Article(id=1228279665186505373, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2407182, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1727193600000, receivedDateStr=2024-09-25, revisedDate=1747065600000, revisedDateStr=2025-05-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1770774292512, onlineDateStr=2026-02-11, pubDate=1754582400000, pubDateStr=2025-08-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770774292512, onlineIssueDateStr=2026-02-11, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770774292512, creator=13701087609, updateTime=1770774292512, updator=13701087609, issue=Issue{id=1228279664221815452, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='22', pageStart='9211', pageEnd='9648', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1770774292283, creator=13701087609, updateTime=1770777611996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228293588207992892, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228293588207992893, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=9398, endPage=9407, ext={EN=ArticleExt(id=1228279666591597239, articleId=1228279665186505373, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Imbalanced Lithology Identification Based on ECA-MSCB ResNet, columnId=1228279666528682676, journalTitle=Science Technology and Engineering, columnName=Papers·Electronic and Communicational Technology, runingTitle=null, highlight=null, articleAbstract=

In order to improve the prediction accuracy of lithology affected by imbalanced geological data, an ECA-MSCB ResNet model was proposed. The model integrates ECA (efficient channel attention) and MSCB (multi-scale convolutional block) into the traditional ResNet architecture to achieve efficient extraction and representation of lithological data features. For the issue of imbalanced lithology categories, prior probability-balanced logit bias was introduced during model training, and the focal loss function was modified to enhance the recognition of minority lithology classes. Experimental results show that the model based on ECA-MSCB ResNet performs well on the imbalanced geological lithology dataset, achieving an average prediction accuracy improvement of approximately 7.45% compared to the original ResNet model and 27.33% compared to the random forest method. Notably, the recognition of minority lithology classes improves by an average of 17.9%. Furthermore, the model demonstrates strong lithology classification ability on public datasets, achieving an F1-score of 75.77%. In addition, the recognition accuracy of the proposed model outperformed both traditional and mainstream methods. The ECA-MSCB ResNet method holds significant application value in the field of imbalanced geological lithology recognition.

, correspAuthors=Bo LI, 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=Mou PEI, Bo LI, Yong HU), CN=ArticleExt(id=1228279670559408922, articleId=1228279665186505373, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=电子技术、通信技术基于ECA-MSCB ResNet的不均衡岩性识别, columnId=1228279666679677625, journalTitle=科学技术与工程, columnName=论文·电子技术、通信技术, runingTitle=null, highlight=null, articleAbstract=

为了改善由于地质数据类别不均衡导致的岩性预测精度不高的问题,提出了一种ECA-MSCB ResNet模型,集成高效通道注意力机制(efficient channel attention,ECA)和多尺度卷积块(multi-scale convolutional block,MSCB)于传统的ResNet架构中,实现了对岩性数据特征的高效提取和表征。针对岩性类别不均衡的问题,在模型训练过程中引入先验概率平衡logit偏差,改进焦点损失函数,以提升对少数类岩性的识别能力。实验结果表明,基于ECA-MSCB ResNet的模型在地质岩性不均衡数据集上表现良好,与原ResNet模型相比,平均预测准确率提升约7.45%,与随机森林相比提升27.33%,特别是在少数类岩性的识别上取得了显著进步,平均提高约17.9%。同时,本文模型在公开数据集上表现良好,F1-score达到75.77%。此外,本文模型识别准确率高于目前主流方法,在地质不均衡岩性识别领域具有良好的应用价值。

, correspAuthors=李波, authorNote=null, correspAuthorsNote=
* 李波(1975—),男,汉族,湖北宜都人,博士,教授。研究方向:机器学习及模式识别。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=JH6ZK4N48xTUR3p0eP/S/Q==, magXml=efOD7fpCX15cdo2cY+Ckqw==, pdfUrl=null, pdf=HqkheWHg/OGl3h0HnXjzLQ==, pdfFileSize=14841988, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=IB+sej6aJK7PamstT56Y+g==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ON9G6tz4AXMIFreWg/Kfcg==, mapNumber=null, authorCompany=null, fund=null, authors=

裴谋(1999—),女,土家族,湖北宜昌人,硕士研究生。研究方向:机器学习及数值分析。E-mail:

, authorsList=裴谋, 李波, 胡勇)}, authors=[Author(id=1228369772178505810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2022120377@mail.scuec.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228369772321112154, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369772178505810, language=EN, stringName=Mou PEI, firstName=Mou, middleName=null, lastName=PEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369772467912806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369772178505810, language=CN, stringName=裴谋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中南民族大学计算机学院, 武汉 430074, bio={"content":"

裴谋(1999—),女,土家族,湖北宜昌人,硕士研究生。研究方向:机器学习及数值分析。E-mail:

