gQ4HEQHmgw==, magXml=FQJG9DEauMfL1Zwv9/gl1g==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=W7XmpGWm1NGWN2HljfXEkw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=wyj4iI6eT+yJjQ+7cf1uTQ==, mapNumber=null, fund=null)}, authors=[Author(id=1322941070522331282, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=309479810@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322941070610411668, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070522331282, language=EN, stringName=Bin XIE, firstName=Bin, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China, bio={"content":"

XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

"}, bioImg=null, bioContent=

XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941070685909141, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070522331282, language=CN, stringName=谢斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000, bio={"content":"

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

"}, bioImg=null, bioContent=

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070107095170, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070115483779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070123872388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000)])]), Author(id=1322941070916595863, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=1, 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=1322941070992093338, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070916595863, language=EN, stringName=Guishan GAO, firstName=Guishan, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941071063396507, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070916595863, language=CN, stringName=高桂山, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070186786949, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070195175558, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China), AuthorCompanyExt(id=1322941070203564167, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128)])]), Author(id=1322941071285694621, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, 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=1322941071361192096, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071285694621, language=EN, stringName=Zhiyong HUANG, firstName=Zhiyong, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China
4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941071419912353, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071285694621, language=CN, stringName=黄志勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041
4 中国科学院大学, 北京市玉泉路19号, 100049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070258090120, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070266478729, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China), AuthorCompanyExt(id=1322941070274867338, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041)]), AuthorCompany(id=1322941070333587595, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070341976204, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China), AuthorCompanyExt(id=1322941070350364813, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 中国科学院大学, 北京市玉泉路19号, 100049)])]), Author(id=1322941071721902243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liang.feng@jxust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322941073298960550, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071721902243, language=EN, stringName=Liang FENG, firstName=Liang, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China
1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941073370263719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071721902243, language=CN, stringName=冯亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000
1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070434250894, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070442639503, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070451028112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000)]), AuthorCompany(id=1322941070107095170, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070115483779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070123872388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000)])])], keywords=[Keyword(id=1322941073491898536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, orderNo=1, keyword=avalanche rockfall), Keyword(id=1322941073579978921, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, orderNo=2, keyword=seismic monitoring), Keyword(id=1322941073672253610, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, orderNo=3, keyword=machine learning), Keyword(id=1322941073739362475, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, orderNo=4, keyword=early warning), Keyword(id=1322941073802277036, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, orderNo=1, keyword=崩塌落石), Keyword(id=1322941073873580205, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, orderNo=2, keyword=微震监测), Keyword(id=1322941073932300462, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, orderNo=3, keyword=机器学习), Keyword(id=1322941073991020719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, orderNo=4, keyword=监测预警)], refs=[Reference(id=1322941076092367047, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1007/s11629-018-5286-6, pmid=null, pmcid=null, year=2019, volume=16, issue=5, pageStart=955, pageEnd=970, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=Feng L, Pazzi V, Intrieri E, journalName=Journal of Mountain Science, refType=null, unstructuredReference= Feng L , Pazzi V , Intrieri E , et al. Rockfall Seismic Features Analysis Based on in Situ Tests: Frequency, Amplitude, and Duration[J]. Journal of Mountain Science, 2019, 16 (5): 955- 970, articleTitle=Rockfall Seismic Features Analysis Based on in Situ Tests: Frequency, Amplitude, and Duration, refAbstract=null), Reference(id=1322941077698785480, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1126/science.abj1227, pmid=null, pmcid=null, year=2021, volume=374, issue=6563, pageStart=87, pageEnd=92, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=Cook K L, Rekapalli R, Dietze M, journalName=Science, refType=null, unstructuredReference= Cook K L , Rekapalli R , Dietze M , et al. Detection and Potential Early Warning of Catastrophic Flow Events with Regional Seismic Networks[J]. Science, 2021, 374 (6563): 87- 92, articleTitle=Detection and Potential Early Warning of Catastrophic Flow Events with Regional Seismic Networks, refAbstract=null), Reference(id=1322941077778477257, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2021, volume=411, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=Falcin A, Métaxian J P, Mars J, journalName=Journal of Volcanology and Geothermal Research, refType=null, unstructuredReference= Falcin A , Métaxian J P , Mars J , et al. A Machine-Learning Approach for Automatic Classification of Volcanic Seismicity at La Soufrière Volcano, Guadeloupe[J]. Journal of Volcanology and Geothermal Research, 2021, 411, articleTitle=A Machine-Learning Approach for Automatic Classification of Volcanic Seismicity at La Soufrière Volcano, Guadeloupe, refAbstract=null), Reference(id=1322941077837197514, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1016/j.cageo.2015.04.007, pmid=null, pmcid=null, year=2015, volume=81, issue=null, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=Goetz J N, Brenning A, Petschko H, journalName=Computers and Geosciences, refType=null, unstructuredReference= Goetz J N , Brenning A , Petschko H , et al. Evaluating Machine Learning and Statistical Prediction Techniques for Landslide Susceptibility Modeling[J]. Computers and Geosciences, 2015, 81, 1- 11, articleTitle=Evaluating Machine Learning and Statistical Prediction Techniques for Landslide Susceptibility Modeling, refAbstract=null), Reference(id=1322941077916889291, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.5194/esurf-5-283-2017, pmid=null, pmcid=null, year=2017, volume=5, issue=2, pageStart=283, pageEnd=292, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=Hibert C, Malet J P, Bourrier F, journalName=Earth Surface Dynamics, refType=null, unstructuredReference= Hibert C , Malet J P , Bourrier F , et al. Single-Block Rockfall Dynamics Inferred from Seismic Signal Analysis[J]. Earth Surface Dynamics, 2017, 5 (2): 283- 292, articleTitle=Single-Block Rockfall Dynamics Inferred from Seismic Signal Analysis, refAbstract=null), Reference(id=1322941077996581068, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1002/2016GL070709, pmid=null, pmcid=null, year=2017, volume=44, issue=1, pageStart=113, pageEnd=120, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=Provost F, Hibert C, Malet J P, journalName=Geophysical Research Letters, refType=null, unstructuredReference= Provost F , Hibert C , Malet J P . Automatic Classification of Endogenous Landslide Seismicity Using the Random Forest Supervised Classifier[J]. Geophysical Research Letters, 2017, 44 (1): 113- 120, articleTitle=Automatic Classification of Endogenous Landslide Seismicity Using the Random Forest Supervised Classifier, refAbstract=null), Reference(id=1322941078063689933, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1007/s11069-021-04823-5, pmid=null, pmcid=null, year=2021, volume=108, issue=3, pageStart=3271, pageEnd=3304, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=Nath S K, Sengupta A, Srivastava A, journalName=Natural Hazards, refType=null, unstructuredReference= Nath S K , Sengupta A , Srivastava A . Remote Sensing GIS-Based Landslide Susceptibility and Risk Modeling in Darjeeling-Sikkim Himalaya Together with FEM-Based Slope Stability Analysis of the Terrain[J]. Natural Hazards, 2021, 108 (3): 3271- 3304, articleTitle=Remote Sensing GIS-Based Landslide Susceptibility and Risk Modeling in Darjeeling-Sikkim Himalaya Together with FEM-Based Slope Stability Analysis of the Terrain, refAbstract=null), Reference(id=1322941078130798798, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.5194/nhess-21-339-2021, pmid=null, pmcid=null, year=2021, volume=21, issue=1, pageStart=339, pageEnd=361, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=Wenner M, Hibert C, van Herwijnen A, journalName=Natural Hazards and Earth System Sciences, refType=null, unstructuredReference= Wenner M , Hibert C , van Herwijnen A , et al. Near-Real-Time Automated Classification of Seismic Signals of Slope Failures with Continuous Random Forests[J]. Natural Hazards and Earth System Sciences, 2021, 21 (1): 339- 361, articleTitle=Near-Real-Time Automated Classification of Seismic Signals of Slope Failures with Continuous Random Forests, refAbstract=null), Reference(id=1322941078197907663, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2021, volume=48, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=Chmiel M, Walter F, Wenner M, journalName=Geophysical Research Letters, refType=null, unstructuredReference= Chmiel M , Walter F , Wenner M , et al. Machine Learning Improves Debris Flow Warning[J]. Geophysical Research Letters, 2021, 48 (3), articleTitle=Machine Learning Improves Debris Flow Warning, refAbstract=null), Reference(id=1322941078256627920, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2018, volume=33, issue=5, pageStart=1844, pageEnd=1853, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=杨德贺, 王秀英, 申旭辉, journalName=地球物理学进展, refType=null, unstructuredReference=杨德贺, 王秀英, 申旭辉, 等. 基于自编码网络的浅源和深源诱发型微震识别[J]. 地球物理学进展, 2018, 33 (5): 1844- 1853, articleTitle=基于自编码网络的浅源和深源诱发型微震识别, refAbstract=null), Reference(id=1322941078332125393, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2018, volume=33, issue=5, pageStart=1844, pageEnd=1853, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=Yang Dehe, Wang Xiuying, Shen Xuhui, journalName=null, refType=null, unstructuredReference= Yang Dehe , Wang Xiuying , Shen Xuhui , et al. Discrimination of Shallow and Deep Induced-Microearthquakes Based on Autoencoder Network[J]. Progress in Geophysics, 2018, 33 (5): 1844- 1853, articleTitle=null, refAbstract=null), Reference(id=1322941078390845650, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2016, volume=16, issue=6, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=Antolini F, Barla M, Gigli G, journalName=International Journal of Geomechanics, refType=null, unstructuredReference= Antolini F , Barla M , Gigli G , et al. Combined Finite-Discrete Numerical Modeling of Runout of the Torgiovannetto Di Assisi Rockslide in Central Italy[J]. International Journal of Geomechanics, 2016, 16 (6), articleTitle=Combined Finite-Discrete Numerical Modeling of Runout of the Torgiovannetto Di Assisi Rockslide in Central Italy, refAbstract=null), Reference(id=1322941078512480467, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2012, volume=147, issue=null, pageStart=124, pageEnd=136, url=null, language=null, rfNumber=12, rfOrder=12, authorNames=Intrieri E, Gigli G, Mugnai F, journalName=Engineering Geology, refType=null, unstructuredReference= Intrieri E , Gigli G , Mugnai F , et al. Design and Implementation of a Landslide Early Warning System[J]. Engineering Geology, 2012, 147, 124- 136, articleTitle=Design and Implementation of a Landslide Early Warning System, refAbstract=null), Reference(id=1322941080437666004, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1007/s11629-014-3164-4, pmid=null, pmcid=null, year=2014, volume=11, issue=6, pageStart=1521, pageEnd=1530, url=null, language=null, rfNumber=13, rfOrder=13, authorNames=Gigli G, Intrieri E, Lombardi L, journalName=Journal of Mountain Science, refType=null, unstructuredReference= Gigli G , Intrieri E , Lombardi L , et al. Event Scenario Analysis for the Design of Rockslide Countermeasures[J]. Journal of Mountain Science, 2014, 11 (6): 1521- 1530, articleTitle=Event Scenario Analysis for the Design of Rockslide Countermeasures, refAbstract=null), Reference(id=1322941082106998997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=10.1093/gji/ggaa287, pmid=null, pmcid=null, year=2020, volume=222, issue=3, pageStart=2108, pageEnd=2120, url=null, language=null, rfNumber=14, rfOrder=14, authorNames=Feng L, Pazzi V, Intrieri E, journalName=Geophysical Journal International, refType=null, unstructuredReference= Feng L , Pazzi V , Intrieri E , et al. Joint Detection and Classification of Rockfalls in a Microseismic Monitoring Network[J]. Geophysical Journal International, 2020, 222 (3): 2108- 2120, articleTitle=Joint Detection and Classification of Rockfalls in a Microseismic Monitoring Network, refAbstract=null), Reference(id=1322941082199273686, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=2, pageStart=545, pageEnd=564, url=null, language=null, rfNumber=15, rfOrder=15, authorNames=冯亮, 张振, journalName=工程地质学, refType=null, unstructuredReference=冯亮, 张振. 