Article(id=1149774728174465670, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149774724923880044, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402357, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1711987200000, receivedDateStr=2024-04-02, revisedDate=1737475200000, revisedDateStr=2025-01-22, acceptedDate=null, acceptedDateStr=null, onlineDate=1752057256978, onlineDateStr=2025-07-09, pubDate=1745769600000, pubDateStr=2025-04-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752057256978, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752057256978, creator=13701087609, updateTime=1752057256978, updator=13701087609, issue=Issue{id=1149774724923880044, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='12', pageStart='4827', pageEnd='5272', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752057256203, creator=13701087609, updateTime=1768456746933, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559174552764785, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149774724923880044, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559174552764786, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149774724923880044, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4913, endPage=4919, ext={EN=ArticleExt(id=1149774728409346698, articleId=1149774728174465670, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Long Term Displacement Prediction of Landslides Based on GCformer, columnId=1156262729351549255, journalTitle=Science Technology and Engineering, columnName=Papers·Astronomy and Geosciences, runingTitle=null, highlight=null, articleAbstract=

To enhance the long-term displacement prediction accuracy of landslides, the GCformer model was applied to landslide displacement forecasting, and a novel landslide displacement prediction approach grounded in the GCformer model was proposed. This methodology leveraged rainfall and displacement as input variables, utilized the GConvmsk module to capture the global information of the sequence, and combined a linear scaling technique of sequence length to efficiently extract data features. Concurrently, the PatchTST model was employed to automatically extract short-term and long-term signals from the sequence data, in order to obtain more comprehensive historical information and bolster the model's robustness and modeling capability. Finally, the landslide displacement monitoring data from Jinliuping Village and Yuanshitan Village in Huichuan County, Dingxi City, Gansu Province, were utilized for case validation. The findings demonstrate that the proposed model exhibits superior prediction accuracy and reliability. In comparison to the Autoformer model and the FEDformer model, the GCformer model is found to achieve the lowest error in both total displacement and vertical displacement.

, correspAuthors=Hui-qin WANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Wan-li YANG, Yong-qiang HE, Jian-liang ZHANG, Hui-qin WANG, Xiao-juan LI), CN=ArticleExt(id=1149774744758743100, articleId=1149774728174465670, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于GCformer的滑坡长期位移预测, columnId=1156262730077163858, journalTitle=科学技术与工程, columnName=论文·天文学、地球科学, runingTitle=null, highlight=null, articleAbstract=

为提高滑坡长期位移预测精度,将GCformer模型运用到滑坡位移预测,提出一种基于GCformer模型的滑坡位移预测方法。该方法以降雨量和位移量作为输入,利用GConvmsk模块获取序列的全局信息,并结合序列长度线性缩放来高效提取数据特征。同时,利用PatchTST模型来自动提取序列数据中的近短期信号,获取更全面的历史信息,从而提高模型的鲁棒性和对数据的建模能力。最后,利用甘肃定西市会川镇锦柳坪村和元始滩村滑坡位移监测数据进行实例验证。结果表明:该模型与Autoformer模型和FEDformer模型相比,GCformer模型在总位移和垂直位移上具有更高的预测精度和更好的可靠性。

, correspAuthors=王惠琴, authorNote=null, correspAuthorsNote=
* 王惠琴 (1971—),女,汉族,甘肃渭源人,博士,教授。研究方向:无线光通信。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Oon6d3/P6TZYvBGOwj6luw==, magXml=zSS711Khl/EWQlIidi6X8g==, pdfUrl=null, pdf=cK7jCs49uE9ViykoPf+I3Q==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=QXU25ebFUCoeSJvegG0ezg==, mapNumber=null, authorCompany=null, fund=null, authors=

杨万里(1981—),男,汉族,河北承德人,硕士,高级工程师。研究方向:高速公路建设管理。E-mail:

, authorsList=杨万里, 何永强, 张建良, 王惠琴, 李晓娟)}, authors=[Author(id=1179786705797263952, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=305283628@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1179786705897927250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786705797263952, language=EN, stringName=Wan-li YANG, firstName=Wan-li, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Gansu Road and Bridge Highway Investment Co. , Ltd. , Lanzhou 730030, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179786705977619027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786705797263952, language=CN, stringName=杨万里, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 甘肃路桥公路投资有限公司, 兰州 730030, bio={"content":"

杨万里(1981—),男,汉族,河北承德人,硕士,高级工程师。研究方向:高速公路建设管理。E-mail:

