Article(id=1209811346766565386, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405361, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1721059200000, receivedDateStr=2024-07-16, revisedDate=1734883200000, revisedDateStr=2024-12-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1766371102277, onlineDateStr=2025-12-22, pubDate=1751904000000, pubDateStr=2025-07-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766371102277, onlineIssueDateStr=2025-12-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766371102277, creator=13701087609, updateTime=1766371102277, updator=13701087609, issue=Issue{id=1209811339510411616, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='19', pageStart='7885', pageEnd='8315', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766371100547, creator=13701087609, updateTime=1766373228996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1209820266960654935, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1209820266960654936, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=8025, endPage=8033, ext={EN=ArticleExt(id=1209811347672535101, articleId=1209811346766565386, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Geological Profile Generation Method Based on Improved Pix2Pix, columnId=1209811346359710128, journalTitle=Science Technology and Engineering, columnName=Papers∙Petroleum and Natural Gas Industry, runingTitle=null, highlight=null, articleAbstract=

The traditional geological method relies too much on the resolution of seismic reflection and the quality of well data for the determination of geological profiles. In view of the fact that the number of well data that can be used for calibration in the early stage of development is very small, and the traditional geological modeling method generates geological profiles. The efficiency is low and it is difficult to support model establishment and frequent updating. A geological profile generation method based on improved Pix2Pix network was proposed. Firstly, the initial three-dimensional data was sliced. Based on the comprehensive analysis of deep learning network, a Pix2Pix network model based on residual and multi-scale discriminator was constructed. The residual mechanism was introduced in the generator part to improve the learning ability of the network to geological features, and a multi-scale discriminator was set for the model to enhance the discriminant performance of the network. The real seismic reflection data and geological profile data of the oilfield were used to train the model. The experimental results show that the performance of the network model is significantly improved after the introduction of residual mechanism and multi-scale discriminator. The SSIM (structural similarity) score of the generated results and the real geological profile can reach 91.89 %, and the geological features in the generated results are highly fitted with the actual situation.

, correspAuthors=Hua CHEN, 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=Zi-qi SUN, Zhan CAO, Hua CHEN), CN=ArticleExt(id=1209811350524661952, articleId=1209811346766565386, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进Pix2Pix的地质剖面生成方法, columnId=1209811346607174075, journalTitle=科学技术与工程, columnName=论文∙石油、天然气工业, runingTitle=null, highlight=null, articleAbstract=

传统的地质方法对于地质剖面的确定过于依赖地震反射分辨率以及井数据的质量,针对实际情况中开发早期可用于标定的井数据数量极少,且传统地质建模方法生成地质剖面效率较低,难以支撑模型建立和频繁更新的问题,提出了基于改进Pix2Pix网络的地质剖面生成方法。首先对初始的三维数据进行切片处理,在深度学习网络综合分析基础上,构建了基于残差和多尺度判别器的Pix2Pix网络模型,在生成器部分引入残差机制以提高网络对地质特征的学习能力,并为模型设定多尺度判别器,增强网络的判别性能。使用油田的真实地震反射数据和地质剖面数据对模型进行训练,实验结果显示:网络模型在引进残差机制和多尺度判别器后性能得到显著提升,生成结果与真实地质剖面的SSIM (structural similarity)分数能够达到91.89%,生成结果中的地质特征与实际情况高度拟合。

, correspAuthors=陈华, authorNote=null, correspAuthorsNote=
*陈华(1972—),男,汉族,山东聊城人,博士,副教授,硕士研究生导师。研究方向:地球物理数据处理与分析,并行计算和智能算法。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=A+CwXEP+N72ildRY2Dp0tQ==, magXml=0Kzd88C+fBEO7Izwp5zj6w==, pdfUrl=null, pdf=TghDMIsgw2zT/iEBfhGexw==, pdfFileSize=12317678, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=BCpUXBlzO2NSNqkJJvaRPA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3JZmWCy671mExrZsth03Vg==, mapNumber=null, authorCompany=null, fund=null, authors=

孙子奇(2000—),女,汉族,河北保定人,硕士研究生。研究方向:大数据处理与分析。E-mail:

, authorsList=孙子奇, 曹战, 陈华)}, authors=[Author(id=1209888928224637445, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ziqisun200926@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209888928375632400, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928224637445, language=EN, stringName=Zi-qi SUN, firstName=Zi-qi, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Science, China University of Petroleum (East China), Qingdao 266580, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209888928467907094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928224637445, language=CN, stringName=孙子奇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油大学(华东)理学院, 青岛 266580, bio={"content":"

孙子奇(2000—),女,汉族,河北保定人,硕士研究生。研究方向:大数据处理与分析。E-mail:

