首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1322566945237480387, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322566927927591451, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2025.04.132, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1745164800000, receivedDateStr=2025-04-21, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793254131850, onlineDateStr=2026-10-29, pubDate=1773504000000, pubDateStr=2026-03-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793254131850, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793254131850, creator=13701087609, updateTime=1793254131850, updator=13701087609, issue=Issue{id=1322566927927591451, tenantId=1146029695717560320, journalId=1281212831689347082, year='2026', volume='46', issue='3', pageStart='262', pageEnd='391', issueExtLink='null', onlineDate='null', pubDate='1773504000000', pubDateStr='2026-03-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793254127723, creator='13701087609', updateTime=1793254127723, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=360, endPage=367, ext={EN=ArticleExt(id=1322566945413641156, articleId=1322566945237480387, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=A Quality Evaluation Method for InSAR Interferograms Based on Convolutional Neural Network, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Based on convolutional neural network (CNN), an automatic evaluation method for InSAR interferogram quality is proposed. This method is applied to Sentinel-1 data experiments, achieving accuracy and recall rate of 96.5% and 98% on the test set, respectively. The results of automatic screening and manual selection have good consistency. We apply the method to PS-InSAR deformation processing in Nanchang area, it is found that selecting high-quality interferograms for deformation analysis through quality evaluation can significantly improve the accuracy of deformation time series measurement.

, authors=Xiaohui ZHA1, 2, Jiehong CHEN1, Hua GAO1, Shuhua QI1, *, authorsList=Xiaohui ZHA, Jiehong CHEN, Hua GAO, Shuhua QI, authorCompany=null, correspAuthors=Shuhua QI, 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=1322566948689392597, articleId=1322566945237480387, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=基于CNN的InSAR干涉图质量评价方法, 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=

基于卷积神经网络(CNN)提出一种InSAR干涉图质量的自动评价方法, 并将该方法应用于Sentinel-1数据实验中, 测试集的准确率和召回率分别达到96.5%和98%, 自动筛选与人工挑选结果具有很好的一致性。将该方法应用于南昌地区PS-InSAR形变处理, 结果表明, 通过质量评价选择高质量的干涉图开展形变分析, 能够显著提高形变时间序列测量精度。

, authors=查小惠1, 2, 陈皆红1, 高华1, 齐述华1, *, authorsList=查小惠, 陈皆红, 高华, 齐述华, authorCompany=null, correspAuthors=齐述华, authorNote=

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

, correspAuthorsNote=
齐述华, 博士, 教授, 主要研究方向为生态环境遥感, E-mail:
, copyrightStatement=版权所有，未经授权，不得转载。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=Wk1+CljYVkvpfsNAurXfcw==, magXml=jD+GhP2BYFXOx8sdpXGbFA==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=F0Eexii3M5lgah8ZV4+KGQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=IdPIwHacp26B5l+Y/sGq+g==, mapNumber=null, fund=null)}, authors=[Author(id=1322566949100434397, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaxiaohuiouc@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566949192709088, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949100434397, language=EN, stringName=Xiaohui ZHA, firstName=Xiaohui, middleName=null, lastName=ZHA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China
2 Jiangxi Earthquake Agency, Nanchang 330026, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949255623649, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949100434397, language=CN, stringName=查小惠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 江西师范大学地理与环境学院, 南昌, 330022
2 江西省地震局, 南昌, 330026, bio={"content":"