"}, bioImg=null, bioContent=

杨万里(1981—),男,汉族,河北承德人,硕士,高级工程师。研究方向:高速公路建设管理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179786705570771524, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=1, ext=[AuthorCompanyExt(id=1179786705574965829, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705570771524, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Gansu Road and Bridge Highway Investment Co. , Ltd. , Lanzhou 730030, China), AuthorCompanyExt(id=1179786705583354438, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705570771524, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 甘肃路桥公路投资有限公司, 兰州 730030)])]), Author(id=1179786706061505109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, 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=1179786706162168407, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706061505109, language=EN, stringName=Yong-qiang HE, firstName=Yong-qiang, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179786706317357656, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706061505109, language=CN, stringName=何永强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 西北民族大学土木工程学院, 兰州 730030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179786705650463303, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=2, ext=[AuthorCompanyExt(id=1179786705658851912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China), AuthorCompanyExt(id=1179786705667240521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西北民族大学土木工程学院, 兰州 730030)])]), Author(id=1179786706388660826, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, 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=1179786706455769692, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706388660826, language=EN, stringName=Jian-liang ZHANG, firstName=Jian-liang, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179786706577404509, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706388660826, language=CN, stringName=张建良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 兰州理工大学计算机与通信学院, 兰州 730050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179786705717572170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=3, ext=[AuthorCompanyExt(id=1179786705725960779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China), AuthorCompanyExt(id=1179786705730155084, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 兰州理工大学计算机与通信学院, 兰州 730050)])]), Author(id=1179786706669679199, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Whq1222@lut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1179786706803896929, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706669679199, language=EN, stringName=Hui-qin WANG, firstName=Hui-qin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179786706887783010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786706669679199, language=CN, stringName=王惠琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 兰州理工大学计算机与通信学院, 兰州 730050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179786705717572170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=3, ext=[AuthorCompanyExt(id=1179786705725960779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China), AuthorCompanyExt(id=1179786705730155084, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 兰州理工大学计算机与通信学院, 兰州 730050)])]), Author(id=1179786707013612132, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, 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=1179786707097498214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786707013612132, language=EN, stringName=Xiao-juan LI, firstName=Xiao-juan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179786707152024167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, authorId=1179786707013612132, language=CN, stringName=李晓娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 西北民族大学土木工程学院, 兰州 730030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179786705650463303, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=2, ext=[AuthorCompanyExt(id=1179786705658851912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China), AuthorCompanyExt(id=1179786705667240521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西北民族大学土木工程学院, 兰州 730030)])])], keywords=[Keyword(id=1179786707298824808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, orderNo=1, keyword=landslide displacement prediction), Keyword(id=1179786707370127977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, orderNo=2, keyword=GCformer model), Keyword(id=1179786707441431146, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, orderNo=3, keyword=FEDformer model), Keyword(id=1179786707533705835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, orderNo=4, keyword=Autoformer model), Keyword(id=1179786707596620396, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, orderNo=1, keyword=滑坡位移预测), Keyword(id=1179786707667923565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, orderNo=2, keyword=GCformer模型), Keyword(id=1179786707760198254, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, orderNo=3, keyword=FEDformer模型), Keyword(id=1179786707818918511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, orderNo=4, keyword=Autoformer模型)], refs=[Reference(id=1179786709140124287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=89, pageEnd=94, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=武鑫, 郑东健, 刘永涛, journalName=水利水电科技进展, refType=null, unstructuredReference=武鑫, 郑东健, 刘永涛, 等. 滑坡失稳时间预测方法研究综述[J]. 水利水电科技进展, 2021, 41(4): 89-94., articleTitle=滑坡失稳时间预测方法研究综述, refAbstract=null), Reference(id=1179786709253370496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=4, pageStart=89, pageEnd=94, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Wu Xin, Zheng Dongjian, Liu Yongtao, journalName=Progress in Water Resources and Hydropower Science and Technology, refType=null, unstructuredReference=Wu Xin, Zheng Dongjian, Liu Yongtao, et al. Review of landslide instability time prediction method[J]. Progress in Water Resources and Hydropower Science and Technology, 2021, 41(4): 89-94., articleTitle=Review of landslide instability time prediction method, refAbstract=null), Reference(id=1179786709345645185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=5, pageStart=1657, pageEnd=1674, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=窦杰, 向子林, 许强, journalName=地球科学, refType=null, unstructuredReference=窦杰, 向子林, 许强, 等. 机器学习在滑坡智能防灾减灾中的应用与发展趋势[J]. 地球科学, 2023, 48(5): 1657-1674., articleTitle=机器学习在滑坡智能防灾减灾中的应用与发展趋势, refAbstract=null), Reference(id=1179786709408559746, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=5, pageStart=1657, pageEnd=1674, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Dou Jie, Xiang Zilin, Xu Qiang, journalName=Earth Science, refType=null, unstructuredReference=Dou Jie, Xiang Zilin, Xu Qiang, et al. Application and development trend of machine learning in landslide intelligent disaster prevention and mitigation[J]. Earth Science, 2023, 48(5): 1657-1674., articleTitle=Application and development trend of machine learning in landslide intelligent disaster prevention and mitigation, refAbstract=null), Reference(id=1179786709488251523, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=李骅锦, journalName=运用深度学习和统计学习方法预测库岸滑坡变形, refType=null, unstructuredReference=李骅锦. 运用深度学习和统计学习方法预测库岸滑坡变形[D]. 成都: 成都理工大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1179786709656023684, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Li Huajin, journalName=Predicting landslide deformation of bank bank using deep learning and statistical learning methods, refType=null, unstructuredReference=Li Huajin. Predicting landslide deformation of bank bank using deep learning and statistical learning methods[D]. Chengdu: Chengdu University of Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1179786709760881285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=14, pageEnd=27, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=张抒, 唐辉明, 龚文平, journalName=地质科技通报, refType=null, unstructuredReference=张抒, 唐辉明, 龚文平, 等. 基于物理力学机制的滑坡数值预报模式: 综述、挑战与机遇[J]. 地质科技通报, 2022, 41(6): 14-27., articleTitle=基于物理力学机制的滑坡数值预报模式: 综述、挑战与机遇, refAbstract=null), Reference(id=1179786709811212934, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=14, pageEnd=27, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Zhang Shu, Tang Huiming, Gong Wenping, journalName=Geoscience and Technology Bulletin, refType=null, unstructuredReference=Zhang Shu, Tang Huiming, Gong Wenping, et al. Numerical landslide prediction model based on physical-mechanical mechanisms: overview, challenges and opportunities[J]. Geoscience and Technology Bulletin, 2022, 41(6): 14-27., articleTitle=Numerical landslide prediction model based on physical-mechanical mechanisms: overview, challenges and opportunities, refAbstract=null), Reference(id=1179786709874127495, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=李晴文, journalName=基于智能算法组合模型的边坡位移预测研究, refType=null, unstructuredReference=李晴文. 基于智能算法组合模型的边坡位移预测研究[D]. 大连: 大连理工大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1179786709924459144, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Li Qingwen, journalName=Research on slope displacement prediction based on intelligent algorithm combination model, refType=null, unstructuredReference=Li Qingwen. Research on slope displacement prediction based on intelligent algorithm combination model[D]. Dalian: Dalian University of Technology, 2021., articleTitle=null, refAbstract=null), Reference(id=1179786709987373705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=19, pageStart=7845, pageEnd=7855, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=王念秦, 申辉辉, 鲁兴生, journalName=科学技术与工程, refType=null, unstructuredReference=王念秦, 申辉辉, 鲁兴生. 边坡变形监测技术发展现状及问题对策[J]. 科学技术与工程, 2021, 21(19): 7845-7855., articleTitle=边坡变形监测技术发展现状及问题对策, refAbstract=null), Reference(id=1179786710096425610, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=19, pageStart=7845, pageEnd=7855, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Wang Nianqin, Shen Huihui, Lu Xingsheng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Nianqin, Shen Huihui, Lu Xingsheng. Development status and problem countermeasures of slope deformation monitoring technology[J]. Science Technology and Engineering, 2021, 21(19): 7845-7855., articleTitle=Development status and problem countermeasures of slope deformation monitoring technology, refAbstract=null), Reference(id=1179786710167728779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=4, pageStart=461, pageEnd=473, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=袁维, 孙瑞峰, 钟辉亚, journalName=水利学报, refType=null, unstructuredReference=袁维, 孙瑞峰, 钟辉亚, 等. 阶跃型滑坡综合变形预测及监测预警方法研究[J]. 水利学报, 2023, 54(4): 461-473., articleTitle=阶跃型滑坡综合变形预测及监测预警方法研究, refAbstract=null), Reference(id=1179786710222254732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=4, pageStart=461, pageEnd=473, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Yuan Wei, Sun Ruifeng, Zhong Huiya, journalName=Journal of Water Resources, refType=null, unstructuredReference=Yuan Wei, Sun Ruifeng, Zhong Huiya, et al. Research on integrated deformation prediction and monitoring and warning methods for step-type landslides[J]. Journal of Water Resources, 2023, 54(4): 461-473., articleTitle=Research on integrated deformation prediction and monitoring and warning methods for step-type landslides, refAbstract=null), Reference(id=1179786710285169293, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=105, pageEnd=113, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=曾斌, 吕权儒, 寇磊, journalName=中国地质灾害与防治学报, refType=null, unstructuredReference=曾斌, 吕权儒, 寇磊, 等. 基于Logistic回归和随机森林的清江流域长阳库岸段堆积层滑坡易发性评价[J]. 