"}, bioImg=null, bioContent=

孙子奇(2000—),女,汉族,河北保定人,硕士研究生。研究方向:大数据处理与分析。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209888928111391224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, xref=null, ext=[AuthorCompanyExt(id=1209888928115585529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Science, China University of Petroleum (East China), Qingdao 266580, China), AuthorCompanyExt(id=1209888928123974139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油大学(华东)理学院, 青岛 266580)])]), Author(id=1209888928585347617, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, 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=1209888928702788136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928585347617, language=EN, stringName=Zhan CAO, firstName=Zhan, middleName=null, lastName=CAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Science, China University of Petroleum (East China), Qingdao 266580, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209888928799257134, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928585347617, language=CN, stringName=曹战, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国石油大学(华东)理学院, 青岛 266580, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209888928111391224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, xref=null, ext=[AuthorCompanyExt(id=1209888928115585529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Science, China University of Petroleum (East China), Qingdao 266580, China), AuthorCompanyExt(id=1209888928123974139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油大学(华东)理学院, 青岛 266580)])]), Author(id=1209888928912503350, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=delaunay@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1209888928992195132, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928912503350, language=EN, stringName=Hua CHEN, firstName=Hua, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=School of Science, China University of Petroleum (East China), Qingdao 266580, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209888929063498304, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, authorId=1209888928912503350, language=CN, stringName=陈华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=中国石油大学(华东)理学院, 青岛 266580, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209888928111391224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, xref=null, ext=[AuthorCompanyExt(id=1209888928115585529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Science, China University of Petroleum (East China), Qingdao 266580, China), AuthorCompanyExt(id=1209888928123974139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油大学(华东)理学院, 青岛 266580)])])], keywords=[Keyword(id=1209888929256436300, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, orderNo=1, keyword=image semantic recognition), Keyword(id=1209888929336128084, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, orderNo=2, keyword=deep generative models), Keyword(id=1209888929399042651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, orderNo=3, keyword=Pix2Pix networks), Keyword(id=1209888929558426207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, orderNo=4, keyword=geological modeling), Keyword(id=1209888929688449641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, orderNo=1, keyword=图像语义识别), Keyword(id=1209888929852027503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, orderNo=2, keyword=深度生成模型), Keyword(id=1209888929944302199, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, orderNo=3, keyword=Pix2Pix网络), Keyword(id=1209888930040771195, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, orderNo=4, keyword=地质建模)], refs=[Reference(id=1209888932314084064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=8, pageStart=3107, pageEnd=3114, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=赵兵, 罗攀登, 张妹珠, journalName=科学技术与工程, refType=null, unstructuredReference=赵兵, 罗攀登, 张妹珠, 等. 基于“地质-工程”耦合平台的顺北断溶体储层地应力分布规律分析[J]. 科学技术与工程, 2024, 24(8): 3107-3114., articleTitle=基于“地质-工程”耦合平台的顺北断溶体储层地应力分布规律分析, refAbstract=null), Reference(id=1209888932393775840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=8, pageStart=3107, pageEnd=3114, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhao Bing, Luo Pandeng, Zhang Meizhu, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhao Bing, Luo Pandeng, Zhang Meizhu, et al. In-situ stress distribution analysis of shunbei fault-karst reservoir based on “ geology-engineering” coupling platform[J]. Science Technology and Engineering, 2024, 24(8): 3107-3114., articleTitle=In-situ stress distribution analysis of shunbei fault-karst reservoir based on “ geology-engineering” coupling platform, refAbstract=null), Reference(id=1209888932536382184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=朱莹, journalName=地质剖面自动绘制系统研究, refType=null, unstructuredReference=朱莹. 地质剖面自动绘制系统研究[D]. 南京: 南京师范大学, 2006., articleTitle=null, refAbstract=null), Reference(id=1209888932620268263, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Zhu Ying, journalName=Nanjing: Nanjing Normal University, refType=null, unstructuredReference=Zhu Ying. Research on automatic drawing system of geological section[D]. Nanjing: Nanjing Normal University, 2006., articleTitle=null, refAbstract=null), Reference(id=1209888932712542954, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2013, volume=38, issue=2, pageStart=49, pageEnd=50, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=宋仁波, journalName=测绘地理信息, refType=null, unstructuredReference=宋仁波. 基于ArcGIS和Google SketchUp的三维地质剖面绘制方法[J]. 测绘地理信息, 2013, 38(2): 49-50, 53., articleTitle=基于ArcGIS和Google SketchUp的三维地质剖面绘制方法, refAbstract=null), Reference(id=1209888932855149298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2013, volume=38, issue=2, pageStart=49, pageEnd=50, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Song Renbo, journalName=Mapping Geographic Information, refType=null, unstructuredReference=Song Renbo. 3D geological section drawing method based on ArcGIS and Google SketchUp[J]. Mapping Geographic Information, 2013, 38(2): 49-50, 53., articleTitle=3D geological section drawing method based on ArcGIS and Google SketchUp, refAbstract=null), Reference(id=1209888932947423990, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=1, pageStart=203, pageEnd=212, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=段太忠, 张文彪, 何治亮, journalName=石油与天然气地质, refType=null, unstructuredReference=段太忠, 张文彪, 何治亮, 等. 塔里木盆地顺北油田超深断溶体深度学习地质建模方法[J]. 石油与天然气地质, 2023, 44(1): 203-212., articleTitle=塔里木盆地顺北油田超深断溶体深度学习地质建模方法, refAbstract=null), Reference(id=1209888933043892985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=1, pageStart=203, pageEnd=212, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Duan Taizhong, Zhang Wenbiao, He Zhiliang, journalName=Oil and Natural Gas Geology, refType=null, unstructuredReference=Duan Taizhong, Zhang Wenbiao, He Zhiliang, et al. Deep learning geological modeling method for ultra-deep fault-karst in Shunbei Oilfield, Tarim Basin [J]. Oil and Natural Gas Geology, 2023, 44(1): 203-212., articleTitle=Deep learning geological modeling method for ultra-deep fault-karst in Shunbei Oilfield, Tarim Basin [J], refAbstract=null), Reference(id=1209888933136167676, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=235, pageEnd=241, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=刘彦锋, 张文彪, 段太忠, journalName=地质科技通报, refType=null, unstructuredReference=刘彦锋, 张文彪, 段太忠, 等. 深度学习油气藏地质建模研究进展[J]. 地质科技通报, 2021, 40(4): 235-241., articleTitle=深度学习油气藏地质建模研究进展, refAbstract=null), Reference(id=1209888933241025279, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=235, pageEnd=241, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Liu Yanfeng, Zhang Wenbiao, Duan Taizhong, journalName=Geological Science and Technology Bulletin, refType=null, unstructuredReference=Liu Yanfeng, Zhang Wenbiao, Duan Taizhong, et al. Research progress of deep learning reservoir geological modeling[J]. Geological Science and Technology Bulletin, 2021, 40(4): 235-241., articleTitle=Research progress of deep learning reservoir geological modeling[J], refAbstract=null), Reference(id=1209888933341688577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=9407, pageEnd=9415, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Chavdarova T, Fleuret F, journalName=2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Chavdarova T, Fleuret F. SGAN: an alternative training of generative adversarial networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 9407-9415., articleTitle=SGAN: an alternative training of generative adversarial networks, refAbstract=null), Reference(id=1209888933450740483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2017, volume=70, issue=null, pageStart=214, pageEnd=223, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Arjovsky M, Chintala S, Bottou L, journalName=International Conference on Machine Learning, refType=null, unstructuredReference=Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[J]. International Conference on Machine Learning, 2017, 70: 214-223., articleTitle=Wasserstein generative adversarial networks, refAbstract=null), Reference(id=1209888933576569607, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=3, pageStart=1251, pageEnd=1273, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=Song S H, Mukerji T, Hou J G, journalName=Computational Geosciences, refType=null, unstructuredReference=Song S H, Mukerji T, Hou J G. Geological facies modeling based on progressive growing of generative adversarial networks (GANs)[J]. Computational Geosciences, 2021, 25(3): 1251-1273., articleTitle=Geological facies modeling based on progressive growing of generative adversarial networks (GANs), refAbstract=null), Reference(id=1209888933652067081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=7, pageStart=1413, pageEnd=1444, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Song S H, Mukerji T, Hou J G, journalName=Mathematical Geosciences, refType=null, unstructuredReference=Song S H, Mukerji T, Hou J G. GANSim: conditional facies simulation using an improved progressive growing of generative adversarial networks (GANs)[J]. Mathematical Geosciences, 2021, 53(7): 1413-1444., articleTitle=GANSim: conditional facies simulation using an improved progressive growing of generative adversarial networks (GANs), refAbstract=null), Reference(id=1209888933748536077, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=31, issue=6, pageStart=182, pageEnd=191, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=李佳琪, 邓玉娇, 吴湘宁, journalName=计算机系统应用, refType=null, unstructuredReference=李佳琪, 邓玉娇, 吴湘宁, 等. 