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

"}, bioImg=null, bioContent=

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)]), AuthorCompany(id=1322566949008159705, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566949016548314, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangxi Earthquake Agency, Nanchang 330026, China), AuthorCompanyExt(id=1322566949024936923, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江西省地震局, 南昌, 330026)])]), Author(id=1322566949339509731, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, 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=1322566949419201509, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949339509731, language=EN, stringName=Jiehong CHEN, firstName=Jiehong, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949482116070, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949339509731, language=CN, stringName=陈皆红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])]), Author(id=1322566949561807848, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, 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=1322566949654082538, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949561807848, language=EN, stringName=Hua GAO, firstName=Hua, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949763134443, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949561807848, language=CN, stringName=高华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])]), Author(id=1322566949855409133, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qishuhua11@jxnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322566949947683823, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949855409133, language=EN, stringName=Shuhua QI, firstName=Shuhua, middleName=null, lastName=QI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566950035764208, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949855409133, language=CN, stringName=齐述华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])])], keywords=[Keyword(id=1322566950161593329, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, orderNo=1, keyword=CNN), Keyword(id=1322566950258062322, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, orderNo=2, keyword=time series InSAR), Keyword(id=1322566950337754099, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, orderNo=3, keyword=interferogram quality), Keyword(id=1322566950421640180, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, orderNo=4, keyword=StaMPS), Keyword(id=1322566950513914869, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, orderNo=5, keyword=PS-InSAR), Keyword(id=1322566950597800950, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, orderNo=1, keyword=CNN), Keyword(id=1322566950677492727, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, orderNo=2, keyword=时序InSAR), Keyword(id=1322566950761378808, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, orderNo=3, keyword=干涉图质量), Keyword(id=1322566950857847801, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, orderNo=4, keyword=StaMPS), Keyword(id=1322566950958511098, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, orderNo=5, keyword=PS-InSAR)], refs=[Reference(id=1322566954423005198, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2017, volume=46, issue=10, pageStart=1421, pageEnd=1433, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=林珲, 马培峰, 王伟玺, journalName=测绘学报, refType=null, unstructuredReference=林珲, 马培峰, 王伟玺. 监测城市基础设施健康的星载MT-InSAR方法介绍[J]. 测绘学报, 2017, 46 (10): 1421- 1433, articleTitle=监测城市基础设施健康的星载MT-InSAR方法介绍, refAbstract=null), Reference(id=1322566954494308367, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2017, volume=46, issue=10, pageStart=1421, pageEnd=1433, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=Lin Hui, Ma Peifeng, Wang Weixi, journalName=null, refType=null, unstructuredReference= Lin Hui , Ma Peifeng , Wang Weixi . Urban Infrastructure Health Monitoring with Spaceborne Multi-Temporal Synthetic Aperture Radar Interferometry[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46 (10): 1421- 1433, articleTitle=null, refAbstract=null), Reference(id=1322566954561417232, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2017, volume=46, issue=10, pageStart=1717, pageEnd=1733, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=朱建军, 李志伟, 胡俊, journalName=测绘学报, refType=null, unstructuredReference=朱建军, 李志伟, 胡俊. InSAR变形监测方法与研究进展[J]. 测绘学报, 2017, 46 (10): 1717- 1733, articleTitle=InSAR变形监测方法与研究进展, refAbstract=null), Reference(id=1322566954636914705, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2017, volume=46, issue=10, pageStart=1717, pageEnd=1733, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=Zhu Jianjun, Li Zhiwei, Hu Jun, journalName=null, refType=null, unstructuredReference= Zhu Jianjun , Li Zhiwei , Hu Jun . Research Progress and Methods of InSAR for Deformation Monitoring[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46 (10): 1717- 1733, articleTitle=null, refAbstract=null), Reference(id=1322566954712412178, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2004, volume=70, issue=10, pageStart=1131, pageEnd=1137, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=Li Z L, Zou W B, Ding X L, journalName=Photogrammetric Engineering and Remote Sensing, refType=null, unstructuredReference= Li Z L , Zou W B , Ding X L , et al. A Quantitative Measure for the Quality of InSAR Interferograms Based on Phase Differences[J]. Photogrammetric Engineering and Remote Sensing, 2004, 70 (10): 1131- 1137, articleTitle=A Quantitative Measure for the Quality of InSAR Interferograms Based on Phase Differences, refAbstract=null), Reference(id=1322566954779521043, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=1, pageStart=96, pageEnd=100, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=赵超英, 张勤, journalName=大地测量与地球动力学, refType=null, unstructuredReference=赵超英, 张勤. 一种新的干涉图质量评定指标研究[J]. 大地测量与地球动力学, 2009, 29 (1): 96- 100, articleTitle=一种新的干涉图质量评定指标研究, refAbstract=null), Reference(id=1322566954867601428, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2009, volume=29, issue=1, pageStart=96, pageEnd=100, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=Zhao Chaoying, Zhang Qin, journalName=null, refType=null, unstructuredReference= Zhao Chaoying , Zhang Qin . Research on a Novel Index for Assessment of Interferogram Quality[J]. Journal of Geodesy and Geodynamics, 2009, 29 (1): 96- 100, articleTitle=null, refAbstract=null), Reference(id=1322566954930515989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang T, Lü X L, Hong J. A Novel Interferogram Quality Assessment Index Based on Connected Area[C]. IEEE International Geoscience and Remote Sensing Symposium, Beijing, 2016, articleTitle=null, refAbstract=null), Reference(id=1322566954993430550, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=112898, pageEnd=112909, url=null, language=null, rfNumber=6, rfOrder=8, authorNames=Duan M, Xu B, Li Z W, journalName=IEEE Access, refType=null, unstructuredReference= Duan M , Xu B , Li Z W , et al. Adaptively Selecting Interferograms for SBAS-InSAR Based on Graph Theory and Turbulence Atmosphere[J]. IEEE Access, 2020, 8, 112898- 112909, articleTitle=Adaptively Selecting Interferograms for SBAS-InSAR Based on Graph Theory and Turbulence Atmosphere, refAbstract=null), Reference(id=1322566955077316631, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=9, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=Wang T, Zhang Q, Wu Z P, journalName=Remote Sensing, refType=null, unstructuredReference= Wang T , Zhang Q , Wu Z P . A Deep-Learning-Facilitated, Detection-First Strategy for Operationally Monitoring Localized Deformation with Large-Scale InSAR[J]. Remote Sensing, 2023, 15 (9), articleTitle=A Deep-Learning-Facilitated, Detection-First Strategy for Operationally Monitoring Localized Deformation with Large-Scale InSAR, refAbstract=null), Reference(id=1322566955152814104, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=2, pageStart=166, pageEnd=188, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=张敬业, 孙珂, 张国宏, journalName=地震, refType=null, unstructuredReference=张敬业, 孙珂, 张国宏. 深度学习在InSAR数据处理与地壳形变观测中的应用研究进展[J]. 地震, 2023, 43 (2): 166- 188, articleTitle=深度学习在InSAR数据处理与地壳形变观测中的应用研究进展, refAbstract=null), Reference(id=1322566955245088793, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=2, pageStart=166, pageEnd=188, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=Zhang Jingye, Sun Ke, Zhang Guohong, journalName=null, refType=null, unstructuredReference= Zhang Jingye , Sun Ke , Zhang Guohong . Research Progress in Data Processing and Application of Deep Learning in InSAR Crustal Deformation Observation[J]. Earthquake, 2023, 43 (2): 166- 188, articleTitle=null, refAbstract=null), Reference(id=1322566955324780570, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2022, volume=196, issue=null, pageStart=151, pageEnd=158, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=Silva B, Sousa J J, Lazecky M, journalName=Procedia Computer Science, refType=null, unstructuredReference= Silva B , Sousa J J , Lazecky M , et al. Deformation Fringes Detection in SAR Interferograms Using Deep Learning[J]. Procedia Computer Science, 2022, 196, 151- 158, articleTitle=Deformation Fringes Detection in SAR Interferograms Using Deep Learning, refAbstract=null), Reference(id=1322566955396083739, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2021, volume=22, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=13, authorNames=Brengman C M J, Barnhart W D, journalName=Geochemistry, Geophysics, Geosystems, refType=null, unstructuredReference= Brengman C M J , Barnhart W D . Identification of Surface Deformation in InSAR Using Machine Learning[J]. Geochemistry, Geophysics, Geosystems, 2021, 22 (3), articleTitle=Identification of Surface Deformation in InSAR Using Machine Learning, refAbstract=null), Reference(id=1322566955471581212, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2020, volume=166, issue=null, pageStart=169, pageEnd=182, url=null, language=null, rfNumber=11, rfOrder=14, authorNames=Tiwari A, Narayan A B, Dikshit O, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference= Tiwari A , Narayan A B , Dikshit O . Deep Learning Networks for Selection of Measurement Pixels in Multi-Temporal SAR Interferometric Processing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166, 169- 182, articleTitle=Deep