中国地质灾害与防治学报, 2023, 34(4): 105-113., articleTitle=基于Logistic回归和随机森林的清江流域长阳库岸段堆积层滑坡易发性评价, refAbstract=null), Reference(id=1179786710364861070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=4, pageStart=105, pageEnd=113, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Zeng Bin, Lü Quanru, Kou Lei, journalName=Chinese Journal of Geological Hazards and Prevention, refType=null, unstructuredReference=Zeng Bin, Quanru, Kou Lei, et al. Evaluation of landslide susceptibility of stacked layer landslides in the bank section of Changyang Reservoir in Qingjiang River Basin based on Logistic regression and random forest[J]. Chinese Journal of Geological Hazards and Prevention, 2023, 34(4): 105-113., articleTitle=Evaluation of landslide susceptibility of stacked layer landslides in the bank section of Changyang Reservoir in Qingjiang River Basin based on Logistic regression and random forest, refAbstract=null), Reference(id=1179786710431969935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=1096, pageEnd=1110, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=杨玲, 魏静, 许子伏, journalName=地球科学与环境学报, refType=null, unstructuredReference=杨玲, 魏静, 许子伏. 基于平滑先验法-麻雀搜索算法-支持向量机回归模型的滑坡位移预测——以三峡库区八字门和白水河滑坡为例[J]. 地球科学与环境学报, 2022, 44(6): 1096-1110., articleTitle=基于平滑先验法-麻雀搜索算法-支持向量机回归模型的滑坡位移预测——以三峡库区八字门和白水河滑坡为例, refAbstract=null), Reference(id=1179786710524244624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=6, pageStart=1096, pageEnd=1110, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Yang Ling, Wei Jing, Xu Zifu, journalName=Journal of Earth Sciences and Environment, refType=null, unstructuredReference=Yang Ling, Wei Jing, Xu Zifu. Landslide displacement prediction based on smoothing prior method-sparrow search algorithm-support vector machine regression model: a case study of Bazimen and Baishuihe landslides in the Three Gorges Reservoir Area[J]. Journal of Earth Sciences and Environment, 2022, 44(6): 1096-1110., articleTitle=Landslide displacement prediction based on smoothing prior method-sparrow search algorithm-support vector machine regression model: a case study of Bazimen and Baishuihe landslides in the Three Gorges Reservoir Area, refAbstract=null), Reference(id=1179786710587159185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=5, pageStart=1786, pageEnd=1793, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=马飞燕, 李向新, journalName=科学技术与工程, refType=null, unstructuredReference=马飞燕, 李向新. 基于改进麻雀搜索算法-核极限学习机耦合算法的滑坡位移预测模型[J]. 科学技术与工程, 2022, 22(5): 1786-1793., articleTitle=基于改进麻雀搜索算法-核极限学习机耦合算法的滑坡位移预测模型, refAbstract=null), Reference(id=1179786710645879442, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=5, pageStart=1786, pageEnd=1793, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=Ma Feiyan, Li Xiangxin, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Ma Feiyan, Li Xiangxin. Landslide displacement prediction model based on improved sparrow search algorithm-kernel extreme learning machine coupling algorithm[J]. Science Technology and Engineering, 2022, 22(5): 1786-1793., articleTitle=Landslide displacement prediction model based on improved sparrow search algorithm-kernel extreme learning machine coupling algorithm, refAbstract=null), Reference(id=1179786710712988307, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=6, pageEnd=13, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=张明岳, 李丽敏, 温宗周, journalName=人民珠江, refType=null, unstructuredReference=张明岳, 李丽敏, 温宗周. RNN与LSTM方法用于滑坡位移动态预测的研究[J]. 人民珠江, 2021, 42(9): 6-13., articleTitle=RNN与LSTM方法用于滑坡位移动态预测的研究, refAbstract=null), Reference(id=1179786710775902868, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=6, pageEnd=13, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=Zhang Mingyue, Li Limin, Wen Zongzhou, journalName=People's Pearl River, refType=null, unstructuredReference=Zhang Mingyue, Li Limin, Wen Zongzhou. Research on RNN and LSTM method for landslide position movement prediction[J]. People's Pearl River, 2021, 42(9): 6-13., articleTitle=Research on RNN and LSTM method for landslide position movement prediction, refAbstract=null), Reference(id=1179786710838817429, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=10, pageStart=3597, pageEnd=3616, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=Saha S, Saha A, Hembram T K, journalName=Stochastic Environmental Research and Risk Assessment, refType=null, unstructuredReference=Saha S, Saha A, Hembram T K, et al. Prediction of spatial landslide susceptibility applying the novel ensembles of CNN, GLM and random forest in the Indian Himalayan region[J]. Stochastic Environmental Research and Risk Assessment, 2022, 36(10): 3597-3616., articleTitle=Prediction of spatial landslide susceptibility applying the novel ensembles of CNN, GLM and random forest in the Indian Himalayan region, refAbstract=null), Reference(id=1179786710910120598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=1, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=鄢好, 陈骄锐, 李绍红, journalName=人民长江, refType=null, unstructuredReference=鄢好, 陈骄锐, 李绍红, 等. 基于时间序列和GRU的滑坡位移预测[J]. 人民长江, 2021, 52(1): 102-107, 133., articleTitle=基于时间序列和GRU的滑坡位移预测, refAbstract=null), Reference(id=1179786710985618071, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=1, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=Yan Hao, Chen Jiaorui, Li Shaohong, journalName=People's Yangtze River, refType=null, unstructuredReference=Yan Hao, Chen Jiaorui, Li Shaohong, et al. Landslide displacement prediction based on time series and GRU[J]. People's Yangtze River, 2021, 52(1): 102-107, 133., articleTitle=Landslide displacement prediction based on time series and GRU, refAbstract=null), Reference(id=1179786711048532632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=1, pageStart=19, pageEnd=27, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=梁阳, 肖婷, 胡程, journalName=信号处理, refType=null, unstructuredReference=梁阳, 肖婷, 胡程, 等. 基于长期监测数据与LSTM网络的滑坡位移预测[J]. 信号处理, 2022, 38(1): 19-27., articleTitle=基于长期监测数据与LSTM网络的滑坡位移预测, refAbstract=null), Reference(id=1179786711107252889, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=38, issue=1, pageStart=19, pageEnd=27, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=Liang Yang, Xiao Ting, Hu Cheng, journalName=Signal Processing, refType=null, unstructuredReference=Liang Yang, Xiao Ting, Hu Cheng, et al. Landslide displacement prediction based on long-term monitoring data and LSTM network[J]. Signal Processing, 2022, 38(1): 19-27., articleTitle=Landslide displacement prediction based on long-term monitoring data and LSTM network, refAbstract=null), Reference(id=1179786711165973146, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=2, pageStart=197, pageEnd=210, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=田原, 庞骁, 赵文祎, journalName=北京大学学报: 自然科学版, refType=null, unstructuredReference=田原, 庞骁, 赵文祎, 等. 基于Transformer的滑坡短期位移预测模型[J]. 北京大学学报: 自然科学版, 2023, 59(2): 197-210., articleTitle=基于Transformer的滑坡短期位移预测模型, refAbstract=null), Reference(id=1179786711245664923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=2, pageStart=197, pageEnd=210, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=Tian Yuan, Pang Xiao, Zhao Wenyi, journalName=Journal of Peking University: Natural Science Edition, refType=null, unstructuredReference=Tian Yuan, Pang Xiao, Zhao Wenyi, et al. Short-term displacement prediction model of landslide based on Transformer[J]. Journal of Peking University: Natural Science Edition, 2023, 59(2): 197-210., articleTitle=Short-term displacement prediction model of landslide based on Transformer, refAbstract=null), Reference(id=1179786711300190876, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2021, volume=34, issue=null, pageStart=22419, pageEnd=22430, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=Wu H, Xu J, Wang J, journalName=Advances in Neural Information Processing Systems, refType=null, unstructuredReference=Wu H, Xu J, Wang J, et al. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in Neural Information Processing Systems, 2021, 34: 22419-22430., articleTitle=Autoformer: decomposition transformers with auto-correlation for long-term series forecasting, refAbstract=null), Reference(id=1179786711463768733, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=27268, pageEnd=27286, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=Zhou T, Ma Z, Wen Q, journalName=International Conference on Machine Learning, refType=null, unstructuredReference=Zhou T, Ma Z, Wen Q, et al. Fedformer: frequency enhanced decomposed transformer for long-term series forecasting[C]// International Conference on Machine Learning. Cambridge: PMLR, 2022: 27268-27286., articleTitle=Fedformer: frequency enhanced decomposed transformer for long-term series forecasting, refAbstract=null), Reference(id=1179786711518294686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=3464, pageEnd=3473, url=null, language=null, rfNumber=[18], rfOrder=31, authorNames=Zhao Y, Ma Z, Zhou T, journalName=Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, refType=null, unstructuredReference=Zhao Y, Ma Z, Zhou T, et al. Gcformer:an efficient solution for accurateand scalable long-term multivariate timeseries forecasting[C]// Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. New York: ACM, 2023: 3464-3473., articleTitle=Gcformer:an efficient solution for accurateand scalable long-term multivariate timeseries forecasting, refAbstract=null), Reference(id=1179786711577014943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=32, authorNames=沈平, journalName=通渭至定西G310马营镇滑坡处治工程设计, refType=null, unstructuredReference=沈平. 通渭至定西G310马营镇滑坡处治工程设计[D]. 西安: 长安大学, 2016., articleTitle=null, refAbstract=null), Reference(id=1179786711644123808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=Shen Ping, journalName=Design of landslide treatment engineering from Tongwei to Dingxi G310 Maying Town, refType=null, unstructuredReference=Shen Ping. Design of landslide treatment engineering from Tongwei to Dingxi G310 Maying Town[D]. Xi'an: Chang'an University, 2016., articleTitle=null, refAbstract=null)], funds=[Fund(id=1179786708951380606, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, awardId=21YF1GA381, language=CN, fundingSource=甘肃省重点研发计划-工业类(21YF1GA381), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1179786705570771524, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=1, ext=[AuthorCompanyExt(id=1179786705574965829, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705570771524, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Gansu Road and Bridge Highway Investment Co. , Ltd. , Lanzhou 730030, China), AuthorCompanyExt(id=1179786705583354438, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705570771524, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 甘肃路桥公路投资有限公司, 兰州 730030)]), AuthorCompany(id=1179786705650463303, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=2, ext=[AuthorCompanyExt(id=1179786705658851912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China), AuthorCompanyExt(id=1179786705667240521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705650463303, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西北民族大学土木工程学院, 兰州 730030)]), AuthorCompany(id=1179786705717572170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, xref=3, ext=[AuthorCompanyExt(id=1179786705725960779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China), AuthorCompanyExt(id=1179786705730155084, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, companyId=1179786705717572170, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 兰州理工大学计算机与通信学院, 兰州 730050)])], figs=[ArticleFig(id=1179786707969913456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Fig.1, caption=Diagram of the main body of the GCformer model, figureFileSmall=/ehNpQZF7f3Rv0iGSti8gg==, figureFileBig=1vs6Zy8RuKvWyVxTlsf/8g==, tableContent=null), ArticleFig(id=1179786708053799537, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=图1, caption=GCformer模型主体结构图