微震技术在崩塌落石监测预警应用的研究进展[J]. 工程地质学, 2024, 32 (2): 545- 564, articleTitle=微震技术在崩塌落石监测预警应用的研究进展, refAbstract=null), Reference(id=1322941082287354071, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=2, pageStart=545, pageEnd=564, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=Feng Liang, Zhang Zhen, journalName=null, refType=null, unstructuredReference= Feng Liang , Zhang Zhen . Seismic Monitoring in Rockfall: A Literature Review[J]. Journal of Engineering Geology, 2024, 32 (2): 545- 564, articleTitle=null, refAbstract=null), Reference(id=1322941082388017368, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=1998, volume=41, issue=8, pageStart=16, pageEnd=20, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=Trnkoczy A, journalName=Application Note, refType=null, unstructuredReference= Trnkoczy A . Understanding and Setting STA/LTA Trigger Algorithm Parameters for the K2[J]. Application Note, 1998, 41 (8): 16- 20, articleTitle=Understanding and Setting STA/LTA Trigger Algorithm Parameters for the K2, refAbstract=null), Reference(id=1322941082476097753, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Cortes G, Arambula R, Gutierrez L, et al. Evaluating Robustness of a HMM-Based Classification System of Volcano-Seismic Events at Colima and Popocatepetl Volcanoes[C]. 2009 IEEE International Geoscience and Remote Sensing Symposium, Cape Town, 2009, articleTitle=null, refAbstract=null), Reference(id=1322941082547400922, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2012, volume=102, issue=3, pageStart=948, pageEnd=960, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=Hammer C, Beyreuther M, Ohrnberger M, journalName=The Bulletin of the Seismological Society of America, refType=null, unstructuredReference= Hammer C , Beyreuther M , Ohrnberger M . A Seismic-Event Spotting System for Volcano Fast-Response Systems[J]. The Bulletin of the Seismological Society of America, 2012, 102 (3): 948- 960, articleTitle=A Seismic-Event Spotting System for Volcano Fast-Response Systems, refAbstract=null), Reference(id=1322941082635481307, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=1996, volume=13, issue=3, pageStart=205, pageEnd=228, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=Falsaperla S, Graziani S, Nunnari G, journalName=Natural Hazards, refType=null, unstructuredReference= Falsaperla S , Graziani S , Nunnari G , et al. Automatic Classification of Volcanic Earthquakes by Using Multi-Layered Neural Networks[J]. Natural Hazards, 1996, 13 (3): 205- 228, articleTitle=Automatic Classification of Volcanic Earthquakes by Using Multi-Layered Neural Networks, refAbstract=null), Reference(id=1322941082710978780, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2017, volume=3, issue=9, pageStart=715, pageEnd=726, url=null, language=null, rfNumber=20, rfOrder=21, authorNames=Barari M, Hosseini M, journalName=Civil Engineering Journal, refType=null, unstructuredReference= Barari M , Hosseini M . A Modern Method to Improve of Detecting and Categorizing Mechanism for Micro Seismic Events Data Using Boost Learning System[J]. Civil Engineering Journal, 2017, 3 (9): 715- 726, articleTitle=A Modern Method to Improve of Detecting and Categorizing Mechanism for Micro Seismic Events Data Using Boost Learning System, refAbstract=null), Reference(id=1322941082778087645, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2011, volume=12, issue=null, pageStart=2825, pageEnd=2830, url=null, language=null, rfNumber=21, rfOrder=22, authorNames=Pedregosa F, Varoquaux G, Gramfort A, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference= Pedregosa F , Varoquaux G , Gramfort A , et al. Scikit-Learn: Machine Learning in Python[J]. Journal of Machine Learning Research, 2011, 12, 2825- 2830, articleTitle=Scikit-Learn: Machine Learning in Python, refAbstract=null), Reference(id=1322941082849390814, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2014, volume=15, issue=1, pageStart=3133, pageEnd=3181, url=null, language=null, rfNumber=22, rfOrder=23, authorNames=Murphy K, Schölkopf B, Fernández-Delgado M, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference= Murphy K , Schölkopf B , Fernández-Delgado M , et al. Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?[J]. Journal of Machine Learning Research, 2014, 15 (1): 3133- 3181, articleTitle=Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?, refAbstract=null), Reference(id=1322941082916499679, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=1, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=23, rfOrder=24, authorNames=Breiman L, journalName=Machine Learning, refType=null, unstructuredReference= Breiman L . Random Forests[J]. Machine Learning, 2001, 45 (1): 5- 32, articleTitle=Random Forests, refAbstract=null), Reference(id=1322941082991997152, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2016, volume=17, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=25, authorNames=Huang B F, Boutros P C, journalName=BMC Bioinformatics, refType=null, unstructuredReference= Huang B F , Boutros P C . The Parameter Sensitivity of Random Forests[J]. BMC Bioinformatics, 2016, 17 (1), articleTitle=The Parameter Sensitivity of Random Forests, refAbstract=null), Reference(id=1322941083080077537, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Snoek J, Larochelle H, Adams R P, et al. Practical Bayesian Optimization of Machine Learning Algorithms[C]. Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 2012, articleTitle=null, refAbstract=null), Reference(id=1322941083159769314, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=10, pageStart=154, pageEnd=157, url=null, language=null, rfNumber=26, rfOrder=27, authorNames=温博文, 董文瀚, 解武杰, journalName=计算机工程与应用, refType=null, unstructuredReference=温博文, 董文瀚, 解武杰, 等. 基于改进网格搜索算法的随机森林参数优化[J]. 计算机工程与应用, 2018, 54 (10): 154- 157, articleTitle=基于改进网格搜索算法的随机森林参数优化, refAbstract=null), Reference(id=1322941083252044003, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=10, pageStart=154, pageEnd=157, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=Wen Bowen, Dong Wenhan, Xie Wujie, journalName=null, refType=null, unstructuredReference= Wen Bowen , Dong Wenhan , Xie Wujie , et al. Parameter Optimization Method for Random Forest Based on Improved Grid Search Algorithm[J]. Computer Engineering and Applications, 2018, 54 (10): 154- 157, articleTitle=null, refAbstract=null), Reference(id=1322941083344318692, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=1960, volume=20, issue=1, pageStart=37, pageEnd=46, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=Cohen J, journalName=Educational and Psychological Measurement, refType=null, unstructuredReference= Cohen J . A Coefficient of Agreement for Nominal Scales[J]. Educational and Psychological Measurement, 1960, 20 (1): 37- 46, articleTitle=A Coefficient of Agreement for Nominal Scales, refAbstract=null), Reference(id=1322941083432399077, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=1997, volume=97, issue=1-2, pageStart=273, pageEnd=324, url=null, language=null, rfNumber=28, rfOrder=30, authorNames=Kohavi R, John G H, journalName=Artificial Intelligence, refType=null, unstructuredReference= Kohavi R , John G H . Wrappers for Feature Subset Selection[J]. Artificial Intelligence, 1997, 97 (1-2): 273- 324, articleTitle=Wrappers for Feature Subset Selection, refAbstract=null), Reference(id=1322941083512090854, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, doi=null, pmid=null, pmcid=null, year=2011, volume=1, issue=1, pageStart=14, pageEnd=23, url=null, language=null, rfNumber=29, rfOrder=31, authorNames=Loh W Y, journalName=WIREs Data Mining and Knowledge Discovery, refType=null, unstructuredReference= Loh W Y . Classification and Regression Trees[J]. WIREs Data Mining and Knowledge Discovery, 2011, 1 (1): 14- 23, articleTitle=Classification and Regression Trees, refAbstract=null)], funds=[Fund(id=1322941075408695486, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=3JH-202401050, language=EN, fundingSource=Combination Project with Monitoring, Prediction and Scientific Research of Earthquake Technology, CEA(3JH-202401050), fundOrder=null, country=null), Fund(id=1322941075526135999, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=3JH-202401050, language=CN, fundingSource=中国地震局“三结合”课题(3JH-202401050), fundOrder=null, country=null), Fund(id=1322941075605827776, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=4210071309, language=EN, fundingSource=National Natural Science Foundation of China(4210071309), fundOrder=null, country=null), Fund(id=1322941075677130945, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=4210071309, language=CN, fundingSource=国家自然科学基金(4210071309), fundOrder=null, country=null), Fund(id=1322941075752628418, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=FD2111-202404, language=EN, fundingSource="2111" Incubation Fund of Jiangxi Earthquake Agency(FD2111-202404), fundOrder=null, country=null), Fund(id=1322941075811348675, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=FD2111-202404, language=CN, fundingSource=江西省地震局“2111”孵化基金(FD2111-202404), fundOrder=null, country=null), Fund(id=1322941075878457540, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=20224BAB203040, language=EN, fundingSource=Natural Science Foundation of Jiangxi Province(20224BAB203040), fundOrder=null, country=null), Fund(id=1322941075991703750, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, awardId=20224BAB203040, language=CN, fundingSource=江西省自然科学基金(20224BAB203040), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322941070107095170, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070115483779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070123872388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000)]), AuthorCompany(id=1322941070186786949, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070195175558, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China), AuthorCompanyExt(id=1322941070203564167, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128)]), AuthorCompany(id=1322941070258090120, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070266478729, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China), AuthorCompanyExt(id=1322941070274867338, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041)]), AuthorCompany(id=1322941070333587595, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070341976204, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China), AuthorCompanyExt(id=1322941070350364813, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 中国科学院大学, 北京市玉泉路19号, 100049)]), AuthorCompany(id=1322941070434250894, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070442639503, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070451028112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000)])], figs=[ArticleFig(id=1322941074112655536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Fig. 1, caption=Seismic signal of rockfall in rockfall artificial released test, figureFileSmall=ufaoILrkyYXim7DiQUyTGA==, figureFileBig=W7XmpGWm1NGWN2HljfXEkw==, tableContent=null), ArticleFig(id=1322941074196541617, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=图1, caption=人工投石实验微震标准落石信号, figureFileSmall=ufaoILrkyYXim7DiQUyTGA==, figureFileBig=W7XmpGWm1NGWN2HljfXEkw==, tableContent=null), ArticleFig(id=1322941074418839730, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Fig. 2, caption=The results of classification, figureFileSmall=eQokqN1JvduPVJQ4odr+ww==, figureFileBig=tecXyiDCvzwELnrbbx24QQ==, tableContent=null), ArticleFig(id=1322941074485948595, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=图2, caption=微震事件分类结果, figureFileSmall=eQokqN1JvduPVJQ4odr+ww==, figureFileBig=tecXyiDCvzwELnrbbx24QQ==, tableContent=null), ArticleFig(id=1322941074561446068, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Fig. 3, caption=Confusion matrix of random forest model after grid search optimization, figureFileSmall=ZZl8sCCqyZWbbaE6zq8VQQ==, figureFileBig=iutTRlMhOTQEKU9PTDwi3w==, tableContent=null), ArticleFig(id=1322941074641137845, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=图3, caption=网格搜索优化后的随机森林模型的混淆矩阵, figureFileSmall=ZZl8sCCqyZWbbaE6zq8VQQ==, figureFileBig=iutTRlMhOTQEKU9PTDwi3w==, tableContent=null), ArticleFig(id=1322941074725023926, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Fig. 4, caption=Weight of feature parameters in the classification model(average value of 100 training sessions), figureFileSmall=kV03PID2BRTWqvoE40WInw==, figureFileBig=EEpZgAprS3ZLZSQJKJtuwA==, tableContent=null), ArticleFig(id=1322941074783744183, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=图4, caption=特征参数在分类模型中的权重(100次训练平均值), figureFileSmall=kV03PID2BRTWqvoE40WInw==, figureFileBig=EEpZgAprS3ZLZSQJKJtuwA==, tableContent=null), ArticleFig(id=1322941074850853048, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Fig. 5, caption=Average classification accuracy under 100 training sessions with different sample sizes, figureFileSmall=fM5HTjqFlPUDFTP1nQymTQ==, figureFileBig=PGoPxxzhANt+FC/8Mi/Frg==, tableContent=null), ArticleFig(id=1322941074922156217, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=图5, caption=训练100次不同样本量情况下平均分类准确率, figureFileSmall=fM5HTjqFlPUDFTP1nQymTQ==, figureFileBig=PGoPxxzhANt+FC/8Mi/Frg==, tableContent=null), ArticleFig(id=1322941075022819514, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Tab. 1, caption=