"}, bioImg=null, bioContent=

裴谋(1999—),女,土家族,湖北宜昌人,硕士研究生。研究方向:机器学习及数值分析。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369771813601336, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, xref=1, ext=[AuthorCompanyExt(id=1228369771817795641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China), AuthorCompanyExt(id=1228369771830378554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中南民族大学计算机学院, 武汉 430074)])]), Author(id=1228369773906559094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=libo@mail.scuec.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1228369774003028094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369773906559094, language=EN, stringName=Bo LI, firstName=Bo, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369774112080007, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369773906559094, language=CN, stringName=李波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 中南民族大学计算机学院, 武汉 430074, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369771813601336, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, xref=1, ext=[AuthorCompanyExt(id=1228369771817795641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China), AuthorCompanyExt(id=1228369771830378554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中南民族大学计算机学院, 武汉 430074)])]), Author(id=1228369774229520527, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, 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=1228369774367932571, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369774229520527, language=EN, stringName=Yong HU, firstName=Yong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Resources and Environment, Yangtze University, Wuhan 430100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369774460207269, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, authorId=1228369774229520527, language=CN, stringName=胡勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 长江大学资源与环境学院, 武汉 430100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369771910070339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, xref=2, ext=[AuthorCompanyExt(id=1228369772019122247, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771910070339, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Resources and Environment, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1228369772031705162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771910070339, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长江大学资源与环境学院, 武汉 430100)])])], keywords=[Keyword(id=1228369774669922483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, orderNo=1, keyword=lithology identification), Keyword(id=1228369774749614265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, orderNo=2, keyword=logging data), Keyword(id=1228369774829306046, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, orderNo=3, keyword=imbalanced data), Keyword(id=1228369774900609221, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, orderNo=4, keyword=ECA-MSCB ResNet), Keyword(id=1228369775013855438, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, orderNo=1, keyword=岩性预测), Keyword(id=1228369775139684565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, orderNo=2, keyword=测井数据), Keyword(id=1228369775257125089, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, orderNo=3, keyword=不均衡数据), Keyword(id=1228369775366176999, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, orderNo=4, keyword=ECA-MSCB ResNet)], refs=[Reference(id=1228369780218986940, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=508, pageEnd=522, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=李宁, 徐彬森, 武宏亮, journalName=石油学报, refType=null, unstructuredReference=李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4): 508-522., articleTitle=人工智能在测井地层评价中的应用现状及前景, refAbstract=null), Reference(id=1228369780349010367, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=508, pageEnd=522, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Li Ning, Xu Binsen, Wu Hongliang, journalName=Acta Petrolei Sinica, refType=null, unstructuredReference=Li Ning, Xu Binsen, Wu Hongliang, et al. Application status and prospects of artificial intelligence in well logging formation evaluation[J]. Acta Petrolei Sinica, 2021, 42(4): 508-522., articleTitle=Application status and prospects of artificial intelligence in well logging formation evaluation, refAbstract=null), Reference(id=1228369780432896452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=48, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=匡立春, 刘合, 任义丽, journalName=石油勘探与开发, refType=null, unstructuredReference=匡立春, 刘合, 任义丽, 等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发, 2021, 48(1): 1-11., articleTitle=人工智能在石油勘探开发领域的应用现状与发展趋势, refAbstract=null), Reference(id=1228369780529365447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=48, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Kuang Lichun, Liu He, Ren Yili, journalName=Petroleum Exploration and Development, refType=null, unstructuredReference=Kuang Lichun, Liu He, Ren Yili, et al. Application and developement trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development, 2021, 48(1): 1-11., articleTitle=Application and developement trend of artificial intelligence in petroleum exploration and development, refAbstract=null), Reference(id=1228369780671971790, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=220, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Ren Q, Zhang H, Zhang D, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Ren Q, Zhang H, Zhang D, et al. Lithology identification using principal component analysis and particle swarm optimization fuzzy decision tree[J]. Journal of Petroleum Science and Engineering, 2023, 220.DOI: 10.1016/j.petrol.2022.111233., articleTitle=Lithology identification using principal component analysis and particle swarm optimization fuzzy decision tree, refAbstract=null), Reference(id=1228369780793606611, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=205, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Feng R, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Feng R. Uncertainty analysis in well log classification by Bayesian long short-term memory networks[J]. Journal of Petroleum Science and Engineering, 2021, 205.DOI: 10.1016/j.petrol.2021.108816., articleTitle=Uncertainty analysis in well log classification by Bayesian long short-term memory networks, refAbstract=null), Reference(id=1228369780927824346, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=8, pageStart=8073, pageEnd=8087, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Chang J, Kang Y, Zheng W X, journalName=IEEE Transactions on Cybernetics, refType=null, unstructuredReference=Chang J, Kang Y, Zheng W X, et al. Active domain adaptation with application to intelligent logging lithology identification[J]. IEEE Transactions on Cybernetics, 2022, 52(8): 8073-8087., articleTitle=Active domain adaptation with application to intelligent logging lithology identification, refAbstract=null), Reference(id=1228369781020099037, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=null, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Liu N, Huang T, Gao J, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Liu N, Huang T, Gao J, et al. Quantum-enhanced deep learning-based lithology interpretation from well logs[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-13., articleTitle=Quantum-enhanced deep learning-based lithology interpretation from well logs, refAbstract=null), Reference(id=1228369781145928164, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2019, volume=182, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Ren X, Hou J, Song S, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Ren X, Hou J, Song S, et al. Lithology identification using well logs: a method by integrating artificial neural networks and sedimentary patterns[J]. Journal of Petroleum Science and Engineering, 2019, 182.DOI: 10.1016/j.petrol.2019.106336., articleTitle=Lithology identification using well logs: a method by integrating artificial neural networks and sedimentary patterns, refAbstract=null), Reference(id=1228369781263368684, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=null, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Zhang H, He Z, Li X, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Zhang H, He Z, Li X, et al. Study on the intelligent identification method of formation lithology by element and gamma spectrum[J]. Neural Computing and Applications, 2022, 34: 1-9., articleTitle=Study on the intelligent identification method of formation lithology by element and gamma spectrum, refAbstract=null), Reference(id=1228369781364031984, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=86, issue=5, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Jiang C, Zhang D, Chen S, journalName=Geophysics, refType=null, unstructuredReference=Jiang C, Zhang D, Chen S. Lithology identification from well-log curves via neural networks with additional geologic constraint[J]. Geophysics, 2021, 86(5): IM85-IM100., articleTitle=Lithology identification from well-log curves via neural networks with additional geologic constraint, refAbstract=null), Reference(id=1228369782773318136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=null, pageStart=1, pageEnd=19, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Duan Y, Li J, Li B, journalName=Carbonates and Evaporites, refType=null, unstructuredReference=Duan Y, Li J, Li B, et al. Lithology identification and reservoir characteristics of the mixed siliciclastic-carbonate rocks of the lower third member of the Shahejie formation in the south of the Laizhouwan Sag, Bohai Bay Basin, China[J]. Carbonates and Evaporites, 2020, 35: 1-19., articleTitle=Lithology identification and reservoir characteristics of the mixed siliciclastic-carbonate rocks of the lower third member of the Shahejie formation in the south of the Laizhouwan Sag, Bohai Bay Basin, China, refAbstract=null), Reference(id=1228369782873981437, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2019, volume=173, issue=null, pageStart=197, pageEnd=208, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Lai J, Pang X, Chen G, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Lai J, Pang X, Chen G, et al. Prediction of reservoir quality in carbonates via porosity spectrum from image logs[J]. Journal of Petroleum Science and Engineering, 2019, 173: 197-208., articleTitle=Prediction of reservoir quality in carbonates via porosity spectrum from image logs, refAbstract=null), Reference(id=1228369782966256130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=85, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=Kolbjørnsen O, Buland A, Hauge R, journalName=Geophysics, refType=null, unstructuredReference=Kolbjørnsen O, Buland A, Hauge R, et al. Bayesian seismic inversion for stratigraphic horizon, lithology, and fluid prediction[J]. Geophysics, 2020, 85: R207-R221., articleTitle=Bayesian seismic inversion for stratigraphic horizon, lithology, and fluid prediction, refAbstract=null), Reference(id=1228369783071113734, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2019, volume=175, issue=null, pageStart=342, pageEnd=355, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=Liu S, Zhang Z, Zhao P, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Liu S, Zhang Z, Zhao P. Machine learning methods for lithology classification based on well log data: a comparative study[J]. Journal of Petroleum Science and Engineering, 2019, 175: 342-355., articleTitle=Machine learning methods for lithology classification based on well log data: a comparative study, refAbstract=null), Reference(id=1228369783154999820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=144, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=Ao Y, Zhang B, Wang T, journalName=Computers & Geosciences, refType=null, unstructuredReference=Ao Y, Zhang B, Wang T, et al. Probabilistic logging lithology characterization with random forest probability estimation[J]. Computers & Geosciences, 2020, 144.DOI: 10.1016/j.cageo.2020.104556., articleTitle=Probabilistic logging lithology characterization with random forest probability estimation, refAbstract=null), Reference(id=1228369783264051730, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=9, pageStart=3696, pageEnd=3704, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=黄安, 蔡文渊, 魏新路, journalName=科学技术与工程, refType=null, unstructuredReference=黄安, 蔡文渊, 魏新路, 等. 基于改进随机森林的火山岩测井岩性识别[J]. 科学技术与工程, 2023, 23(9): 3696-3704., articleTitle=基于改进随机森林的火山岩测井岩性识别, refAbstract=null), Reference(id=1228369783352132116, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=9, pageStart=3696, pageEnd=3704, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=Huang An, Cai Wenyuan, Wei Xinlu, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Huang An, Cai Wenyuan, Wei Xinlu, et al. Lithology identification of volcanic logging based on improved random forest[J]. Science Technology and Engineering, 2023, 23(9): 3696-3704., articleTitle=Lithology identification of volcanic logging based on improved random forest, refAbstract=null), Reference(id=1228369783461184023, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=18, issue=1, pageStart=13, pageEnd=17, url=null, language=null, rfNumber=[16], rfOrder=18, authorNames=Zhang J, Li J, Chen X, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Zhang J, Li J, Chen X, et al. Seismic lithology/fluid prediction via a hybrid ISD-CNN[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 18(1): 13-17., articleTitle=Seismic lithology/fluid prediction via a hybrid ISD-CNN, refAbstract=null), Reference(id=1228369783553458714, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2019, volume=179, issue=null, pageStart=966, pageEnd=978, url=null, language=null, rfNumber=[17], rfOrder=19, authorNames=Gu Y Bao, Song X, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Gu Y Bao, Song X, et al. Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization[J]. Journal of Petroleum Science and Engineering, 2019, 179: 966-978., articleTitle=Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization, refAbstract=null), Reference(id=1228369783662510625, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2019, volume=174, issue=null, pageStart=216, pageEnd=228, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=Imamverdiyev Y, Sukhostat L, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Imamverdiyev Y, Sukhostat L. Lithological facies classification using deep convolutional neural network[J]. Journal of Petroleum Science and Engineering, 2019, 174: 216-228., articleTitle=Lithological facies classification using deep convolutional neural network, refAbstract=null), Reference(id=1228369783771562531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=208, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=Ao Y, Lu W, Hou Q, journalName=Journal of Petroleum Science and Engineering, refType=null, unstructuredReference=Ao Y, Lu W, Hou Q, et al. Sequence-to-sequence borehole formation property prediction via multi-task deep networks with sparse core calibration[J]. Journal of Petroleum Science and Engineering, 2022, 208.DOI: 10.1016/j.petrol.2021.109637., articleTitle=Sequence-to-sequence borehole formation property prediction via multi-task deep networks with sparse core calibration, refAbstract=null), Reference(id=1228369783863837221, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=null, volume=58, issue=8, pageStart=5932, pageEnd=5943, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=Chen Y, Zhang D, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Chen Y, Zhang D. Physics-constrained deep learning of geomechanical logs[J]. IEEE Transactions on Geoscience and Remote Sensing, Aug. 2020, 58(8): 5932-5943., articleTitle=Physics-constrained deep learning of geomechanical logs, refAbstract=null), Reference(id=1228369783960306220, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=7, pageStart=2759, pageEnd=2767, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=王胜, 张拯, 谌强, journalName=科学技术与工程, refType=null, unstructuredReference=王胜, 张拯, 谌强, 等. 基于振动与声音信号深度学习的岩性识别方法[J]. 科学技术与工程, 2023, 23(7): 2759-2767., articleTitle=基于振动与声音信号深度学习的岩性识别方法, refAbstract=null), Reference(id=1228369784065163824, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=7, pageStart=2759, pageEnd=2767, url=null, language=null, rfNumber=[21], rfOrder=24, authorNames=Wang Sheng, Zhang Zheng, Chen Qiang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Sheng, Zhang Zheng, Chen Qiang, et al. Lithology identification method based on deep learning of vibration and sound signals[J]. Science Technology and Engineering, 2023, 23(7): 2759-2767., articleTitle=Lithology identification method based on deep learning of vibration and sound signals, refAbstract=null), Reference(id=1228369784178410036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2024, volume=22, issue=3, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[22], rfOrder=25, authorNames=Zhao F, Zhou Z, Zhai H, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Zhao F, Zhou Z, Zhai H, et al. ResGAT: a residual graph attention network for lithology identification[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 22(3): 1-5., articleTitle=ResGAT: a residual graph attention network for lithology identification, refAbstract=null), Reference(id=1228369784253907513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=3, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[23], rfOrder=26, authorNames=Sun Y, Pang S, Zhang Y, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference=Sun Y, Pang S, Zhang Y. Application of adaboost-transformer algorithm for lithology identification based on well logging data[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21(3): 1-5., articleTitle=Application of adaboost-transformer algorithm for lithology identification based on well logging data, refAbstract=null), Reference(id=1228369784354570816, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=null, volume=103, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=27, authorNames=Gu J, Lu S, journalName=Computers & Security, refType=null, unstructuredReference=Gu J, Lu S. An effective intrusion detection approach using SVM with naïve Bayes feature embedding[J]. Computers & Security, Mar. 2021, 103.DOI: 10.1016/j.cose.2020.102158., articleTitle=An effective intrusion detection approach using SVM with naïve Bayes feature embedding, refAbstract=null), Reference(id=1228369784472011333, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=4, pageStart=2464, pageEnd=2478, url=null, language=null, rfNumber=[25], rfOrder=28, authorNames=Yang K, Yu Z, Chen C P, journalName=Man, and Cybernetics: Systems, refType=null, unstructuredReference=Yang K, Yu Z, Chen C P, et al. Progressive hybrid classifier ensemble for imbalanced data[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(4): 2464-2478., articleTitle=Progressive hybrid classifier ensemble for imbalanced data, refAbstract=null), Reference(id=1228369784551703115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=251, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=29, authorNames=Jin J, Qin Z, Yu D, journalName=Knowledge-Based Systems, refType=null, unstructuredReference=Jin J, Qin Z, Yu D, et al. Regularized discriminative broad learning system for image classification[J]. Knowledge-Based Systems, 2022, 251.DOI: 10.1016/j.knosys.2022.109306., articleTitle=Regularized discriminative broad learning system for image classification, refAbstract=null), Reference(id=1228369784639783503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=241, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=30, authorNames=Mayabadi S, Saadatfar H, journalName=Knowledge-Based Systems, refType=null, unstructuredReference=Mayabadi S, Saadatfar H. Two density-based sampling approaches for imbalanced and overlap data[J]. Knowledge-Based Systems, 2022, 241.DOI: 10.1016/j.knosys.2022.108217., articleTitle=Two density-based sampling approaches for imbalanced and overlap data, refAbstract=null), Reference(id=1228369784727863894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=56, issue=2, pageStart=845, pageEnd=863, url=null, language=null, rfNumber=[28], rfOrder=31, authorNames=Lin C, Tsai C F, Lin W C, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=Lin C, Tsai C F, Lin W C. Towards hybrid over-and under-sampling combination methods for class imbalanced datasets: an experimental study[J]. Artificial Intelligence Review, 2023, 56(2): 845-863., articleTitle=Towards hybrid over-and under-sampling combination methods for class imbalanced datasets: an experimental study, refAbstract=null), Reference(id=1228369784811749977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=15793, pageEnd=15803, url=null, language=null, rfNumber=[29], rfOrder=32, authorNames=Xu Z, Liu R, Yang S, journalName=Proceedings of the IEEE/CVF Conference on Computer Visionand Pattern Recognition, refType=null, unstructuredReference=Xu Z, Liu R, Yang S, et al. Learning imbalanced data with vision transformers[C]// Proceedings of the IEEE/CVF Conference on Computer Visionand Pattern Recognition. Piscataway: IEEE, 2023: 15793-15803., articleTitle=Learning imbalanced data with vision transformers, refAbstract=null), Reference(id=1228369784920801883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=[30], rfOrder=33, authorNames=He K, Zhang X, Ren S, journalName=Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778., articleTitle=Deep residual learning for image recognition, refAbstract=null), Reference(id=1228369785042436705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=34, authorNames=Ma L, Wu H, Samundeeswari P, journalName=Pattern Recognition, refType=null, unstructuredReference=Ma L, Wu H, Samundeeswari P. GoogLeNet-AL: a fully automated adaptive model for lung cancer detection[J]. Pattern Recognition, 2024.DOI: 10.1016/j.patcog.2024.110657., articleTitle=GoogLeNet-AL: a fully automated adaptive model for lung cancer detection, refAbstract=null), Reference(id=1228369785164071528, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=11534, pageEnd=11542, url=null, language=null, rfNumber=[32], rfOrder=35, authorNames=Wang Q, Wu B, Zhu P, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11534-11542., articleTitle=ECA-Net: efficient channel attention for deep convolutional neural networks, refAbstract=null), Reference(id=1228369785285706348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2980, pageEnd=2988, url=null, language=null, rfNumber=[33], rfOrder=36, authorNames=Ross T Y, Dollár G K H P, journalName=Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Ross T Y, Dollár G K H P. Focal loss for dense object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2980-2988., articleTitle=Focal loss for dense object detection, refAbstract=null), Reference(id=1228369785411535476, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=33, issue=null, pageStart=4175, pageEnd=4186, url=null, language=null, rfNumber=[34], rfOrder=37, authorNames=Ren J, Yu C, Ma X, journalName=Inc, refType=null, unstructuredReference=Ren J, Yu C, Ma X, et al. Balanced meta-softmax for long-tailed visual recognition[J]. NeurIPS, Red Hook: Curran Associates, Inc, 2020, 33: 4175-4186., articleTitle=Balanced meta-softmax for long-tailed visual recognition, refAbstract=null), Reference(id=1228369785583501947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2022, volume=23, issue=7, pageStart=1234, pageEnd=1249, url=null, language=null, rfNumber=[35], rfOrder=38, authorNames=Zhang H, Wang L, Liu Y, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=Zhang H, Wang L, Liu Y. Simulated annealing-based optimization of loss function for deep learning in geological data analysis[J]. Journal of Machine Learning Research, 2022, 23(7): 1234-1249., articleTitle=Simulated annealing-based optimization of loss function for deep learning in geological data analysis, refAbstract=null), Reference(id=1228369785700942463, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[36], rfOrder=39, authorNames=Dubois M K, Bohling G C, Chakrabarti S, journalName=null, refType=null, unstructuredReference=Dubois M K, Bohling G C, Chakrabarti S.An integrated application of neural network and Markov chain techniques to prediction of lithofacies from well logs[EB/OL]. [2025-01-07]. https://www.kaggle.com/datasets/imeintanis/well-log-facies-dataset., articleTitle=An integrated application of neural network and Markov chain techniques to prediction of lithofacies from well logs, refAbstract=null), Reference(id=1228369785797411460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[37], rfOrder=40, authorNames=Ahmed U, Jiangbin Z, Almogren A, journalName=Scientific Reports, refType=null, unstructuredReference=Ahmed U, Jiangbin Z, Almogren A, et al. Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems[J]. Scientific Reports, 2024, 14(1).DOI: 10.1038/s41598-024-81151-1., articleTitle=Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems, refAbstract=null), Reference(id=1228369785893880458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2016, volume=112, issue=null, pageStart=2171, pageEnd=2186, url=null, language=null, rfNumber=[38], rfOrder=41, authorNames=Silva R, Brito J, Dhir R, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=Silva R, Brito J, Dhir R. Establishing a relationship between modulus of elasticity and compressive strength of recycled aggregate concrete[J]. Journal of Cleaner Production, 2016, 112: 2171-2186., articleTitle=Establishing a relationship between modulus of elasticity and compressive strength of recycled aggregate concrete, refAbstract=null), Reference(id=1228369787227669133, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=3, pageStart=105, pageEnd=110, url=null, language=null, rfNumber=[39], rfOrder=42, authorNames=魏杰, 杨斌, 刘锋, journalName=石油化工应用, refType=null, unstructuredReference=魏杰, 杨斌, 刘锋, 等. 基于岩性识别的BP神经网络孔隙度预测[J]. 石油化工应用, 2020, 39(3): 105-110., articleTitle=基于岩性识别的BP神经网络孔隙度预测, refAbstract=null), Reference(id=1228369787307360914, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=3, pageStart=105, pageEnd=110, url=null, language=null, rfNumber=[39], rfOrder=43, authorNames=Wei Jie, Yang Bin, Liu Feng, journalName=Petrochemical Application, refType=null, unstructuredReference=Wei Jie, Yang Bin, Liu Feng, et al. Porosity prediction based on BP neural network for lithology identification[J]. Petrochemical Application, 2020, 39(3): 105-110., articleTitle=Porosity prediction based on BP neural network for lithology identification, refAbstract=null), Reference(id=1228369787399635607, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, doi=null, pmid=null, pmcid=null, year=2023, volume=16, issue=3, pageStart=2545, pageEnd=2557, url=null, language=null, rfNumber=[40], rfOrder=44, authorNames=Zhang X, Wen J, Sun Q, journalName=Earth Science Informatics, refType=null, unstructuredReference=Zhang X, Wen J, Sun Q, et al. Lithology identification technology of logging data based on deep learning model[J]. Earth Science Informatics, 2023, 16(3): 2545-2557., articleTitle=Lithology identification technology of logging data based on deep learning model, refAbstract=null)], funds=[Fund(id=1228369779916997041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, awardId=2022-10897, language=CN, fundingSource=长庆油田校企合作项目(2022-10897), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228369771813601336, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, xref=1, ext=[AuthorCompanyExt(id=1228369771817795641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China), AuthorCompanyExt(id=1228369771830378554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771813601336, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中南民族大学计算机学院, 武汉 430074)]), AuthorCompany(id=1228369771910070339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, xref=2, ext=[AuthorCompanyExt(id=1228369772019122247, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771910070339, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Resources and Environment, Yangtze University, Wuhan 430100, China), AuthorCompanyExt(id=1228369772031705162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, companyId=1228369771910070339, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 长江大学资源与环境学院, 武汉 430100)])], figs=[ArticleFig(id=1228369775638806779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.1, caption=Structure of the ECA-MSCB ResNet network, figureFileSmall=LPBLjquwZtYrAMAv6Qlmcg==, figureFileBig=CfTzZOHCsuqB84bXF4JZRA==, tableContent=null), ArticleFig(id=1228369775747858692, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图1, caption=ECA-MSCB ResNet网络结构