基于注意力及生成对抗网络的遥感影像目标检测[J]. 计算机系统应用, 2022, 31(6): 182-191., articleTitle=基于注意力及生成对抗网络的遥感影像目标检测, refAbstract=null), Reference(id=1209888933840810770, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=31, issue=6, pageStart=182, pageEnd=191, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Li Jiaqi, Deng Yujiao, Wu Xiangning, journalName=Computer System Application, refType=null, unstructuredReference=Li Jiaqi, Deng Yujiao, Wu Xiangning, et al. Remote sensing image target detection based on attention and generative adversarial networks [J]. Computer System Application, 2022, 31( 6 ) : 182-191., articleTitle=Remote sensing image target detection based on attention and generative adversarial networks [J], refAbstract=null), Reference(id=1209888933954056983, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2794, pageEnd=2802, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Mao X, Li Q, Xie H, journalName=Proceedings of the IEEE International Conference on Computer Vision, refType=null, unstructuredReference=Mao X, Li Q, Xie H, et al. Least squares generative adversarial networks[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 2794-2802., articleTitle=Least squares generative adversarial networks, refAbstract=null), Reference(id=1209888934067303194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=142, issue=null, pageStart=104693, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Li T, Zuo R, Zhao X, journalName=Ore Geology Reviews, refType=null, unstructuredReference=Li T, Zuo R, Zhao X, et al. Mapping prospectivity for regolith-hosted REE deposits via convolutional neural network with generative adversarial network augmented data[J]. Ore Geology Reviews, 2022, 142: 104693., articleTitle=Mapping prospectivity for regolith-hosted REE deposits via convolutional neural network with generative adversarial network augmented data, refAbstract=null), Reference(id=1209888934142800669, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2020, volume=52, issue=1, pageStart=53, pageEnd=79, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Mosser L, Dubrule O, Blunt M J, journalName=Mathematical Geosciences, refType=null, unstructuredReference=Mosser L, Dubrule O, Blunt M J. Stochastic seismic waveform inversion using generative adversarial networks as a geological prior[J]. Mathematical Geosciences, 2020, 52(1): 53-79., articleTitle=Stochastic seismic waveform inversion using generative adversarial networks as a geological prior, refAbstract=null), Reference(id=1209888934226686756, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=14, pageStart=5804, pageEnd=5811, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=何鹏, 罗智浩, 胡蓉, journalName=科学技术与工程, refType=null, unstructuredReference=何鹏, 罗智浩, 胡蓉, 等. 基于改进GAN的水力测功器轴承故障在线诊断方法[J]. 科学技术与工程, 2024, 24(14): 5804-5811., articleTitle=基于改进GAN的水力测功器轴承故障在线诊断方法, refAbstract=null), Reference(id=1209888934323155753, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=14, pageStart=5804, pageEnd=5811, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=He Peng, Luo Zhihao, Hu Rong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=He Peng, Luo Zhihao, Hu Rong, et al. Online fault diagnosis method of hydraulic dynamometer bearing based on improved GAN[J]. Science Technology and Engineering, 2024, 24(14): 5804-5811., articleTitle=Online fault diagnosis method of hydraulic dynamometer bearing based on improved GAN, refAbstract=null), Reference(id=1209888934432207660, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=23, pageStart=10015, pageEnd=10022, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=刘慧, 卢云志, 张雷, journalName=科学技术与工程, refType=null, unstructuredReference=刘慧, 卢云志, 张雷. 基于Dropout改进的SRGAN网络DrSRGAN[J]. 科学技术与工程, 2023, 23(23): 10015-10022., articleTitle=基于Dropout改进的SRGAN网络DrSRGAN, refAbstract=null), Reference(id=1209888934545453873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=23, pageStart=10015, pageEnd=10022, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Liu Hui, Lu Yunzhi, Zhang Lei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liu Hui, Lu Yunzhi, Zhang Lei. An improved SRGAN network based on Dropout called DrSRGAN[J]. Science Technology and Engineering, 2023, 23(23): 10015-10022., articleTitle=An improved SRGAN network based on Dropout called DrSRGAN, refAbstract=null), Reference(id=1209888934646117175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=23, pageStart=10155, pageEnd=10161, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=林洋平, 张明书, 陈培, journalName=科学技术与工程, refType=null, unstructuredReference=林洋平, 张明书, 陈培, 等. 基于GAN的视频隐写算法[J]. 科学技术与工程, 2022, 22(23): 10155-10161., articleTitle=基于GAN的视频隐写算法, refAbstract=null), Reference(id=1209888934763557693, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=23, pageStart=10155, pageEnd=10161, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Lin Yangping, Zhang Mingshu, Chen Pei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Lin Yangping, Zhang Mingshu, Chen Pei, et al. Video steganography algorithm based on generative adversarial network[J]. Science Technology and Engineering, 2022, 22(23): 10155-10161., articleTitle=Video steganography algorithm based on generative adversarial network, refAbstract=null), Reference(id=1209888934864220994, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=10, pageStart=94100, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=何怡, 赵德, 任泽民, journalName=激光杂志, refType=null, unstructuredReference=何怡, 赵德, 任泽民, 等. 基于改进pix2pix框架的人脸图像修复模型[J]. 激光杂志, 2024, 45(10): 94100., articleTitle=基于改进pix2pix框架的人脸图像修复模型, refAbstract=null), Reference(id=1209888934985855812, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=10, pageStart=94100, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=He Yi, Zhao De, Ren Zemin, journalName=Laser Magazine, refType=null, unstructuredReference=He Yi, Zhao De, Ren Zemin, et al. Face image inpainting model based on improved pix2pix framework [J]. Laser Magazine, 2024, 45(10): 94100., articleTitle=Face image inpainting model based on improved pix2pix framework [J], refAbstract=null), Reference(id=1209888935065547591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=5, pageStart=1151, pageEnd=1158, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=谢威夷, 徐锡杰, 芮小平, journalName=遥感技术与应用, refType=null, unstructuredReference=谢威夷, 徐锡杰, 芮小平, 等. 基于Pix2Pix网络的遥感影像样本扩增方法[J]. 遥感技术与应用, 2024, 39(5): 1151-1158., articleTitle=基于Pix2Pix网络的遥感影像样本扩增方法, refAbstract=null), Reference(id=1209888935141045067, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=5, pageStart=1151, pageEnd=1158, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Xie Weiyi, Xu Xijie, Rui Xiaoping, journalName=Remote Sensing Technology and Application, refType=null, unstructuredReference=Xie Weiyi, Xu Xijie, Rui Xiaoping, et al. Remote sensing image sample amplification method based on Pix2Pix network[J]. Remote Sensing Technology and Application, 2024, 39(5): 1151-1158., articleTitle=Remote sensing image sample amplification method based on Pix2Pix network, refAbstract=null), Reference(id=1209888935237514064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=12, pageStart=3083, pageEnd=3095, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=段凌凤, 王新轶, 王治昊, journalName=作物学报, refType=null, unstructuredReference=段凌凤, 王新轶, 王治昊, 等. 基于改进Pix2Pix-HD网络的多品种水稻生长可视化预测方法[J]. 作物学报, 2024, 50(12): 3083-3095., articleTitle=基于改进Pix2Pix-HD网络的多品种水稻生长可视化预测方法, refAbstract=null), Reference(id=1209888935313011539, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=12, pageStart=3083, pageEnd=3095, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=Duan Lingfeng, Wang Xinyi, Wang Zhihao, journalName=Journal of Crops, refType=null, unstructuredReference=Duan Lingfeng, Wang Xinyi, Wang Zhihao, et al. Visual prediction method of multi-variety rice growth based on improved Pix2Pix-HD network [J]. Journal of Crops, 2024, 50(12): 3083-3095., articleTitle=Visual prediction method of multi-variety rice growth based on improved Pix2Pix-HD network [J], refAbstract=null), Reference(id=1209888935426257751, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1125, pageEnd=1134, url=null, language=null, rfNumber=[20], rfOrder=31, authorNames=Isola P, Zhu J Y, Zhou T H, journalName=Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Isola P, Zhu J Y, Zhou T H, et al. Image-to-image translation with conditional adversarial networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1125-1134., articleTitle=Image-to-image translation with conditional adversarial networks, refAbstract=null), Reference(id=1209888935531115356, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=8160, pageEnd=8168, url=null, language=null, rfNumber=[21], rfOrder=32, authorNames=Qu Y, Chen Y, Huang J, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Qu Y, Chen Y, Huang J, et al. Enhanced pix2pix dehazing network[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 8160-8168., articleTitle=Enhanced pix2pix dehazing network, refAbstract=null), Reference(id=1209888935627584351, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=5, pageStart=57, pageEnd=65, url=null, language=null, rfNumber=[22], rfOrder=33, authorNames=黄聪, 周坤, 安学刚, journalName=兰州交通大学学报, refType=null, unstructuredReference=黄聪, 周坤, 安学刚. 基于改进pix2pix的遥感图像语义分割[J]. 