X:(b,n,d)为输入序列长度,其中,b (batch size)为批量大小;n为每个样本的特征数量;d为每个特征的向量维度;X为输入序列长度;Xtail为序列尾部;Y:(b,n,d)为输出序列长度;q(Query)为查询向量;k(Key)为键向量;v(Value)为值向量;n'为序列尾部的特征数量

, figureFileSmall=/ehNpQZF7f3Rv0iGSti8gg==, figureFileBig=1vs6Zy8RuKvWyVxTlsf/8g==, tableContent=null), ArticleFig(id=1179786708112519794, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Fig.2, caption=Flowchart of landslide displacement prediction, figureFileSmall=LFJHQ53GoB++bAFPkY2ONQ==, figureFileBig=VJ8aal5AKv/IpKE7oR1xYA==, tableContent=null), ArticleFig(id=1179786708179628659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=图2, caption=滑坡位移预测流程图, figureFileSmall=LFJHQ53GoB++bAFPkY2ONQ==, figureFileBig=VJ8aal5AKv/IpKE7oR1xYA==, tableContent=null), ArticleFig(id=1179786708234154612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Fig.3, caption=Monitoring point displacement-rainfall monitoring, figureFileSmall=3JeNWRsX5EDqvVieKEPygw==, figureFileBig=WZSZgB5NwZIlyUjN5GH4zQ==, tableContent=null), ArticleFig(id=1179786708284486261, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=图3, caption=监测点位移-降雨量监测曲线, figureFileSmall=3JeNWRsX5EDqvVieKEPygw==, figureFileBig=WZSZgB5NwZIlyUjN5GH4zQ==, tableContent=null), ArticleFig(id=1179786708355789430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Fig.4, caption=Comparative effect of the total displacement, vertical landslide displacement in Jinliuping Village, figureFileSmall=C7hus7OM7CCgVwVSl9VYpQ==, figureFileBig=hg01ig9aZJyy2pkfVud2Rw==, tableContent=null), ArticleFig(id=1179786708410315383, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=图4, caption=锦柳坪村滑坡总位移、垂直方向位移对比效果图, figureFileSmall=C7hus7OM7CCgVwVSl9VYpQ==, figureFileBig=hg01ig9aZJyy2pkfVud2Rw==, tableContent=null), ArticleFig(id=1179786708481618552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Fig.5, caption=Comparison results of total displacement and vertical displacement of Yuanshitan Village Landslide, figureFileSmall=Kyj0R6DHFZrtrD+rYcc5AQ==, figureFileBig=hg1B6kabv3ZnurXBDAmLyA==, tableContent=null), ArticleFig(id=1179786708536144505, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=图5, caption=元始滩村滑坡总位移、垂直方向滑坡位移对比结果, figureFileSmall=Kyj0R6DHFZrtrD+rYcc5AQ==, figureFileBig=hg1B6kabv3ZnurXBDAmLyA==, tableContent=null), ArticleFig(id=1179786708603253370, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Table 1, caption=

Comparison of the displacement prediction accuracy of different models of total displacement and vertical direction of landslide in Jinliuping Village

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 预测模型 MAE/mm MSE/mm RMSE/mm R2
GCformer 0.274 0.130 0.360 0.907
总位移 FEDformer 0.357 0.208 0.456 0.851
Autoformer 0.345 0.201 0.449 0.856
GCformer 0.553 0.505 0.711 0.871
垂直方向 FEDformer 0.586 0.551 0.742 0.859
Autoformer 0.700 0.784 0.885 0.800
), ArticleFig(id=1179786708670362235, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=表1, caption=