Selection and calculation of characteristic parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 描述 公式或代码实现 来源
时域 1 持续时间 ts-tf,ts和tf分别为开始和结束时间 参考文献[6]
2 最大振幅 max(xi) 参考文献[6]
3 相对微震能量 $\int_0^T x_i^2$,T为持续时间 本文
4 相对微震能量与最大振幅的比值 - 本文
5 波峰数量 - 参考文献[6]
6 均峰比 $\frac{\operatorname{Mean}\left(\operatorname{abs}\left(x_i\right)\right)}{\operatorname{Max}\left(\operatorname{abs}\left(x_i\right)\right)}$ 参考文献[6]
7 包络线中值与最大值信号之比 $\frac{\operatorname{Median}\left(\operatorname{abs}\left(x_i\right)\right)}{\operatorname{Max}\left({abs}\left(x_i\right)\right)}$ 参考文献[6]
8 升序和降序时间之比 $\frac{t_{\max }-t_s}{t_{\max }-t_f}$, tmax为最大振幅的时间 参考文献[6]
9 原始信号峰度 Kurtosis(xi), Kurtosis为峰度函数 参考文献[6]
10 原始信号偏度 Skewness(xi), Skewness为偏度函数 参考文献[6]
11 包络线峰度 Kurtosis(xi_rolling), xi_rolling为滑窗均值构造包络线 参考文献[6]
12 包络线偏度 Skewness(xi_rolling) 参考文献[6]
13 自相关函数前1/3能量 $\int_0^{T / 3} C\left(x_i\right)$, C为自相关函数 参考文献[6]
14 自相关函数剩余能量 $\int_{T / 3}^T C\left(x_i\right)$ 参考文献[6]
15 13和14的比值 - 参考文献[6]
16 自相关函数波峰 findpeaks(C(xi))或自编代码,findpeaks为MATLAB中波峰函数 参考文献[6]
17 信号的能量以5~10 Hz的频率过滤 $\int_0^T y_i^2, y_i$为在频率范围内滤波后的信号 参考文献[6]
18 5~10 Hz过滤信号峰度 Kurtosis(yi) 参考文献[6]
19 信号的能量以10~50 Hz的频率过滤 见参数17 参考文献[6]
20 10~50 Hz过滤信号峰度 见参数18 参考文献[6]
21 信号的能量以5~70 Hz的频率过滤 见参数17 参考文献[6]
22 5~70 Hz过滤信号峰度 见参数18 参考文献[6]
23 信号的能量以50~100 Hz的频率过滤 见参数17 参考文献[6]
24 50~100 Hz过滤信号峰度 见参数18 参考文献[6]
25 信号的能量以5~100 Hz的频率过滤 见参数17 参考文献[6]
26 5~100 Hz过滤信号峰度 见参数18 参考文献[6]
27 信号递减部分与频谱特征的均方根值 $\sqrt{\overline{Y(t)-I(t)^2}}, Y$为包络线信号 参考文献[6]
28 最大频率 argmax(FFTAi), FFTA为傅里叶变换系数 参考文献[5]
29 DFT平均值 mean(data_DFT),data_DFT = abs(fft(Zdata)) 参考文献[5]
30 DFT最大值 max(data_DFT) 参考文献[5]
31 标准化DFT的中值 median(normal_DFT),normal_DFT为DFT标准化 参考文献[5]
32 标准化DFT的方差 var(normal_DFT), var为方差 参考文献[5]
33 DFT 0~1/4的能量 $\int_{f_1}^{f_2} \operatorname{DFT}(f) \mathrm{d} f, f_1、f_2$为频率范围 参考文献[5]
34 DFT 1/4~1/2的能量 见参数33 参考文献[5]
35 DFT 1/2~3/4的能量 见参数33 参考文献[5]
36 DFT 3/4~1的能量 见参数33 参考文献[5]
时频域 37 自相关函数波峰数 size(findpeaks(DFT_auto), 2),DFT_auto为DFT自相关 参考文献[8]
38 DFT作时间的函数 $\text { Kurtosis }\left[\max\limits _{t=0, \cdots, T}(\operatorname{SPEC}(t, f))\right], \operatorname{SPEC}(t, f)$为光谱图 参考文献[8]
39 DFT峰值数量 size(findpeaks(abs(max(cwtmatr))), 2) 参考文献[8]
40 DFT均值数量 见参数39 参考文献[8]
41 DFT中值数量 见参数39 参考文献[8]
42 39和40的比值 - 参考文献[8]
43 39和41的比值 - 参考文献[8]
44 DFT的最大值与中值之间的平均比值 mean(dfts_max/dfts_median) 参考文献[8]
45 DFT的中值和第1个四分位数之间的平均距离作为时间的函数 mean(quartile(2)-quartile(1)),quartile=prctile(dfts_median, [25 50 75]), Prctile为计算百分位数参考文献[8]
46 DFT的第3个四分位数和第1个四分位数之间的平均距离作为时间的函数 见参数45 参考文献[8]
47 DFT的第3个四分位数和中值之间的平均距离作为时间的函数 见参数45 参考文献[8]
多基站网络 48 振幅比 参数2在不同基站的比值 参考文献[14]
49 频率比 参数28在不同基站的比值 参考文献[14]
), ArticleFig(id=1322941075127677115, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=表1, caption=