兰州交通大学学报, 2023, 42(5): 57-65., articleTitle=基于改进pix2pix的遥感图像语义分割, refAbstract=null), Reference(id=1209888935736636258, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=5, pageStart=57, pageEnd=65, url=null, language=null, rfNumber=[22], rfOrder=34, authorNames=Huang Cong, Zhou Kun, An Xuegang, journalName=Journal of Lanzhou Jiaotong University, refType=null, unstructuredReference=Huang Cong, Zhou Kun, An Xuegang. Semantic segmentation of remote sensing images based on improved pix2pix[J]. Journal of Lanzhou Jiaotong University, 2023, 42(5): 57-65., articleTitle=Semantic segmentation of remote sensing images based on improved pix2pix, refAbstract=null), Reference(id=1209888935820522344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=10, pageStart=242, pageEnd=248, url=null, language=null, rfNumber=[23], rfOrder=35, authorNames=吴雅琴, 侯云峰, 陈林, journalName=计算机仿真, refType=null, unstructuredReference=吴雅琴, 侯云峰, 陈林. 基于改进Pix2Pix网络的去口罩遮挡修复研究[J]. 计算机仿真, 2023, 40(10): 242-248., articleTitle=基于改进Pix2Pix网络的去口罩遮挡修复研究, refAbstract=null), Reference(id=1209888935900214122, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=10, pageStart=242, pageEnd=248, url=null, language=null, rfNumber=[23], rfOrder=36, authorNames=Wu Yaqin, Hou Yunfeng, Chen Lin, journalName=Computer Simulation, refType=null, unstructuredReference=Wu Yaqin, Hou Yunfeng, Chen Lin. Research on mask removal and occlusion repair based on improved Pix2Pix network[J]. Computer Simulation, 2023, 40(10): 242-248., articleTitle=Research on mask removal and occlusion repair based on improved Pix2Pix network, refAbstract=null), Reference(id=1209888936017654642, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=7, pageStart=1157, pageEnd=1163, url=null, language=null, rfNumber=[24], rfOrder=37, authorNames=叶明亮, 史春景, 郝永平, journalName=激光与红外, refType=null, unstructuredReference=叶明亮, 史春景, 郝永平, 等. 基于改进pix2pix的红外图像转换技术[J]. 激光与红外, 2024, 54(7): 1157-1163., articleTitle=基于改进pix2pix的红外图像转换技术, refAbstract=null), Reference(id=1209888936109929333, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=7, pageStart=1157, pageEnd=1163, url=null, language=null, rfNumber=[24], rfOrder=38, authorNames=Ye Mingliang, Shi Chunjing, Hao Yongping, journalName=Laser and Infrared, refType=null, unstructuredReference=Ye Mingliang, Shi Chunjing, Hao Yongping, et al. Infrared image conversion technology based on improved pix2pix [J]. Laser and Infrared, 2024, 54(7): 1157-1163., articleTitle=Infrared image conversion technology based on improved pix2pix [J], refAbstract=null), Reference(id=1209888936202204027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=172, pageEnd=189, url=null, language=null, rfNumber=[25], rfOrder=39, authorNames=Huang X, Liu M Y, Belongie S, journalName=Proceedings of the European Conference on Computer Vision, refType=null, unstructuredReference=Huang X, Liu M Y, Belongie S, et al. Multimodal unsupervised image-to-image translation[C]// Proceedings of the European Conference on Computer Vision, New York: IEEE, 2018: 172-189., articleTitle=Multimodal unsupervised image-to-image translation, refAbstract=null), Reference(id=1209888936290284417, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=9, pageStart=1393, pageEnd=1398, url=null, language=null, rfNumber=[26], rfOrder=40, authorNames=李鸿翔, 王晓丽, 阳春华, journalName=控制理论与应用, refType=null, unstructuredReference=李鸿翔, 王晓丽, 阳春华, 等. 基于GAN-UNet的矿石图像分割方法[J]. 控制理论与应用, 2021, 38(9): 1393-1398., articleTitle=基于GAN-UNet的矿石图像分割方法, refAbstract=null), Reference(id=1209888936390947718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=9, pageStart=1393, pageEnd=1398, url=null, language=null, rfNumber=[26], rfOrder=41, authorNames=Li Hongxiang, Wang Xiaoli, Yang Chunhua, journalName=Control Theory and Application, refType=null, unstructuredReference=Li Hongxiang, Wang Xiaoli, Yang Chunhua, et al. Ore image segmentation method based on GAN-UNet [J]. Control Theory and Application, 2021, 38(9): 1393-1398., articleTitle=Ore image segmentation method based on GAN-UNet [J], refAbstract=null), Reference(id=1209888936499999626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/1701.02676, language=null, rfNumber=[27], rfOrder=42, authorNames=Dong H, Neekhara P, Wu C, journalName=arXiv, refType=null, unstructuredReference=Dong H, Neekhara P, Wu C, et al. Unsupervised image-to-image translation with generative adversarial networks[J]. arXiv, 2017, https://arxiv.org/abs/1701.02676., articleTitle=Unsupervised image-to-image translation with generative adversarial networks, refAbstract=null), Reference(id=1209888936583885710, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=7, issue=1, pageStart=34, pageEnd=49, url=null, language=null, rfNumber=[28], rfOrder=43, authorNames=宋随宏, 史燕青, 侯加根, journalName=石油科学通报, refType=null, unstructuredReference=宋随宏, 史燕青, 侯加根. 基于生成对抗网络的储层地质建模方法研究进展[J]. 石油科学通报, 2022, 7(1): 34-49., articleTitle=基于生成对抗网络的储层地质建模方法研究进展, refAbstract=null), Reference(id=1209888936671966100, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2022, volume=7, issue=1, pageStart=34, pageEnd=49, url=null, language=null, rfNumber=[28], rfOrder=44, authorNames=Song Suihong, Shi Yanqing, Hou Jiagen, journalName=Petroleum Science Bulletin, refType=null, unstructuredReference=Song Suihong, Shi Yanqing, Hou Jiagen. Research progress of reservoir geological modeling methods based on generative adversarial networks [J]. Petroleum Science Bulletin, 2022, 7(1): 34-49., articleTitle=Research progress of reservoir geological modeling methods based on generative adversarial networks [J], refAbstract=null), Reference(id=1209888936760046486, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://arxiv.org/abs/1711.11585, language=null, rfNumber=[29], rfOrder=45, authorNames=Wang T C, Liu M Y, Zhu J Y, journalName=arXiv, refType=null, unstructuredReference=Wang T C, Liu M Y, Zhu J Y. High-resolution image synthesis and semantic manipulation with conditional GANs[J]. arXiv, 2018, https://arxiv.org/abs/1711.11585., articleTitle=High-resolution image synthesis and semantic manipulation with conditional GANs, refAbstract=null)], funds=[Fund(id=1209888932154700501, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, awardId=ZD2019-183-006, language=CN, fundingSource=中石油重大科技项目(ZD2019-183-006), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1209888928111391224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, xref=null, ext=[AuthorCompanyExt(id=1209888928115585529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Science, China University of Petroleum (East China), Qingdao 266580, China), AuthorCompanyExt(id=1209888928123974139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, companyId=1209888928111391224, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国石油大学(华东)理学院, 青岛 266580)])], figs=[ArticleFig(id=1209888930351149698, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.1, caption=Model structure, figureFileSmall=ask1pUKQ1k0kiSGYpPZ16A==, figureFileBig=ZWxK9Cm/cdwevNFgYFp3aw==, tableContent=null), ArticleFig(id=1209888930447618695, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图1, caption=模型示意图, figureFileSmall=ask1pUKQ1k0kiSGYpPZ16A==, figureFileBig=ZWxK9Cm/cdwevNFgYFp3aw==, tableContent=null), ArticleFig(id=1209888930548281998, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.2, caption=Generator model structure, figureFileSmall=YU9bXqxV08tecyk7WLCoSw==, figureFileBig=s9adjxfqHw21Gy4Y8WO3uQ==, tableContent=null), ArticleFig(id=1209888930665722516, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图2, caption=生成器模型结构, figureFileSmall=YU9bXqxV08tecyk7WLCoSw==, figureFileBig=s9adjxfqHw21Gy4Y8WO3uQ==, tableContent=null), ArticleFig(id=1209888930732831382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.3, caption=Schematic diagram of the residual module, figureFileSmall=y4tuWedKQv+VqWRmcqjnUA==, figureFileBig=7qQYpjw+LTiPyLpkaOntoQ==, tableContent=null), ArticleFig(id=1209888930850271901, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图3, caption=残差模块示意图, figureFileSmall=y4tuWedKQv+VqWRmcqjnUA==, figureFileBig=7qQYpjw+LTiPyLpkaOntoQ==, tableContent=null), ArticleFig(id=1209888931009655458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.4, caption=Discriminator model structure, figureFileSmall=mdJGGQ/l9QUqLKWvH4vGpQ==, figureFileBig=InrllVB2gAeWbZdVg8VRFw==, tableContent=null), ArticleFig(id=1209888931106124452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图4, caption=判别器模型结构, figureFileSmall=mdJGGQ/l9QUqLKWvH4vGpQ==, figureFileBig=InrllVB2gAeWbZdVg8VRFw==, tableContent=null), ArticleFig(id=1209888931177427623, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.5, caption=Schematic diagram of a multiscale discriminator, figureFileSmall=PdWf114y2F5IN00sUeVzlw==, figureFileBig=qnSKYra0mou9yeudCw/QUg==, tableContent=null), ArticleFig(id=1209888931269702316, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图5, caption=多尺度判别器示意图, figureFileSmall=PdWf114y2F5IN00sUeVzlw==, figureFileBig=qnSKYra0mou9yeudCw/QUg==, tableContent=null), ArticleFig(id=1209888931370365616, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.6, caption=Initial data set, figureFileSmall=3wmP7rrQa/pNpu3wkz9C2w==, figureFileBig=cz8UALXNnMqWPRCfGQt8EA==, tableContent=null), ArticleFig(id=1209888931471028915, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图6, caption=初始数据集, figureFileSmall=3wmP7rrQa/pNpu3wkz9C2w==, figureFileBig=cz8UALXNnMqWPRCfGQt8EA==, tableContent=null), ArticleFig(id=1209888931575886522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.7, caption=A set of images from the dataset, figureFileSmall=qpzL8co9xHlVSOEi2EPRgA==, figureFileBig=MuRn/0rXnXd26hTDcs2z9g==, tableContent=null), ArticleFig(id=1209888931676549825, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图7, caption=从数据集中截取的一组图片, figureFileSmall=qpzL8co9xHlVSOEi2EPRgA==, figureFileBig=MuRn/0rXnXd26hTDcs2z9g==, tableContent=null), ArticleFig(id=1209888931756241603, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Fig.8, caption=Comparison of the generation results of different models, figureFileSmall=2Q5Lre2NF1hkZ8/mro7FqA==, figureFileBig=rvpkRPeLh817qrrKSE5MZg==, tableContent=null), ArticleFig(id=1209888931831739079, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=图8, caption=不同模型的生成结果对比, figureFileSmall=2Q5Lre2NF1hkZ8/mro7FqA==, figureFileBig=rvpkRPeLh817qrrKSE5MZg==, tableContent=null), ArticleFig(id=1209888931911430861, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=EN, label=Table 1, caption=

