Article(id=1322566895992156734, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322566845215912204, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2025.03.086, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1742313600000, receivedDateStr=2025-03-19, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793254120109, onlineDateStr=2026-10-29, pubDate=1771084800000, pubDateStr=2026-02-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793254120109, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793254120109, creator=13701087609, updateTime=1793254120109, updator=13701087609, issue=Issue{id=1322566845215912204, tenantId=1146029695717560320, journalId=1281212831689347082, year='2026', volume='46', issue='2', pageStart='139', pageEnd='261', issueExtLink='null', onlineDate='null', pubDate='1771084800000', pubDateStr='2026-02-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793254108003, creator='13701087609', updateTime=1793254108003, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=139, endPage=147, ext={EN=ArticleExt(id=1322566896210260543, articleId=1322566895992156734, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=A Combined Prediction Model of Landslide Displacement with Weighted Combination of Multiple Neural Networks, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

A multi-neural-network weighted ensemble model for landslide displacement prediction is constructed by integrating three machine learning models: support vector regression (SVR), back propagation neural network (BPNN), and linear regression neural network (LRNN). The model development process primarily consists of two components: individual model prediction and multi-neural-network weighting. Instead of emphasizing prediction errors from all historical moments preceding the current prediction point, this ensemble model focuses on the proximity period around the current prediction point. Optimal weight coefficients for individual prediction models are calculated using the least squares method based on observed data, followed by weighted summation of predictions from individual models at the current point using these weights, ultimately achieving high-precision forecasting results. Comparative tests conducted on Beidou/GNSS monitoring data from the Dangchuan landslide mass at Heifangtai in Gansu province—a typical loess landslide area in China—demonstrate that this proposed ensemble model exhibits superior prediction accuracy compared to single-model approaches, simple averaging ensemble models, and multi-neural-network switching models. The proposed methodology shows significant potential for practical applications in landslide displacement prediction.

, authors=Wei QU1, 2, Yize DU1, Rongtang XU1, Jiuyuan LI1, Zice BIAN1, authorsList=Wei QU, Yize DU, Rongtang XU, Jiuyuan LI, Zice BIAN, authorCompany=null, correspAuthors=null, authorNote=null, 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=1322566899657978450, articleId=1322566895992156734, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=一种多神经网络加权组合的滑坡位移组合预测模型, columnId=1322566785874908034, journalTitle=大地测量与地球动力学, columnName=特色栏目: 地震大地测量学, runingTitle=null, highlight=null, articleAbstract=

结合支持向量回归(SVR)、反向传播神经网络(BPNN)和线性回归神经网络(LRNN)三种机器学习模型, 构建一种多神经网络加权组合的滑坡位移组合预测模型。该组合模型构建过程主要由单一模型预测和多神经网络加权两部分组成, 模型并不着重于当前预测点之前所有历史时刻的预测误差, 而更关注当前预测点的邻近时段, 根据实测数据利用最小二乘法计算赋予当前预测点最优的单一类预测模型的权重系数, 再基于此权重系数对单一类预测模型当前预测点的预测结果进行加权求和, 最终获得高精度预测结果。通过对我国典型黄土滑坡域甘肃黑方台党川滑坡体北斗/GNSS实测数据对比测试表明, 相较于单一类型预测模型、简单平均组合预测模型及多神经网络切换预测模型, 本文组合预测模型具有更高的预测精度, 具有较好的推广应用价值。

, authors=瞿伟1, 2, 杜易泽1, 徐荣堂1, 李久元1, 边子策1, authorsList=瞿伟, 杜易泽, 徐荣堂, 李久元, 边子策, authorCompany=null, correspAuthors=null, authorNote=

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

, correspAuthorsNote=null, 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=+tWQ3VMuTJe1fziT+lgZPw==, magXml=aDe+9RxgS8WHH6TmHEC4mA==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=lWdv9YbfP5DVBku3q0QRsg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=w4YZAQDaJBbuS8yBaL0k3w==, mapNumber=null, fund=null)}, authors=[Author(id=1322566900039660122, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=maikerqq@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566900127740509, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900039660122, language=EN, stringName=Wei QU, firstName=Wei, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China
2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900203237982, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900039660122, language=CN, stringName=瞿伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 长安大学地质工程与测绘学院, 西安, 710054
2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054, bio={"content":"