ECA为高效通道注意力机制;MSCB-Block为多尺度卷积块;Conv 1D为1D卷积层;BN+ReLU为批量归一化和修正线性单元Concat为拼接操作;Avg-Pool为平均池化层;FC为全连接层;GAP为全局平均池化层;Output为输出端

, figureFileSmall=LPBLjquwZtYrAMAv6Qlmcg==, figureFileBig=CfTzZOHCsuqB84bXF4JZRA==, tableContent=null), ArticleFig(id=1228369775877882124, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.2, caption=Structure of the Inception, figureFileSmall=vDQnWHMjLXBO8Iy4BjNQGQ==, figureFileBig=G3ElH97Fi0oXbh1v8hl0yg==, tableContent=null), ArticleFig(id=1228369775957573910, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图2, caption=Inception模块结构, figureFileSmall=vDQnWHMjLXBO8Iy4BjNQGQ==, figureFileBig=G3ElH97Fi0oXbh1v8hl0yg==, tableContent=null), ArticleFig(id=1228369776058237212, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.3, caption=Structure of the MSCB Block, figureFileSmall=pYD8MfnkzcHMUSo+UybmlA==, figureFileBig=Vp08e4I8F43B042WxkNU4g==, tableContent=null), ArticleFig(id=1228369776137928994, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图3, caption=MSCB Block模块结构, figureFileSmall=pYD8MfnkzcHMUSo+UybmlA==, figureFileBig=Vp08e4I8F43B042WxkNU4g==, tableContent=null), ArticleFig(id=1228369776242786604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.4, caption=Logging curve of LX-5, figureFileSmall=/vajxozgndMMp/ohdpB8Tg==, figureFileBig=GpbDT7MCmFZyZPBh+63TYA==, tableContent=null), ArticleFig(id=1228369776326672691, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图4, caption=LX-5的测井曲线

DEPTH为深度;SP为自发电位;GR为伽马;DT为声波时差;RHOB为体积密度

, figureFileSmall=/vajxozgndMMp/ohdpB8Tg==, figureFileBig=GpbDT7MCmFZyZPBh+63TYA==, tableContent=null), ArticleFig(id=1228369776427335994, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.5, caption=SHAP feature importance analysis, figureFileSmall=DEeJoOFq+g+qzEN3PeCT5g==, figureFileBig=8JIXHHoIa4r5BvRIA5wndw==, tableContent=null), ArticleFig(id=1228369776519610686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图5, caption=SHAP特征重要性分析, figureFileSmall=DEeJoOFq+g+qzEN3PeCT5g==, figureFileBig=8JIXHHoIa4r5BvRIA5wndw==, tableContent=null), ArticleFig(id=1228369776632856902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.6, caption=Comparison of algorithm performance, figureFileSmall=Tndz9zlE8751AsWil/IxQQ==, figureFileBig=Lmg9p8q9K19cp3qt240PdQ==, tableContent=null), ArticleFig(id=1228369776829989196, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图6, caption=各算法性能指标对比, figureFileSmall=Tndz9zlE8751AsWil/IxQQ==, figureFileBig=Lmg9p8q9K19cp3qt240PdQ==, tableContent=null), ArticleFig(id=1228369776918069588, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.7, caption=Predicted results for the test set, figureFileSmall=rMLHVRKJRQ17/h75Dmg9mA==, figureFileBig=rDh1OTElnubU1FflSsGNxQ==, tableContent=null), ArticleFig(id=1228369778293801306, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图7, caption=测试集的预测结果, figureFileSmall=rMLHVRKJRQ17/h75Dmg9mA==, figureFileBig=rDh1OTElnubU1FflSsGNxQ==, tableContent=null), ArticleFig(id=1228369778444796255, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.8, caption=Accuracy variation curves for each class, figureFileSmall=lOMWdjY811Im8mLV0u6mew==, figureFileBig=twOnYro48uzT7Z6U8hmeBQ==, tableContent=null), ArticleFig(id=1228369778524488036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图8, caption=各类别准确率的变化曲线, figureFileSmall=lOMWdjY811Im8mLV0u6mew==, figureFileBig=twOnYro48uzT7Z6U8hmeBQ==, tableContent=null), ArticleFig(id=1228369778650317162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Fig.9, caption=Convergence curves of the ECA-MSCB ResNet model, figureFileSmall=81/aiAWTAqfi6gLodrOPlg==, figureFileBig=r3SHM1blQy1uBfLkk3+1lA==, tableContent=null), ArticleFig(id=1228369778750980462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=图9, caption=ECA-MSCB ResNet 模型的收敛曲线, figureFileSmall=81/aiAWTAqfi6gLodrOPlg==, figureFileBig=r3SHM1blQy1uBfLkk3+1lA==, tableContent=null), ArticleFig(id=1228369778826477938, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Table 1, caption=