Comparison of SSIM results generated by different models

, figureFileSmall=null, figureFileBig=null, tableContent=
图片编号\
网络模型
SSIM/%
Pix2Pix 残差P2P 多尺度判别P2P 改进P2P
图片1 87.823 92.213 89.017 93.752
图片2 83.316 90.007 88.119 91.213
图片3 81.176 87.665 88.949 89.234
图片4 86.116 91.958 90.226 93.375
图片5 86.554 91.275 90.112 91.889
平均 84.997 90.824 88.684 91.893
), ArticleFig(id=1209888932003705553, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209811346766565386, language=CN, label=表1, caption=

不同模型生成结果的SSIM对比

, figureFileSmall=null, figureFileBig=null, tableContent=
图片编号\
网络模型
SSIM/%
Pix2Pix 残差P2P 多尺度判别P2P 改进P2P
图片1 87.823 92.213 89.017 93.752
图片2 83.316 90.007 88.119 91.213
图片3 81.176 87.665 88.949 89.234
图片4 86.116 91.958 90.226 93.375
图片5 86.554 91.275 90.112 91.889
平均 84.997 90.824 88.684 91.893
)], 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.1671-1815.2405361, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405361, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405361, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405361, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进Pix2Pix的地质剖面生成方法
收藏切换
PDF下载
孙子奇 , 曹战 , 陈华 *
科学技术与工程 | 论文∙石油、天然气工业 2025,25(19): 8025-8033
收起
收藏切换
科学技术与工程 | 论文∙石油、天然气工业 2025, 25(19): 8025-8033
基于改进Pix2Pix的地质剖面生成方法
全屏
孙子奇 , 曹战, 陈华*
作者信息
  • 中国石油大学(华东)理学院, 青岛 266580
  • 孙子奇(2000—),女,汉族,河北保定人,硕士研究生。研究方向:大数据处理与分析。E-mail:

通讯作者:

*陈华(1972—),男,汉族,山东聊城人,博士,副教授,硕士研究生导师。研究方向:地球物理数据处理与分析,并行计算和智能算法。E-mail:
Geological Profile Generation Method Based on Improved Pix2Pix
Zi-qi SUN , Zhan CAO, Hua CHEN*
Affiliations
  • School of Science, China University of Petroleum (East China), Qingdao 266580, China
出版时间: 2025-07-08 doi: 10.12404/j.issn.1671-1815.2405361
文章导航
收藏切换

传统的地质方法对于地质剖面的确定过于依赖地震反射分辨率以及井数据的质量,针对实际情况中开发早期可用于标定的井数据数量极少,且传统地质建模方法生成地质剖面效率较低,难以支撑模型建立和频繁更新的问题,提出了基于改进Pix2Pix网络的地质剖面生成方法。首先对初始的三维数据进行切片处理,在深度学习网络综合分析基础上,构建了基于残差和多尺度判别器的Pix2Pix网络模型,在生成器部分引入残差机制以提高网络对地质特征的学习能力,并为模型设定多尺度判别器,增强网络的判别性能。使用油田的真实地震反射数据和地质剖面数据对模型进行训练,实验结果显示:网络模型在引进残差机制和多尺度判别器后性能得到显著提升,生成结果与真实地质剖面的SSIM (structural similarity)分数能够达到91.89%,生成结果中的地质特征与实际情况高度拟合。

图像语义识别  /  深度生成模型  /  Pix2Pix网络  /  地质建模

The traditional geological method relies too much on the resolution of seismic reflection and the quality of well data for the determination of geological profiles. In view of the fact that the number of well data that can be used for calibration in the early stage of development is very small, and the traditional geological modeling method generates geological profiles. The efficiency is low and it is difficult to support model establishment and frequent updating. A geological profile generation method based on improved Pix2Pix network was proposed. Firstly, the initial three-dimensional data was sliced. Based on the comprehensive analysis of deep learning network, a Pix2Pix network model based on residual and multi-scale discriminator was constructed. The residual mechanism was introduced in the generator part to improve the learning ability of the network to geological features, and a multi-scale discriminator was set for the model to enhance the discriminant performance of the network. The real seismic reflection data and geological profile data of the oilfield were used to train the model. The experimental results show that the performance of the network model is significantly improved after the introduction of residual mechanism and multi-scale discriminator. The SSIM (structural similarity) score of the generated results and the real geological profile can reach 91.89 %, and the geological features in the generated results are highly fitted with the actual situation.