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

"}, bioImg=null, bioContent=

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)]), AuthorCompany(id=1322566899968356950, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899972551255, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China), AuthorCompanyExt(id=1322566899980939864, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054)])]), Author(id=1322566900274541152, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900350038626, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900274541152, language=EN, stringName=Yize DU, firstName=Yize, middleName=null, lastName=DU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900429730403, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900274541152, language=CN, stringName=杜易泽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900501033573, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900580725351, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900501033573, language=EN, stringName=Rongtang XU, firstName=Rongtang, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900673000040, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900501033573, language=CN, stringName=徐荣堂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900752691818, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900828189292, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900752691818, language=EN, stringName=Jiuyuan LI, firstName=Jiuyuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900895298157, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900752691818, language=CN, stringName=李久元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900974989935, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566901050487409, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900974989935, language=EN, stringName=Zice BIAN, firstName=Zice, middleName=null, lastName=BIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566901125984882, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900974989935, language=CN, stringName=边子策, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])])], keywords=[Keyword(id=1322566901214065267, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, orderNo=1, keyword=landslide), Keyword(id=1322566901268591220, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, orderNo=2, keyword=displacement prediction), Keyword(id=1322566901335700085, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, orderNo=3, keyword=neural network), Keyword(id=1322566901415391862, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, orderNo=4, keyword=least squares), Keyword(id=1322566901499277943, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, orderNo=5, keyword=weighted summation), Keyword(id=1322566901566386808, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, orderNo=1, keyword=滑坡), Keyword(id=1322566901633495673, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, orderNo=2, keyword=位移预测), Keyword(id=1322566901708993146, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, orderNo=3, keyword=神经网络), Keyword(id=1322566901797073531, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, orderNo=4, keyword=最小二乘), Keyword(id=1322566901868376700, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, orderNo=5, keyword=加权组合)], refs=[Reference(id=1322566906012349081, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=12, pageStart=1551, pageEnd=1561, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=朱庆, 曾浩炜, 丁雨淋, journalName=测绘学报, refType=null, unstructuredReference=朱庆, 曾浩炜, 丁雨淋, 等. 重大滑坡隐患分析方法综述[J]. 测绘学报, 2019, 48 (12): 1551- 1561, articleTitle=重大滑坡隐患分析方法综述, refAbstract=null), Reference(id=1322566906083652250, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=12, pageStart=1551, pageEnd=1561, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=Zhu Qing, Zeng Haowei, Ding Yulin, journalName=null, refType=null, unstructuredReference= Zhu Qing , Zeng Haowei , Ding Yulin , et al. A Review of Major Potential Landslide Hazards Analysis[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48 (12): 1551- 1561, articleTitle=null, refAbstract=null), Reference(id=1322566906180121243, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=32, issue=增2, pageStart=3868, pageEnd=3877, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=王佳佳, 殷坤龙, 杜娟, journalName=岩石力学与工程学报, refType=null, unstructuredReference=王佳佳, 殷坤龙, 杜娟, 等. 基于GIS考虑准动态湿度指数的滑坡危险性预测水文-力学耦合模型研究[J]. 岩石力学与工程学报, 2013, 32 (增2): 3868- 3877, articleTitle=基于GIS考虑准动态湿度指数的滑坡危险性预测水文-力学耦合模型研究, refAbstract=null), Reference(id=1322566906247230108, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=32, issue=S2, pageStart=3868, pageEnd=3877, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=Wang Jiajia, Yin Kunlong, Du Juan, journalName=null, refType=null, unstructuredReference= Wang Jiajia , Yin Kunlong , Du Juan , et al. Research on Hydrology-Mechanics Coupling Model of Landslide Hazards Prediction Base on GIS by Using Quasi-Dynamic Wetness Index[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32 (S2): 3868- 3877, articleTitle=null, refAbstract=null), Reference(id=1322566906322727581, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=1, pageStart=154, pageEnd=163, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=詹威威, 黄润秋, 裴向军, journalName=工程地质学报, refType=null, unstructuredReference=詹威威, 黄润秋, 裴向军, 等. 沟道型滑坡-碎屑流运动距离经验预测模型研究[J]. 工程地质学报, 2017, 25 (1): 154- 163, articleTitle=沟道型滑坡-碎屑流运动距离经验预测模型研究, refAbstract=null), Reference(id=1322566906381447838, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=1, pageStart=154, pageEnd=163, url=null, language=null, rfNumber=3, rfOrder=5, authorNames=Zhan Weiwei, Huang Runqiu, Pei Xiangjun, journalName=null, refType=null, unstructuredReference= Zhan Weiwei , Huang Runqiu , Pei Xiangjun , et al. Empirical Prediction Model for Movement Distance of Gully-Type Rock Avalanches[J]. Journal of Engineering Geology, 2017, 25 (1): 154- 163, articleTitle=null, refAbstract=null), Reference(id=1322566906465333919, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=黄发明. 基于3S和人工智能的滑坡位移预测与易发性评价[D]. 武汉: 中国地质大学(武汉), 2017, articleTitle=null, refAbstract=null), Reference(id=1322566908122084000, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Faming. Landslide Displacement Prediction and Susceptibility Assessment Based on 3S and Artificial Intelligence[D]. Wuhan: China University of Geosciences, 2017, articleTitle=null, refAbstract=null), Reference(id=1322566908197581473, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2012, volume=28, issue=2, pageStart=39, pageEnd=43, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=方臣, 王正海, 耿欣, journalName=防灾减灾学报, refType=null, unstructuredReference=方臣, 王正海, 耿欣, 等. 基于ε-SVR的滑坡位移预测[J]. 防灾减灾学报, 2012, 28 (2): 39- 43, articleTitle=基于ε-SVR的滑坡位移预测, refAbstract=null), Reference(id=1322566908277273250, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2012, volume=28, issue=2, pageStart=39, pageEnd=43, url=null, language=null, rfNumber=5, rfOrder=9, authorNames=Fang Chen, Wang Zhenghai, Geng Xin, journalName=null, refType=null, unstructuredReference= Fang Chen , Wang Zhenghai , Geng Xin , et al. Prediction of Landslide Displacement Based on ε-Support Vector Regression Machine[J]. Journal of Disaster Prevention and Reduction, 2012, 28 (2): 39- 43, articleTitle=null, refAbstract=null), Reference(id=1322566908340187811, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=30, issue=2, pageStart=6, pageEnd=11, url=null, language=null, rfNumber=6, rfOrder=10, authorNames=李德营, 殷坤龙, journalName=长江科学院院报, refType=null, unstructuredReference=李德营, 殷坤龙. 基于影响因子的GM(1, 1)-BP模型在八字门滑坡变形预测中的应用[J]. 长江科学院院报, 2013, 30 (2): 6- 11, articleTitle=基于影响因子的GM(1, 1)-BP模型在八字门滑坡变形预测中的应用, refAbstract=null), Reference(id=1322566908403102372, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=30, issue=2, pageStart=6, pageEnd=11, url=null, language=null, rfNumber=6, rfOrder=11, authorNames=Li Deying, Yin Kunlong, journalName=null, refType=null, unstructuredReference= Li Deying , Yin Kunlong . Application of GM(1, 1)-BP Model to the Deformation Prediction of Bazimen Landslide in Consideration of Influencing Factors[J]. Journal of Yangtze River Scientific Research Institute, 2013, 30 (2): 6- 11, articleTitle=null, refAbstract=null), Reference(id=1322566908466016933, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=353-356, issue=null, pageStart=1101, pageEnd=1105, url=null, language=null, rfNumber=7, rfOrder=12, authorNames=Zhang W Z, Li Y J, Li X S, journalName=Applied Mechanics and Materials, refType=null, unstructuredReference= Zhang W Z , Li Y J , Li X S , et al. Forecasting of Landslide Displacement Based on Exponential Smoothing and Nonlinear Regression Analysis[J]. Applied Mechanics and Materials, 2013, 353-356, 1101- 1105, articleTitle=Forecasting of Landslide Displacement Based on Exponential Smoothing and Nonlinear Regression Analysis, refAbstract=null), Reference(id=1322566908541514406, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=3, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=8, rfOrder=13, authorNames=王朝阳, 李丽敏, 温宗周, journalName=国外电子测量技术, refType=null, unstructuredReference=王朝阳, 李丽敏, 温宗周, 等. 基于时间序列和CNN-LSTM的滑坡位移动态预测[J]. 国外电子测量技术, 2022, 41 (3): 1- 8, articleTitle=基于时间序列和CNN-LSTM的滑坡位移动态预测, refAbstract=null), Reference(id=1322566908637983399, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=3, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=8, rfOrder=14, authorNames=Wang Chaoyang, Li Limin, Wen Zongzhou, journalName=null, refType=null, unstructuredReference= Wang Chaoyang , Li Limin , Wen Zongzhou , et al. Dynamic Prediction of Landslide Displacement Based on Time Series and CNN-LSTM[J]. Foreign Electronic Measurement Technology, 2022, 41 (3): 1- 8, articleTitle=null, refAbstract=null), Reference(id=1322566908713480872, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2013, volume=838-841, issue=null, pageStart=2179, pageEnd=2184, url=null, language=null, rfNumber=9, rfOrder=15, authorNames=Long H T, Zhang G D, Cao J L, journalName=Advanced Materials Research, refType=null, unstructuredReference= Long H T , Zhang G D , Cao J L . The Use of BP Neural Network in the Landslide Prediction of Three Gorges Reservoir[J]. Advanced Materials Research, 2013, 838-841, 2179- 2184, articleTitle=The Use of BP Neural Network in the Landslide Prediction of Three Gorges Reservoir, refAbstract=null), Reference(id=1322566908780589737, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2024, volume=83, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=16, authorNames=Melati D N, Umbara R P, Astisiasari A, journalName=Environmental Earth Sciences, refType=null, unstructuredReference= Melati D N , Umbara R P , Astisiasari A , et al. A Comparative Evaluation of Landslide Susceptibility Mapping Using Machine Learning-Based Methods in Bogor Area of Indonesia[J]. Environmental Earth Sciences, 2024, 83 (3), articleTitle=A Comparative Evaluation of Landslide Susceptibility Mapping Using Machine Learning-Based Methods in Bogor Area of Indonesia, refAbstract=null), Reference(id=1322566908872864426, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2018, volume=67, issue=2, pageStart=105, pageEnd=113, url=null, language=null, rfNumber=11, rfOrder=17, authorNames=Jiang T, Shen Z Z, Yang M, journalName=Structural Engineering and Mechanics, refType=null, unstructuredReference= Jiang T , Shen Z Z , Yang M , et al. A New Model Approach to Predict the Unloading Rock Slope Displacement Behavior Based on Monitoring Data[J]. Structural Engineering and Mechanics, 2018, 67 (2): 105- 113, articleTitle=A New Model Approach to Predict the Unloading Rock Slope Displacement Behavior Based on Monitoring Data, refAbstract=null), Reference(id=1322566908952556203, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=10, pageStart=2160, pageEnd=2170, url=null, language=null, rfNumber=12, rfOrder=18, authorNames=罗袆沅, 蒋亚楠, 许强, journalName=测绘学报, refType=null, unstructuredReference=罗袆沅, 蒋亚楠, 许强, 等. 基于深度学习的滑坡位移时空预测[J]. 测绘学报, 2022, 51 (10): 2160- 2170, articleTitle=基于深度学习的滑坡位移时空预测, refAbstract=null), Reference(id=1322566909032247980, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=10, pageStart=2160, pageEnd=2170, url=null, language=null, rfNumber=12, rfOrder=19, authorNames=Luo Huiyuan, Jiang Yanan, Xu Qiang, journalName=null, refType=null, unstructuredReference= Luo Huiyuan , Jiang Yanan , Xu Qiang , et al. A Spatio-Temporal Network for Landslide Displacement Prediction Based on Deep Learning[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51 (10): 2160- 2170, articleTitle=null, refAbstract=null), Reference(id=1322566909107745453, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=8, pageStart=1380, pageEnd=1388, url=null, language=null, rfNumber=13, rfOrder=20, authorNames=李达, 瞿伟, 张勤, journalName=武汉大学学报: 信息科学版, refType=null, unstructuredReference=李达, 瞿伟, 张勤, 等. 