Learning Networks for Selection of Measurement Pixels in Multi-Temporal SAR Interferometric Processing, refAbstract=null), Reference(id=1322566955547078685, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=112, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=15, authorNames=Zhang Y, Wei J, Duan M, journalName=International Journal of Applied Earth Observation and Geoinformation, refType=null, unstructuredReference= Zhang Y , Wei J , Duan M , et al. Coherent Pixel Selection Using a Dual-Channel 1-D CNN for Time Series InSAR Analysis[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112, articleTitle=Coherent Pixel Selection Using a Dual-Channel 1-D CNN for Time Series InSAR Analysis, refAbstract=null), Reference(id=1322566955639353374, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=14, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=Sun X Y, Zimmer A, Mukherjee S, journalName=Remote Sensing, refType=null, unstructuredReference= Sun X Y , Zimmer A , Mukherjee S , et al. DeepInSAR: A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation[J]. Remote Sensing, 2020, 12 (14), articleTitle=DeepInSAR: A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation, refAbstract=null), Reference(id=1322566955714850847, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2021, volume=18, issue=11, pageStart=1971, pageEnd=1975, url=null, language=null, rfNumber=14, rfOrder=17, authorNames=Mukherjee S, Zimmer A, Sun X Y, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference= Mukherjee S , Zimmer A , Sun X Y , et al. An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18 (11): 1971- 1975, articleTitle=An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation, refAbstract=null), Reference(id=1322566955777765408, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2020, volume=58, issue=7, pageStart=4653, pageEnd=4665, url=null, language=null, rfNumber=15, rfOrder=18, authorNames=Zhou L F, Yu H W, Lan Y, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference= Zhou L F , Yu H W , Lan Y . Deep Convolutional Neural Network-Based Robust Phase Gradient Estimation for Two-Dimensional Phase Unwrapping Using SAR Interferograms[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58 (7): 4653- 4665, articleTitle=Deep Convolutional Neural Network-Based Robust Phase Gradient Estimation for Two-Dimensional Phase Unwrapping Using SAR Interferograms, refAbstract=null), Reference(id=1322566955844874273, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2021, volume=13, issue=21, pageStart=4468, pageEnd=4468, url=null, language=null, rfNumber=16, rfOrder=19, authorNames=He Y F, Zhang G Z, Kaufmann H, journalName=Remote Sensing, refType=null, unstructuredReference= He Y F , Zhang G Z , Kaufmann H , et al. Automatic Interferogram Selection for SBAS-InSAR Based on Deep Convolutional Neural Networks[J]. Remote Sensing, 2021, 13 (21): 4468- 4468, articleTitle=Automatic Interferogram Selection for SBAS-InSAR Based on Deep Convolutional Neural Networks, refAbstract=null), Reference(id=1322566955911983138, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=20, authorNames=刘国祥, 陈强, 罗小军, journalName=InSAR原理与应用, refType=null, unstructuredReference=刘国祥, 陈强, 罗小军, 等. InSAR原理与应用[M]. 北京: 科学出版社, 2019, articleTitle=null, refAbstract=null), Reference(id=1322566955970703395, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=21, authorNames=Liu Guoxiang, Chen Qiang, Luo Xiaojun, journalName=null, refType=null, unstructuredReference= Liu Guoxiang , Chen Qiang , Luo Xiaojun , et al. Principles and Applications of InSAR[M]. Beijing: Science Press, 2019, articleTitle=null, refAbstract=null), Reference(id=1322566957623259173, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2007, volume=112, issue=B7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=22, authorNames=Hooper A, Segall P, Zebker H, journalName=Journal of Geophysical Research: Solid Earth, refType=null, unstructuredReference= Hooper A , Segall P , Zebker H . Persistent Scatterer Interferometric Synthetic Aperture Radar for Crustal Deformation Analysis, with Application to Volcán Alcedo, Galápagos[J]. Journal of Geophysical Research: Solid Earth, 2007, 112 (B7), articleTitle=Persistent Scatterer Interferometric Synthetic Aperture Radar for Crustal Deformation Analysis, with Application to Volcán Alcedo, Galápagos, refAbstract=null), Reference(id=1322566957698756646, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2000, volume=38, issue=5, pageStart=2202, pageEnd=2212, url=null, language=null, rfNumber=19, rfOrder=23, authorNames=Ferretti A, Prati C, Rocca F, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference= Ferretti A , Prati C , Rocca F . Nonlinear Subsidence Rate Estimation Using Permanent Scatterers in Differential SAR Interferometry[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38 (5): 2202- 2212, articleTitle=Nonlinear Subsidence Rate Estimation Using Permanent Scatterers in Differential SAR Interferometry, refAbstract=null), Reference(id=1322566957770059815, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, doi=null, pmid=null, pmcid=null, year=2016, volume=115, issue=null, pageStart=78, pageEnd=89, url=null, language=null, rfNumber=20, rfOrder=24, authorNames=Crosetto M, Monserrat O, Cuevas-González M, journalName=ISPRS Journal of Photogrammetry and Remote Sensing, refType=null, unstructuredReference= Crosetto M , Monserrat O , Cuevas-González M , et al. Persistent Scatterer Interferometry: A Review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 115, 78- 89, articleTitle=Persistent Scatterer Interferometry: A Review, refAbstract=null)], funds=[Fund(id=1322566954234261516, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, awardId=41761076, language=CN, fundingSource=国家自然科学基金(41761076), fundOrder=null, country=null), Fund(id=1322566954305564685, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, awardId=20232BBE50021, language=CN, fundingSource=江西省重点研发计划(20232BBE50021), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)]), AuthorCompany(id=1322566949008159705, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566949016548314, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangxi Earthquake Agency, Nanchang 330026, China), AuthorCompanyExt(id=1322566949024936923, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江西省地震局, 南昌, 330026)])], figs=[ArticleFig(id=1322566951105311739, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 1, caption=High-quality wrapped interferogram and unwrapped interferogram, figureFileSmall=xpkGYsUQjAzPA0j3Z1ePAw==, figureFileBig=F0Eexii3M5lgah8ZV4+KGQ==, tableContent=null), ArticleFig(id=1322566951197586428, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图1, caption=高质量的缠绕干涉图和解缠干涉图, figureFileSmall=xpkGYsUQjAzPA0j3Z1ePAw==, figureFileBig=F0Eexii3M5lgah8ZV4+KGQ==, tableContent=null), ArticleFig(id=1322566951419884541, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 2, caption=Low-quality wrapped interferogram and unwrapped interferogram, figureFileSmall=OzWZr7EtrHpsN+GN+jAfag==, figureFileBig=Tx0N7tZSy87V3ubUxj73Fg==, tableContent=null), ArticleFig(id=1322566953076634622, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图2, caption=低质量的缠绕干涉图和解缠干涉图, figureFileSmall=OzWZr7EtrHpsN+GN+jAfag==, figureFileBig=Tx0N7tZSy87V3ubUxj73Fg==, tableContent=null), ArticleFig(id=1322566953147937791, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 3, caption=Neural network layered model, figureFileSmall=3YuY8Eqib6b6Ea1qmboByw==, figureFileBig=OijDqvNqDE9Tl+uuV2u6SQ==, tableContent=null), ArticleFig(id=1322566953210852352, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图3, caption=神经网络层状模型, figureFileSmall=3YuY8Eqib6b6Ea1qmboByw==, figureFileBig=OijDqvNqDE9Tl+uuV2u6SQ==, tableContent=null), ArticleFig(id=1322566953286348800, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 4, caption=Error function, accuracy, precision, and recall rate evolution curves of CNN model, figureFileSmall=C7S06FZi7nGcvQT3jN7yXQ==, figureFileBig=DI4pP2xYH9RTp1GGbD1p4g==, tableContent=null), ArticleFig(id=1322566953387012097, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图4, caption=CNN模型误差函数、准确率、精度和召回率演化曲线, figureFileSmall=C7S06FZi7nGcvQT3jN7yXQ==, figureFileBig=DI4pP2xYH9RTp1GGbD1p4g==, tableContent=null), ArticleFig(id=1322566953458315266, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 5, caption=Error function, accuracy, precision, and recall rate evolution curves of pre-trained models, figureFileSmall=8RuMHXCIX5dg+zSA777kqA==, figureFileBig=mpsuBxZax1QGhsCDlLIeCg==, tableContent=null), ArticleFig(id=1322566953538007043, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图5, caption=预训练模型误差函数、准确率、精度和召回率演化曲线, figureFileSmall=8RuMHXCIX5dg+zSA777kqA==, figureFileBig=mpsuBxZax1QGhsCDlLIeCg==, tableContent=null), ArticleFig(id=1322566953609310212, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 6, caption=Probability distribution of interferogram quality for training and testing sets, figureFileSmall=efF148+tfgyr8boxmClBJA==, figureFileBig=SwFotT4IkcXJ9HpM2/jitA==, tableContent=null), ArticleFig(id=1322566953689001989, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图6, caption=训练集和测试集干涉图质量概率分布, figureFileSmall=efF148+tfgyr8boxmClBJA==, figureFileBig=SwFotT4IkcXJ9HpM2/jitA==, tableContent=null), ArticleFig(id=1322566953756110854, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 7, caption=Histograms of velocity standard deviation before and after interferogram screening, figureFileSmall=p0/9qOAgr2+7dhi7jc2ZRQ==, figureFileBig=knNnjuOhV2bD2hu0CJw86w==, tableContent=null), ArticleFig(id=1322566953835802631, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图7, caption=干涉图剔除前后的速率标准差直方图, figureFileSmall=p0/9qOAgr2+7dhi7jc2ZRQ==, figureFileBig=knNnjuOhV2bD2hu0CJw86w==, tableContent=null), ArticleFig(id=1322566953898717192, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Fig. 8, caption=Comparison of deformation time series before and after interferogram screening, figureFileSmall=aos4Loyg+5vxMmOGdZnUGA==, figureFileBig=SNOYM/EGONv14qwIV6cWMQ==, tableContent=null), ArticleFig(id=1322566953970020361, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=图8, caption=干涉图剔除前后形变时间序列对比, figureFileSmall=aos4Loyg+5vxMmOGdZnUGA==, figureFileBig=SNOYM/EGONv14qwIV6cWMQ==, tableContent=null), ArticleFig(id=1322566954041323530, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=EN, label=Tab. 1, caption=