锦柳坪村滑坡总位移和垂直方向不同模型位移预测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 预测模型 MAE/mm MSE/mm RMSE/mm R2
GCformer 0.274 0.130 0.360 0.907
总位移 FEDformer 0.357 0.208 0.456 0.851
Autoformer 0.345 0.201 0.449 0.856
GCformer 0.553 0.505 0.711 0.871
垂直方向 FEDformer 0.586 0.551 0.742 0.859
Autoformer 0.700 0.784 0.885 0.800
), ArticleFig(id=1179786708733276796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=EN, label=Table 2, caption=

Comparison of prediction accuracy of total displacement and vertical displacement of different models at the landslide site in Yuanshitan Village

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 预测模型 MAE/mm MSE/mm RMSE/mm R2
GCformer 0.274 0.130 0.360 0.917
总位移 FEDformer 0.357 0.208 0.456 0.851
Autoformer 0.441 0.317 0.563 0.902
GCformer 0.553 0.505 0.711 0.871
垂直方向 FEDformer 0.586 0.551 0.742 0.859
Autoformer 0.845 1.160 1.072 0.636
), ArticleFig(id=1179786708812968573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149774728174465670, language=CN, label=表2, caption=

元始滩村滑坡点总位移和垂直方向不同模型位移预测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 预测模型 MAE/mm MSE/mm RMSE/mm R2
GCformer 0.274 0.130 0.360 0.917
总位移 FEDformer 0.357 0.208 0.456 0.851
Autoformer 0.441 0.317 0.563 0.902
GCformer 0.553 0.505 0.711 0.871
垂直方向 FEDformer 0.586 0.551 0.742 0.859
Autoformer 0.845 1.160 1.072 0.636
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402357, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402357, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402357, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402357, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于GCformer的滑坡长期位移预测
收藏切换
PDF下载
杨万里 1 , 何永强 2 , 张建良 3 , 王惠琴 3, * , 李晓娟 2
科学技术与工程 | 论文·天文学、地球科学 2025,25(12): 4913-4919
收起
收藏切换
科学技术与工程 | 论文·天文学、地球科学 2025, 25(12): 4913-4919
基于GCformer的滑坡长期位移预测
全屏
杨万里1 , 何永强2, 张建良3, 王惠琴3, * , 李晓娟2
作者信息
  • 1 甘肃路桥公路投资有限公司, 兰州 730030
  • 2 西北民族大学土木工程学院, 兰州 730030
  • 3 兰州理工大学计算机与通信学院, 兰州 730050
  • 杨万里(1981—),男,汉族,河北承德人,硕士,高级工程师。研究方向:高速公路建设管理。E-mail:

通讯作者:

* 王惠琴 (1971—),女,汉族,甘肃渭源人,博士,教授。研究方向:无线光通信。E-mail:
Long Term Displacement Prediction of Landslides Based on GCformer
Wan-li YANG1 , Yong-qiang HE2, Jian-liang ZHANG3, Hui-qin WANG3, * , Xiao-juan LI2
Affiliations
  • 1 Gansu Road and Bridge Highway Investment Co. , Ltd. , Lanzhou 730030, China
  • 2 School of Civil Engineering, Northwest Minzu University, Lanzhou 730030, China
  • 3 School of Computing and Communications, Lanzhou University of Technology, Lanzhou 730050, China
出版时间: 2025-04-28 doi: 10.12404/j.issn.1671-1815.2402357
文章导航
收藏切换

为提高滑坡长期位移预测精度,将GCformer模型运用到滑坡位移预测,提出一种基于GCformer模型的滑坡位移预测方法。该方法以降雨量和位移量作为输入,利用GConvmsk模块获取序列的全局信息,并结合序列长度线性缩放来高效提取数据特征。同时,利用PatchTST模型来自动提取序列数据中的近短期信号,获取更全面的历史信息,从而提高模型的鲁棒性和对数据的建模能力。最后,利用甘肃定西市会川镇锦柳坪村和元始滩村滑坡位移监测数据进行实例验证。结果表明:该模型与Autoformer模型和FEDformer模型相比,GCformer模型在总位移和垂直位移上具有更高的预测精度和更好的可靠性。

滑坡位移预测  /  GCformer模型  /  FEDformer模型  /  Autoformer模型

To enhance the long-term displacement prediction accuracy of landslides, the GCformer model was applied to landslide displacement forecasting, and a novel landslide displacement prediction approach grounded in the GCformer model was proposed. This methodology leveraged rainfall and displacement as input variables, utilized the GConvmsk module to capture the global information of the sequence, and combined a linear scaling technique of sequence length to efficiently extract data features. Concurrently, the PatchTST model was employed to automatically extract short-term and long-term signals from the sequence data, in order to obtain more comprehensive historical information and bolster the model's robustness and modeling capability. Finally, the landslide displacement monitoring data from Jinliuping Village and Yuanshitan Village in Huichuan County, Dingxi City, Gansu Province, were utilized for case validation. The findings demonstrate that the proposed model exhibits superior prediction accuracy and reliability. In comparison to the Autoformer model and the FEDformer model, the GCformer model is found to achieve the lowest error in both total displacement and vertical displacement.