融合多层感知机和优化支持向量回归的滑坡位移预测模型[J]. 武汉大学学报: 信息科学版, 2023, 48 (8): 1380- 1388, articleTitle=融合多层感知机和优化支持向量回归的滑坡位移预测模型, refAbstract=null), Reference(id=1322566909174854318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=8, pageStart=1380, pageEnd=1388, url=null, language=null, rfNumber=13, rfOrder=21, authorNames=Li Da, Qu Wei, Zhang Qin, journalName=null, refType=null, unstructuredReference= Li Da , Qu Wei , Zhang Qin , et al. Landslide Displacement Prediction Model Integrating Multi-Layer Perceptron and Optimized Support Vector Regression[J]. Geomatics and Information Science of Wuhan University, 2023, 48 (8): 1380- 1388, articleTitle=null, refAbstract=null), Reference(id=1322566909246157487, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2015, volume=186, issue=null, pageStart=91, pageEnd=99, url=null, language=null, rfNumber=14, rfOrder=22, authorNames=Lian C, Zeng Z G, Yao W, journalName=Engineering Geology, refType=null, unstructuredReference= Lian C , Zeng Z G , Yao W , et al. Multiple Neural Networks Switched Prediction for Landslide Displacement[J]. Engineering Geology, 2015, 186, 91- 99, articleTitle=Multiple Neural Networks Switched Prediction for Landslide Displacement, refAbstract=null), Reference(id=1322566909317460656, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=1995, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=23, authorNames=Vapnik V N, journalName=The Nature of Statistical Learning Theory, refType=null, unstructuredReference= Vapnik V N . The Nature of Statistical Learning Theory[M]. New York: Springer, 1995, articleTitle=null, refAbstract=null), Reference(id=1322566909388763825, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2015, volume=34, issue=2, pageStart=382, pageEnd=391, url=null, language=null, rfNumber=16, rfOrder=24, authorNames=张俊, 殷坤龙, 王佳佳, journalName=岩石力学与工程学报, refType=null, unstructuredReference=张俊, 殷坤龙, 王佳佳, 等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34 (2): 382- 391, articleTitle=基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究, refAbstract=null), Reference(id=1322566909485232819, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2015, volume=34, issue=2, pageStart=382, pageEnd=391, url=null, language=null, rfNumber=16, rfOrder=25, authorNames=Zhang Jun, Yin Kunlong, Wang Jiajia, journalName=null, refType=null, unstructuredReference= Zhang Jun , Yin Kunlong , Wang Jiajia , et al. Displacement Prediction of Baishuihe Landslide Based on Time Series and pso-Svr Model[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34 (2): 382- 391, articleTitle=null, refAbstract=null), Reference(id=1322566909556535988, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Hecht-Nielsen. Theory of the Backpropagation Neural Network[C]. International Joint Conference on Neural Networks, Washington DC, 1989, articleTitle=null, refAbstract=null), Reference(id=1322566909644616373, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2015, volume=42, issue=1, pageStart=134, pageEnd=139, url=null, language=null, rfNumber=18, rfOrder=27, authorNames=张群, 许强, 吴礼舟, journalName=水文地质工程地质, refType=null, unstructuredReference=张群, 许强, 吴礼舟, 等. 南江滑坡群体积的BP神经网络模型与预测[J]. 水文地质工程地质, 2015, 42 (1): 134- 139, articleTitle=南江滑坡群体积的BP神经网络模型与预测, refAbstract=null), Reference(id=1322566909724308150, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2015, volume=42, issue=1, pageStart=134, pageEnd=139, url=null, language=null, rfNumber=18, rfOrder=28, authorNames=Zhang Qun, Xu Qiang, Wu Lizhou, journalName=null, refType=null, unstructuredReference= Zhang Qun , Xu Qiang , Wu Lizhou , et al. BP Neural Network Model for Forecasting Volume of Landslide Group in Nanjiang[J]. Hydrogeology and Engineering Geology, 2015, 42 (1): 134- 139, articleTitle=null, refAbstract=null), Reference(id=1322566909803999927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2012, volume=34, issue=7, pageStart=90, pageEnd=92, url=null, language=null, rfNumber=19, rfOrder=29, authorNames=王秀丽, 李恒凯, journalName=人民黄河, refType=null, unstructuredReference=王秀丽, 李恒凯. 滑坡变形的回归-神经网络预测模型研究[J]. 人民黄河, 2012, 34 (7): 90- 92, articleTitle=滑坡变形的回归-神经网络预测模型研究, refAbstract=null), Reference(id=1322566909862720184, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2012, volume=34, issue=7, pageStart=90, pageEnd=92, url=null, language=null, rfNumber=19, rfOrder=30, authorNames=Wang Xiuli, Li Hengkai, journalName=null, refType=null, unstructuredReference= Wang Xiuli , Li Hengkai . Research on Prediction Model of Regression-Neural Network for Landslide Deformation[J]. Yellow River, 2012, 34 (7): 90- 92, articleTitle=null, refAbstract=null), Reference(id=1322566909925634745, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2017, volume=42, issue=12, pageStart=105, pageEnd=112, url=null, language=null, rfNumber=20, rfOrder=31, authorNames=苏盈盈, 李太福, 康东帅, journalName=西南师范大学学报: 自然科学版, refType=null, unstructuredReference=苏盈盈, 李太福, 康东帅, 等. 多层线性神经网络与单层线性神经网络的等效性研究[J]. 西南师范大学学报: 自然科学版, 2017, 42 (12): 105- 112, articleTitle=多层线性神经网络与单层线性神经网络的等效性研究, refAbstract=null), Reference(id=1322566909996937914, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2017, volume=42, issue=12, pageStart=105, pageEnd=112, url=null, language=null, rfNumber=20, rfOrder=32, authorNames=Su Yingying, Li Taifu, Kang Dongshuai, journalName=null, refType=null, unstructuredReference= Su Yingying , Li Taifu , Kang Dongshuai , et al. On Equivalence Verification between Single-Layer and Multi-Layer Linear Neural Network[J]. Journal of Southwest China Normal University (Natural Science Edition), 2017, 42 (12): 105- 112, articleTitle=null, refAbstract=null), Reference(id=1322566910064046779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=11, pageStart=1424, pageEnd=1429, url=null, language=null, rfNumber=21, rfOrder=33, authorNames=白正伟, 张勤, 黄观文, journalName=测绘学报, refType=null, unstructuredReference=白正伟, 张勤, 黄观文, 等. "轻终端+行业云"的实时北斗滑坡监测技术[J]. 测绘学报, 2019, 48 (11): 1424- 1429, articleTitle="轻终端+行业云"的实时北斗滑坡监测技术, refAbstract=null), Reference(id=1322566910126961340, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=11, pageStart=1424, pageEnd=1429, url=null, language=null, rfNumber=21, rfOrder=34, authorNames=Bai Zhengwei, Zhang Qin, Huang Guanwen, journalName=null, refType=null, unstructuredReference= Bai Zhengwei , Zhang Qin , Huang Guanwen , et al. Real-Time Beidou Landslide Monitoring Technology of "Light Terminal Plus Industry Cloud"[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48 (11): 1424- 1429, articleTitle=null, refAbstract=null)], funds=[Fund(id=1322566905643250325, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, awardId=42174006, language=CN, fundingSource=国家自然科学基金(42174006), fundOrder=null, country=null), Fund(id=1322566905739719318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, awardId=42090055, language=CN, fundingSource=国家自然科学基金(42090055), fundOrder=null, country=null), Fund(id=1322566905815216791, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, awardId=2022JC-18, language=CN, fundingSource=陕西省杰出青-科学基金(2022JC-18), fundOrder=null, country=null), Fund(id=1322566905886519960, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, awardId=300102263201, language=CN, fundingSource=长安大学中央高校基本科研业务费专项(300102263201), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)]), AuthorCompany(id=1322566899968356950, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899972551255, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China), AuthorCompanyExt(id=1322566899980939864, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054)])], figs=[ArticleFig(id=1322566901998400125, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 1, caption=Flowchart for constructing a weighted combination model of multiple neural networks, figureFileSmall=mqzG2H7V0O7gxLUHkYzxfQ==, figureFileBig=lWdv9YbfP5DVBku3q0QRsg==, tableContent=null), ArticleFig(id=1322566903655150206, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图1, caption=多神经网络加权组合模型构建流程, figureFileSmall=mqzG2H7V0O7gxLUHkYzxfQ==, figureFileBig=lWdv9YbfP5DVBku3q0QRsg==, tableContent=null), ArticleFig(id=1322566903860671103, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 2, caption=Distribution of HF05 and HF09 Beidou/GNSS monitoring stations corresponding to the two landslide events in Dangchuan, figureFileSmall=WigwqhRcq/FfaWQzytb/9A==, figureFileBig=O89+HdfMytdzB3HsfNtNtA==, tableContent=null), ArticleFig(id=1322566903931974272, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图2, caption=党川2次滑坡事件对应的HF05和HF09北斗/GNSS监测站点分布, figureFileSmall=WigwqhRcq/FfaWQzytb/9A==, figureFileBig=O89+HdfMytdzB3HsfNtNtA==, tableContent=null), ArticleFig(id=1322566904003277441, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 3, caption=Raw landslide time series monitoring displacements, figureFileSmall=fwUQrWti9cdhLgqWztyD3Q==, figureFileBig=bo/T32DNrb4NvlC8170AWw==, tableContent=null), ArticleFig(id=1322566904099746434, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图3, caption=原始滑坡时序监测位移, figureFileSmall=fwUQrWti9cdhLgqWztyD3Q==, figureFileBig=bo/T32DNrb4NvlC8170AWw==, tableContent=null), ArticleFig(id=1322566904179438211, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 4, caption=Time series monitoring displacements of landslide at 12-hour intervals after preprocessing, figureFileSmall=0qcQMkGVpE4HfD75vqtGfg==, figureFileBig=ILujfPolyUJ41hMKoRJt5A==, tableContent=null), ArticleFig(id=1322566904267518596, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图4, caption=经预处理后12 h间隔的滑坡时序监测位移, figureFileSmall=0qcQMkGVpE4HfD75vqtGfg==, figureFileBig=ILujfPolyUJ41hMKoRJt5A==, tableContent=null), ArticleFig(id=1322566904334627461, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 5, caption=Comparison of prediction results of different prediction models in the HF05 test set, figureFileSmall=sqrWcfpXrNpIx+xwdPgzBA==, figureFileBig=GtMoOJM1SiS2IBD43BfOdw==, tableContent=null), ArticleFig(id=1322566904422707846, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图5, caption=HF05测试集中不同预测模型的预测结果对比, figureFileSmall=sqrWcfpXrNpIx+xwdPgzBA==, figureFileBig=GtMoOJM1SiS2IBD43BfOdw==, tableContent=null), ArticleFig(id=1322566904527565447, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 6, caption=Comparison of prediction results of different prediction models in the HF09 test set, figureFileSmall=i/fc2I88AFZNourdqv3rCg==, figureFileBig=XvhqZlsn6bHsjc7dCzpT9w==, tableContent=null), ArticleFig(id=1322566904619840136, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图6, caption=HF09测试集中不同预测模型的预测结果对比, figureFileSmall=i/fc2I88AFZNourdqv3rCg==, figureFileBig=XvhqZlsn6bHsjc7dCzpT9w==, tableContent=null), ArticleFig(id=1322566904703726217, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 7, caption=Comparison of absolute residual values predicted by different models during sudden and rapid changes in the sliding stage, figureFileSmall=xv0ieMrihsYDSZzoWiNVuw==, figureFileBig=gn7Lw95Z84z6dF2KBvO6Kw==, tableContent=null), ArticleFig(id=1322566904779223690, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图7, caption=不同模型在滑体临滑阶段突变与临滑急速变化下预测残差绝对值对比, figureFileSmall=xv0ieMrihsYDSZzoWiNVuw==, figureFileBig=gn7Lw95Z84z6dF2KBvO6Kw==, tableContent=null), ArticleFig(id=1322566904854721163, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 8, caption=Time series monitoring data of landslide displacements in the Three Gorges reservoir area, figureFileSmall=xjMG6Q7MvMPdEKEtZDyTVA==, figureFileBig=7NdGhDPm/kR0WV7MQg7xhw==, tableContent=null), ArticleFig(id=1322566904926024332, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图8, caption=三峡库区滑坡位移时序监测数据, figureFileSmall=xjMG6Q7MvMPdEKEtZDyTVA==, figureFileBig=7NdGhDPm/kR0WV7MQg7xhw==, tableContent=null), ArticleFig(id=1322566904993133197, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Fig. 9, caption=Error comparison of different lookback lengths, figureFileSmall=ut1w+x9uXNnaA36dnCYzOA==, figureFileBig=mSt7NR0bqO7gUW3GYhpdZQ==, tableContent=null), ArticleFig(id=1322566905068630670, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=图9, caption=不同回望长度的误差对比, figureFileSmall=ut1w+x9uXNnaA36dnCYzOA==, figureFileBig=mSt7NR0bqO7gUW3GYhpdZQ==, tableContent=null), ArticleFig(id=1322566905148322447, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Tab. 1, caption=