特征参数选取及计算

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 描述 公式或代码实现 来源
时域 1 持续时间 ts-tf,ts和tf分别为开始和结束时间 参考文献[6]
2 最大振幅 max(xi) 参考文献[6]
3 相对微震能量 $\int_0^T x_i^2$,T为持续时间 本文
4 相对微震能量与最大振幅的比值 - 本文
5 波峰数量 - 参考文献[6]
6 均峰比 $\frac{\operatorname{Mean}\left(\operatorname{abs}\left(x_i\right)\right)}{\operatorname{Max}\left(\operatorname{abs}\left(x_i\right)\right)}$ 参考文献[6]
7 包络线中值与最大值信号之比 $\frac{\operatorname{Median}\left(\operatorname{abs}\left(x_i\right)\right)}{\operatorname{Max}\left({abs}\left(x_i\right)\right)}$ 参考文献[6]
8 升序和降序时间之比 $\frac{t_{\max }-t_s}{t_{\max }-t_f}$, tmax为最大振幅的时间 参考文献[6]
9 原始信号峰度 Kurtosis(xi), Kurtosis为峰度函数 参考文献[6]
10 原始信号偏度 Skewness(xi), Skewness为偏度函数 参考文献[6]
11 包络线峰度 Kurtosis(xi_rolling), xi_rolling为滑窗均值构造包络线 参考文献[6]
12 包络线偏度 Skewness(xi_rolling) 参考文献[6]
13 自相关函数前1/3能量 $\int_0^{T / 3} C\left(x_i\right)$, C为自相关函数 参考文献[6]
14 自相关函数剩余能量 $\int_{T / 3}^T C\left(x_i\right)$ 参考文献[6]
15 13和14的比值 - 参考文献[6]
16 自相关函数波峰 findpeaks(C(xi))或自编代码,findpeaks为MATLAB中波峰函数 参考文献[6]
17 信号的能量以5~10 Hz的频率过滤 $\int_0^T y_i^2, y_i$为在频率范围内滤波后的信号 参考文献[6]
18 5~10 Hz过滤信号峰度 Kurtosis(yi) 参考文献[6]
19 信号的能量以10~50 Hz的频率过滤 见参数17 参考文献[6]
20 10~50 Hz过滤信号峰度 见参数18 参考文献[6]
21 信号的能量以5~70 Hz的频率过滤 见参数17 参考文献[6]
22 5~70 Hz过滤信号峰度 见参数18 参考文献[6]
23 信号的能量以50~100 Hz的频率过滤 见参数17 参考文献[6]
24 50~100 Hz过滤信号峰度 见参数18 参考文献[6]
25 信号的能量以5~100 Hz的频率过滤 见参数17 参考文献[6]
26 5~100 Hz过滤信号峰度 见参数18 参考文献[6]
27 信号递减部分与频谱特征的均方根值 $\sqrt{\overline{Y(t)-I(t)^2}}, Y$为包络线信号 参考文献[6]
28 最大频率 argmax(FFTAi), FFTA为傅里叶变换系数 参考文献[5]
29 DFT平均值 mean(data_DFT),data_DFT = abs(fft(Zdata)) 参考文献[5]
30 DFT最大值 max(data_DFT) 参考文献[5]
31 标准化DFT的中值 median(normal_DFT),normal_DFT为DFT标准化 参考文献[5]
32 标准化DFT的方差 var(normal_DFT), var为方差 参考文献[5]
33 DFT 0~1/4的能量 $\int_{f_1}^{f_2} \operatorname{DFT}(f) \mathrm{d} f, f_1、f_2$为频率范围 参考文献[5]
34 DFT 1/4~1/2的能量 见参数33 参考文献[5]
35 DFT 1/2~3/4的能量 见参数33 参考文献[5]
36 DFT 3/4~1的能量 见参数33 参考文献[5]
时频域 37 自相关函数波峰数 size(findpeaks(DFT_auto), 2),DFT_auto为DFT自相关 参考文献[8]
38 DFT作时间的函数 $\text { Kurtosis }\left[\max\limits _{t=0, \cdots, T}(\operatorname{SPEC}(t, f))\right], \operatorname{SPEC}(t, f)$为光谱图 参考文献[8]
39 DFT峰值数量 size(findpeaks(abs(max(cwtmatr))), 2) 参考文献[8]
40 DFT均值数量 见参数39 参考文献[8]
41 DFT中值数量 见参数39 参考文献[8]
42 39和40的比值 - 参考文献[8]
43 39和41的比值 - 参考文献[8]
44 DFT的最大值与中值之间的平均比值 mean(dfts_max/dfts_median) 参考文献[8]
45 DFT的中值和第1个四分位数之间的平均距离作为时间的函数 mean(quartile(2)-quartile(1)),quartile=prctile(dfts_median, [25 50 75]), Prctile为计算百分位数参考文献[8]
46 DFT的第3个四分位数和第1个四分位数之间的平均距离作为时间的函数 见参数45 参考文献[8]
47 DFT的第3个四分位数和中值之间的平均距离作为时间的函数 见参数45 参考文献[8]
多基站网络 48 振幅比 参数2在不同基站的比值 参考文献[14]
49 频率比 参数28在不同基站的比值 参考文献[14]
), ArticleFig(id=1322941075224146108, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=EN, label=Tab. 2, caption=