landslide displacement prediction  /  GCformer model  /  FEDformer model  /  Autoformer model
杨万里, 何永强, 张建良, 王惠琴, 李晓娟. 基于GCformer的滑坡长期位移预测. 科学技术与工程, 2025 , 25 (12) : 4913 -4919 . DOI: 10.12404/j.issn.1671-1815.2402357
Wan-li YANG, Yong-qiang HE, Jian-liang ZHANG, Hui-qin WANG, Xiao-juan LI. Long Term Displacement Prediction of Landslides Based on GCformer[J]. Science Technology and Engineering, 2025 , 25 (12) : 4913 -4919 . DOI: 10.12404/j.issn.1671-1815.2402357
滑坡作为一种危害极大的地质灾害,会造成阻断交通、毁坏生活设施、破坏生态环境等,给人民的生命财产安全造成极大危害。因此,如何精准有效地预防滑坡灾害已成为地质灾害领域的研究热点[1]。近年来,随着传感器、通信、计算机以及人工智能等技术的发展,各种边坡稳定监测方法层出不穷。这些监测方法根据滑坡灾害的特征,实时监测地质环境,精准分析位移数据变化和发展趋势。同时,依据区域气象环境变化,分析降雨量与滑坡灾害的关系,极大地保障了人民的生命财产安全。
滑坡位移预测作为滑坡灾害防治的关键环节,其对滑坡稳定性有着至关重要的作用。也就是说,准确研究滑坡位移的稳定性,可以更精准地监测和预警滑坡的发生,以便及时采取措施,降低滑坡对人类和环境的影响。日本学者斋藤迪孝提出的加速蠕变微分方程模型,是滑坡预报研究的重要基础[2]。随着研究理论的不断深化与拓展,模糊数学论、统计学和概率论等统计分析理论[3-6]逐渐被引入并应用于时间序列预测中。近年来,随着计算机、人工智能和机器学习的蓬勃发展,多项式函数[7]、随机森林[8]、支持向量机 (support vector machines,SVM)[9]以及极限学习机(extreme learning machines,ELM)[10]等机器学习方法,也已被广泛地应用于滑坡位移预测当中,极大地提升了预测的精准度与效率。这些算法通过提取输入输出的非线性关系较好地实现了滑坡预测。但是,面对复杂的滑坡位移系统,这些算法很容易受到数据中的噪声和偏差的影响,从而会造成机器学习模型的误差较大。
在处理滑坡位移非线性关系时,需要考虑多个因素的影响,包括地质环境、降雨量和库水位等,增大了机器学习模型的复杂度,而且其往往容易出现过拟合现象。随着计算机性能的增强,深度学习因具有高效数据表征和复杂非线性关系建模的能力而被广泛应用于滑坡位移预测。鉴于此,学者们相继将循环神经网络 (recurrent neural network,RNN)[11]、卷积神经网络(convolutional neural networks, CNN)[12]、门控循环单元(gated recurrent unit,GRU)[13]和长短时记忆网络(long short term memory,LSTM)[14] 等深度学习方法用于滑坡预测,并取得了较好的效果。田原等[15]将时序卷积网络(temporal convolutional networks,TCN)与 Transformer 解码器组合,提出了改进的 Transformer 滑坡短期位移预测模型,实现了快速变形期预测精度的提升。但是,Transformer对内存和运算速度的要求较高,导致在长期时序预测中难以取得较好的预测效果。为此,Wu等[16]采用一种简单的深度趋势分解架构,提出了Autoformer 模型,旨在准确分解时态数据的趋势和季节信号。同时,采用自相关机制代替注意力模块,有效地提高了计算效率,降低了内存复杂度。随后,以Autoformer模型作为基础,Zhou等[17]提出了FEDformer 模型。该模型将趋势季节性分解引入Transformer模型,同时采用傅里叶增强和小波增强来降低线性计算复杂度和内存开销。但是Autoformer 和 FEDformer模型仍不能对输入时间序列进行准确预测。这是因为其无法从时间序列数据中捕获全局依赖关系,而且在处理长期位移预测时,对预测模型的精度和计算效率均有较高的要求。特别是,时序序列会受到分布偏移和噪声的影响,使得预测难度增加。
为了解决这些不足,Zhao等[18]提出了GCformer模型。该模型是在Transformer的基础上,分别引入结构化的全局卷积分支和基于Transformer的局部分支来获取长输入序列的全局信息和近短期信息,从而有效解决了Transformer模型难以捕获序列长期依赖关系和计算效率低下的问题,可以高效地处理冗长含噪的输入信号。基于此,将GCformer模型引入滑坡位移预测,提出基于GCformer模型的滑坡长期位移预测方法,同时利用甘肃省渭源县会川镇某滑坡位移监测数据进行验证,旨在提升滑坡位移长期预测的精度和可靠性。
GCformer模型是一种独特的双分支结构,其上下分支被分别用于捕获、提取不同类型的全局和局部信息。之后,分别利用解码器中线性变换来专门整合和合并这两类信息,从而最大限度地提高它们之间的互补性。其主体结构如图1所示。
图1所示,GCformer模型主要由编码器和解码器构成。编码器用来提取长时间序列的全局特征和近短期特征。其结构由两个并行分支组成。上分支,即全局分支,主要用于提取存在于整个序列中的长期依赖关系。同时,通过采用全局卷积核,能够捕获跨越整个序列的长期模式,从而获取全局信息。下分支则专注于捕获近期的局部信息。同时,利用自注意力机制关注序列中相邻时间步之间的相互作用,并且只处理输入序列的尾部部分(而非整个序列)。从而使得模型在不牺牲预测准确性的前提下,减小了整体复杂度。这种双分支结构使得GCformer能够高效处理长序列数据,同时保持高预测精确度。
全局分支反映的是序列中存在的长期依赖关系,通过采用全局卷积核和多种高效的参数化方法,成功解决了Transformer模型在处理长序列时的局限性。该结构主要包含GConvmsk、GConfreq和GConleg共3种方法。其中, GConvmsk方法通过组装一系列规模逐渐增大的子内核来构建全局卷积内核,从而提高了序列的建模速度,增强模型捕捉长期依赖关系的能力。GConfreq方法利用时间序列的时频变换特性来获取时序中的全局依赖关系,并同时保持参数的亚线性比例,以便获得高效、准确的建模。GConleg方法通过定义状态转移矩阵、输入矩阵、输出矩阵等参数,将原始信号从时域空间投影到其他空间(如Legendre空间)进行卷积核操作,再投影回时域空间,以达到对长序列高效建模和处理的目的。
GCformer的局部分支是一个基于Transformer的结构分支,它专注于处理输入序列的尾部片段,提取时间节点附近之间的数据特征,从而降低模型整体复杂度。通过这种设计,GCformer能够有效地利用Transformer模型在捕获短期和近期信息方面的优势。基于Transformer的结构分支模型,主要包括PatchTST、Autoformer、Dlinear和TCN 4种模型。
在解码器中,通过集成全局信息和局部信息来有效地融合时间序列特征,实现两者的优势互补,并输出最终的预测结果。首先,利用多层感知机将全局和局部特征映射到令牌级别的隐藏维度,确保全局和局部特征能够在同一空间内进行交互,提高了全局和局部信息的利用率。其次,以全局特征作为查询向量q(Query)、局部特征作为键向量k(Key)和值向量v(Value),同时输入至交叉注意力机制模块中,以便同时考虑长期和短期依赖关系,提升预测的准确度。最后,将得到的特征向量进一步通过多层感知机以生成最终的预测结果。
滑坡位移数据通常具有非线性、高维度和时序性等特点,并且存在大量噪声。在处理这类数据时,传统的模型往往难以完整捕捉到数据中的重要特征。GCformer模型具有快速提取长期序列中全局和局部数据特征的优势,同时还可以高效、有效地处理冗长、含噪的输入信号。因此,将其运用到滑坡位移预测,提出了一种基于GCformer模型的滑坡长期位移预测方法。使用GCformer的最佳组合模型,即上行分支采用GConvmsk模块来提取全局数据特征,下行分支则通过PatchTST模块来捕捉数据近短期的特征信息。
在进行滑坡位移数据预测之前,首先利用重采样和插值法对输入的降雨量及位移数据进行预处理,旨在填补缺失值、光滑噪声数据,平滑或删除异常点。其次,对预处理后的数据进行归一化,以便消除奇异样本数据导致的不良影响。同时,将归一化后的样本数据以7∶1∶2的比例划分为训练集、验证集和测试集。在模型训练时,将训练集输入GCformer模型,利用全局分支中GConvmsk卷积块函数进行卷积块操作,从而输出全局数据特征序列。利用局部分支中PatchTST模型进行池化操作,从而输出局部数据特征序列。接着,利用残差网络计算全局和局部分支的残差,以此保证数据特征的完整性。在解码器中,全局信息和局部信息先经过线性层将其映射到隐状态空间,并利用注意力机制进行信息交互。同时,将交互后的信息与残差进行求和,经反归一化后输出最终的训练结果,从而得到最优预测模型。利用验证集验证模型的性能,以验证模型的有效性。将测试集数据输入最优模型进行结果预测,得到最终预测结果。基于GCformer的滑坡位移长期预测模型的预测流程如图2所示。