Data sets for different landslides at different time intervals

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集HF05HF09
6 h12 h6 h12 h
训练集1 03051419696
验证集131662614
测试集127622512
), ArticleFig(id=1322566905240597136, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=表1, caption=

不同滑坡体在不同时间间隔内的数据集

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集HF05HF09
6 h12 h6 h12 h
训练集1 03051419696
验证集131662614
测试集127622512
), ArticleFig(id=1322566905320288913, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Tab. 2, caption=

Predicted RMSE values of prediction models at different time intervals

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点时间间隔/h本文模型
RMSE/mm
对比模型
RMSE/mm
组合3模型1模型2模型3组合1组合2
HF0561.19.07.43.36.43.3
125.416.012.16.1211.36.1
HF09614.342.276.120.045.020.0
1227.288.991.734.670.434.6
), ArticleFig(id=1322566905387397778, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=表2, caption=

预测模型在不同时间间隔下的预测RMSE值

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点时间间隔/h本文模型
RMSE/mm
对比模型
RMSE/mm
组合3模型1模型2模型3组合1组合2
HF0561.19.07.43.36.43.3
125.416.012.16.1211.36.1
HF09614.342.276.120.045.020.0
1227.288.991.734.670.434.6
), ArticleFig(id=1322566905462895251, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=EN, label=Tab. 3, caption=

Predictive RMSE of the predictive models in the supplementary data sets

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点本文模型/mm对比模型/mm
组合3模型1模型2模型3组合1组合2
白水河滑坡8.6654.3239.3634.4742.6534.47
八字门滑坡17.5556.8855.6221.642.8621.6
), ArticleFig(id=1322566905534198420, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, language=CN, label=表3, caption=

预测模型在补充数据集的预测RMSE值

, figureFileSmall=null, figureFileBig=null, tableContent=
监测点本文模型/mm对比模型/mm
组合3模型1模型2模型3组合1组合2
白水河滑坡8.6654.3239.3634.4742.6534.47
八字门滑坡17.5556.8855.6221.642.8621.6
)], 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.2025.03.086, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2025.03.086, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2025.03.086, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2025.03.086, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1771084800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
一种多神经网络加权组合的滑坡位移组合预测模型
收藏切换
瞿伟 1, 2 , 杜易泽 1 , 徐荣堂 1 , 李久元 1 , 边子策 1
大地测量与地球动力学 | 特色栏目: 地震大地测量学 2026,46(2): 139-147
收起
收藏切换
大地测量与地球动力学 |特色栏目: 地震大地测量学 2026 , 46 (2) : 139 -147
一种多神经网络加权组合的滑坡位移组合预测模型
全屏
[Author(id=1322566900039660122, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=maikerqq@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566900127740509, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900039660122, language=EN, stringName=Wei QU, firstName=Wei, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China
2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900203237982, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900039660122, language=CN, stringName=瞿伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 长安大学地质工程与测绘学院, 西安, 710054
2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054, bio={"content":"

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

"}, bioImg=null, bioContent=

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)]), AuthorCompany(id=1322566899968356950, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899972551255, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China), AuthorCompanyExt(id=1322566899980939864, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899968356950, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054)])]), Author(id=1322566900274541152, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900350038626, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900274541152, language=EN, stringName=Yize DU, firstName=Yize, middleName=null, lastName=DU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900429730403, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900274541152, language=CN, stringName=杜易泽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900501033573, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900580725351, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900501033573, language=EN, stringName=Rongtang XU, firstName=Rongtang, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900673000040, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900501033573, language=CN, stringName=徐荣堂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900752691818, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566900828189292, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900752691818, language=EN, stringName=Jiuyuan LI, firstName=Jiuyuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566900895298157, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900752691818, language=CN, stringName=李久元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])]), Author(id=1322566900974989935, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, 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=1322566901050487409, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900974989935, language=EN, stringName=Zice BIAN, firstName=Zice, middleName=null, lastName=BIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566901125984882, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, authorId=1322566900974989935, language=CN, stringName=边子策, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 长安大学地质工程与测绘学院, 西安, 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566899897053779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, xref=null, ext=[AuthorCompanyExt(id=1322566899905442388, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China), AuthorCompanyExt(id=1322566899913830997, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566895992156734, companyId=1322566899897053779, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 长安大学地质工程与测绘学院, 西安, 710054)])])]
瞿伟1, 2 , 杜易泽1, 徐荣堂1, 李久元1, 边子策1
作者信息
  • 1 长安大学地质工程与测绘学院, 西安, 710054
  • 2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054
作者简介:

瞿伟, 博士, 教授, 博士生导师, 主要从事地壳形变大地测量反演与地质灾害高精度监测及成因机理研究, E-mail:

A Combined Prediction Model of Landslide Displacement with Weighted Combination of Multiple Neural Networks
Wei QU1, 2 , Yize DU1, Rongtang XU1, Jiuyuan LI1, Zice BIAN1
Affiliations
  • 1 College of Geology Engineering and Geomatics, Chang'an University, Xi'an 710054, China
  • 2 Key Laboratory of Western China's Mineral Resources and Geological Engineering, Ministry of Education, Xi'an 710054, China
出版时间: 2026-02-15 doi: 10.14075/j.jgg.2025.03.086
文章导航
收藏切换

结合支持向量回归(SVR)、反向传播神经网络(BPNN)和线性回归神经网络(LRNN)三种机器学习模型, 构建一种多神经网络加权组合的滑坡位移组合预测模型。该组合模型构建过程主要由单一模型预测和多神经网络加权两部分组成, 模型并不着重于当前预测点之前所有历史时刻的预测误差, 而更关注当前预测点的邻近时段, 根据实测数据利用最小二乘法计算赋予当前预测点最优的单一类预测模型的权重系数, 再基于此权重系数对单一类预测模型当前预测点的预测结果进行加权求和, 最终获得高精度预测结果。通过对我国典型黄土滑坡域甘肃黑方台党川滑坡体北斗/GNSS实测数据对比测试表明, 相较于单一类型预测模型、简单平均组合预测模型及多神经网络切换预测模型, 本文组合预测模型具有更高的预测精度, 具有较好的推广应用价值。

滑坡  /  位移预测  /  神经网络  /  最小二乘  /  加权组合

A multi-neural-network weighted ensemble model for landslide displacement prediction is constructed by integrating three machine learning models: support vector regression (SVR), back propagation neural network (BPNN), and linear regression neural network (LRNN). The model development process primarily consists of two components: individual model prediction and multi-neural-network weighting. Instead of emphasizing prediction errors from all historical moments preceding the current prediction point, this ensemble model focuses on the proximity period around the current prediction point. Optimal weight coefficients for individual prediction models are calculated using the least squares method based on observed data, followed by weighted summation of predictions from individual models at the current point using these weights, ultimately achieving high-precision forecasting results. Comparative tests conducted on Beidou/GNSS monitoring data from the Dangchuan landslide mass at Heifangtai in Gansu province—a typical loess landslide area in China—demonstrate that this proposed ensemble model exhibits superior prediction accuracy compared to single-model approaches, simple averaging ensemble models, and multi-neural-network switching models. The proposed methodology shows significant potential for practical applications in landslide displacement prediction.