Statistical results of logging curve values

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 自发电
位/mV
伽马/
gAPI
声波时差/
(μs·ft-1)
体积密度/
(g·cm-3)
最大值 488.922 557.141 472.573 3.355
最小值 -150.804 17.032 47.929 1.166
平均值 179.480 102.370 128.598 2.485
标准差 175.285 33.440 81.923 0.250
), ArticleFig(id=1228369778922946936, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=表1, caption=

长庆油田数据测井曲线值统计

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 自发电
位/mV
伽马/
gAPI
声波时差/
(μs·ft-1)
体积密度/
(g·cm-3)
最大值 488.922 557.141 472.573 3.355
最小值 -150.804 17.032 47.929 1.166
平均值 179.480 102.370 128.598 2.485
标准差 175.285 33.440 81.923 0.250
), ArticleFig(id=1228369779019415933, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Table 2, caption=

Summary of lithology and its frequency

, figureFileSmall=null, figureFileBig=null, tableContent=
岩性 缩写名称 标签 出现频次
碳质泥岩 CS 0 405
Coal 1 1 921
泥岩 Shale 2 47 025
粉砂质泥岩 Sil 3 2 409
砂砾岩 CL 4 279
粗砂岩 Cst 5 4 104
中砂岩 Mst 6 5 573
细砂岩 Fst 7 5 502
粉砂岩 S 8 6 348
泥质粉砂岩 As 9 1 481
石灰岩 Ls 10 550
), ArticleFig(id=1228369779132662148, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=表2, caption=

长庆油田数据岩性的缩写标记及其出现频率

, figureFileSmall=null, figureFileBig=null, tableContent=
岩性 缩写名称 标签 出现频次
碳质泥岩 CS 0 405
Coal 1 1 921
泥岩 Shale 2 47 025
粉砂质泥岩 Sil 3 2 409
砂砾岩 CL 4 279
粗砂岩 Cst 5 4 104
中砂岩 Mst 6 5 573
细砂岩 Fst 7 5 502
粉砂岩 S 8 6 348
泥质粉砂岩 As 9 1 481
石灰岩 Ls 10 550
), ArticleFig(id=1228369779233325450, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Table 3, caption=

Performance comparison of recognition algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 长庆油田数据集 公开数据集Council Grove
精确率/% 召回率/% 准确率/% F1-score/% 精确率/% 召回率/% 准确率/% F1-score/%
Random Forest[14] 59.19 46.93 46.94 52.35 71.84 70.18 72.45 70.02
BP Neural Network[39] 56.38 50.23 50.45 53.13 58.47 52.49 52.67 55.38
U-CNN[40] 66.81 65.20 65.18 65.98 65.77 68.69 69.22 66.78
EMResNet 73.86 73.47 74.27 73.65 77.46 77.14 77.46 75.77
), ArticleFig(id=1228369779342377364, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=表3, caption=

各种识别算法的性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 长庆油田数据集 公开数据集Council Grove
精确率/% 召回率/% 准确率/% F1-score/% 精确率/% 召回率/% 准确率/% F1-score/%
Random Forest[14] 59.19 46.93 46.94 52.35 71.84 70.18 72.45 70.02
BP Neural Network[39] 56.38 50.23 50.45 53.13 58.47 52.49 52.67 55.38
U-CNN[40] 66.81 65.20 65.18 65.98 65.77 68.69 69.22 66.78
EMResNet 73.86 73.47 74.27 73.65 77.46 77.14 77.46 75.77
), ArticleFig(id=1228369779447234967, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Table 4, caption=

Results of 5-fold cross-validation

, figureFileSmall=null, figureFileBig=null, tableContent=
折数 精确率/% 召回率/% 准确率/% F1-score/%
第1折 73.12 70.19 70.19 71.81
第2折 73.91 71.12 71.32 72.23
第2折 73.91 71.12 71.32 72.23
第3折 75.74 72.35 72.87 74.12
第4折 73.58 72.47 72.35 72.55
第5折 73.59 72.28 72.28 72.56
平均值 73.98 71.68 71.80 72.45
), ArticleFig(id=1228369779514343837, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=表4, caption=

五折交叉验证结果

, figureFileSmall=null, figureFileBig=null, tableContent=
折数 精确率/% 召回率/% 准确率/% F1-score/%
第1折 73.12 70.19 70.19 71.81
第2折 73.91 71.12 71.32 72.23
第2折 73.91 71.12 71.32 72.23
第3折 75.74 72.35 72.87 74.12
第4折 73.58 72.47 72.35 72.55
第5折 73.59 72.28 72.28 72.56
平均值 73.98 71.68 71.80 72.45
), ArticleFig(id=1228369779610812833, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=EN, label=Table 5, caption=

Model ablation experiments

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 精确率/% 召回率/% 准确率/% F1-score/%
Baseline 69.21 66.82 66.82 67.89
Baseline+MCSB 72.48 69.12 69.13 70.46
Baseline+ECA 73.32 70.25 70.00 71.18
Baseline+ECA&MCSB 73.86 73.47 74.27 73.65
), ArticleFig(id=1228369779728253352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279665186505373, language=CN, label=表5, caption=

模型消融实验

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 精确率/% 召回率/% 准确率/% F1-score/%
Baseline 69.21 66.82 66.82 67.89
Baseline+MCSB 72.48 69.12 69.13 70.46
Baseline+ECA 73.32 70.25 70.00 71.18
Baseline+ECA&MCSB 73.86 73.47 74.27 73.65
)], 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.1671-1815.2407182, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2407182, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2407182, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2407182, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
电子技术、通信技术基于ECA-MSCB ResNet的不均衡岩性识别
收藏切换
PDF下载
裴谋 1 , 李波 1, * , 胡勇 2
科学技术与工程 | 论文·电子技术、通信技术 2025,25(22): 9398-9407
收起
收藏切换
科学技术与工程 | 论文·电子技术、通信技术 2025, 25(22): 9398-9407
电子技术、通信技术基于ECA-MSCB ResNet的不均衡岩性识别
全屏
裴谋1 , 李波1, * , 胡勇2
作者信息
  • 1 中南民族大学计算机学院, 武汉 430074
  • 2 长江大学资源与环境学院, 武汉 430100
  • 裴谋(1999—),女,土家族,湖北宜昌人,硕士研究生。研究方向:机器学习及数值分析。E-mail:

通讯作者:

* 李波(1975—),男,汉族,湖北宜都人,博士,教授。研究方向:机器学习及模式识别。E-mail:
Imbalanced Lithology Identification Based on ECA-MSCB ResNet
Mou PEI1 , Bo LI1, * , Yong HU2
Affiliations
  • 1 School of Computer Science, South-Central Minzu University, Wuhan 430074, China
  • 2 College of Resources and Environment, Yangtze University, Wuhan 430100, China
出版时间: 2025-08-08 doi: 10.12404/j.issn.1671-1815.2407182
文章导航
收藏切换