基于GCformer的滑坡长期位移预测模型的预测流程其如下。
(1)数据预处理。对输入的降雨数据和滑坡位移数据进行重采样、插值和归一化处理。同时,将降雨量和位移数据以7∶1∶2的比例划分为训练集、验证集和测试集,并将其转换成低维特征向量。
(2)GCformer模型架构。将训练集数据输入GCformer模型中,利用全局分支中的GConvmsk卷积块捕捉输入序列数据中的全局特征。同时,利用局部分支中的PatchTST模型提取输入序列尾段Xtail 的近短期信号特征。
(3)模型优化。使用ADAM优化器,初始化模型的学习率,并利用反向传播和梯度下降等技术优化GConvmsk和PatchTST模型的参数,直至模型输出与实际滑坡位移值之间的误差最小,从而获得最优参数模型。
(4)模型评估。设置更新模型的超参数,使用验证集评估模型的性能,并选用平均绝对误差(mean absolute error,MAE)、 均方误差(mean squared error,MSE)、均方根误差(root mean square error,RMSE)和确定系数R2,4个指标来评估模型的性能。通常,预测误差越小,模型的性能越好。
(5)模型预测。将测试集代入训练好的模型进行预测与分析,并与Autoformer模型和FEDformer模型进行性能对比。
会川镇锦柳坪村滑坡位于甘肃省渭源县,地处秦岭山地陇中黄土高原地带,丘陵连绵,多以山地为主。随着人口数量的不断增加,长期以来,毁草开荒,陡坡开垦,农业灌溉,盲目扩大耕地,坡面土体结构遭到破坏,造成大量水土流失,进一步引发或加剧滑坡地质灾害[19]。该监测点为推移式黄土层内滑坡,原始的坡长与坡度分别为30 m和35°,滑坡长度100 m,发育宽度150 m,平均坡度与总体坡向分别为35°和280°,坡顶裂缝持续发育,最大宽度0.2 m。该滑坡体的变形主要为坡体上部发育的横向拉张裂缝和前缘陡坎处局部掉块等。在监测期间,滑坡体持续滑动,并在汛期呈现明显的加速趋势,发生滑坡灾害的潜在风险较高,极易造成人民生命财产损失。
选用锦柳坪村滑坡在2021年3月—2024年4月的监测数据,其总位移与降雨监测曲线如图3所示。可以看出,该区域降雨量少,蒸发量大,年内降水分配不均,多集中于 5—8月份,占年降水总量的50%,且多以大雨、暴雨的形式出现。该监测点随着降雨量的持续上升,位移滑动也呈上升趋势。由此可见,该区域的滑坡位移量与降雨量有着密切的相关性。
对原始监测数据采用重采样和插值方法进行预处理,旨在补偿数据集中的异常值和缺失值。同时,将原始监测数据处理为规则的等时距序列数据。为了提高模型的训练效果,减少模型的过拟合和欠拟合问题,对所有处理后的数据进行归一化处理。
实验时,使用Pytorch框架搭建 GCformer模型。输入的数据以7∶1∶2的比例划分训练集、验证集和测试集。其中,验证集主要是为了调整模型的超参数,获得模型在预测过程中的最优结果,保存验证集中损失最低的模型用于最终测试。使用ADAM优化器,学习率为1×10-4~1×10-3,并选用均方误差(MSE)、平均绝对误差(MAE)、均方根误差(RMSE)和确定系数R2作为评价指标。
为了说明本文方法的有效性,分别对GNSS监测点的总位移和垂直方向位移进行了预测,并与深度学习Autoformer算法和FEDformer算法的预测效果进行了对比,结果如图4所示。可以看出,相对于Autoformer模型和FEDformer模型,GCformer模型在总位移和垂直方向位移上均具有更好的预测结果。这是因为GCformer模型分别利用增强型的全局卷积分支GConvmsk和PatchTST结构分支分别精准捕捉了时序数据中的全局特征和局部特征,从而有效降低了整体复杂度,提高了模型的预测精度。
表1给出了锦柳坪村滑坡总位移和垂直方向不同模型位移预测精度对比。可以看出,相较于Autoformer模型和FEDformer模型,GCformer模型的误差均达到了最低,其预测精度有了明显的提升。
为了验证GCformer模型方法的可靠性,本文还采用甘肃定西市渭源县会川镇元始滩村GNSS滑坡23QJ01监测点的相关数据进行了实验验证。该滑坡为碎石土与泥岩接触面滑动,且常年蠕动,滑面处常有流水。坡长20 m,发育宽度200 m,平均坡度25°,总体坡向130°。为了数据的完整性和统一性,采用与锦柳坪村监测点相同时间的监测数据,其处理结果与预测结果分别如图5表2所示。
图5为元始滩村滑坡点总位移和垂直方向位移对比结果。可以看出,图5得到的结果与图4结果基本一致,表明采用GCformer模型后元始滩村滑坡的拟合度最高。表2为元始滩村滑坡点总位移与垂直方向位移不同模型位移预测精度对比,表2所得结论与表1基本一致,表明GCformer模型的预测精度最高。
以渭源会川镇锦柳坪村滑坡监测为背景,利用GCformer模型提出一种基于GCformer的滑坡长期位移预测模型,并用元始滩村滑坡监测点数据验证了模型的可靠性和泛化性。得出如下结论。
(1)本文模型采用全局分支中的卷积核高效参数化,提取了滑坡位移数据的长期信息,从而有效解决了Transformer 结构在捕获长期依赖性方面存在的局限性。相较于Autoformer模型和FEDformer模型,在锦柳坪村和元始滩村滑坡监测点实例中,GCformer模型的R2均达到最高,此模型可有效用于滑坡位移预测,且具有一定的可靠性和泛化性,对于提高滑坡位移的预测预警具有良好的作用。
(2)利用PatchTST 模型中独特的补丁设计方法,使模型追溯到更长的历史信息,提取到更全面的局部数据特征,从而显著提高了模型的预测性能,大大降低了模型的空间和时间复杂度。在锦柳坪村和元始滩村滑坡监测点中,GCformer模型总位移与垂直方向均实现了误差最低,预测精度更高、预测效果更加稳定可靠。
所提滑坡长期位移预测模型在滑坡位移预测方面取得了较高的预测精度,但是本文方法未考虑该滑坡点人类活动和地下水位对滑位移的影响。因此,如何提取有效的周期特征,以实现更具有解释力的滑坡结果仍需进一步研究。
  • 甘肃省重点研发计划-工业类(21YF1GA381)
参考文献 引证文献
排序方式:
[1]
武鑫, 郑东健, 刘永涛, 等. 滑坡失稳时间预测方法研究综述[J]. 水利水电科技进展, 2021, 41(4): 89-94.
Wu Xin, Zheng Dongjian, Liu Yongtao, et al. Review of landslide instability time prediction method[J]. Progress in Water Resources and Hydropower Science and Technology, 2021, 41(4): 89-94.
[2]
窦杰, 向子林, 许强, 等. 机器学习在滑坡智能防灾减灾中的应用与发展趋势[J]. 地球科学, 2023, 48(5): 1657-1674.
Dou Jie, Xiang Zilin, Xu Qiang, et al. Application and development trend of machine learning in landslide intelligent disaster prevention and mitigation[J]. Earth Science, 2023, 48(5): 1657-1674.
[3]
李骅锦. 运用深度学习和统计学习方法预测库岸滑坡变形[D]. 成都: 成都理工大学, 2020.
Li Huajin. Predicting landslide deformation of bank bank using deep learning and statistical learning methods[D]. Chengdu: Chengdu University of Technology, 2020.
[4]
张抒, 唐辉明, 龚文平, 等. 基于物理力学机制的滑坡数值预报模式: 综述、挑战与机遇[J]. 地质科技通报, 2022, 41(6): 14-27.
Zhang Shu, Tang Huiming, Gong Wenping, et al. Numerical landslide prediction model based on physical-mechanical mechanisms: overview, challenges and opportunities[J]. Geoscience and Technology Bulletin, 2022, 41(6): 14-27.
[5]
李晴文. 基于智能算法组合模型的边坡位移预测研究[D]. 大连: 大连理工大学, 2021.
Li Qingwen. Research on slope displacement prediction based on intelligent algorithm combination model[D]. Dalian: Dalian University of Technology, 2021.
[6]
王念秦, 申辉辉, 鲁兴生. 边坡变形监测技术发展现状及问题对策[J]. 科学技术与工程, 2021, 21(19): 7845-7855.
Wang Nianqin, Shen Huihui, Lu Xingsheng. Development status and problem countermeasures of slope deformation monitoring technology[J]. Science Technology and Engineering, 2021, 21(19): 7845-7855.