Parameters of satellite data

, figureFileSmall=null, figureFileBig=null, tableContent=
覆盖区域起止时间数量卫星空间裁剪范围
南昌市2018-01—2022-06129Sentinel-1A115.65°~116.05°E, 28.40°~28.85°N
南昌市2018-01—2022-06109Sentinel-1B115.65°~116.05°E, 28.40°~28.85°N
赣州市2019-01—2021-1282Sentinel-1A114.81°~115.05°E, 25.77°~25.91°N
九江市2020-01—2023-0599Sentinel-1A115.80°~116.10°E, 29.55°~29.80°N
九江市2018-01—2022-0695Sentinel-1B115.80°~116.10°E, 29.55°~29.80°N
), ArticleFig(id=1322566954129403915, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, language=CN, label=表1, caption=

卫星数据参数

, figureFileSmall=null, figureFileBig=null, tableContent=
覆盖区域起止时间数量卫星空间裁剪范围
南昌市2018-01—2022-06129Sentinel-1A115.65°~116.05°E, 28.40°~28.85°N
南昌市2018-01—2022-06109Sentinel-1B115.65°~116.05°E, 28.40°~28.85°N
赣州市2019-01—2021-1282Sentinel-1A114.81°~115.05°E, 25.77°~25.91°N
九江市2020-01—2023-0599Sentinel-1A115.80°~116.10°E, 29.55°~29.80°N
九江市2018-01—2022-0695Sentinel-1B115.80°~116.10°E, 29.55°~29.80°N
)], 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.2025.04.132, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2025.04.132, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2025.04.132, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2025.04.132, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1773504000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于CNN的InSAR干涉图质量评价方法
收藏切换
查小惠 1, 2 , 陈皆红 1 , 高华 1 , 齐述华 1, *
大地测量与地球动力学 | 特色栏目: 地震大地测量学 2026,46(3): 360-367
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 (3) : 360 -367
基于CNN的InSAR干涉图质量评价方法
全屏
[Author(id=1322566949100434397, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaxiaohuiouc@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322566949192709088, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949100434397, language=EN, stringName=Xiaohui ZHA, firstName=Xiaohui, middleName=null, lastName=ZHA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China
2 Jiangxi Earthquake Agency, Nanchang 330026, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949255623649, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949100434397, language=CN, stringName=查小惠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 江西师范大学地理与环境学院, 南昌, 330022
2 江西省地震局, 南昌, 330026, bio={"content":"

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

"}, bioImg=null, bioContent=

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)]), AuthorCompany(id=1322566949008159705, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566949016548314, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangxi Earthquake Agency, Nanchang 330026, China), AuthorCompanyExt(id=1322566949024936923, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566949008159705, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江西省地震局, 南昌, 330026)])]), Author(id=1322566949339509731, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, 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=1322566949419201509, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949339509731, language=EN, stringName=Jiehong CHEN, firstName=Jiehong, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949482116070, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949339509731, language=CN, stringName=陈皆红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])]), Author(id=1322566949561807848, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, 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=1322566949654082538, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949561807848, language=EN, stringName=Hua GAO, firstName=Hua, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566949763134443, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949561807848, language=CN, stringName=高华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])]), Author(id=1322566949855409133, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qishuhua11@jxnu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322566949947683823, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949855409133, language=EN, stringName=Shuhua QI, firstName=Shuhua, middleName=null, lastName=QI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322566950035764208, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, authorId=1322566949855409133, language=CN, stringName=齐述华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 江西师范大学地理与环境学院, 南昌, 330022, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322566948920079318, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, xref=null, ext=[AuthorCompanyExt(id=1322566948928467927, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China), AuthorCompanyExt(id=1322566948936856536, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322566945237480387, companyId=1322566948920079318, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 江西师范大学地理与环境学院, 南昌, 330022)])])]
查小惠1, 2 , 陈皆红1, 高华1, 齐述华1, *
作者信息
  • 1 江西师范大学地理与环境学院, 南昌, 330022
  • 2 江西省地震局, 南昌, 330026
通讯作者:
齐述华, 博士, 教授, 主要研究方向为生态环境遥感, E-mail:
作者简介:

查小惠, 高级工程师, 主要研究方向为地震监测和InSAR, E-mail:

A Quality Evaluation Method for InSAR Interferograms Based on Convolutional Neural Network
Xiaohui ZHA1, 2 , Jiehong CHEN1, Hua GAO1, Shuhua QI1, *
Affiliations
  • 1 School of Geography and Environment, Jiangxi Normal University, Nanchang 330022, China
  • 2 Jiangxi Earthquake Agency, Nanchang 330026, China
出版时间: 2026-03-15 doi: 10.14075/j.jgg.2025.04.132
文章导航
收藏切换
摘要
收起

基于卷积神经网络(CNN)提出一种InSAR干涉图质量的自动评价方法, 并将该方法应用于Sentinel-1数据实验中, 测试集的准确率和召回率分别达到96.5%和98%, 自动筛选与人工挑选结果具有很好的一致性。将该方法应用于南昌地区PS-InSAR形变处理, 结果表明, 通过质量评价选择高质量的干涉图开展形变分析, 能够显著提高形变时间序列测量精度。

CNN  /  时序InSAR  /  干涉图质量  /  StaMPS  /  PS-InSAR

Based on convolutional neural network (CNN), an automatic evaluation method for InSAR interferogram quality is proposed. This method is applied to Sentinel-1 data experiments, achieving accuracy and recall rate of 96.5% and 98% on the test set, respectively. The results of automatic screening and manual selection have good consistency. We apply the method to PS-InSAR deformation processing in Nanchang area, it is found that selecting high-quality interferograms for deformation analysis through quality evaluation can significantly improve the accuracy of deformation time series measurement.