landslide  /  displacement prediction  /  neural network  /  least squares  /  weighted summation
瞿伟, 杜易泽, 徐荣堂, 李久元, 边子策. 一种多神经网络加权组合的滑坡位移组合预测模型. 大地测量与地球动力学, 2026 , 46 (2) : 139 -147 . DOI: 10.14075/j.jgg.2025.03.086
Wei QU, Yize DU, Rongtang XU, Jiuyuan LI, Zice BIAN. A Combined Prediction Model of Landslide Displacement with Weighted Combination of Multiple Neural Networks[J]. Journal of Geodesy and Geodynamics, 2026 , 46 (2) : 139 -147 . DOI: 10.14075/j.jgg.2025.03.086
开展滑坡位移的高精度预测研究,对滑坡灾害预警防范具有重要的现实意义[1]。从模型的构成方式来看,滑坡位移预测模型主要有单一类型模型与组合模型两大类,其中单一类型模型有基于岩土理论的力学模型[2]、基于统计学方法的简单经验模型[3]及传统机器学习与深度学习模型[4]等,如利用支持向量回归(SVR)[5]、反向传播神经网络(BPNN)[6]、线性回归神经网络(LRNN)[7]和卷积神经网络模型[8]等,可显著减少人工经验假设等对滑坡位移的预测影响[9]。为进一步提升预测精度,组合模型逐渐成为滑坡位移预测研究的热点问题之一[10],如组合遗传算法与BPNN模型,可较好地预测卸载影响下的滑坡位移量[11],通过发展组合集合图卷积网络模型和门控循环单元模型的滑坡位移预测模型[12],建立融合多层感知机和优化支持向量回归的滑坡位移组合预测模型[13],开发多神经网络切换预测模型,对滑坡体位移量及其发展趋势进行有效预测[14]等。
相较于单一类型预测模型,组合预测模型可在一定程度上弥补如SVR存在的调参困难与可解释性弱、BPNN易陷入局部最优、LRNN易受噪声影响等不足。但当前滑坡位移组合预测模型的分析中,简单平均组合预测模型常将多种单一类预测模型的预测结果进行平均作为最终的预测结果,多神经网络切换预测模型会根据所有历史时刻的预测误差来评估多种单一类预测模型,并据此选择最优的预测模型,获得的预测结果完全由这一最优预测模型确定(即权为1)。这些组合预测模型的预测结果,无论是取几类单一类预测结果的简单平均值,还是基于所有历史时刻表现选取预测模型及其结果的方式,均会极大地限制组合模型的适用性,特别是对临滑急速变化阶段位移的预测效果较差。
基于此,本文针对滑坡位移组合预测模型研究中存在的问题,结合SVR、BPNN和LRNN三类机器学习模型,构建了一种多神经网络加权组合的滑坡位移组合预测模型。该组合模型并不着重于当前预测点之前所有历史时刻的预测误差分析,而更关注当前预测点的邻近时段,根据实测数据计算赋予当前预测点最优的单一类预测模型的权重系数,再基于此权重系数对单一类预测模型当前预测点的预测结果进行加权求和,最终获得高精度预测结果。同时,以我国典型黄土滑坡域甘肃黑方台党川滑坡为实验区,基于滑坡北斗/GNSS实测数据构建多神经网络加权组合模型,并与单SVR模型、单BPNN模型、单LRNN模型、简单平均组合预测模型和多神经网络切换预测模型进行对比分析,验证本文组合模型的有效性,尤其在滑坡临滑加速变化末段的预测优势。
支持向量回归(SVR)模型是一种针对非线性问题的回归预测方法[15],通过引入核函数将输入向量映射到高维度特征空间,通过定义损失函数和优化目标构建出最优决策函数模型,使回归模型的复杂度最小,从而达到较好的预测效果[16]。SVR模型因其较强的拟合能力和鲁棒性,能有效处理复杂影响因素作用下的滑坡位移预测这一非线性问题。
SVR通过构建非线性映射关系建立滑坡影响因素与滑坡位移量之间的预测模型,其回归估计函数$f(\boldsymbol{x})$可表示为:
$f(\boldsymbol{x})=\boldsymbol{W}^{\mathrm{T}} \varphi(\boldsymbol{x})+b$
式中,在滑坡位移预测研究中特征向量$\boldsymbol{x}$一般为滑坡历史位移时序数据等;$\varphi(\boldsymbol{x})$为将样本数据映射到特征空间的非线性映射函数;$\boldsymbol{W}^{\mathrm{T}}$为自变函数系数;$b$为偏置量。为求解获得$\boldsymbol{W}^{\mathrm{T}}$与$b$,以$\alpha$、$\alpha^*$为拉格朗日系数,构建出拉格朗日函数:
$\begin{gathered}L(\boldsymbol{W}, \alpha, b, \varepsilon, y)=\min _{\alpha, \alpha^*} \frac{1}{2} \sum\limits_{r, i=1}^n\left(\alpha_r-\alpha_r^*\right)^{\mathrm{T}} \\\kappa\left(x_r, x_i\right) \cdots\left(\alpha_j-\alpha_j^*\right)+\varepsilon \sum\limits_{r=1}^n\left(\alpha_r-\alpha_r^*\right)+ \\\sum\limits_{r=1}^n y_r\left(\alpha_r-\alpha_r^*\right), 0 \leqslant \alpha_r, \alpha_r^* \leqslant C, \\r=1, 2, \cdots, n\end{gathered}$
式中,$\kappa\left(x_r, x_i\right)$为核函数;y为$f(\boldsymbol{x})$; $\boldsymbol{W}$为自变函数系数的转置。基于结构风险最小化原则,在特征空间中构建ε不敏感带,使多数样本的预测值位于该敏感带内,对超出敏感带的偏差施加松弛因子惩罚,利用惩罚系数C调整对松弛因子的惩罚强度,再采用网格搜索交叉验证优化模型中的超参数来求解最优回归函数,使模型复杂度与经验风险达到平衡,提升模型对未知数据的泛化能力。
SVR模型在拟合滑坡位移的非线性趋势(如位移突变、周期性变化)时表现突出,通过正则化能有效平衡模型的复杂度与泛化能力,避免过拟合现象,提高滑坡位移预测结果的准确性。特别是SVR在处理小样本滑坡监测数据时更具优势,通过最大化间隔和最小化复杂度策略,能够在滑坡监测数据量较少的情况下仍然保持较好的滑坡位移预测能力,但也会存在调参复杂、计算成本高、解释性弱等局限。
反向传播神经网络(BPNN)模型是当前人工神经网络中应用最为广泛的一类架构模型,该类模型具有较强的非线性映射和泛化能力,通过反向传播算法逐层调整网络参数,使网络输出尽可能接近目标值,在滑坡位移预测研究中得到较好的应用[17]。
在滑坡位移预测研究中,BPNN模型的输入层通常为滑坡时序监测位移等,输出层为预测的滑坡位移量。模型通过多层隐藏层学习滑坡监测位移中的复杂非线性关系,可有效提高预测精度,其训练过程由两部分组成:前向信息传播和误差反向传播[18]。
在前向信息传播阶段,网络接收输入数据,并通过多层神经元逐层计算得到输出。设输入节点数为n,隐藏层节点数为n1,输出节点数为m,输入层到隐藏层、隐藏层到输出层的数学关系可分别表示为:
$y_i=f_1\left(\sum\limits_{i=1}^n \omega_i y_i-\mu_i\right), 1 \leqslant i \leqslant n_1$
$y_j=f_2\left(\sum\limits_{j=1}^{n_1} \omega_j y_j-\mu_j\right), 1 \leqslant j \leqslant m$
式中,yi、yj分别为隐藏层和输出层的值;ωi为输入层到隐藏层节点间连接权重;ωj为隐藏层到输出层节点间连接权重;μi和μj分别为隐藏层和输出层节点输出阈值。
在误差反向传播阶段,首先计算实际输出与目标输出间的误差,再由输出层到输入层利用链式法则计算损失函数关于每个权重和偏置的梯度,按梯度下降方向调整参数,不断优化模型性能。
BPNN模型能够从历史滑坡监测数据中自主学习监测数据间的规律,具有强大的自适应学习力。同时,能够通过迭代训练,可利用误差反向传播机制结合梯度下降优化,动态调整权重以抑制数据噪声,同时综合考虑多个影响因素进行多变量建模和预测,进一步提高预测的准确性。但其也存在易陷入局部最优、收敛速度慢、网络结构设计复杂等缺点。
线性回归神经网络(LRNN)模型是一种结合传统线性回归和人工神经网络的模型,将回归任务嵌入到神经网络框架,通过神经网络的训练机制,能够更灵活地优化模型参数,捕捉到输入特征和目标变量之间的内在关系,在滑坡位移预测研究中也得到较好的应用[19]。
在滑坡位移预测研究中,LRNN模型一般以滑坡监测位移量等作为输入特征建立模型,假设输入特征为x1、x2、…、xn,模型输出为Y,则利用LRNN模型开展滑坡位移预测可表示为:
$\boldsymbol{Y}=W_1 x_1+W_2 x_2+\cdots+W_n x_n+b$
式中,W1、W2、…、Wn为神经网络中的权重;b为偏置项。通过对输入特征赋予权重和偏置,从而产生符合期望的输出,LRNN模型的目标就是通过最小化损失函数来优化网络中的权重和偏置,使模型的预测滑坡位移结果尽可能接近实际观测的滑坡位移[20]。损失函数一般定义为均方误差(MSE):
$\mathrm{MSE}=\frac{1}{n} \sum\limits_{k=1}^n(d(i)-y(i))^2$
式中,n为训练样本的数量;y为滑坡位移的实际值;d为LRNN模型的预测值。
LRNN模型结构相对简单,能够通过神经网络框架直接建立以线性回归为核心的特征关系,训练速度快,计算资源需求低,且具有较好的可解释性。可通过网络中的权重,了解输入特征对滑坡位移的影响程度,但该类模型对滑坡位移中的非线性动态,如滑坡加速形变阶段的位移拟合能力较弱,对滑坡监测数据中的异常值较为敏感。
鉴于SVR、BPNN和LRNN模型在滑坡位移预测中的优势与局限性,为进一步提高模型的预测精度,本文结合3类神经网络模型构建出一种多神经网络加权组合模型,其构建过程主要由单一模型预测和多神经网络加权两部分组成。
设滑坡位移时序监测数据集为y={y1, y2, …, ym},按不同结构训练m种神经网络模型1、模型2、…、模型m,将整个滑坡位移监测数据集分为3个部分:训练集、验证集和预测集。其中,训练集的数据用于训练机器学习模型,验证集用于确定组合模型加权系数,预测集用于评估模型的预测性能。预测值可表示为$\hat{y}=\left\{\hat{y}_1, \hat{y}_2, \cdots\right.$,$\left.\hat{y}_n\right\}$,单一模型预测策略可表示为:
$y_{i+1}=\hat{f}\left(x_i, \cdots, x_{i-d}\right)+\varepsilon$