image semantic recognition  /  deep generative models  /  Pix2Pix networks  /  geological modeling
孙子奇, 曹战, 陈华. 基于改进Pix2Pix的地质剖面生成方法. 科学技术与工程, 2025 , 25 (19) : 8025 -8033 . DOI: 10.12404/j.issn.1671-1815.2405361
Zi-qi SUN, Zhan CAO, Hua CHEN. Geological Profile Generation Method Based on Improved Pix2Pix[J]. Science Technology and Engineering, 2025 , 25 (19) : 8025 -8033 . DOI: 10.12404/j.issn.1671-1815.2405361
在油气资源勘探开发中,地质特征的学习挖掘具有十分重要的作用[1]。地质剖面图是沿某一方向显示地表或一定深度内地质构造情况的实际(或推断)切面。它能为系统分析区域或局部的油藏地质条件、正确指导油藏资源开发利用和优化管理提供依据。
地质剖面图的绘制方法主要有传统的手工绘制、利用计算机辅助设计(computer aided design,CAD)技术结合编程语言进行绘制以及利用组件式地理信息系统(geographic information system,GIS)技术结合编程语言绘制[1-3]。传统的手工绘制地质剖面图,是根据在地表上的一条剖面线,使用剖面线上分布的钻孔和地质构造相关数据,依次绘出地层界线、断层线和褶皱线,然后根据岩层倾角,利用不用的颜色和规定的图元符号对表示各个地层的区域进行岩性花纹填充,完成该剖面的二维图形绘制工作。CAD技术和GIS技术与编程语言结合的方法,通常是基于一些专业软件平台进行的,用户在软件操作平台进行数据输入、脚本编写与执行、生成剖面图、符号化、图形调整与输出等操作来完成地质剖面的绘制,常见的软件包括AutoCAD、ArcGIS、QGIS等。通过这些工具和方法,提高了绘制地质剖面的工作效率,但传统方法生成地质剖面时仍存在人工干预较多且效率低[4-5],难以支撑模型建立和频繁更新,与地质信息化相悖,急需使用智能化地质剖面生成方法,来实现地质剖面的高效生成,进而提高油气资源勘探开发的效率。近年来深度生成模型在图像生成转换、医学影像处理、工业产品和各种三维建模的领域中都取得了显著成就。在地质勘探领域中,不同地理位置的地层数据存在较大的差异性,在生成地质模型的过程中更考验模型的收敛性和拟合性能,所以近年来在地质领域发展了许多基于生成对抗网络(generative adversarial networks,GAN)的改进算法[6-7],例如Song等[8-9]将地下暗河河道特征和砂岩泥岩等地质特征构建三维深度生成模型直接生成地下暗河溶洞的模型,取得良好的效果。李佳琪等[10]将生成对抗网络与注意力机制和MASK R-CNN(mask region-based convolutional neural network)相结合,提升了目标检测中的效率和准确率。Mao等[11]提出了一个基于条件GAN的地图生成模型,通过引入地图类别信息作为条件,实现了更具语义的地图生成。Li等[12]通过生成对抗网络生成额外的训练数据,提高了地球物理数据的学习性能。Mosser等[13]提出了一种使用生成对抗网络模拟地质过程的方法,模拟了地球内部温度、压力等参数的演化过程,为地质学的定量研究提供了新的视角。何鹏等[14]提出的故障在线诊断方法通过改进GAN增强训练极大提升了轴承故障诊断的实时准确率,并具有抗噪声干扰性强的特点。刘慧等[15]在超分辨率视觉任务中,以SRGAN(super-resolution generative adversarial network)为基础进行改进,改进后网络缓解了训练不稳定问题。林洋平等[16]提出了一种基于生成对抗网络(GAN)的视频隐写算法,有效解决视频隐写算法中最优修改概率矩阵生成困难的问题,提高信息传输的隐蔽性。
Pix2Pix作为一种生成对抗网络技术,在中国的应用取得了显著的进展。例如,何怡等[17]在模型Pix2Pix的基础上提出了一种改进的人脸图像修复模型,取得了较好的视觉效果;谢威夷等[18]基于Pix2Pix网络设计了一种的有效的遥感影像样本扩增方法;段凌凤等[19]提出了一种基于改进Pix2Pix-HD模型的多品种水稻生长可视化预测方法,利用数据驱动的方式,实现了对水稻抽穗期到灌浆期的高分辨率生长可视化预测。Pix2Pix方法在中国的多项应用中取得了显著效果,为图像修复、数据扩增、作物生长预测等领域提供了创新的解决方案。提出一种基于残差和多尺度判别器的Pix2Pix网络的地质剖面生成方法,能够直接利用地震数据作为条件,从而实现对地质剖面的直接生成,且生成的地质剖面图片在细节方面得到明显改善,在实际中达到油田任务的要求。
Pix2Pix方法由Isola等[20]于2017年提出,最初是为了应对图像翻译任务,如将黑白图像转换为彩色图像,或将草图转换为真实图像。该方法基于生成对抗网络(GANs),通过一个生成器和一个鉴别器的对抗过程,能够学习从源图像到目标图像的映射。生成器通过条件输入(源图像)生成目标图像,而鉴别器则判断生成的图像是否真实。通过对抗训练,生成器逐渐改进,使得生成的图像更加接近真实样本。
Pix2Pix网络结构包含一个生成器和一个鉴别器,其中生成器可以根据输入图像生成其在目标图像域的对应图像,而鉴别器则是尝试分辨输入图像的真实性, 它们通过对抗训练来学习生成真实样本的生成器和判别器的对抗过程。Pix2Pix的训练过程通过最小化生成器和判别器之间的对抗损失来学习生成更真实的图像。此外,还有一个L1损失,用于最小化生成图像与真实图像之间的像素级差异。受到输入图像的影响,使得生成器可以有针对性地生成与输入图像对应的输出图像,可以表示为
$ L_{\text {total }}(G, D)=L_{\mathrm{GAN}}(G, D)+\lambda L_{\mathrm{L} 1}(G)$
$ \begin{aligned}L_{\text {GAN }}(G, D)= & E_{x, y}[\lg D(x, y)]+ \\& E_{x, z}\{\lg [z)]\}\end{aligned}$
$ L_{\mathrm{L} 1}=E_{x, y, z}\left[\|y-G(x, z)\|_{1}\right]$
式中:Ltotal(G,D)为Pix2pix网络总损失;LGAN(G,D)为对抗损失;LL1为L1损失;G表示生成器;D表示判别器;x为样本,y为条件;z为噪声;λ为生成器的L1损失权重。
相较于传统的GAN的训练从随机噪声向量开始生成目标,Pix2Pix生成对抗网络最大的优势是通过引入条件变量来控制生成过程[17,21],使得生成器能够根据条件生成特定的输出。近年来中国学者针对不同的任务对Pix2Pix网络模型进行了改进,改进方法基本都在经典的Pix2Pix架构基础上,通过生成器架构的优化、注意力机制的引入、损失函数和训练策略的改进、判别器优化等手段提升网络对图像细节的捕捉能力和图像生成的质量,改进后的Pix2Pix网络模型在图像修复、预测、分割和转换等多个任务中提高了模型的稳定性、生成图像的质量与视觉效果,表现出更强的稳定性和处理复杂细节的能力。例如:黄聪等[22]在遥感图像语义分割任务中,引入空洞空间金字塔池化模块来提取不同尺度的图像上下文特征,并在跳跃连接阶段加入空间注意力机制,增强地物边缘的细节信息,显著提高了分割边界清晰度;吴雅琴等[23]针对口罩遮挡问题,使用改进后的Pix2Pix网络进行图像修复,使用联合PatchGAN判别器抑制噪声,并引入Smooth L1损失函数提高了模型的修复精度;叶明亮等[24]为了解决不同波段图像转换中的效率和质量问题,通过改进生成器,采用残差结构、可变形卷积和BAM(bottleneck attention module)注意力机制,显著提高了红外图像和可见光图像之间的转换效果。
最初的Pix2Pix网络生成器是通过多层的卷积网络结构对图片进行生成,经过几年时间的发展,现在普遍的Pix2Pix模型的生成器大多采用U-net结构[25-26]。U-net结构的设计有助于从输入到输出的端到端映射,使得生成器能够有效地学习并保留输入图像的细节信息。针对原始模型的生成结果无法在细节上反映地质特征的问题,本文中在Pix2Pix网络模型的基础上进行了针对性的改进,在生成器部分引入残差机制以提高网络对地质特征的学习能力,并为模型设定多尺度判别器代替原有的单一判别器,增强网络的判别性能,将地震反射数据进行预处理之后作为限制条件代入改进后的模型,模型会将生成的实际地质剖面图尽量的去拟合地震数据的特征,生成效果得到显著提升,并且生成结果中的地质特征与实际情况高度拟合。实验的具体结构思路如图1所示。
U-net在图像分割等领域已经证明其通用性。将其纳入生成器的设计中可以充分利用这种通用性,尤其是在需要还原输入图像结构和细节的任务时,将U-net作为生成对抗网络的生成器能够带来一些优势[27]。在将地震反射数据和三维地质数据切片之后,生成器部分可以理解为一个U-net图像识别网络,如图2所示。
U-net结构有助于在生成器中保留输入图像的细节信息。这对于本文中将地震数据翻译为地质图像的需求非常契合,跳跃连接使得网络能够更好地传递低级别的特征,使得网络在生成器部分能够保留一些地震数据中的地震波走势、地层差异等细节。
为使生成图像在细节方面体现地质特征,并进一步帮助网络提高生成性能,在网络的下采样路径中引进残差模块,下采样是为负责提取输入图像的特征表示,将其压缩成低分辨率的特征图,在此路径中引入残差模块,有助于在压缩分辨率的过程中保留重要的特征以更好地恢复细节,使得网络能够更有效地传递和利用信息。此外,将网络在原有的四层网络基础上增加一层,提高对图像中更小区域的细节特征的提取,从而提升生成图像的质量。残差模块的结构示意图如图3所示。
图3所示,x作为残差连接的初始输入进入下两个采样层,每个下采样过程中设置3×3的卷积层,将padding设置为1保持特征图的尺寸不变,输入通过卷积操作之后由ReLU函数进行激活并通过BN层(BatchNormalization),设置BN层有助于加速收敛并稳定训练过程,对经过第一轮下采样之后的结果进行一次重复操作,再通过一层池化层后将结果与初始输入x实现残差连接。残差模块的设计使得网络能够学习到输入和输出之间的残差信息,让生成器网络在编码的下采样阶段能够更好地保留上层的地质特征信息,残差链接还有助于减缓反向传播中的梯度消失问题,从而加快训练速度,提升网络的性能和稳定性。
在Pix2pix网络中,判别器主要通过两个方面来评估网络生成的结果的质量。首先,它对生成结果的整体性进行评估,通过对生成结果与真实图像的整体结构、目标分布等要素进行全局对比,以此判断它们之间的整体一致性。其次,判别器会对生成结果与目标图像之间的局部细节进行评估。在这一阶段,判别器会在局部区域提取图像的结构、颜色、纹理变化等细节信息,再次对生成结果进行判断。通过对整体性和局部细节两方面的评估[28],判别器能够有效地评估生成的图像是否与目标图像相似,并且能够符合输入中的条件限制。判别器的模型结构如图4所示。
判别器将接收到的生成结果与真实图片这两个输入被合并为一个张量,沿着通道维度进行拼接,形成一个包含生成结果和真实图像信息的输入张量,合并后的输入张量通过两个下采样层,每个下采样层包含一个卷积层和ReLU激活函数,经过两次下采样之后,进入一个卷积层进行特征加工,卷积之后由ReLU激活并被送入BN层进行归一化操作,然后对特征图进行池化操作以减少模型的过拟合,最后经过Sigmoid激活函数输出结果。
为了使判别器对生成结果和真实地质剖面的细节部分做出更好的对比和判断,使得网络提高判别器的性能,本文提出一种多尺度判别器结构。如图5所示。
在模型进行判别之前,设置这个判别器的所包含的尺度数量,多尺度判别器模型中设置为4尺度,每个尺度的判别器由一系列卷积层、池化层以及批归一化层组成,各个尺度的判别器之间参数独立,最后输出一个标量值,用于判断每个尺度内输入图像的真实性,每个尺度的判别结果会被记录到一个list中,每轮训练的最后对每个判别结果的损失进行加权综合得到最终的判别损失。为了实现多尺度的判别,每次在前向传播过程中,都会将输入图像和标注图像进行平均池化操作,以便在较高的尺度上进行判别。第一个尺度的判别器接收原始的实际地质剖面图和生成作为输入,第二个尺度的输入图像是在第一个尺度的基础上通过池化操作实现进行了下采样,然后进入新的判别器进行判别。随着尺度的增加,判别器的感受野逐渐增大,能够捕获到不同尺度的特征信息。低尺度的判别器更关注全局特征,而较高尺度的判别器更关注局部细节,从而提高了对生成图像的全面评估能力。