Parameter optimization analysis results of random forest mode

, figureFileSmall=null, figureFileBig=null, tableContent=
参数介绍 调优范围 最优选择
n_estimators RF中决策树的个数 range(1, 100, 1) 50
max_depth 决策树的最大深度 range(1, 100, 1) 9
min_samples_leaf 叶子节点最少样本数 range(1, 100, 1) 1
min_samples_split 内部节点再划分所需最小样本数 range(1, 100, 1) 3
max_features RF划分时考虑的最大特征数 range(1, 100, 1) 11
criterion 度量分裂质量的方法 [‘gini’, ‘entropy’] gini
), ArticleFig(id=1322941075303837885, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, language=CN, label=表2, caption=

随机森林模型参数优化分析结果

, figureFileSmall=null, figureFileBig=null, tableContent=
参数介绍 调优范围 最优选择
n_estimators RF中决策树的个数 range(1, 100, 1) 50
max_depth 决策树的最大深度 range(1, 100, 1) 9
min_samples_leaf 叶子节点最少样本数 range(1, 100, 1) 1
min_samples_split 内部节点再划分所需最小样本数 range(1, 100, 1) 3
max_features RF划分时考虑的最大特征数 range(1, 100, 1) 11
criterion 度量分裂质量的方法 [‘gini’, ‘entropy’] gini
)], attaches=null, journal=Journal(id=1281211523964080133, delFlag=0, nameCn=大地测量与地球动力学, nameEn=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, issn=1671-5942, eissn=null, cn=42-1655/P, coden=null, periodic=0, 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=BeWo6OWOseISH6uPOmc2hA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geodesy and Geodynamics, journalRemark=null, publicationField=null, createdTime=1783394231074, updatedTime=1788951966472, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=BeWo6OWOseISH6uPOmc2hA==, picEn=YHLfVa8gITbOo0FeIjbLDg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522356412666698, language=CN, name=大地测量与地球动力学, 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=1788951966622, updatedTime=1788951966622, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522356576244555, language=EN, name=Journal of Geodesy and Geodynamics, 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=1788951966661, updatedTime=1788951966661, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1281212831689347082, websiteList=[Website(id=1281216327125799907, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/CN, language=CN, createTime=1783395376235, createBy=18614031015, updateTime=1783395439358, updateBy=18614031015, name=大地测量与地球动力学-中文, tplId=1146099689490845704, title=大地测量与地球动力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216715371548758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=articleTextType, value=kx, createTime=1783395468800, updateTime=1783395468800, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715346382931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=banner, value=null, createTime=1783395468794, updateTime=1783395468794, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715400908889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=grayFlag, value=0, createTime=1783395468807, updateTime=1783395468807, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715333800018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395468791, updateTime=1783395468791, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715421880411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=minRunFlag, value=0, createTime=1783395468812, updateTime=1783395468812, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715363160149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic, createTime=1783395468798, updateTime=1783395468798, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715409297498, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=silenceFlag, value=0, createTime=1783395468809, updateTime=1783395468809, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715358965844, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1783395468797, updateTime=1783395468797, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715384131671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeColor, value=null, createTime=1783395468803, updateTime=1783395468803, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715392520280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeStyle, value=null, createTime=1783395468805, updateTime=1783395468805, creator=18614031015, updator=18614031015)]), Website(id=1281216327713002474, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/EN, language=EN, createTime=1783395376375, createBy=18614031015, updateTime=1783395435863, updateBy=18614031015, name=大地测量与地球动力学-英文, tplId=1146101810881728533, title=Journal of Geodesy and Geodynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216680483328066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=articleTextType, value=kx, createTime=1783395460482, updateTime=1783395460483, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680453967935, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=banner, value=null, createTime=1783395460475, updateTime=1783395460475, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680521076805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=grayFlag, value=0, createTime=1783395460491, updateTime=1783395460491, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680437190718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395460471, updateTime=1783395460471, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680542048327, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=minRunFlag, value=0, createTime=1783395460496, updateTime=1783395460496, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680474939457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic, createTime=1783395460480, updateTime=1783395460480, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680533659718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=silenceFlag, value=0, createTime=1783395460494, updateTime=1783395460494, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680462356544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1783395460477, updateTime=1783395460477, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680495910979, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeColor, value=null, createTime=1783395460485, updateTime=1783395460485, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680508493892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeStyle, value=null, createTime=1783395460488, updateTime=1783395460488, creator=18614031015, updator=18614031015)])], journalTitle=大地测量与地球动力学, weixinUrl=null, journalUrl=http://www.jgg09.com/CN/home, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geodesy and Geodynamics, journalPhotoCn=BeWo6OWOseISH6uPOmc2hA==, journalPhotoEn=YHLfVa8gITbOo0FeIjbLDg==, journalFirstLetter=D, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.08.369, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.08.369, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2024.08.369, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2024.08.369, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1749916800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
机器学习实现崩塌落石微震信号自动化检测和分类
收藏切换
谢斌 1 , 高桂山 2 , 黄志勇 3, 4 , 冯亮 5, *
大地测量与地球动力学 | 观测技术 2025,45(6): 654-660
收起
收藏切换
大地测量与地球动力学 |观测技术 2025 , 45 (6) : 654 -660
机器学习实现崩塌落石微震信号自动化检测和分类
全屏
[Author(id=1322941070522331282, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=309479810@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322941070610411668, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070522331282, language=EN, stringName=Bin XIE, firstName=Bin, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China, bio={"content":"

XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

"}, bioImg=null, bioContent=

XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941070685909141, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070522331282, language=CN, stringName=谢斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000, bio={"content":"

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

"}, bioImg=null, bioContent=

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070107095170, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070115483779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070123872388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000)])]), Author(id=1322941070916595863, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=1, 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=1322941070992093338, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070916595863, language=EN, stringName=Guishan GAO, firstName=Guishan, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941071063396507, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941070916595863, language=CN, stringName=高桂山, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070186786949, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070195175558, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China), AuthorCompanyExt(id=1322941070203564167, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070186786949, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128)])]), Author(id=1322941071285694621, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, 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=1322941071361192096, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071285694621, language=EN, stringName=Zhiyong HUANG, firstName=Zhiyong, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China
4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941071419912353, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071285694621, language=CN, stringName=黄志勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041
4 中国科学院大学, 北京市玉泉路19号, 100049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070258090120, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070266478729, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China), AuthorCompanyExt(id=1322941070274867338, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070258090120, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041)]), AuthorCompany(id=1322941070333587595, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070341976204, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China), AuthorCompanyExt(id=1322941070350364813, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070333587595, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 中国科学院大学, 北京市玉泉路19号, 100049)])]), Author(id=1322941071721902243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liang.feng@jxust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322941073298960550, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071721902243, language=EN, stringName=Liang FENG, firstName=Liang, middleName=null, lastName=FENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China
1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322941073370263719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, authorId=1322941071721902243, language=CN, stringName=冯亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, *, address=5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000
1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322941070434250894, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070442639503, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070451028112, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070434250894, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000)]), AuthorCompany(id=1322941070107095170, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, xref=null, ext=[AuthorCompanyExt(id=1322941070115483779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China), AuthorCompanyExt(id=1322941070123872388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322941066751651957, companyId=1322941070107095170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000)])])]
谢斌1 , 高桂山2, 黄志勇3, 4, 冯亮5, *
作者信息
  • 1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000
  • 2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128
  • 3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041
  • 4 中国科学院大学, 北京市玉泉路19号, 100049
  • 5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000
通讯作者:

冯亮,博士,副教授,主要从事地质灾害与环境地震学研究,E-mail:

FENG Liang, PhD, associate professor, majors in geological hazards and environmental seismology, E-mail:

作者简介:

谢斌,工程师,主要从事地震监测预报预警相关研究,E-mail:

Machine Learning for Automated Detection and Classification of Microseismic Signals from Avalanche Rockfalls
Bin XIE1 , Guishan GAO2, Zhiyong HUANG3, 4, Liang FENG5, *
Affiliations
  • 1 Ganzhou Earthquake Monitoring Center Station, 55 Helanshan Road, Ganzhou 341000, China
  • 2 Guangdong Dabaoshan Mining Co Ltd, Shaxi Town, Shaoguan 512128, China
  • 3 Institute of Mountain Hazards and Environment, CAS, 189 South-Qunxian Road, Chengdu 610041, China
  • 4 University of Chinese Academy of Sciences, A19 Yuquan Road, Beijing 100049, China
  • 5 College of Sources and Environmental Engineering, Jiangxi University of Science and Technology, 156 Kejia Road, Ganzhou 341000, China
  • XIE Bin, engineer, majors in earthquake monitoring and forecasting early warning, E-mail:

出版时间: 2025-06-15 doi: 10.14075/j.jgg.2024.08.369
文章导航
收藏切换

基于意大利中部佩鲁贾市某大理石矿山微震监测数据和49个微震特征参数,对比分析神经网络、决策树和随机森林3种机器学习模型在微震信号自动化分类中的精度,通过网格搜索算法优化模型参数提高模型性能,讨论特征参数的选择和分类集的大小对分类结果的影响。结果表明,随机森林分类器在微震信号分类中获得的准确度最高,优化后分类准确度为98.11%,同时减少部分权重小的特征参数,分类计算效率大幅提高,准确度下降较少,训练集与测试集的最佳分配比例为8 ∶2。

崩塌落石  /  微震监测  /  机器学习  /  监测预警

In this paper, based on microseismic monitoring data and 49 microseismic feature parameters of a marble mine in Perugia, central Italy, we compare and analyze the accuracy of three machine learning models, namely, neural networks, decision trees and random forests, in the automated classification of microseismic signals, and optimize the model parameters to improve the performance of the model through the grid searcher algorithm, with an emphasis on discussing the effects of the feature parameter selection and the size of the classification set on the classification results. The results show that the random forest classifier obtains the highest accuracy in microseismic signal classification, with 98.11% classification accuracy after optimization, meanwhile, by reducing some of the feature parameters with small weights, the efficiency of the classification computation is greatly improved and the accuracy decreases less, and the optimal allocation ratio of the training set to the test set is 8 ∶2.