CNN  /  time series InSAR  /  interferogram quality  /  StaMPS  /  PS-InSAR
查小惠, 陈皆红, 高华, 齐述华. 基于CNN的InSAR干涉图质量评价方法. 大地测量与地球动力学, 2026 , 46 (3) : 360 -367 . DOI: 10.14075/j.jgg.2025.04.132
Xiaohui ZHA, Jiehong CHEN, Hua GAO, Shuhua QI. A Quality Evaluation Method for InSAR Interferograms Based on Convolutional Neural Network[J]. Journal of Geodesy and Geodynamics, 2026 , 46 (3) : 360 -367 . DOI: 10.14075/j.jgg.2025.04.132
正文
收起
InSAR技术利用覆盖同一区域的2幅或2幅以上SAR图像的相位信号提取地球表面的微小形变[1-2]，在形变测量精度上能达厘米甚至毫米级，已成为大地测量的有力工具，广泛应用于滑坡监测、采矿沉陷分析及地表变形监测等领域。该技术的实现依赖于高质量的干涉图。干涉图质量一般指干涉图在反映地表形变等信息时的准确性和可靠性，其直接关系到形变测量结果的精度。因此，通过干涉图质量评价，挑选质量高的干涉图开展形变研究很有必要[3-4]。
目前干涉图的质量评价方法主要有基于视觉判断的定性法和统计指标的定量法。其中，视觉判断主要依赖处理人员的经验，需要耗费大量的时间和精力。统计指标定量法主要利用相位差分和(SPD)[3]与相位差分加权平均[4]等统计量开展干涉图质量评价。此外，Zhang等[5]根据干涉图的纹理细节特征，提出一种基于连通面积的干涉图质量评价指标。Duan等[6]提出一种基于图论和干涉图的大气湍流方差的自适应优化选择方法，利用整个干涉图的方差对干涉图质量进行评价。然而，目前还没有任何一个单一评价指标可以完备地评价干涉图质量，且指标阈值选择具有主观性，不适用于大规模数据处理。
随着合成孔径雷达卫星的密集发射，InSAR数据处理面临海量数据的挑战，人机交互的数据处理方式已很难满足业务需求。机器学习在海量数据的自动化处理方面具有显著优势，基于卷积神经网络(CNN)的深度学习算法[7-10]被广泛应用，并已深入到相干点提取[11-12]、相位滤波[13-14]和相位解缠[15]等InSAR数据处理各环节。
InSAR干涉图质量评价的本质是干涉图的识别，而CNN在图像处理方面常表现出优异的性能。Wang等[7]对InSAR应用中针对不同目标所采用的深度学习框架进行总结，指出CNN架构在目标识别或分类问题中应用广泛。He等[16]提出以ResNet50为基模型的DCNN深度学习网络，用于识别和删除污染严重的干涉图，实现优质干涉图的自动选择。该方法具有更高效的图像特征提取能力和更优的分类性能，但存在模型复杂且计算量大的问题。
本文首先分析InSAR干涉图质量的影响因素，然后构建用于评价干涉图质量的CNN模型。在此基础上，采用800幅InSAR干涉图对模型进行训练，并用600幅干涉图测试模型性能，探索基于CNN的深度学习模型在干涉图优选方面的应用潜力。
1 原理与方法
收起
1.1 InSAR干涉图质量影响因素和评价标准
InSAR主要用于地表形变监测，干涉图的生成是InSAR技术的关键环节。生成干涉图需要获取2幅或2幅以上覆盖同一地区的不同时间的SAR复数影像，对这些影像进行几何精确配准，通过影像对应像素逐点复共轭相乘，生成系列干涉影像图。差分干涉图的相位变化信息可以用于反演地面的形变信息。
干涉相位变化信息具有2个主要的噪声来源，包括由SAR硬件与处理系统等自身因素产生的多普勒失相干和热噪声失相干，以及由空间基线和时间基线过长造成的失相干[17]。
$\rho_{\text {total }}=\rho_{\text {temporal }} \cdot \rho_{\text {spatial }} \cdot \rho_{\text {Doppler }} \cdot \rho_{\text {thermal }}$
式中，ρtotal为总噪声；ρtemporal为时间失相干；ρspatial为空间失相干；ρDoppler为多普勒失相干；ρthermal为热噪声失相干。
随着雷达卫星制造工艺的改进和卫星轨道控制精度的提高，多普勒失相干、热噪声失相干和空间基线失相干都可以得到较好的控制。在时间基线方面，大气效应是相位噪声的主要来源，通常由沿高度向分层大气和局部湍流组成。通过相位滤波处理可在一定程度上降低相位噪声，提高InSAR干涉图质量，但对于相位噪声太大的干涉图，其滤波效果仍难以满足相位解缠和形变反演的精度要求。因此，在InSAR形变监测中，开展干涉图质量评价，优选高质量干涉图是提高形变监测精度的重要环节。
InSAR干涉图质量评估通常包括定性和定量2种方法，本次研究综合运用定性和定量方法对干涉图质量进行评价。对于缠绕干涉图，主要采用定性的主观目视方法，干涉图中条纹的清晰度是衡量其质量的重要指标。通常情况下，相位梯度较大的区域往往表明存在显著的噪声，这些区域在干涉图中表现为干涉条纹异常密集。这种密集的条纹分布可直观反映干涉图的噪声水平，为质量评估提供重要的视觉依据。对于解缠干涉图，主要采用基于相位变化幅值的定量指标评价其质量，干涉图的幅值变化异常通常暗示着可能存在噪声。通过进一步目视检查缠绕干涉图，可以更准确地判断噪声的存在及其分布情况。这种将定量分析与定性观察相结合的方法，能够更全面地评估干涉图质量，为后续的InSAR数据处理和分析提供可靠的基础。
1.2 干涉图集的生成及其质量的目视判别
为实现深度学习模型的训练，利用Sentinel-1A和Sentinel-1B数据，基于ISCE和StaMPS[18]软件制作训练样本集，卫星数据参数见表 1。选用不同日期的卫星影像作为主影像，进行PS-InSAR数据处理，然后基于StaMPS软件绘制缠绕干涉图和解缠干涉图。基于解缠干涉图结果和缠绕干涉图的目视识别，判断缠绕干涉图质量。本次生成的干涉图均覆盖城市区域，高质量的解缠干涉图相位值稳定，变化范围大致在10 rad以内，且其对应的缠绕干涉图也表现平滑(图 1)。低质量的解缠干涉图相位值变化范围一般在20 rad以上，其对应的缠绕干涉图中存在密集的干涉条纹(图 2)。
高质量和低质量干涉图样本比例的不平衡问题，会使深度学习结果产生偏向性。因此，在数据集准备过程中，需有效增加低质量干涉图的数量，以缓解此类不平衡问题。
本文使用不同主影像进行PS-InSAR处理[19-20]，并从中挑选出低质量的干涉图。以南昌市为例，Sentinel-1A卫星影像共129景，分别使用2018-07-31、2019-07-02、2019-11-11、2019-12-29、2020-01-22、2020-02-03和2020-05-09作为主影像进行处理。结果表明，低质量的干涉图表现出相同特征，当原始SAR数据存在严重的大气干扰时，其他数据与该景SAR影像干涉得到的干涉图质量一般都较差。因此，为了得到更多低质量的干涉图，以2020-05-09的Sentinel-1A影像作为主影像进行PS-InSAR处理，结果表明，缠绕干涉图都包含较为密集的干涉条纹，但解缠干涉图大部分则比较正常。这说明StaMPS处理过程中已估计出主影像的大气相位并成功进行去除，而辅影像的大气相位去除则需要借助其他方法。
本研究针对赣州、九江与南昌地区，分别选取3次、2次和8次不同主影像进行PS-InSAR处理，共生成干涉图若干，并初步筛选出394幅低质量的缠绕干涉图。为扩充低质量的样本集，对上述干涉图进行裁剪变换，使样本数量增至788幅，然后对其施加旋转、缩放及翻转等数据增强操作，最终生成900幅低质量的差分缠绕干涉图。为弥补自然低质量样本的不足，另基于SarNet开源程序[10]合成100幅含噪缠绕干涉图。最终共生成低质量的干涉图样本1 000幅。高质量样本则直接从PS-InSAR处理所得的所有干涉图中挑选，共获得441幅优质缠绕干涉图。同样地，经过裁剪、数据增强等步骤，将其数量扩充至1 000幅。最终，将2 000幅缠绕干涉图数据集按4 ∶ 3 ∶ 3比例随机划分为训练集(800幅)、验证集(600幅)与测试集(600幅)。
2 基于CNN的InSAR干涉图挑选
收起
2.1 CNN模型的构建和训练
使用开源库Keras构建经典的卷积神经网络，该模型由输入层、输出层、5个卷积层、4个池化层和1个全连接层组成(图 3)。其输入数据为RGB图像，数组维度为180×180×3，将输入数据除以255实现归一化。图像标签为标量(1和0)，其中高质量的干涉图标签为1，低质量的干涉图标签为0。卷积层和池化层均为三维数组，全连接层为一维数组，5个卷积层的滤波器数量分别设置为4、8、8、16和16。卷积层中的卷积核大小均为3×3，移动步长为1。池化层采用最大池化方法，内核尺寸为2。第5个卷积层输出后三维数组被展平为一维数组，连接Dropout层并按照0.5的概率舍弃部分神经元，以防止训练过程中的过拟合，然后送入全连接层，最终输出1个神经元。在全连接层使用Sigmoid激活函数输出1个[0, 1]范围内的概率值，表示样本目标值等于1的可能性，即干涉图质量预测为好的概率。此外，每个卷积层均采用ReLU激活函数来提高模型的非线性能力，并应用L2正则化，正则化因子设置为0.000 5。优化器采用RMSprop，学习率设置为0.000 1，迭代次数为1 000次。
训练过程中会保存最佳模型，一旦模型训练完成，使用测试集进行测试。二分类问题常用的评价指标包括准确率、精度和召回率。准确率表示正负样本被正确标记的比例；精度表示样本中被正确标记为正样本的数量占总的标记为正样本数量的比例；召回率也称灵敏度，表示正样本中被标记为正样本的比例。各评价指标的计算公式为：