模型中损失函数使用均方误差损失函数。其定义为
$\operatorname{MSE}(G, R)=\frac{1}{N} \sum_{i=1}^{N}\left(G_{i}-R_{i}\right)^{2}$
式(4)中:G为生成的图像;R为真实图像;N为图像的总像素;GiRi分别为生成结果和真实图像中的第i个像素,最后生成器部分的损失函数可以表示为
$L_{\text {gen_L1 }}=\text { torch. mean }\left[\operatorname{torch.} \operatorname{abs}\left(G_{i}-R_{i}\right)\right]$
$L_{\text {gen }}=\operatorname{MSE}[d(G), \text { ones }]+\lambda L_{\text {gen_Ll }}$
式中: Lgen_L1为生成器中的L1损失;Lgen为生成器损失;d(G)为生成结果;λ为生成器的L1损失权重,L1损失计算的是预测值和实际值之间的绝对差异的平均值,最后生成器部分的损失函数由均方误差损失MSE和L1损失Lgen_L1两部分组成。
判别器部分的损失函数可以表示为
$L_{\mathrm{dis}}=\operatorname{MSE}[d(G), \text { zeros }]+\operatorname{MSE}[d(R), \text { ones }]$
式(7)中:Ldis为判别器损失;d(G)为生成结果;d(R)为真实结果。采用多尺度判别器模型的损失函数可以表示为
$L_{\text {gen }}=\sum_{i=1}^{N} W_{i} \operatorname{MSE}\left[d\left(G_{i}\right), \text { ones }\right]+\lambda L_{\text {gen_ll }}$
$\begin{aligned}L_{\mathrm{dis}}= & \sum_{i=1}^{N} W_{i}\left\{\operatorname{MSE}\left[d\left(G_{i}\right), \text { zeros }\right]+\right. \\& \left.\operatorname{MSE}\left[d\left(R_{i}\right), \text { ones }\right]\right\}\end{aligned}$
式中:N为判别器的尺度数量;Wi为每个尺度的权重;GiRi分别为每个尺度下的生成结果和真实结果。
判别器会对每个尺度下的真实图片和生成结果进行评估,生成相应的损失值[29],随后这些损失值按照权重进行综合加权,形成最终的判别器损失。
实验内容所用的数据集为两组油田工区的真实地震反射数据和地质信息数据,初始数据均为三维ASCLL格式,三维地质数据能够与地震反射数据相对应,维度大小为706×161×400,如图6所示。
在本文的实际问题中利用地震反射数据作为Pix2Pix网络中的条件限制,使所生成的地质剖面结果尽可能地吻合地震反射数据的特征,因此需要成对组合的地质数据构建训练集和测试集。首先对初始数据在同一维度上进行了切片处理,利用pandas、numpy等工具对三维数据进行切片操作,为了方便模型训练,切片之后将代表岩层基质的背景色设置为易于识别的蓝色色调,最后得到706组成对数据集。在这706对数据中随意选择一组数据展示如图7所示。
在这个数据集中,每组数据所包含的地质特征种类、各种特征的所占比例以及特征位置分布都各有不同。
本次试验使用配置如下:操作系统为Windows11,处理器型号:i5-12500H 3.10 GHz,内存16 GB,GPU型号NVIDIA 3050Ti,编程语言python3.7,Cuda版本为11.1。同时安装深度学习框Pytorch1.11.0等第三方库。
模型训练采用能够实现学习率自动调整的Adam优化器,训练集的batch_size设置为32,学习率为0.000 1。
在油田探索生成地质剖面的任务中,使用U-net网络作为生成对抗网络的生成器,引入残差机制进一步帮助网络提高生成性能,引入多尺度判别器使网络在不同尺度上对生成的图片进行判别,可以有效地捕获图像的不同尺度的特征,提高判别器对图像的感知能力。为避免在某一张图片上出现偶然性结果的影响,确保实验结果的可靠性,在数据集中随机选择多组图片对其生成结果进行综合分析。所有模型均在相同的数据条件和设备条件下进行了训练,训练结束之后的模型生成结果如图8所示。
分析图8中的这组地质剖面图的生成结果,从左到右的生成结果对应的网络模型依次是原始Pix2Pix网络、加入残差机制的Pix2Pix网络、设置多尺度判别器的Pix2Pix网络以及基于残差的多尺度判别器Pix2Pix网络。从图8中可以看出,生成结果越往右,图片在生成的细节方面表现得越好。
SSIM(structural similarity)指标是一种用于衡量两幅图像之间相似性的指标,常用于图像处理领域。SSIM的计算基于3个方面:亮度相似性、对比度相似性和结构相似性。
SSIM的表达式为
$\operatorname{SSIM}(x, y)=\frac{\left(2 \mu_{x} \mu_{y}+c_{1}\right)\left(2 \sigma_{x y}+c_{2}\right)}{\left(\mu_{x}^{2}+\mu_{y}^{2}+c_{1}\right)\left(\sigma_{x}^{2}+\sigma_{y}^{2}+c_{2}\right)}$
式(10)中:xy为待比较的两幅图像;μxμy为两幅图的均值; σ x 2 σ y 2为图像的方差;σxy为两幅图的协方差;c1c2为用于稳定计算的常数。均值、方差和协方差均通过对图像像素值的统计计算得到,最后得到的SSIM分数是一个介于-1~1的数值, SSIM越接近1,表示图像之间的相似性越高。SSIM发展至今已被广泛应用于图像质量评价、图像压缩、画面增强等图像处理领域。
从实际任务出发可知,该油田工区探索生成地质剖面的需求本质上是彩色目标的图像生成任务,结果如图8所示。评判生成结果是否与真实的地质剖面图接近,主要取决于不同颜色特征的分布和结构是否符合真实地质剖面,因此使用SSIM分数作为评判指标与本文的研究内容和实验背景十分契合。
在模型训练的过程中对每个模型的每轮生成结果进行记录,图8中的所展示图片生成结果的对应SSIM分数如表1所示。
基于残差的多尺度判别器Pix2Pix网络模型相较于原始Pix2Pix网络模型在SSIM分数上提高了约6.9%。通过消融实验发现,残差机制和多尺度判别器对模型性能均有正向影响,引入残差机制平均带来了约5.8%的SSIM分数提升,而多尺度判别器则平均提升了约3.7%左右。值得注意的是,将残差机制和多尺度判别器同时引入模型后,所有图片的生成结果在SSIM分数上均有所提升,这表明这两个模型机制能够相互兼容,并且有效地发挥各自的优势,从而提升整个Pix2Pix网络的性能水平。
综合生成图像效果和客观量化结果可以得出结论,相较于原始的Pix2Pix网络,基于残差和多尺度判别器的Pix2Pix网络在生成地质剖面的任务中有明显的性能优势,模型在改进之后提高了生成器的学习能力和判别器的感知能力,基于残差和多尺度判别器的Pix2Pix网络的生成结果在特征细节上的表现更好,结果更加符合真实的地质特征。
基于残差和多尺度判别器的Pix2Pix模型在地质勘探领域的创新性应用,突破了传统地震数据解释方法的局限性。与传统方法需要手工调整和复杂处理步骤不同,该模型能够直接利用原始地震数据作为条件,通过端到端的深度学习框架自动生成高质量的地质剖面图像。具体而言该模型的创新点体现在以下几个方面。
(1)传统地质方法依赖于地质专家的经验和大量的前期处理工作,而基于改进Pix2Pix模型的自动化生成方式,能够通过学习大量的地震数据和已知地质剖面之间的映射关系,实现地质剖面智能化生成。这种方式提高了自动化程度,能更好地应对复杂的地震数据和潜在的地质变化,减少了人工干预的需求。
(2)通过引入残差模块,基于改进Pix2Pix模型在训练过程中有效避免了梯度消失问题,并增强了对复杂数据特征的捕捉能力,在高噪声、低信噪比的地震数据中能够更加稳定地输出清晰的地质图像。
(3)采用多尺度判别器,使模型能够从不同的尺度上对生成图像进行判断,从而进一步提高了图像的细节表现和全局一致性,保证了生成的地质剖面图在不同分辨率下的质量。
基于改进Pix2Pix模型具有广泛的应用前景,可以推广到矿产资源勘探、地下水资源评估等领域,为勘探企业提供自动化、高效、低成本的解决方案,降低误差,提高地质勘探的智能化水平。
  • 中石油重大科技项目(ZD2019-183-006)
参考文献 引证文献
排序方式:
[1]
赵兵, 罗攀登, 张妹珠, 等. 基于“地质-工程”耦合平台的顺北断溶体储层地应力分布规律分析[J]. 科学技术与工程, 2024, 24(8): 3107-3114.
Zhao Bing, Luo Pandeng, Zhang Meizhu, et al. In-situ stress distribution analysis of shunbei fault-karst reservoir based on “ geology-engineering” coupling platform[J]. Science Technology and Engineering, 2024, 24(8): 3107-3114.
[2]
朱莹. 地质剖面自动绘制系统研究[D]. 南京: 南京师范大学, 2006.
Zhu Ying. Research on automatic drawing system of geological section[D]. Nanjing: Nanjing Normal University, 2006.
[3]
宋仁波. 基于ArcGIS和Google SketchUp的三维地质剖面绘制方法[J]. 测绘地理信息, 2013, 38(2): 49-50, 53.
Song Renbo. 3D geological section drawing method based on ArcGIS and Google SketchUp[J]. Mapping Geographic Information, 2013, 38(2): 49-50, 53.
[4]
段太忠, 张文彪, 何治亮, 等. 塔里木盆地顺北油田超深断溶体深度学习地质建模方法[J]. 石油与天然气地质, 2023, 44(1): 203-212.
Duan Taizhong, Zhang Wenbiao, He Zhiliang, et al. Deep learning geological modeling method for ultra-deep fault-karst in Shunbei Oilfield, Tarim Basin [J]. Oil and Natural Gas Geology, 2023, 44(1): 203-212.
[5]
刘彦锋, 张文彪, 段太忠, 等. 深度学习油气藏地质建模研究进展[J]. 地质科技通报, 2021, 40(4): 235-241.
Liu Yanfeng, Zhang Wenbiao, Duan Taizhong, et al. Research progress of deep learning reservoir geological modeling[J]. Geological Science and Technology Bulletin, 2021, 40(4): 235-241.
[6]
Chavdarova T, Fleuret F. SGAN: an alternative training of generative adversarial networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 9407-9415.
[7]
Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks[J]. International Conference on Machine Learning, 2017, 70: 214-223.