avalanche rockfall  /  seismic monitoring  /  machine learning  /  early warning
谢斌, 高桂山, 黄志勇, 冯亮. 机器学习实现崩塌落石微震信号自动化检测和分类. 大地测量与地球动力学, 2025 , 45 (6) : 654 -660 . DOI: 10.14075/j.jgg.2024.08.369
Bin XIE, Guishan GAO, Zhiyong HUANG, Liang FENG. Machine Learning for Automated Detection and Classification of Microseismic Signals from Avalanche Rockfalls[J]. Journal of Geodesy and Geodynamics, 2025 , 45 (6) : 654 -660 . DOI: 10.14075/j.jgg.2024.08.369
微震技术依靠远程无接触、低成本、广覆盖、全天候、高频率和无间断的监测能力,被逐步应用于崩塌落石监测预警[1]及其他地质灾害和人类环境动态监测[2]。近年来,随着微震数据量的快速增长,手动分类[3]显现出较大的局限性,而机器学习算法能帮助我们从庞大的数据库中提取出有价值的信息,为目标动态演变的预测带来很大帮助[4-5]。国内外许多学者针对微震事件的自动分类方法进行了大量研究,取得了很多进展[6-10]。
本文对比分析决策树模型、随机森林模型和神经网络模型在微震信号分类中的应用效果,选用随机森林(RF)分类器作为微震信号的主要分类模型,同时利用MATLAB作为科学计算与编程平台,在时域、频域、时频域和多基站网络4个特征域编写了49个微震信号特征作为自动分类的参数,对意大利某大理石矿山边坡微震监测项目和意大利地震局(INGV)在2012-12-07—18共12 d监测到的信号进行处理,将获得的1 860个准确信号作为训练集,利用随机森林分类器对微震事件进行自动化分类测试,并采用网格搜索算法构建最优随机森林分类模型和最优特征参数。通过基尼指数计算发现,本文提出的新参数在分类模型中贡献占比很大。本文微震事件分类模型可应用于崩塌落石微震监测系统,为相关部门崩塌落石地质灾害监测预警、道路交通管制和应急抢险等提供决策参考。
微震监测及人工投石实验研究区为一处废弃大理石矿山(Torgiovannetto)边坡,位于意大利中部地区佩鲁贾市Subasio山北面。研究区不稳定岩土体位于该矿山的上部区域[11],于2003-05首次被发现,其形成的主要原因为矿山生产活动[12]。在不稳定岩土体发现初期,佛罗伦萨大学地球科学学院应用多种监测手段对潜在滑动体的稳定性进行了多方位长周期连续监测,其中包括伸长位移计、雨量计、地基雷达和微震监测。目前矿山活动已停止,相关部门对潜在滑动岩土体进行了减灾治理[13]。
本文数据来源于佛罗伦萨大学地球科学学院在该区域开展的微震监测实验,微震监测网络由4个三轴速度型检波器(TOR1、TOR2、TOR3和TOR4)组成,并于2012-12—2013-07对不稳定岩土体开展连续监测,期间进行了2次人工投石实验,用于采集微震标准落石信号样本。微震监测网络的布设及传感器分布见参考文献[1],其中3个传感器分布于不稳定岩土体周围,一个传感器安装于不稳定岩土体之上。实验采用的三轴速度型检波器为意大利SARA公司生产的SS45型,自然频率为4.5 Hz,监测过程中采样频率设置为200 Hz。微震监测网络数据格式被保存为miniSEED格式。
人工投石实验分别于2013-06-25和2013-07-04分2次进行,共计从边坡的不同位置制造90次落石事件,所有落石均来自于矿山本身,保持岩性一致。落石的平均密度为2.6 kg/m3,平均单轴抗压强度为120 MPa,落石尺寸从21 cm×20 cm×19 cm到105 cm×58 cm×39 cm均有分布。实验期间共有4架摄像机(2台Canon EOS 600D,1台Canon 660D和1台Nikon D700)进行全角度轨迹录像,所有落石被涂装亮色,以便摄像机定位和识别落石。人工投石微震监测标准信号见图1。时域分析表明,滚动型落石的持续时间更长,振幅相对较小;而频域分析显示,弹跳型落石的频谱范围较宽,为10~60 Hz,滚动型落石频谱范围较窄,为10~40 Hz,主要集中在20 Hz左右。这些事件记录为微震事件分类提供了落石信号的标准样本。地震信号标准样本可查阅意大利国家地震台网地震目录网站。
本文在微震信号的识别中运用了窗口比法,该方法利用长、短窗口在信号时间轴上滑动,遇到微震信号时,短窗口响应快,振幅突然增大,而长窗口依然保持信号背景噪音的振幅,不会产生响应造成窗口比增大的现象,形成事件识别的标志,最终达到微震事件识别的目的[14],具体算法见参考文献[15-16]。
在微震信号识别和分类中,根据微震事件的振幅、频率等频谱特征和震源性质,本文将微震监测网络监测到的微震事件分为4类:微颤(tremor)、地震(earthquake)、落石(rockfall)和噪音(noise),其中微颤的发生主要是由于深源地震和地质构造产生的微弱信号在微震采集过程中交织接收,具有长时间和低震级的特征。
微震信号特征参数是将不同类型微震事件的微震信号特征数值化,转换为可被机器学习算法使用的数学参数。关键特征差异的数值化是成功自动识别微震信号的决定性因素。目前很多参数已经在该领域得到广泛应用,如与微震信号频谱属性相关的特征参数[17]、根据微震波形计算的特征参数、微震信号极化属性[18]及多频带的能量及其比率或自相关函数[19]等,但对于在用于自动识别精确度最高的特征参数组合上还没有达成共识。
本文基于当前被普遍接受的微震信号时域、频域、时频域和多基站网络参数,对微颤、地震、落石及噪音进行自动化分类。采用MATLAB软件将4个特征域编写一套微震特征参数集合,分析RF模型分类效果及选取特征参数对分类效果的影响。所有特征参数为MATLAB自动计算得到,极大提升了大数据自动化分析能力。本文应用特征参数的具体计算公式及文献来源见表1。
本文重点分析微震事件分类预测中常用的神经网络(neural networks)、决策树(DT)和随机森林(RF)[6, 10, 20]3种机器学习模型,通过混淆矩阵与准确率对三者进行对比。神经网络模型采用多层感知器,结合卷积神经网络的结构,由2个卷积层、1个全连接层及输出层组成。与传统的基于原始信号输入的卷积模型不同,本文模型输入的为49个特征参数(表1),并在输入前对其进行标准化处理。
本文采用的49个特征参数是对原始微震信号进行深入分析提取的,直接输入到神经网络中进行学习和分类。决策树模型则采用基于卡方自动交互检测算法,而对于随机森林模型,本文采用python中自带的scikit-learn库[21]进行建模。为防止不同训练集大小对分类准确度的影响,训练集与测试集的比值均采用8 ∶2,最终得出三者准确率分别为93.80%、90.30%与96.77%(图2)。对比发现,随机森林模型的准确率最高,与Murphy等[22]的结果一致。
随机森林算法是Bagging集成方法中最具代表性的学习算法之一,应用简洁,具有收敛性[23]。随机森林模型是一个包含多个决策树的分类器,其分类类别由决策树群中的大多数决定。参数选择是模型拟合的一个关键步骤[24],不同的参数选择直接关系到模型的泛化特性。参数选取的正确性会不可避免地影响随机森林分类算法的计算速度和分类效果。
网格搜索算法是把变量区域网格化,遍历所有网格点,求出满足约束函数的目标函数,最后选取最佳点。Snoek等[25]认为机器学习算法经常需要估计模型参数和超参数,通常采用网格搜索实现。温博文等[26]在对UCI数据库中的11个数据集进行分类时,利用网格搜索算法对随机森林模型进行了参数优化,从而提高了分类效果。本文采用基于OOB(out of bag)误差的网格搜索(grid search)法对RF进行参数寻优(表2)。
在微震事件分类任务中,模型评价是评估模型在测试集上表现的重要环节,能够帮助量化模型的预测能力和泛化性。本文通过混淆矩阵、分类准确率和Kappa系数[27]等多项指标对基于优化的随机森林模型进行评价。
混淆矩阵(confusion matrix)是一种用于可视化分类模型性能的工具,能够直观地显示模型在每个类别上的预测结果。其定义式为:
$\text { ConfusionMatrix }=\left[\begin{array}{ccc}M_{11} & \cdots & M_{14} \\\vdots & \ddots & \vdots \\M_{41} & \cdots & M_{44}\end{array}\right]$
式中,Mij为实际类别为i而被预测为j的样本数量。在多分类问题中,混淆矩阵能够准确描述模型对每类事件的分类表现。
Kappa系数是衡量分类模型整体性能的重要指标,可计算模型预测结果与随机分类结果之间的一致性。其定义如下:
$\text { Kappa }=\frac{p_0-p_e}{1-p_e}$
式中,p0为观察到的分类精度,表示实际预测正确的比例;pe为预期的随机分类精度,表示在随机分类下预测正确的概率。
除了混淆矩阵和Kappa系数外,本文还使用了精确率(precision)指标来评估RF模型的性能,定义为:
$\text { precision }=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FP}}$
式中,TP(true positive)表示某一类事件被正确分类为该类事件的样本数;FP(false positive)表示某一类事件被错误预测为其他类的样本数。
基于优化的RF模型,本文采用混淆矩阵和Kappa系数对模型的微震事件分类精度进行评估。对于本文所采用的优化后的RF模型,Kappa系数达到0.89,表明模型预测结果与实际分类结果之间具有较高的一致性。同时,混淆矩阵分类结果(图3)表明,基于网格搜索优化后的RF模型预测准确率为98.11 %,其中对微颤的分类准确度为100%,地震的为97.22%,落石的为100%,噪音的为97.74%,说明该模型对该4类事件的分类精度较高。
本文共使用49个特征参数,考虑到并不是所有参数都能对4个类别进行正确区分,每个参数对分类效果起到的筛选作用并不相同,且可能出现由于参数过多而引起准确率下降的情况,Kohavi等[28]指出当变量的数量显著高于最优时,许多机器学习算法的准确性会下降。因此,本文通过python中scikit-learn库的基尼指数(Gini index)来构建特征重要性度量,以作为评价指标来计算各特征的重要性权重[29],获得各特征重要性权重。如图4所示,小部分特征所占权重 < 0.01,因此提取重要性占比大于90%的特征对RF模型重新训练,获得的准确率为0.96,与原模型的准确率相比总体预测精度有所下降,但降幅不明显。特征中部分复杂参数的计算量较大但权重占比较小的参数,如DFT 1/4~1/2的能量、信号递减部分与频谱特征的均方根值等,当考虑计算量较大、对精确度变化不敏感时,可优先选择该参数作为训练集对模型进行训练,以减少特征参数的计算时间。根据4类特征的重要性权重累加求和结果发现,时域特征参数的重要性权重之和占比为0.572,超过了一般的权重,频域特征参数的重要性权重之和占比为0.184,时频域特征参数的重要性权重之和占比为0.165,而多基站相干占比为0.079,占比较小。由此可见,当实验条件有限时,应将时域中的特征参数作为重点关注对象。
另外,为提升微震大数据分析效率和地质灾害监测预警时效,本文选取微震大数据分析中容易计算的5个特征参数,既持续时间、最大振幅、相对微震能量与最大振幅的比值、最大频率和标准化DFT的方差(A1、A2、A4、A28、A32),并对其预测效果进行评估,分类准确率为93.28%,说明当基站条件有限且对精度要求不高但对时间要求较高时,可以优先考虑该分类作为模型的特征参数。
为对比样本量对RF模型分类效果的影响,在训练集与测试集大小的选取上,采用python中scikit-learn数据包train_test_split函数,将原始数据按比例分割为训练集和测试集。考虑到训练集大小对模型精度的影响,本文选取初始训练集为样本大小的20%、30%、40%、50%、60%、70%、80%,同时考虑到分割函数的随机性,对训练模型进行100次重复训练,选取不同比例准确率的平均值作为最终准确率,以评价不同训练集大小优劣的依据(图5)。可以看出,落石的分类准确率受训练集大小的影响最大,其他的分类精度随训练集的增大而有所增大,且比例为2 ∶8(既测试集371个,训练集1 489个)时的准确率最好。
1) 将49个微震特征与1 860个微震事件作为模型建立的基础,利用混淆矩阵和Kappa系数作为评价指标,比较随机森林模型、神经网络模型和决策树模型下微震事件分类的优劣性,发现三者中RF模型效果最优。同时,验证了基于网格搜索算法可提高RF模型各项的准确度,使其分类准确率达到98.11%,表明该预测模型在微震事件预测中具有准确性,可作为该地区微震灾害预测预报工作的参考依据。
2) 模型的特征参数对分类准确度起着关键性的作用。获得不同特征的重要性权重后,采用占比大于90%的特征参数和5个易获取的特征参数分别作为模型的训练集,前者使模型的分类准确度小幅度下降,后者使分类准确度从97%降至93%。当需要节省计算时间时,可以考虑减少部分权重较小的特征参数作为训练集。不同属性特征参数的权重占比也具有明显差异,如时域特征参数的权重占比大于频域与时频域特征参数权重占比之和,因此在微震事件分类过程中应重点关注时域特征参数。
  • 中国地震局“三结合”课题(3JH-202401050)
  • 国家自然科学基金(4210071309)
  • 江西省地震局“2111”孵化基金(FD2111-202404)
  • 江西省自然科学基金(20224BAB203040)
参考文献 引证文献
排序方式:
1
Feng L , Pazzi V , Intrieri E , et al. Rockfall Seismic Features Analysis Based on in Situ Tests: Frequency, Amplitude, and Duration[J]. Journal of Mountain Science, 2019, 16 (5): 955- 970
2