式中,d为时滞;ε为加性噪声。函数$ \hat{f} $可利用SVR、BPNN或LRNN模型进行估计,SVR、BPNN及LRNN模型中的超参数(如正则化参数C和核参数γ等)可由训练集和验证集确定。
多神经网络加权组合模型中权系数反映的是各个单一类预测模型在组合模型中的影响程度,单一模型预测后,获得已训练完成的参数固定的单一滑坡位移预测模型,即分别为BPNN、SVR和LRNN模型,此时将模型作为加权组合模型由输入数据到输出数据的固定映射。假设输入长度为n,预测长度为1,可表示为:
本文采用最小二乘法来确定权系数,基于各个已完成训练的模型对预测点过去一段时间的预测结果进行动态权重分配。
设现有测试集为$ \boldsymbol{D}=\left\{x_{i-n}, x_{i-n+1}, \cdots\right.$ , $\left.x_{i-1} ; x_i\right\} $,对应的标签(真值)数据为$ \boldsymbol{Y}=\left\{x_i\right\} $,对于已训练模型而言,其模型输入数据为:
$\boldsymbol{X}=\left\{x_{i-n}, x_{i-n+1}, \cdots, x_{i-1}\right\}$
因此,当预测真值数据$ \boldsymbol{Y} $时,数据x1至xi-1均为已知值,可计算已训练好模型在预测点xi过去一段时间的预测情况。将“过去一段时间”称为回望长度,设置回望长度为L,本文中回望长度设置为10,可将其表示为:
$\begin{aligned}& x_{i-1}^{\mathrm{SVR}}=\operatorname{SVR}\left(\left[x_{i-1-n}: x_{i-1}\right)\right) \\& x_{i-1}^{\mathrm{BPNN}}=\operatorname{BPNN}\left(\left[x_{i-1-n}: x_{i-1}\right)\right) \\& x_{i-1}^{\mathrm{LNN}}=\operatorname{LRNN}\left(\left[x_{i-1-n}: x_{i-1}\right)\right)\end{aligned}$
式中,$x_{i-1}^{\mathrm{SVR}}$为SVR模型对$x_{i-1}$的预测值,其余同理;$\left[x_{i-1-n}: x_{i-1}\right)$为$x_{i-1-n}$至$x_{i-1}$之间的所有数据,均为已知值,其中包括$x_{i-1-n}$但不包括$x_{i-1}$。可根据已知值计算出以下数据:
$\begin{aligned}& \boldsymbol{X}^{\mathrm{SVR}}=\left(\begin{array}{c}x_{i-1}^{\mathrm{SVR}} \\x_{i-2}^{\mathrm{SVR}} \\\cdots \\x_{i-L}^{\mathrm{SVR}}\end{array}\right), \boldsymbol{X}^{\mathrm{BPNN}}=\left(\begin{array}{c}x_{i-1}^{\mathrm{BPNN}} \\x_{i-2}^{\mathrm{BPNN}} \\\cdots \\x_{i-L}^{\mathrm{BPNN}}\end{array}\right), \\& \boldsymbol{X}^{\mathrm{LRNN}}=\left(\begin{array}{c}x_{i-1}^{\mathrm{LRNN}} \\x_{i-2}^{\mathrm{LRNN}} \\\cdots \\x_{i-L}^{\mathrm{LRNN}}\end{array}\right), \boldsymbol{X}^{\mathrm{True}}=\left(\begin{array}{c}x_{i-1}^{\mathrm{True}} \\x_{i-2}^{\mathrm{True}} \\\cdots \\x_{i-L}^{\mathrm{True}}\end{array}\right)\end{aligned}$
式中,$\boldsymbol{X}^{\text {True }}$为真值。据此,可构建出以下公式:
$\begin{gathered}\boldsymbol{X}_{L \times 1}^{\mathrm{True}}=\alpha_1 \boldsymbol{X}_{L \times 1}^{\mathrm{SVR}}+\alpha_2 \boldsymbol{X}_{L \times 1}^{\mathrm{BPNN}}+ \\\alpha_3 \boldsymbol{X}_{L \times 1}^{\mathrm{LRNN}}+\alpha_4 \boldsymbol{I}_{L \times 1}\end{gathered}$
式中,$\boldsymbol{X}^{\mathrm{SVR}}、\boldsymbol{X}^{\mathrm{BPNN}}$和$\boldsymbol{X}^{\mathrm{LRNN}}$均为L行1列的列向量,其值如式(10)所示;IL×1为L行的单位列向量;α1~α4均为标量,为待拟和参数, α1、α2、α3分别为SVR、BPNN、LRNN模型的权重, α4为附加偏置参数,反映了观测值均值与单一模型预测值加权均值的差异。若省略偏置参数α4,可能会导致权重系数α1、α2、α3无法最优拟合数据,此时预测的表现则是3种单一模型的加权和能够捕捉目标变量的变化趋势,但实际数据可能也会存在整体偏移。
首先,构建观测向量B,设计矩阵A:
$\boldsymbol{B}=\boldsymbol{X}_{L \times 1}^{\mathrm{True}}=\left(\begin{array}{c}x_{i-1} \\x_{i-2} \\\cdots \\x_{i-L}\end{array}\right)$
$\boldsymbol{A}=\left(\boldsymbol{X}^{\mathrm{SVR}}, \boldsymbol{X}^{\mathrm{BPNN}}, \boldsymbol{X}^{\mathrm{LRNN}}, \boldsymbol{I}\right)_{L \times 4}$
则
$\boldsymbol{B}=\boldsymbol{A}\left(\alpha_1, \alpha_2, \alpha_3, \alpha_4\right)^{\mathrm{T}}$
因此,可基于最小平方和误差构建上述矩阵方程的误差模型,记为E(α),其公式为:
$\begin{gathered}E(\alpha)=E\left(\alpha_1, \alpha_2, \alpha_3, \alpha_4\right)= \\\left\|\boldsymbol{A}\left(\alpha_1, \alpha_2, \alpha_3, \alpha_4\right)^{\mathrm{T}}-\boldsymbol{X}^{\text {True }}\right\|_2^2\end{gathered}$
将待求参数向量(α1, α2, α3, α4)T记为β,通过最小化残差平方和,得到以下公式:
$\begin{gathered}\boldsymbol{A}^{\mathrm{T}} \boldsymbol{A} \boldsymbol{\beta}=\boldsymbol{A}^{\mathrm{T}} \boldsymbol{B} \\\boldsymbol{\beta}=\left(\boldsymbol{A}^{\mathrm{T}} \boldsymbol{A}\right)^{-1} \boldsymbol{A}^{\mathrm{T}} \boldsymbol{B}\end{gathered}$
即可求解出3个单一类预测模型的权重值α1、α2、α3和偏置参数α4。记最优参数为β*,则预测值组合模型可表示为:
$\tilde{x}_i=\alpha_1 x_i^{\mathrm{SVR}}+\alpha_2 x_i^{\mathrm{BPNN}}+\alpha_3 x_i^{\mathrm{LRNN}}+\alpha_4$
式中,$x_i^{\mathrm{SVR}}、x_i^{\mathrm{BPNN}}、x_i^{\mathrm{LRNN}}$分别为各单一模型在第i个时刻的滑坡位移预测值。通过构建上述公式,利用最小二乘法可求解出当前第i个时刻最优的3个单一类预测模型的权重系数。
对预测点xi进行加权求和预测,则结果$\hat{\boldsymbol{Y}}_i$可表示为:
$\hat{\boldsymbol{Y}}_i=\left(x_i^{\mathrm{SVR}}, x_i^{\mathrm{BPNN}}, x_i^{\mathrm{LRNN}}, 1\right) \boldsymbol{\beta}^*$
在加权组合模型中,SVR、BPNN和LRNN模型分别发挥互补优势,SVR模型作为非线性建模的核心,负责捕捉滑坡位移中的复杂趋势与高维非线性关系,尤其是在数据量较少时可提供稳健的预测;BPNN模型可通过多层网络结构自主学习多特征间的深层非线性关系,增强模型对动态变化如滑坡临滑阶段的适应能力;LRNN模型则可提供较好的线性基准预测,平衡组合模型的复杂度,同时具有快速收敛的特性,可弥补其他2种单一模型的计算效率和可解释性问题。通过最小二乘法动态分配权重,组合模型能够融合单一模型各自的优势特性,使3种单一模型最优预测性能达到相对平衡,最终可获得更高的预测精度。
多神经网络加权组合模型的具体构建步骤可概述如下:
1) 对滑坡历史时序监测数据进行预处理。首先进行粗差处理,剔除异常值和噪声,确保数据的可靠性;然后,将原始时序数据重采样调整为适合模型训练的时间尺度;最后,将数据集划分为训练集、验证集和测试集。
2) 选定某单一类模型进行预测分析。首先,针对不同模型的特点,调整其关键参数,如对SVR模型优化其核函数类型、惩罚系数C和核参数γ,对BPNN模型调整其隐藏层节点数、学习率和迭代次数,对LRNN模型通过最小化损失函数(如MSE)来优化其权重和偏置参数。利用训练集确定单一类预测模型的最优参数组合,基于此获得预测结果。该步骤主要是挖掘出单一类预测模型的最佳性能,为后续加权组合提供可靠的基础。
3) 构建多神经网络加权组合模型。在对测试集进行滑坡位移预测时,首先计算各单一类预测模型在当前预测点前一段时间的预测值,结合前一段时间的观测值并基于最小二乘算法,可拟合得到当前预测点最优的单一类预测模型的权重系数,再基于此权重系数对单一类预测模型当前预测点的预测结果进行加权求和,得到最终的预测结果。进一步通过对比预测RMSE,可评估预测模型的预测性能。多神经网络加权组合模型的总体流程见图 1。
本文选择我国典型黄土滑坡区域甘肃黑方台党川滑坡域为实验区[21],长安大学空间监测与灾害研究所已在该区域布设了北斗/GNSS高精度监测网络(图 2)。本文具体针对该区域内2021-01-27和2021-07-08发生在党川附近的2次滑坡事件,选取对应的HF05和HF09北斗/GNSS监测站点实测数据进行建模与对比测试。