$\mathrm{ACC}=(\mathrm{TP}+\mathrm{TN}) /(\mathrm{TP}+\mathrm{TN}+\mathrm{FP}+\mathrm{FN})$
$\mathrm{PPV}=\mathrm{TP} /(\mathrm{TP}+\mathrm{FP})$
$\mathrm{TPR}=\mathrm{TP} /(\mathrm{TP}+\mathrm{FN})$
式中，ACC为准确率；PPV为精度；TPR为召回率；TP为判正的正样本数量；TN为判负的负样本数量；FP为判正的负样本数量；FN为判负的正样本数量。目标函数为二元交叉熵，具体表达式为：
$\begin{gathered}L(y, \tilde{y})=-\frac{1}{N} \sum\limits_{i=1}^N\left[y_i \lg \tilde{y}_i+\right. \\\left.\left(1-y_i\right) \lg \left(1-\tilde{y}_i\right)\right]\end{gathered}$
式中，L为损失函数；N为样本数量；yi为第i个样本的真实标签(0或1)；$\tilde{y}_i$为第i个样本的预测概率。使用随机批量方法提高模型的泛化能力和降低过拟合的风险，即每次随机选择32个数据进行训练，每次迭代需要训练25次。由于本次训练数据量较小，模型参数有限，每次迭代训练的时间约为170 ms。
2.2 结果和讨论
本次构建的模型共有5 265个参数，模型训练过程中的误差函数、准确率、精度和召回率曲线如图 4所示。从图 4(a)可以看出，随着训练的进行，训练集损失值一直在降低，验证集损失值表现为先减小后逐渐增大的过程，表明训练出现过拟合。对比CNN模型测试集预测结果和实际情况可知，TP为294，TN为285，FP为15，FN为6，进一步计算可得准确率为0.965，精度为0.952，召回率为0.980。
为了降低CNN模型的过拟合风险，本次采用多种正则化方法构建CNN模型。L2权重正则化的本质是简化模型，以解决特征过多、模型过于复杂的问题。通常认为，权重越小，模型复杂度越低，越能简单有效地描述数据。因此，本文倾向于选择较小的权重。模型训练过程中，对超参数的处理是一个需要经验和时间的步骤。模型层数、卷积层的滤波器数量、学习率和批处理大小等都对模型测试结果存在一定影响, 经过多轮实验训练，最终确定合适的超参数组合，并成功完成模型的训练。
Silva等[9]使用预训练的CNN模型作为卷积基进行特征提取；He等[16]提出基于DCNN的干涉图自动选择方法，使用ResNet50作为卷积基。本文尝试使用预训练的卷积基(VGG16)作为神经网络的前端对干涉图进行预处理，然后对密集连接层进行训练，但模型准确率在测试集上未超过简单的CNN模型。基于预训练模型的深度学习训练速度更快(图 5)，在很少的训练轮次下就可以达到较高的准确率，但前提是需要花费更长的预处理时间。本文的CNN模型架构更简单、参数更少、推理速度更快、学习训练也更容易。深度学习在计算机领域发展迅速，各种改进的模型和架构不断被推出，能处理复杂问题的能力也越来越强，模型的通用性不断增强。然而，在InSAR领域，目前更需关注的是如何构建高质量的学习数据集，而深度学习模型的构建问题则在其次。如果有大量高质量的学习数据集，那么再考虑更复杂的模型是合适的。本文数据量较小，适合训练简单的CNN模型。目前的预训练模型一般是通用型的，基于SAR数据的预训练模型较少，未来基于大量SAR数据构建的神经网络模型，将显著提高InSAR领域的深度学习模型训练效果。
在获得最佳神经网络模型后，为进一步评价模型判断干涉图质量的准确性，对判断结果和标签不一致的干涉图进行回溯性研究。结果表明，在制作数据集过程中，存在标签错误的情况，即好的干涉图标记为差，差的干涉图标记为好。发现该情况后，人为修改数据集标签，然后对神经网络模型进行重新训练，测试精度得到进一步提高。深度学习由数据驱动，训练数据的质量直接决定了深度学习模型的训练效果。然而，制作训练数据集需要耗费大量时间，也存在主观因素，因此回溯性研究有助于发现相关的问题。
为直观展示神经网络模型的预测效果，对训练集和测试集的预测概率分布进行统计(图 6)。可以看出，模型的大部分预测值都为0或1，即模型可以比较确定地判断干涉图质量，但也有部分干涉图具有一定的“模糊性”，模型难以判断其质量。
3 真实数据验证
收起
基于StaMPS软件的PS-InSAR处理主要分为8个步骤：步骤1~5是在分块上运行，第5步将分块整合为1个文件；步骤6~8则进行相位解缠和误差估计，最终得到形变结果。StaMPS软件在第5步之后，所有PS点被挑选出来并整合为1个文件，随后在第6步进行相位解缠。实际处理过程中发现，在缠绕差分干涉图中存在质量明显很差的干涉图，可能是由大气相位异常干扰所致。如果用这些低质量的干涉图进行解缠和误差估计，会导致部分结果出现异常。因此，有必要在相位解缠之前对参与解缠的干涉图进行质量评估。在干涉图数量足够的情况下，剔除低质量干涉图，从而提高时间序列分析精度。StaMPS软件在第5步之后可提供交互式绘图查看干涉图方法，通过设置drop_ifg_index参数决定舍去的干涉图。为验证本文提出的深度神经网络模型的可用性，尝试将该模型应用于StaMPS软件处理过程中，实现PS-InSAR数据处理过程的自动化，同时降低主观性。
基于覆盖南昌地区的129景Sentinel-1A影像，时间范围为2018-01—2022-06，进行PS-InSAR数据处理。选择2019-11-11的SAR影像作为主影像，利用ISCE软件进行影像配准和差分干涉，然后导入StaMPS软件进行后续处理。在StaMPS软件处理完第5步之后，使用本文训练得到的深度神经网络模型对干涉图质量进行评价，剔除低质量干涉图，从而提高形变序列精度。
使用本文神经网络模型对128幅干涉图进行质量评价，得到128个概率输出值，概率值越接近1，表示模型对干涉图的质量评价越高。为了对比不同质量的干涉图对后续处理结果的影响，将干涉图选取的阈值设为0.9。阈值小于0.9的干涉图有21幅，将这些干涉图设为不可用后进行后续相位解缠和形变解算。根据使用的干涉图数量差异，生成2个版本的PS-InSAR处理结果。第1种使用128幅干涉图，第2种使用107幅干涉图。为了验证干涉图挑选对PS-InSAR处理结果的影响，统计分析干涉图剔除前后平均速率分布和平均速率标准差分布。此外，选择5个特征点，分析干涉图剔除前后其形变时间序列结果。
平均速率计算结果显示，使用128幅干涉图获得的速率结果主要介于-5.39~3.63 mm/a，使用107幅干涉图获得的速率结果则主要介于-5.31~3.39 mm/a；使用128幅干涉图得到的速率结果的绝对值小于2的占比为93.4%，使用107幅干涉图得到的速率结果的绝对值小于2的占比为95.4%，说明干涉图剔除后的速率结果分布更加集中。对比速率标准差结果发现，干涉图剔除前的速率标准差小于0.5的占比为76.4%，干涉图剔除后的速率标准差小于0.5的占比为93.4%，速率标准差明显变小(图 7)。
图 8为干涉图剔除前后5个特征点的时间序列对比结果，可以看出，选取高质量干涉图后，形变时间序列变化幅度更小，异常突跳点基本消失。说明低质量干涉图的加入会影响后续的相位解缠，解缠后获得的形变值也包含大量误差，难以准确反映地表变形。因此，在相位解缠前剔除低质量的干涉图是有必要的。本次处理进一步证明，基于干涉图质量评价挑选高质量的干涉图参与计算，可以有效提高形变时间序列测量精度，减少低质量干涉图对测量的影响。
4 结语
收起
基于Sentinel-1卫星数据，结合ISCE和StaMPS软件，使用2 000个InSAR样本数据，构建含5 265个参数的CNN模型，用于评价InSAR干涉图质量。得到以下结论：
1) 该模型仅需少量训练数据即可有效避免过拟合，测试集的准确率、精度和召回率均超过95%。
2) 与预训练模型相比，本研究的原生传统CNN模型因架构简单、参数少和运算效率高，在大数据量自动化干涉图质量评价中更具优势。
3) 使用129景覆盖南昌地区的Sentinel-1A数据进行模型测试，结果表明，经模型剔除低质量干涉图后获得的形变速率分布更集中，标准差明显更小，验证了该模型在筛选InSAR干涉图方面的有效性。
基金
收起
  • 国家自然科学基金(41761076)
  • 江西省重点研发计划(20232BBE50021)
文献
收起
参考文献 引证文献
排序方式：
1
林珲, 马培峰, 王伟玺. 监测城市基础设施健康的星载MT-InSAR方法介绍[J]. 测绘学报, 2017, 46 (10): 1421- 1433
Lin Hui , Ma Peifeng , Wang Weixi . Urban Infrastructure Health Monitoring with Spaceborne Multi-Temporal Synthetic Aperture Radar Interferometry[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46 (10): 1421- 1433
2
朱建军, 李志伟, 胡俊. InSAR变形监测方法与研究进展[J]. 测绘学报, 2017, 46 (10): 1717- 1733
Zhu Jianjun , Li Zhiwei , Hu Jun . Research Progress and Methods of InSAR for Deformation Monitoring[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46 (10): 1717- 1733