[8]
Song S H, Mukerji T, Hou J G. Geological facies modeling based on progressive growing of generative adversarial networks (GANs)[J]. Computational Geosciences, 2021, 25(3): 1251-1273.
[9]
Song S H, Mukerji T, Hou J G. GANSim: conditional facies simulation using an improved progressive growing of generative adversarial networks (GANs)[J]. Mathematical Geosciences, 2021, 53(7): 1413-1444.
[10]
李佳琪, 邓玉娇, 吴湘宁, 等. 基于注意力及生成对抗网络的遥感影像目标检测[J]. 计算机系统应用, 2022, 31(6): 182-191.
Li Jiaqi, Deng Yujiao, Wu Xiangning, et al. Remote sensing image target detection based on attention and generative adversarial networks [J]. Computer System Application, 2022, 31( 6 ) : 182-191.
[11]
Mao X, Li Q, Xie H, et al. Least squares generative adversarial networks[C]// Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE, 2017: 2794-2802.
[12]
Li T, Zuo R, Zhao X, et al. Mapping prospectivity for regolith-hosted REE deposits via convolutional neural network with generative adversarial network augmented data[J]. Ore Geology Reviews, 2022, 142: 104693.
[13]
Mosser L, Dubrule O, Blunt M J. Stochastic seismic waveform inversion using generative adversarial networks as a geological prior[J]. Mathematical Geosciences, 2020, 52(1): 53-79.
[14]
何鹏, 罗智浩, 胡蓉, 等. 基于改进GAN的水力测功器轴承故障在线诊断方法[J]. 科学技术与工程, 2024, 24(14): 5804-5811.
He Peng, Luo Zhihao, Hu Rong, et al. Online fault diagnosis method of hydraulic dynamometer bearing based on improved GAN[J]. Science Technology and Engineering, 2024, 24(14): 5804-5811.
[15]
刘慧, 卢云志, 张雷. 基于Dropout改进的SRGAN网络DrSRGAN[J]. 科学技术与工程, 2023, 23(23): 10015-10022.
Liu Hui, Lu Yunzhi, Zhang Lei. An improved SRGAN network based on Dropout called DrSRGAN[J]. Science Technology and Engineering, 2023, 23(23): 10015-10022.
[16]
林洋平, 张明书, 陈培, 等. 基于GAN的视频隐写算法[J]. 科学技术与工程, 2022, 22(23): 10155-10161.
Lin Yangping, Zhang Mingshu, Chen Pei, et al. Video steganography algorithm based on generative adversarial network[J]. Science Technology and Engineering, 2022, 22(23): 10155-10161.
[17]
何怡, 赵德, 任泽民, 等. 基于改进pix2pix框架的人脸图像修复模型[J]. 激光杂志, 2024, 45(10): 94100.
He Yi, Zhao De, Ren Zemin, et al. Face image inpainting model based on improved pix2pix framework [J]. Laser Magazine, 2024, 45(10): 94100.
[18]
谢威夷, 徐锡杰, 芮小平, 等. 基于Pix2Pix网络的遥感影像样本扩增方法[J]. 遥感技术与应用, 2024, 39(5): 1151-1158.
Xie Weiyi, Xu Xijie, Rui Xiaoping, et al. Remote sensing image sample amplification method based on Pix2Pix network[J]. Remote Sensing Technology and Application, 2024, 39(5): 1151-1158.
[19]
段凌凤, 王新轶, 王治昊, 等. 基于改进Pix2Pix-HD网络的多品种水稻生长可视化预测方法[J]. 作物学报, 2024, 50(12): 3083-3095.
Duan Lingfeng, Wang Xinyi, Wang Zhihao, et al. Visual prediction method of multi-variety rice growth based on improved Pix2Pix-HD network [J]. Journal of Crops, 2024, 50(12): 3083-3095.
[20]
Isola P, Zhu J Y, Zhou T H, et al. Image-to-image translation with conditional adversarial networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 1125-1134.
[21]
Qu Y, Chen Y, Huang J, et al. Enhanced pix2pix dehazing network[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 8160-8168.
[22]
黄聪, 周坤, 安学刚. 基于改进pix2pix的遥感图像语义分割[J]. 兰州交通大学学报, 2023, 42(5): 57-65.
Huang Cong, Zhou Kun, An Xuegang. Semantic segmentation of remote sensing images based on improved pix2pix[J]. Journal of Lanzhou Jiaotong University, 2023, 42(5): 57-65.
[23]
吴雅琴, 侯云峰, 陈林. 基于改进Pix2Pix网络的去口罩遮挡修复研究[J]. 计算机仿真, 2023, 40(10): 242-248.
Wu Yaqin, Hou Yunfeng, Chen Lin. Research on mask removal and occlusion repair based on improved Pix2Pix network[J]. Computer Simulation, 2023, 40(10): 242-248.
[24]
叶明亮, 史春景, 郝永平, 等. 基于改进pix2pix的红外图像转换技术[J]. 激光与红外, 2024, 54(7): 1157-1163.
Ye Mingliang, Shi Chunjing, Hao Yongping, et al. Infrared image conversion technology based on improved pix2pix [J]. Laser and Infrared, 2024, 54(7): 1157-1163.
[25]
Huang X, Liu M Y, Belongie S, et al. Multimodal unsupervised image-to-image translation[C]// Proceedings of the European Conference on Computer Vision, New York: IEEE, 2018: 172-189.
[26]
李鸿翔, 王晓丽, 阳春华, 等. 基于GAN-UNet的矿石图像分割方法[J]. 控制理论与应用, 2021, 38(9): 1393-1398.
Li Hongxiang, Wang Xiaoli, Yang Chunhua, et al. Ore image segmentation method based on GAN-UNet [J]. Control Theory and Application, 2021, 38(9): 1393-1398.
[27]
Dong H, Neekhara P, Wu C, et al. Unsupervised image-to-image translation with generative adversarial networks[J]. arXiv, 2017, https://arxiv.org/abs/1701.02676. https://arxiv.org/abs/1701.02676
[28]
宋随宏, 史燕青, 侯加根. 基于生成对抗网络的储层地质建模方法研究进展[J]. 石油科学通报, 2022, 7(1): 34-49.
Song Suihong, Shi Yanqing, Hou Jiagen. Research progress of reservoir geological modeling methods based on generative adversarial networks [J]. Petroleum Science Bulletin, 2022, 7(1): 34-49.
[29]
Wang T C, Liu M Y, Zhu J Y. High-resolution image synthesis and semantic manipulation with conditional GANs[J]. arXiv, 2018, https://arxiv.org/abs/1711.11585. https://arxiv.org/abs/1711.11585
2025年第25卷第19期
PDF下载
249
117
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405361
  • 接收时间:2024-07-16
  • 首发时间:2025-12-22
  • 出版时间:2025-07-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-16
  • 修回日期:2024-12-23
基金
中石油重大科技项目(ZD2019-183-006)
作者信息
    中国石油大学(华东)理学院, 青岛 266580

通讯作者:

*陈华(1972—),男,汉族,山东聊城人,博士,副教授,硕士研究生导师。研究方向:地球物理数据处理与分析,并行计算和智能算法。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405361
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