[7]
袁维, 孙瑞峰, 钟辉亚, 等. 阶跃型滑坡综合变形预测及监测预警方法研究[J]. 水利学报, 2023, 54(4): 461-473.
Yuan Wei, Sun Ruifeng, Zhong Huiya, et al. Research on integrated deformation prediction and monitoring and warning methods for step-type landslides[J]. Journal of Water Resources, 2023, 54(4): 461-473.
[8]
曾斌, 吕权儒, 寇磊, 等. 基于Logistic回归和随机森林的清江流域长阳库岸段堆积层滑坡易发性评价[J]. 中国地质灾害与防治学报, 2023, 34(4): 105-113.
Zeng Bin, Quanru, Kou Lei, et al. Evaluation of landslide susceptibility of stacked layer landslides in the bank section of Changyang Reservoir in Qingjiang River Basin based on Logistic regression and random forest[J]. Chinese Journal of Geological Hazards and Prevention, 2023, 34(4): 105-113.
[9]
杨玲, 魏静, 许子伏. 基于平滑先验法-麻雀搜索算法-支持向量机回归模型的滑坡位移预测——以三峡库区八字门和白水河滑坡为例[J]. 地球科学与环境学报, 2022, 44(6): 1096-1110.
Yang Ling, Wei Jing, Xu Zifu. Landslide displacement prediction based on smoothing prior method-sparrow search algorithm-support vector machine regression model: a case study of Bazimen and Baishuihe landslides in the Three Gorges Reservoir Area[J]. Journal of Earth Sciences and Environment, 2022, 44(6): 1096-1110.
[10]
马飞燕, 李向新. 基于改进麻雀搜索算法-核极限学习机耦合算法的滑坡位移预测模型[J]. 科学技术与工程, 2022, 22(5): 1786-1793.
Ma Feiyan, Li Xiangxin. Landslide displacement prediction model based on improved sparrow search algorithm-kernel extreme learning machine coupling algorithm[J]. Science Technology and Engineering, 2022, 22(5): 1786-1793.
[11]
张明岳, 李丽敏, 温宗周. RNN与LSTM方法用于滑坡位移动态预测的研究[J]. 人民珠江, 2021, 42(9): 6-13.
Zhang Mingyue, Li Limin, Wen Zongzhou. Research on RNN and LSTM method for landslide position movement prediction[J]. People's Pearl River, 2021, 42(9): 6-13.
[12]
Saha S, Saha A, Hembram T K, et al. Prediction of spatial landslide susceptibility applying the novel ensembles of CNN, GLM and random forest in the Indian Himalayan region[J]. Stochastic Environmental Research and Risk Assessment, 2022, 36(10): 3597-3616.
[13]
鄢好, 陈骄锐, 李绍红, 等. 基于时间序列和GRU的滑坡位移预测[J]. 人民长江, 2021, 52(1): 102-107, 133.
Yan Hao, Chen Jiaorui, Li Shaohong, et al. Landslide displacement prediction based on time series and GRU[J]. People's Yangtze River, 2021, 52(1): 102-107, 133.
[14]
梁阳, 肖婷, 胡程, 等. 基于长期监测数据与LSTM网络的滑坡位移预测[J]. 信号处理, 2022, 38(1): 19-27.
Liang Yang, Xiao Ting, Hu Cheng, et al. Landslide displacement prediction based on long-term monitoring data and LSTM network[J]. Signal Processing, 2022, 38(1): 19-27.
[15]
田原, 庞骁, 赵文祎, 等. 基于Transformer的滑坡短期位移预测模型[J]. 北京大学学报: 自然科学版, 2023, 59(2): 197-210.
Tian Yuan, Pang Xiao, Zhao Wenyi, et al. Short-term displacement prediction model of landslide based on Transformer[J]. Journal of Peking University: Natural Science Edition, 2023, 59(2): 197-210.
[16]
Wu H, Xu J, Wang J, et al. Autoformer: decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in Neural Information Processing Systems, 2021, 34: 22419-22430.
[17]
Zhou T, Ma Z, Wen Q, et al. Fedformer: frequency enhanced decomposed transformer for long-term series forecasting[C]// International Conference on Machine Learning. Cambridge: PMLR, 2022: 27268-27286.
[18]
Zhao Y, Ma Z, Zhou T, et al. Gcformer:an efficient solution for accurateand scalable long-term multivariate timeseries forecasting[C]// Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. New York: ACM, 2023: 3464-3473.
[19]
沈平. 通渭至定西G310马营镇滑坡处治工程设计[D]. 西安: 长安大学, 2016.
Shen Ping. Design of landslide treatment engineering from Tongwei to Dingxi G310 Maying Town[D]. Xi'an: Chang'an University, 2016.
2025年第25卷第12期
PDF下载
316
135
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402357
  • 接收时间:2024-04-02
  • 首发时间:2025-07-09
  • 出版时间:2025-04-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-02
  • 修回日期:2025-01-22
基金
甘肃省重点研发计划-工业类(21YF1GA381)
作者信息
    1 甘肃路桥公路投资有限公司, 兰州 730030
    2 西北民族大学土木工程学院, 兰州 730030
    3 兰州理工大学计算机与通信学院, 兰州 730050

通讯作者:

* 王惠琴 (1971—),女,汉族,甘肃渭源人,博士,教授。研究方向:无线光通信。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402357
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

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

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