Cook K L , Rekapalli R , Dietze M , et al. Detection and Potential Early Warning of Catastrophic Flow Events with Regional Seismic Networks[J]. Science, 2021, 374 (6563): 87- 92
3
Falcin A , Métaxian J P , Mars J , et al. A Machine-Learning Approach for Automatic Classification of Volcanic Seismicity at La Soufrière Volcano, Guadeloupe[J]. Journal of Volcanology and Geothermal Research, 2021, 411
4
Goetz J N , Brenning A , Petschko H , et al. Evaluating Machine Learning and Statistical Prediction Techniques for Landslide Susceptibility Modeling[J]. Computers and Geosciences, 2015, 81, 1- 11
5
Hibert C , Malet J P , Bourrier F , et al. Single-Block Rockfall Dynamics Inferred from Seismic Signal Analysis[J]. Earth Surface Dynamics, 2017, 5 (2): 283- 292
6
Provost F , Hibert C , Malet J P . Automatic Classification of Endogenous Landslide Seismicity Using the Random Forest Supervised Classifier[J]. Geophysical Research Letters, 2017, 44 (1): 113- 120
7
Nath S K , Sengupta A , Srivastava A . Remote Sensing GIS-Based Landslide Susceptibility and Risk Modeling in Darjeeling-Sikkim Himalaya Together with FEM-Based Slope Stability Analysis of the Terrain[J]. Natural Hazards, 2021, 108 (3): 3271- 3304
8
Wenner M , Hibert C , van Herwijnen A , et al. Near-Real-Time Automated Classification of Seismic Signals of Slope Failures with Continuous Random Forests[J]. Natural Hazards and Earth System Sciences, 2021, 21 (1): 339- 361
9
Chmiel M , Walter F , Wenner M , et al. Machine Learning Improves Debris Flow Warning[J]. Geophysical Research Letters, 2021, 48 (3)
10
杨德贺, 王秀英, 申旭辉, 等. 基于自编码网络的浅源和深源诱发型微震识别[J]. 地球物理学进展, 2018, 33 (5): 1844- 1853
Yang Dehe , Wang Xiuying , Shen Xuhui , et al. Discrimination of Shallow and Deep Induced-Microearthquakes Based on Autoencoder Network[J]. Progress in Geophysics, 2018, 33 (5): 1844- 1853
11
Antolini F , Barla M , Gigli G , et al. Combined Finite-Discrete Numerical Modeling of Runout of the Torgiovannetto Di Assisi Rockslide in Central Italy[J]. International Journal of Geomechanics, 2016, 16 (6)
12
Intrieri E , Gigli G , Mugnai F , et al. Design and Implementation of a Landslide Early Warning System[J]. Engineering Geology, 2012, 147, 124- 136
13
Gigli G , Intrieri E , Lombardi L , et al. Event Scenario Analysis for the Design of Rockslide Countermeasures[J]. Journal of Mountain Science, 2014, 11 (6): 1521- 1530
14
Feng L , Pazzi V , Intrieri E , et al. Joint Detection and Classification of Rockfalls in a Microseismic Monitoring Network[J]. Geophysical Journal International, 2020, 222 (3): 2108- 2120
15
冯亮, 张振. 微震技术在崩塌落石监测预警应用的研究进展[J]. 工程地质学, 2024, 32 (2): 545- 564
Feng Liang , Zhang Zhen . Seismic Monitoring in Rockfall: A Literature Review[J]. Journal of Engineering Geology, 2024, 32 (2): 545- 564
16
Trnkoczy A . Understanding and Setting STA/LTA Trigger Algorithm Parameters for the K2[J]. Application Note, 1998, 41 (8): 16- 20
17
Cortes G, Arambula R, Gutierrez L, et al. Evaluating Robustness of a HMM-Based Classification System of Volcano-Seismic Events at Colima and Popocatepetl Volcanoes[C]. 2009 IEEE International Geoscience and Remote Sensing Symposium, Cape Town, 2009
18
Hammer C , Beyreuther M , Ohrnberger M . A Seismic-Event Spotting System for Volcano Fast-Response Systems[J]. The Bulletin of the Seismological Society of America, 2012, 102 (3): 948- 960
19
Falsaperla S , Graziani S , Nunnari G , et al. Automatic Classification of Volcanic Earthquakes by Using Multi-Layered Neural Networks[J]. Natural Hazards, 1996, 13 (3): 205- 228
20
Barari M , Hosseini M . A Modern Method to Improve of Detecting and Categorizing Mechanism for Micro Seismic Events Data Using Boost Learning System[J]. Civil Engineering Journal, 2017, 3 (9): 715- 726
21
Pedregosa F , Varoquaux G , Gramfort A , et al. Scikit-Learn: Machine Learning in Python[J]. Journal of Machine Learning Research, 2011, 12, 2825- 2830
22
Murphy K , Schölkopf B , Fernández-Delgado M , et al. Do we Need Hundreds of Classifiers to Solve Real World Classification Problems?[J]. Journal of Machine Learning Research, 2014, 15 (1): 3133- 3181
23
Breiman L . Random Forests[J]. Machine Learning, 2001, 45 (1): 5- 32
24
Huang B F , Boutros P C . The Parameter Sensitivity of Random Forests[J]. BMC Bioinformatics, 2016, 17 (1)
25
Snoek J, Larochelle H, Adams R P, et al. Practical Bayesian Optimization of Machine Learning Algorithms[C]. Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 2012
26
温博文, 董文瀚, 解武杰, 等. 基于改进网格搜索算法的随机森林参数优化[J]. 计算机工程与应用, 2018, 54 (10): 154- 157
Wen Bowen , Dong Wenhan , Xie Wujie , et al. Parameter Optimization Method for Random Forest Based on Improved Grid Search Algorithm[J]. Computer Engineering and Applications, 2018, 54 (10): 154- 157
27
Cohen J . A Coefficient of Agreement for Nominal Scales[J]. Educational and Psychological Measurement, 1960, 20 (1): 37- 46
28
Kohavi R , John G H . Wrappers for Feature Subset Selection[J]. Artificial Intelligence, 1997, 97 (1-2): 273- 324
29
Loh W Y . Classification and Regression Trees[J]. WIREs Data Mining and Knowledge Discovery, 2011, 1 (1): 14- 23
2025年第45卷第6期
21
7
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2024.08.369
  • 接收时间:2024-08-02
  • 首发时间:2026-10-30
  • 出版时间:2025-06-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-02
基金
Combination Project with Monitoring, Prediction and Scientific Research of Earthquake Technology, CEA(3JH-202401050)
中国地震局“三结合”课题(3JH-202401050)
National Natural Science Foundation of China(4210071309)
国家自然科学基金(4210071309)
"2111" Incubation Fund of Jiangxi Earthquake Agency(FD2111-202404)
江西省地震局“2111”孵化基金(FD2111-202404)
Natural Science Foundation of Jiangxi Province(20224BAB203040)
江西省自然科学基金(20224BAB203040)
作者信息
    1 赣州地震监测中心站, 江西省赣州市贺兰山路55号, 341000
    2 广东省大宝山矿业有限公司, 广东省韶关市沙溪镇, 512128
    3 中国科学院、水利部成都山地灾害与环境研究所, 成都市群贤南街189号, 610041
    4 中国科学院大学, 北京市玉泉路19号, 100049
    5 江西理工大学资源与环境工程学院, 江西省赣州市客家大道156号, 341000

通讯作者:

冯亮,博士,副教授,主要从事地质灾害与环境地震学研究,E-mail:

FENG Liang, PhD, associate professor, majors in geological hazards and environmental seismology, E-mail:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.08.369
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
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
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