HF05与HF09站点监测数据原始采样间隔为5 min,为便于后续建模及对比分析,本文将N、E、U三个方向的位移量归算至偏移量后形成位移时间序列。但由于受复杂环境等多种因素的影响,原始时序位移数据中含有显著的粗差(图 3)。本文先对时序位移数据进行粗差处理,再进行重采样至6 h和12 h时间间隔(图 4),采样后时序位移数据满足滑坡位移预测的快速响应需求。
为评价不同模型的预测性能,本文利用模型预测结果与真值的均方根误差(RMSE)作为评价指标:
$\operatorname{RMSE}(\hat{y}, y)=\sqrt{\frac{1}{n} \sum\limits_{i=1}^n\left(\hat{y}_i-y_i\right)^2}$
式中,n为选取的点个数;$\hat{y}$为模型预测结果;$\hat{y}_i$为第i组预测结果;y为测试集观测值;yi为第i组观测值。
本文测试集主要选取滑坡临滑加速变化末段这一关键的位移时序监测数据,以评估不同模型在这一关键阶段的预测性能。本文将HF05和HF09站点滑坡时序位移数据的训练集、验证集与测试集分割比例设为8∶1∶1,分别得到2组滑坡数据集(表 1)。
为更好地突出本文模型的优势,将本文模型与几种单一类预测模型和其他两类组合预测模型进行对比分析。在模型方案设置中,模型1、模型2、模型3分别表示利用历史滑坡位移数据建立的单一SVR模型、单一BPNN模型、单一LRNN模型,用于对比的两类组合方法分别为简单平均组合预测模型(组合1,其表示将3种单一类预测模型的预测结果取平均值作为最终的预测结果)和多神经网络切换预测模型[14](组合2,其核心思想是在每个预测时间点,基于候选模型在过去n个时段(本文中设置为10)的历史表现(绝对百分比误差MAPE),实时选择在过去n个时段MAPE最低的某单一类预测模型进行预测,即此时这一单一类预测模型的权为1),组合3为本文构建的组合模型。
根据模型预测性能的评价方法,本文基于HF05与HF09站点时序位移监测数据在6 h、12 h时间间隔下计算不同模型的预测RMSE值,结果见表 2。
从表 2可以看出,无论是对于HF05还是HF09站点,组合3模型预测RMSE值均低于其他所有对比模型。在HF05与HF09站点数据集6 h、12 h间隔中,组合3与组合1模型相比较,预测精度分别提升达约82%、52%、68%、61%,与组合2模型相比较,预测精度提升分别约为66%、12%、29%、21%。组合2模型预测精度高于组合1模型,分析其原因可能是组合1模型会受到预测效果较差的单一类型预测模型的影响,组合2模型则利用了在训练集上表现性能最好的单一类型预测模型。对于单一类型预测模型1和模型2,其预测精度均低于组合1、组合2、组合3模型的预测精度。对于单一模型3预测RMSE值与组合2模型相同的原因,主要是因为多神经网络切换预测模型根据其核心思想最后选择的MAPE最低的预测模型为单一LRNN模型。
为更好地展示本文模型(组合3)的预测性能,对HF05和HF09站点数据集分别选择预测精度最高的6 h时间间隔进行可视化,对比不同模型在临滑加速变化阶段的预测结果。图 5(a)显示,HF05站点测试集临滑阶段滑坡位移整体呈现出持续加速的变化状态,但在其中部阴影部分滑坡位移呈现出显著的阶跃式突变特征。因此,本文选用HF05站点测试集这一中部阶跃式突变作为测试模型在临滑阶段突变中的预测性能,图 5(b)为HF05站点测试集中部阶跃式突变的放大展示。由图 6可知,HF09站点测试集滑坡位移整体也表现出渐变加速的变形特征,在最末端尤为突出,因此本文选用HF09站点测试集尾部作为测试模型在临滑急速变化中的预测性能。
从图 5和6可以明显看出,本文模型(组合3)相较于其他预测模型,在HF05站点测试集中部阶跃式突变与HF09测试集尾部临滑急速变化阶段,预测位移曲线更贴近真值,预测效果也最佳。
为更加细致地对比不同预测模型在临滑阶段突变与临滑急速变化阶段下的预测性能,本文进一步计算了HF05站点中部阶跃式突变与HF09站点末端临滑急速变化阶段下,各组合模型的预测残差绝对值。图 7显示,在滑坡位移突变与临滑急速变化阶段,本文模型(组合3)预测残差均显著小于其他对比模型,组合1、组合2和组合3模型预测残差绝对值均值分别为0.011 1 m、0.005 2 m、0.002 0 m和0.047 1 m、0.013 0 m、0.004 7 m。上述特征也进一步表明,本文模型在滑坡位移突变情况下具有更高的预测精度。
需要说明的是,本文在构建多神经网络加权组合模型过程中结合了3种单一神经网络模型,在实际应用中也可组合其他类型神经网络模型,并进一步结合其他环境影响因子,充分发挥出多类神经网络模型的优势,提高滑坡位移预测精度。
为验证本文组合模型在不同区域滑坡位移预测场景下的适用性,本文进一步选择三峡库区白水河滑坡监测数据和八字门滑坡监测数据,开展模型普适性验证,两处区域滑坡监测数据见图 8。本文研究区域黑方台党川滑坡是典型的黄土滑坡,在外部灌溉、降雨及黄土自身水敏性特性影响下,该滑坡体监测位移呈现出显著的渐进破坏式特征(图 4)。而三峡库区库岸滑坡的变形主要受季节性降雨、库水位及岩土层弱化变形等影响,白水河滑坡与八字门滑坡体运动变形与党川黄土滑坡体均呈现出近似阶跃型周期波动型运动变形特征[6, 16]。
针对黑方台党川滑坡相同的实验设计与模型构建策略,对比不同预测模型在三峡库区白水河、八字门滑坡数据集测试集的预测性能。不同模型在测试集的RMSE值见表 3。
由表 3可知,相较于其他对比模型,本文模型(组合3)无论在白水河滑坡还是八字门滑坡位移预测中,均具有最小的预测RMSE值, 进一步验证了本文构建的多神经网络加权组合模型在不同类型、不同地质条件滑坡场景下的适用性。
本文针对加权组合预测模型解算时利用最小二乘法确定权系数,基于单一模型在预测点过去一段时间的预测结果进行动态权重分配,此时回望长度对最终组合模型的预测精度会产生一定的影响,是组合模型的一个关键超参数,本文设置的回望长度为10。
为进一步测试超参数的敏感性,本文选择HF05和HF09站点数据集6 h时间间隔的其他参数设置进行测试。根据不同的数据量,设置HF05站点数据集的超参数测试集合为[15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100, 105, 110, 115, 120, 125, 130, 135, 140, 145, 150, 155, 160, 165, 170, 175, 180, 185, 190, 195, 200, 205, 210, 215, 220, 225, 230, 235, 240, 245, 250, 255, 260, 400]共计51组,设置HF09站点数据集的超参数测试集合为[15, 20, 25, 30, 35, 40, 45, 50, 55, 60, 65, 70, 75, 80, 85, 90, 95, 100]共计18组。
采用与§1.4相同的实验设计与模型构建策略,仅更改回望长度的参数设置,将不同回望长度下的模型预测误差进行可视化,结果见图 9。
由图 9可以看出,回望长度参数的调整对模型预测误差有较大的影响,同时表明2次加权过程并非冗余操作,也进一步验证了本文组合模型设计的合理性。
在HF05站点数据集中随着回望长度的增加,模型预测误差呈先下降后上升的趋势(图 9(a)),而在HF09站点数据集中随着回望长度的增加,模型的预测误差则呈现出越来越大的趋势(图 9(b))。本文针对HF05与HF09站点数据集的回望长度均设置为10,对于HF09站点数据集而言这一设置是最优超参数(预测误差最小),虽然对HF05站点数据集中这一设置并非是最优超参数(图 9(a)显示25为最优超参数),但在此回望程度设置下, 本文组合模型预测精度仍优于其他对比模型。因此,为实验测试的统一,本文回望长度均设置为10。
在实际滑坡预测研究中,对于不同的数据集,由于其内在特征不同,每个数据集所对应的最优回望长度也不同。但本文组合模型仅涉及回望长度这一个超参数,因此可利用枚举的方式来确定出最优或较优的超参数。
为提高滑坡位移组合模型的预测精度,本文发展了一种多神经网络加权组合的滑坡位移组合预测模型,通过典型滑坡体北斗/GNSS实测数据对比测试,验证了本文组合预测模型的有效性,得出如下结论:
1) 本文组合预测模型的预测结果,可以避免简单平均组合预测模型会受到预测效果较差单一类型模型的影响,相较于多神经网络切换预测模型根据所有历史时刻预测误差评估并选择单一最优预测模型的方式,能够更好地兼顾到历史时刻与当前预测点情况,并通过加权求和的方式获得更高精度的滑坡位移预测值。
2) 相较于单一类预测模型、简单平均组合预测模型及多神经网络切换预测模型,本文组合模型在滑坡临滑加速阶段预测效果最佳,具有较好的推广应用价值。
  • 国家自然科学基金(42174006)
  • 国家自然科学基金(42090055)
  • 陕西省杰出青-科学基金(2022JC-18)
  • 长安大学中央高校基本科研业务费专项(300102263201)
参考文献 引证文献
排序方式:
1
朱庆, 曾浩炜, 丁雨淋, 等. 重大滑坡隐患分析方法综述[J]. 测绘学报, 2019, 48 (12): 1551- 1561
Zhu Qing , Zeng Haowei , Ding Yulin , et al. A Review of Major Potential Landslide Hazards Analysis[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48 (12): 1551- 1561
2
王佳佳, 殷坤龙, 杜娟, 等. 基于GIS考虑准动态湿度指数的滑坡危险性预测水文-力学耦合模型研究[J]. 岩石力学与工程学报, 2013, 32 (增2): 3868- 3877
Wang Jiajia , Yin Kunlong , Du Juan , et al. Research on Hydrology-Mechanics Coupling Model of Landslide Hazards Prediction Base on GIS by Using Quasi-Dynamic Wetness Index[J]. Chinese Journal of Rock Mechanics and Engineering, 2013, 32 (S2): 3868- 3877
3
詹威威, 黄润秋, 裴向军, 等. 沟道型滑坡-碎屑流运动距离经验预测模型研究[J]. 工程地质学报, 2017, 25 (1): 154- 163
Zhan Weiwei , Huang Runqiu , Pei Xiangjun , et al. Empirical Prediction Model for Movement Distance of Gully-Type Rock Avalanches[J]. Journal of Engineering Geology, 2017, 25 (1): 154- 163