为了改善由于地质数据类别不均衡导致的岩性预测精度不高的问题,提出了一种ECA-MSCB ResNet模型,集成高效通道注意力机制(efficient channel attention,ECA)和多尺度卷积块(multi-scale convolutional block,MSCB)于传统的ResNet架构中,实现了对岩性数据特征的高效提取和表征。针对岩性类别不均衡的问题,在模型训练过程中引入先验概率平衡logit偏差,改进焦点损失函数,以提升对少数类岩性的识别能力。实验结果表明,基于ECA-MSCB ResNet的模型在地质岩性不均衡数据集上表现良好,与原ResNet模型相比,平均预测准确率提升约7.45%,与随机森林相比提升27.33%,特别是在少数类岩性的识别上取得了显著进步,平均提高约17.9%。同时,本文模型在公开数据集上表现良好,F1-score达到75.77%。此外,本文模型识别准确率高于目前主流方法,在地质不均衡岩性识别领域具有良好的应用价值。

岩性预测  /  测井数据  /  不均衡数据  /  ECA-MSCB ResNet

In order to improve the prediction accuracy of lithology affected by imbalanced geological data, an ECA-MSCB ResNet model was proposed. The model integrates ECA (efficient channel attention) and MSCB (multi-scale convolutional block) into the traditional ResNet architecture to achieve efficient extraction and representation of lithological data features. For the issue of imbalanced lithology categories, prior probability-balanced logit bias was introduced during model training, and the focal loss function was modified to enhance the recognition of minority lithology classes. Experimental results show that the model based on ECA-MSCB ResNet performs well on the imbalanced geological lithology dataset, achieving an average prediction accuracy improvement of approximately 7.45% compared to the original ResNet model and 27.33% compared to the random forest method. Notably, the recognition of minority lithology classes improves by an average of 17.9%. Furthermore, the model demonstrates strong lithology classification ability on public datasets, achieving an F1-score of 75.77%. In addition, the recognition accuracy of the proposed model outperformed both traditional and mainstream methods. The ECA-MSCB ResNet method holds significant application value in the field of imbalanced geological lithology recognition.