3
Li Z L , Zou W B , Ding X L , et al. A Quantitative Measure for the Quality of InSAR Interferograms Based on Phase Differences[J]. Photogrammetric Engineering and Remote Sensing, 2004, 70 (10): 1131- 1137
4
赵超英, 张勤. 一种新的干涉图质量评定指标研究[J]. 大地测量与地球动力学, 2009, 29 (1): 96- 100
Zhao Chaoying , Zhang Qin . Research on a Novel Index for Assessment of Interferogram Quality[J]. Journal of Geodesy and Geodynamics, 2009, 29 (1): 96- 100
5
Zhang T, Lü X L, Hong J. A Novel Interferogram Quality Assessment Index Based on Connected Area[C]. IEEE International Geoscience and Remote Sensing Symposium, Beijing, 2016
6
Duan M , Xu B , Li Z W , et al. Adaptively Selecting Interferograms for SBAS-InSAR Based on Graph Theory and Turbulence Atmosphere[J]. IEEE Access, 2020, 8, 112898- 112909
7
Wang T , Zhang Q , Wu Z P . A Deep-Learning-Facilitated, Detection-First Strategy for Operationally Monitoring Localized Deformation with Large-Scale InSAR[J]. Remote Sensing, 2023, 15 (9)
8
张敬业, 孙珂, 张国宏. 深度学习在InSAR数据处理与地壳形变观测中的应用研究进展[J]. 地震, 2023, 43 (2): 166- 188
Zhang Jingye , Sun Ke , Zhang Guohong . Research Progress in Data Processing and Application of Deep Learning in InSAR Crustal Deformation Observation[J]. Earthquake, 2023, 43 (2): 166- 188
9
Silva B , Sousa J J , Lazecky M , et al. Deformation Fringes Detection in SAR Interferograms Using Deep Learning[J]. Procedia Computer Science, 2022, 196, 151- 158
10
Brengman C M J , Barnhart W D . Identification of Surface Deformation in InSAR Using Machine Learning[J]. Geochemistry, Geophysics, Geosystems, 2021, 22 (3)
11
Tiwari A , Narayan A B , Dikshit O . Deep Learning Networks for Selection of Measurement Pixels in Multi-Temporal SAR Interferometric Processing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166, 169- 182
12
Zhang Y , Wei J , Duan M , et al. Coherent Pixel Selection Using a Dual-Channel 1-D CNN for Time Series InSAR Analysis[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112
13
Sun X Y , Zimmer A , Mukherjee S , et al. DeepInSAR: A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation[J]. Remote Sensing, 2020, 12 (14)
14
Mukherjee S , Zimmer A , Sun X Y , et al. An Unsupervised Generative Neural Approach for InSAR Phase Filtering and Coherence Estimation[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 18 (11): 1971- 1975
15
Zhou L F , Yu H W , Lan Y . Deep Convolutional Neural Network-Based Robust Phase Gradient Estimation for Two-Dimensional Phase Unwrapping Using SAR Interferograms[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58 (7): 4653- 4665
16
He Y F , Zhang G Z , Kaufmann H , et al. Automatic Interferogram Selection for SBAS-InSAR Based on Deep Convolutional Neural Networks[J]. Remote Sensing, 2021, 13 (21): 4468- 4468
17
刘国祥, 陈强, 罗小军, 等. InSAR原理与应用[M]. 北京: 科学出版社, 2019
Liu Guoxiang , Chen Qiang , Luo Xiaojun , et al. Principles and Applications of InSAR[M]. Beijing: Science Press, 2019
18
Hooper A , Segall P , Zebker H . Persistent Scatterer Interferometric Synthetic Aperture Radar for Crustal Deformation Analysis, with Application to Volcán Alcedo, Galápagos[J]. Journal of Geophysical Research: Solid Earth, 2007, 112 (B7)
19
Ferretti A , Prati C , Rocca F . Nonlinear Subsidence Rate Estimation Using Permanent Scatterers in Differential SAR Interferometry[J]. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38 (5): 2202- 2212
20
Crosetto M , Monserrat O , Cuevas-González M , et al. Persistent Scatterer Interferometry: A Review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 115, 78- 89
2026年第46卷第3期
41
16
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2025.04.132
  • 接收时间：2025-04-21
  • 首发时间：2026-10-29
  • 出版时间：2026-03-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2025-04-21
基金
国家自然科学基金(41761076)
江西省重点研发计划(20232BBE50021)
作者信息
    1 江西师范大学地理与环境学院, 南昌, 330022
    2 江西省地震局, 南昌, 330026

通讯作者:

齐述华, 博士, 教授, 主要研究方向为生态环境遥感, E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2025.04.132
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
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62662699（运营及技术支持）
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持