4
黄发明. 基于3S和人工智能的滑坡位移预测与易发性评价[D]. 武汉: 中国地质大学(武汉), 2017
Huang Faming. Landslide Displacement Prediction and Susceptibility Assessment Based on 3S and Artificial Intelligence[D]. Wuhan: China University of Geosciences, 2017
5
方臣, 王正海, 耿欣, 等. 基于ε-SVR的滑坡位移预测[J]. 防灾减灾学报, 2012, 28 (2): 39- 43
Fang Chen , Wang Zhenghai , Geng Xin , et al. Prediction of Landslide Displacement Based on ε-Support Vector Regression Machine[J]. Journal of Disaster Prevention and Reduction, 2012, 28 (2): 39- 43
6
李德营, 殷坤龙. 基于影响因子的GM(1, 1)-BP模型在八字门滑坡变形预测中的应用[J]. 长江科学院院报, 2013, 30 (2): 6- 11
Li Deying , Yin Kunlong . Application of GM(1, 1)-BP Model to the Deformation Prediction of Bazimen Landslide in Consideration of Influencing Factors[J]. Journal of Yangtze River Scientific Research Institute, 2013, 30 (2): 6- 11
7
Zhang W Z , Li Y J , Li X S , et al. Forecasting of Landslide Displacement Based on Exponential Smoothing and Nonlinear Regression Analysis[J]. Applied Mechanics and Materials, 2013, 353-356, 1101- 1105
8
王朝阳, 李丽敏, 温宗周, 等. 基于时间序列和CNN-LSTM的滑坡位移动态预测[J]. 国外电子测量技术, 2022, 41 (3): 1- 8
Wang Chaoyang , Li Limin , Wen Zongzhou , et al. Dynamic Prediction of Landslide Displacement Based on Time Series and CNN-LSTM[J]. Foreign Electronic Measurement Technology, 2022, 41 (3): 1- 8
9
Long H T , Zhang G D , Cao J L . The Use of BP Neural Network in the Landslide Prediction of Three Gorges Reservoir[J]. Advanced Materials Research, 2013, 838-841, 2179- 2184
10
Melati D N , Umbara R P , Astisiasari A , et al. A Comparative Evaluation of Landslide Susceptibility Mapping Using Machine Learning-Based Methods in Bogor Area of Indonesia[J]. Environmental Earth Sciences, 2024, 83 (3)
11
Jiang T , Shen Z Z , Yang M , et al. A New Model Approach to Predict the Unloading Rock Slope Displacement Behavior Based on Monitoring Data[J]. Structural Engineering and Mechanics, 2018, 67 (2): 105- 113
12
罗袆沅, 蒋亚楠, 许强, 等. 基于深度学习的滑坡位移时空预测[J]. 测绘学报, 2022, 51 (10): 2160- 2170
Luo Huiyuan , Jiang Yanan , Xu Qiang , et al. A Spatio-Temporal Network for Landslide Displacement Prediction Based on Deep Learning[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51 (10): 2160- 2170
13
李达, 瞿伟, 张勤, 等. 融合多层感知机和优化支持向量回归的滑坡位移预测模型[J]. 武汉大学学报: 信息科学版, 2023, 48 (8): 1380- 1388
Li Da , Qu Wei , Zhang Qin , et al. Landslide Displacement Prediction Model Integrating Multi-Layer Perceptron and Optimized Support Vector Regression[J]. Geomatics and Information Science of Wuhan University, 2023, 48 (8): 1380- 1388
14
Lian C , Zeng Z G , Yao W , et al. Multiple Neural Networks Switched Prediction for Landslide Displacement[J]. Engineering Geology, 2015, 186, 91- 99
15
Vapnik V N . The Nature of Statistical Learning Theory[M]. New York: Springer, 1995
16
张俊, 殷坤龙, 王佳佳, 等. 基于时间序列与PSO-SVR耦合模型的白水河滑坡位移预测研究[J]. 岩石力学与工程学报, 2015, 34 (2): 382- 391
Zhang Jun , Yin Kunlong , Wang Jiajia , et al. Displacement Prediction of Baishuihe Landslide Based on Time Series and pso-Svr Model[J]. Chinese Journal of Rock Mechanics and Engineering, 2015, 34 (2): 382- 391
17
Hecht-Nielsen. Theory of the Backpropagation Neural Network[C]. International Joint Conference on Neural Networks, Washington DC, 1989
18
张群, 许强, 吴礼舟, 等. 南江滑坡群体积的BP神经网络模型与预测[J]. 水文地质工程地质, 2015, 42 (1): 134- 139
Zhang Qun , Xu Qiang , Wu Lizhou , et al. BP Neural Network Model for Forecasting Volume of Landslide Group in Nanjiang[J]. Hydrogeology and Engineering Geology, 2015, 42 (1): 134- 139
19
王秀丽, 李恒凯. 滑坡变形的回归-神经网络预测模型研究[J]. 人民黄河, 2012, 34 (7): 90- 92
Wang Xiuli , Li Hengkai . Research on Prediction Model of Regression-Neural Network for Landslide Deformation[J]. Yellow River, 2012, 34 (7): 90- 92
20
苏盈盈, 李太福, 康东帅, 等. 多层线性神经网络与单层线性神经网络的等效性研究[J]. 西南师范大学学报: 自然科学版, 2017, 42 (12): 105- 112
Su Yingying , Li Taifu , Kang Dongshuai , et al. On Equivalence Verification between Single-Layer and Multi-Layer Linear Neural Network[J]. Journal of Southwest China Normal University (Natural Science Edition), 2017, 42 (12): 105- 112
21
白正伟, 张勤, 黄观文, 等. "轻终端+行业云"的实时北斗滑坡监测技术[J]. 测绘学报, 2019, 48 (11): 1424- 1429
Bai Zhengwei , Zhang Qin , Huang Guanwen , et al. Real-Time Beidou Landslide Monitoring Technology of "Light Terminal Plus Industry Cloud"[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48 (11): 1424- 1429
2026年第46卷第2期
39
16
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2025.03.086
  • 接收时间:2025-03-19
  • 首发时间:2026-10-29
  • 出版时间:2026-02-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-19
基金
国家自然科学基金(42174006)
国家自然科学基金(42090055)
陕西省杰出青-科学基金(2022JC-18)
长安大学中央高校基本科研业务费专项(300102263201)
作者信息
    1 长安大学地质工程与测绘学院, 西安, 710054
    2 西部矿产资源与地质工程教育部重点实验室, 西安, 710054
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2025.03.086
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