lithology identification  /  logging data  /  imbalanced data  /  ECA-MSCB ResNet
裴谋, 李波, 胡勇. 电子技术、通信技术基于ECA-MSCB ResNet的不均衡岩性识别. 科学技术与工程, 2025 , 25 (22) : 9398 -9407 . DOI: 10.12404/j.issn.1671-1815.2407182
Mou PEI, Bo LI, Yong HU. Imbalanced Lithology Identification Based on ECA-MSCB ResNet[J]. Science Technology and Engineering, 2025 , 25 (22) : 9398 -9407 . DOI: 10.12404/j.issn.1671-1815.2407182
在地质勘探和油气开发过程中,油气田位置与岩性密切相关,岩性直接影响储层的物理特性如孔隙度和渗透率,从而决定油气的储集能力和生产潜力[1]。因此岩性识别与预测对提高油气开发产量具有重要意义,为油气田的储层划分和开发规划提供了重要依据[2]。为了提高岩性识别的精度,学者们采用了多尺度特征提取和深度学习等方法,处理复杂地质条件下的岩性差异问题[3]。同时,面对岩性类别不均衡的问题,许多研究者提出了改进的损失函数和重采样方法,以优化模型在不均衡数据上的性能[4-6]。此外,针对跨区域数据适应性差的问题,主动域适配技术被提出,显著提升了不同地质区域的岩性识别精度[7]。为了进一步提升预测效率,研究者还探索了利用伽马谱和元素测井数据进行特征优化和降维的方法[8-9]。这些研究为岩性识别领域的发展提供了新的思路,也推动了岩性识别技术从传统方法向智能化、高精度方向演进。
岩性识别技术发展经历了3个阶段:传统岩性识别阶段、浅层神经网络识别阶段和深度神经网络岩性识别阶段。在传统的早期测井岩性识别研究主要是以流体替换、横波速度计算、交会图[10]等,侧重于建立基于地质学专业知识的岩性绘图模型,这在很大程度上依赖于人工解释,并且应用于复杂岩性地层时具有挑战性。
随着技术的发展,Lai等[11]通过孔隙度谱和图像测井数据预测碳酸盐岩储层质量;Kolbjørnsen等[12]采用贝叶斯反演方法提高了岩性预测精度;Liu等[13]对多种机器学习方法进行比较研究,为岩性分类模型的选择和优化提供了重要参考;Ao[14]和黄安等[15]通过引入随机森林模型,对测井数据进行特征提取和分类;Zhang等[16]ISD方法在地震岩性和流体预测中展现了优势,尽管机器学习方法通过增量学习有效捕捉了岩性与测井数据间的复杂非线性关系,但传统方法易陷入局部最小值,且深层网络存在梯度消失或爆炸的问题,限制了模型性能[17]。因此,深度学习网络越来越受到研究者的关注。
卷积神经网络(convolutional neural network,CNN)作为深度学习的重要分支,近年来在测井岩性预测中表现突出。Imamverdiye等[18]采用深度卷积神经网络提高了岩性相分类的精度;Ao等[19]通过多任务深度网络并结合稀疏岩芯校正,增强了地层属性预测模型的精度和鲁棒性;Chen等[20]则结合物理约束与深度学习,提升了地层岩性预测的效率与准确性。王胜等[21]提出了一种基于深度学习的振动与声音信号岩性识别方法,有效提升了识别精度,为地质勘探提供了新技术路径。此外,针对复杂地质条件下的岩性识别问题,Zhao等[22]提出的残差图注意力网络通过捕捉局部特征和全局依赖关系;Sun等[23]通过结合集成学习与深度学习,有效提升了基于井下测井数据的岩性识别准确性。但在实际地质条件下,岩性之间的差异往往较小,许多岩性具有相似的物理特性。这种高相似性的岩性分布使得传统方法难以精确区分。
类别不均衡数据识别是指在样本各类别数量分布不均的情况下进行有效分类的技术。例如,网络入侵检测中异常活动占比小但重要,正确识别少数类至关重要[24]。然而,基于精度设计的模型通常在少数类上表现不佳。近年来,出现了一些不平衡数据分类方法。渐进式混合分类器集成方法[25]和正则化判别广义学习系统[26],均有效提升了分类性能。现有方法还包括数据重采样技术(如过采样少数类或欠采样多数类)[27-28]、使用加权损失函数提高少数类样本的重要性[29]以及采用适合处理不均衡数据的算法等。测井作业主要集中在储层区域,导致其他井段的测井数据稀缺。这导致采集的测井数据存在岩性分布不平衡的问题,进而影响岩性识别的准确性。现有方法为处理复杂地质条件下的不均衡岩性识别问题提供了重要参考。
在实际应用中,测井曲线数据反映的岩性类别不均衡性普遍存在,某些岩性样本数量远多于其他岩性。这种不均衡性会导致预测模型在训练过程中更倾向于预测频次较高的岩性,从而影响模型的整体精度和泛化能力。如何在岩性类别不均衡的情况下,设计出能够准确识别和预测各种岩性的模型,是一项具有挑战性的研究工作。
因此,聚焦于测井曲线的岩性识别问题,现提出一种基于残差网络[30](ResNet)的改进的分类算法,称为ECA-MSCB ResNet(简称EMResNet)。该算法针对不均衡地下地质岩性数据问题,通过融合改进的ECA模块和多尺度卷积块,以增强模型对不同尺度特征的捕捉能力并强化上下文信息提取;同时提出基于先验概率的焦点损失函数,以提高训练稳定性和模型泛化能力。从而实现对地质岩性的精确识别,降低因人为判断错误而导致的风险,提高地质岩性识别的准确性和工程。
本文研究基于ResNet架构,提出了一种在复杂地质环境下进行岩性预测的方法,并引入了增强通道注意力机制(efficient channel attention,ECA)和多尺度卷积块(multi-scale convolutional block,MSCB),ECA-MSCB ResNet模型的网络结构如图1所示。首先,将输入样本输入网络,网络以初始卷积层开始,然后通过最大池化层来降低维度。主干网络由4个阶段组成,每个阶段包含多个残差块,其中传统的卷积被MSCB取代。这些块包含4个并行分支,具有不同的卷积核大小,有效地提取多尺度特征。每个MSCB后还应用了ECA模块分支,自顶向下的通过将这些方法集成到ResNet框架中,观察到岩性预测能力有了显著提升。以下部分将详细描述每个模块及其作用。
ResNet是处理一维信号数据的深度残差网络,其主要目的是解决随着层数增加而出现的梯度消失或梯度爆炸问题。ResNet特征提取模块主要基于残差块(residual block),通过引入“跳跃连接”来实现这一目标。在残差块中残差的计算公式为
Output=F(x)+x
式(1)中:每个输入信号x通过卷积层、批量归一化层和ReLU激活函数进行处理,得到特征映射F(x)。
Inception结构可以提取不同尺度下的信息显示了GoogLeNet的结构它包含4个并行分支[31]。前3个分支使用窗口大小分别为1×1、3×3和5×5的卷积层提取不同尺度的信息,第4个分支使用3×3最大池化层,然后使用1×1卷积层来更改通道的数量,如图2所示。
由于输入参数只是5×1向量,因此调整了Inception结构。一方面,池化分支被删除,只保留了卷积分支。以尺度为3×1的卷积核提取的特征为主体,以尺度为1×1和5×1的卷积核提取的特征为补充。最后,对特征进行合并。3个分支的比例是1∶2∶1。本文的MSCB Block模块结构,如图3所示。
高效渠道注意(ECA)策略[32]是一种不需要降维的局部跨渠道交互方法,具有注意机制对模型性能提升的作用,通过在本地跨通道上应用ECA模块,可以在模块中自适应调整交互范围,大大改善了手动参数优化带来的时间成本和计算资源消耗。改进的ECA模块结构如图3所示,首先通过全局平均池化(global average pooling,GAP)获得每个通道的全局特征Z∈RB×C,其计算公式为
Zc=$\frac{1}{L}\stackrel{L}{\sum _{l=1}}$Xc,l
式(2)中:输入X∈RC×L;L为特征长度;Zc为第c个通道的特征平均值;C为通道数,c=1,2,…,C;Xc,l为输入特征张量在第c个通道、第l个位置上的值。
然后,经过一个全连接层,计算每个通道的权重。该过程自适应地为每个通道分配权重,将权重值用来对原始输入的每个通道进行加权处理,得到输出Y∈RC×L。设全连接层的权重为W∈RC×C,通道权重S∈RC,计算公式分别为
s=σ(Wz)
Yc,l=Xc,lsc,∀c,∀l
式中:σ为sigmoid激活函数,计算通道权重;Xc,l为输入特征张量在第c个通道、第l个位置上的值;Yc,l为输出特征张量在第c个通道、第l个位置上的值;sc为第c个通道的权重值;C为通道数;L为特征长度。
为了提高分类模型在不平衡数据集上的性能,本文研究根据Focal Loss[33]和Balanced Cross-Entropy算法[34]提出了一种改进的平衡焦点损失函数(balanced focal loss,Bal_Focal_loss)。该损失函数结合了类别平衡和焦点损失的思想,并引入了温度缩放和模拟退火机制来进一步提升模型的稳定性和准确性。
在不平衡数据集中,少数类样本往往在训练过程中被忽略,导致模型偏向多数类。为了缓解这一问题,本文在损失函数中引入了类别平衡因子。具体来说,为每个类别计算先验概率,并通过参数τ对先验概率进行缩放,形成类别平衡项,将平衡项在计算损失前加到输入的logits上,从而调整每个类别的预测概率,
在分类任务中,模型的输出通常是通过softmax函数计算得到的概率分布,本文研究引入温度参数,结合模拟退火算法[35]来平滑模型的预测分布,同时通过模拟退火算法动态调整,减少过度自信的预测。计算公式分别为
prior=τln$\frac{1}{C}$
T=max(Tf,)
X=$\frac{x+\mathrm{p}\mathrm{r}\mathrm{i}\mathrm{o}\mathrm{r}}{T}$
式中:prior为先验值,用于调整模型的预测分布;C为类别数;τ为先验参数;T为温度参数;Tf为终止温度;η为退火速率。
本文研究在损失函数中引入焦点损失,通过对难分类样本施加更大的权重,来减少易分类样本对损失的贡献,从而提高模型在难分类样本上的表现。焦点损失的权重因子和最终损失的计算公式分别为
Focal_weight=α$(1-{p}_{t}{)}^{\gamma }$
Loss=$\frac{1}{N}\stackrel{N}{\sum _{i=1}}$αi$(1-{p}_{{t}_{i}}{)}^{\gamma }$ln${p}_{{t}_{i}}$
式中:αi为第i类别权重;γ为调节因子;${P}_{{t}_{i}}$为第i个样本的模型正确类别的预测概率;N为样本总数。
本文使用的测井数据来自长庆油田某采油厂的9口井,按照8∶1∶1的比例划分成训练集、验证集和测试集(以下称长庆油田数据集)。该数据集包括4条电缆测井曲线:自发电位(spontaneous potential,SP)、伽马(gamma ray,GR)、声波时差(acoustic transit time,DT)和体积密度(bulk density,RHOB),以及0.1 m一次岩性标记采样,超过6万个样本, 这些常规测井参数的统计信息如表1所示,单口井的测井曲线如图4所示。数据中包括碳质泥岩、煤、泥岩、粉砂质泥岩、砂砾岩、粗砂岩、中砂岩、细砂岩、粉砂岩、泥质粉砂岩和石灰岩,如表2所示。为了进一步验证所提改进算法的泛化能力,本文研究还使用了公开数据集Council Grove数据集[36]。该数据集包含了来自美国堪萨斯州Council Grove的9口井的测井数据,测井曲线包括伽马(GR)、电阻率(ILD_log10)等7种属性和8类岩性标记。为保证与自有数据集实验的一致性,该数据集也按照8∶1∶1的比例划分成训练集、验证集和测试集。
为确保输入数据的有效性,进一步理解各特征对模型预测的贡献,特别是针对那些样本数量稀少的类别,需要对测井曲线进行相关性分析。本文研究中使用了随机森林(random forest)模型通过SHAP(Shapley additive explanations)[37]方法,分析特征的重要性。随机森林是一种基于多棵决策树的集成模型,其计算公式为
ϕi=$\sum _{S\subseteq N\backslash \left\{i\right\}}\frac{\left|S\right|!(\left|N\right|-\left|S\right|-1)!}{\left|N\right|!}$[f(S∪{i})-f(S)]
式(10)中:N为特征级; $ |N|$为特征的数量;$ |N|$!为特征数量的阶乘;SN的一个不包含特征i的子集; $|S|$为子集大小;f(S)为模型在特征子集S上的预测值;f(S∪{i})为加入特征i后的预测值。
前人所提出的岩性预测方法主要依赖于曲线数据本身,忽略了先验知识的重要性。为了充分利用现有数据资源,本文研究在测井曲线资料的基础上引入了地质物理约束指标弹性模量(modulus of elasticity,EM)[38]。弹性模量是利用声波时差(DT)和体积密度(RHOB)测井数据,计算得到的。弹性模量的引入为岩性分析和储层特性研究提供了更为丰富的力学参数,有助于进一步揭示地层的物理性质和力学行为。弹性模量(EM)的计算公式为
Vp=$\frac{1}{{D}_{\mathrm{T}}}$
E=ρ${V}_{\mathrm{s}}^{2}\frac{3{V}_{\mathrm{p}}^{2}-4{V}_{\mathrm{s}}^{2}}{{V}_{\mathrm{p}}^{2}-{V}_{\mathrm{s}}^{2}}$
式中:E为弹性模;Vp为纵波速度;Vs为横波速度,是1/1.5倍的Vp;ρ为体积密度。
图5所示,SHAP值为解释模型输出提供了透明的依据,揭示了每个特征对预测结果的具体影响。图5(a)是全局视角下的重要性,可以看出SP影响最大,EM特征的整体影响看起来较小;但是,由图5(b)可知,EM与GR特征的交互在class 0识别过程中,EM引入显著增强了模型对这类尾部数据的识别能力,从而为优化模型和解释地质现象提供了更深层次的见解,最后采用所有特征进行预测实验。
实验环境主要包括64位Windows 10操作系统,16 GB RAM, Intel i5-12400F CPU,NVIDIA GeForce RTX 3080Ti GPU。代码运行环境为Pycharm平台下的Python3.9,基于PyTorch和CUDA11.3深度学习框架。训练阶段的初始学习率设置为0.000 1,betas 参数为(0.9,0.999),使用Step Learning Rate Decay策略,每20轮迭代降低学习率。使用Adam作为优化器,迭代次数为300轮,批量大小为64个,为了防止过拟合并确保模型的泛化能力,在训练过程中引入了早停策略,将耐心值(patience)设置为50个周期,即如果验证损失在50个连续周期内没有下降,则停止训练。
常用的分类评价指标包括精确率(precision,P)、召回率(recall,R)、准确率(accuracy,A)和F1-score。为了更好地评价模型的实际效果,本文研究采用该4个指标进行综合评价。精确率是指模型预测为正类样本中实际为正类的比例,召回率是指所有实际为正类的样本中,被模型正确预测为正类的样本所占的比例,准确率是指模型所有预测中正确预测的比例,F1-score是精确率和召回率的调和平均数,用于在精确率和召回率之间进行平衡,它们计算公式分别为
P=$\frac{\mathrm{T}\mathrm{P}}{\mathrm{T}\mathrm{P}+\mathrm{F}\mathrm{P}}$×100%
R=$\frac{\mathrm{T}\mathrm{P}}{\mathrm{T}\mathrm{P}+\mathrm{F}\mathrm{N}}$×100%
A=$\frac{\mathrm{T}\mathrm{P}+\mathrm{T}\mathrm{N}}{\mathrm{T}\mathrm{P}+\mathrm{T}\mathrm{N}+\mathrm{F}\mathrm{P}+\mathrm{F}\mathrm{N}}$×100%
F1-score=2$\frac{PR}{P+R}$×100%
式中:TP、FP、TN、FN分别为被模型预测为正类的正样本、被模型预测为正类的负样本、被模型预测为负类的负样本、被模型预测为负类的正样本。
在地质岩性分类能力方面,本文研究将改进算法与原模型以及若干主流分类模型进行对比,同时,在公开数据集Council Grove上进行了验证实验,以评估改进算法在不同数据集上的泛化能力,结果如表3图6所示。此外,本文研究采用五折交叉验证,在长庆油田数据集上对算法的性能进行进一步验证,结果如表4所示。
表3可以看出,所提出的ECA-MSCB ResNet模型对岩性类别识别精度较高,F1-score达到了73.65%,高于随机森林、BP神经网络、U-CNN模型(分别是52.35%、53.13%、65.98%)。并且从表3可以看出,本文模型在公开数据上表现良好,具有较强的岩性分类能力,F1-score达到了75.77%,高于其他模型。
根据表4中自有数据集的五折交叉实验结果,可以看出本文模型表现稳健。具体而言,该模型的平均F1-score达到了72.45%,同时精确率和召回率分别达到了73.98%和71.68%。此外,各折实验的结果波动较小,F1-score的数值范围在71.81%~74.12%。这一结果表明,该模型在不同的数据划分下均能够保持良好的泛化能力和鲁棒性。
为了充分验证本文研究中针对不均衡数据处理难题的有效性,更加直观说明本文方法的有效性,测试集的预测结果以及各类别准确率的变化曲线,如图7图8所示。
从7(a)和图7(b)可以看出,预测岩性与实际岩性具有较好的对应关系。从图8可以看出尾部类
别在模型性能上有显著提升,相比于基线模型ResNet,碳质泥岩的宏准确率提升了22.6%,砂砾岩的宏准确率提升了18.2%以及石灰岩的宏准确率平均提了12.9%。
为了验证添加到ResNet18模型中的每个模块的有效性,通过顺序添加改进模块来完成实验,在长庆油田数据集上进行了一系列消融实验,实验结果如表5所示,其中基线表示ResNet18检测方法,F1-score为67.89%。增加的MSCB模块后,F1-score增强为70.46%。加入改进的ECA模块后的F1-score增强率为71.18%。两个模块与改进的损失函数融合后的F1-score增强率为73.65%。与基线相比,改进的ResNet18模型的识别分类能力有了明显的提高。
ECA-MSCB ResNet模型在训练过程中的训练和验证损失变化如图9所示。对于训练和验证损失曲线前50轮的损失下降更为明显,收敛速度更快。在150轮后,损失趋于稳定,模型实现收敛。从图9可以看出,ECA-MSCB 1DResNet模型可以很好地在测井数据集上进行训练,没有过拟合。
针对不均衡地质岩性识别的难点,基于ResNet模型,提出了一种改进的ECA-MSCB ResNet模型。通过对该方案进行一系列实验可以得出以下结论。
(1)引入ECA注意力机制,通过增强通道注意力机制,动态调整特征通道的权重,利用有用的特征,增强了模型网络的特征提取能力, 降低了模型在处理复杂地质岩性数据时的噪声干扰,并避免了关键特征在传递过程中的丢失,有效提升了模型的识别性能。
(2)通过将传统的串联卷积改为并行多尺度卷积核,实现了在不增加计算量的前提下,对特征进行多尺度提取。同时,分离特征层预测的方法使得模型能够更加灵活地处理不同尺度的特征,从而提高了对岩性细节的识别能力,为复杂地质条件下的岩性分析提供了一种有效的技术手段,提高了检测精度。
(3)通过对Focal Loss算法引入先验分布的平衡项以及模拟退火算法,通过逐步降低温度,增强了训练的稳定性,提升了模型对尾部数据的识别能力,从而提高了模型在处理不均衡数据时的泛化能力。
基于油田实际工区数据验证,该方法在精度和准确度等方面均取得了较好的效果,未来研究中将从进一步从精确率和准度出发,挖掘数据之间的序列特性,把模型迁移到其他工区,提高模型的工程适用性。
  • 长庆油田校企合作项目(2022-10897)
参考文献 引证文献
排序方式:
[1]
李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4): 508-522.
Li Ning, Xu Binsen, Wu Hongliang, et al. Application status and prospects of artificial intelligence in well logging formation evaluation[J]. Acta Petrolei Sinica, 2021, 42(4): 508-522.
[2]
匡立春, 刘合, 任义丽, 等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发, 2021, 48(1): 1-11.
Kuang Lichun, Liu He, Ren Yili, et al. Application and developement trend of artificial intelligence in petroleum exploration and development[J]. Petroleum Exploration and Development, 2021, 48(1): 1-11.
[3]
Ren Q, Zhang H, Zhang D, et al. Lithology identification using principal component analysis and particle swarm optimization fuzzy decision tree[J]. Journal of Petroleum Science and Engineering, 2023, 220.DOI: 10.1016/j.petrol.2022.111233.
[4]
Feng R. Uncertainty analysis in well log classification by Bayesian long short-term memory networks[J]. Journal of Petroleum Science and Engineering, 2021, 205.DOI: 10.1016/j.petrol.2021.108816.
[5]
Chang J, Kang Y, Zheng W X, et al. Active domain adaptation with application to intelligent logging lithology identification[J]. IEEE Transactions on Cybernetics, 2022, 52(8): 8073-8087.
[6]
Liu N, Huang T, Gao J, et al. Quantum-enhanced deep learning-based lithology interpretation from well logs[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 1-13.
[7]
Ren X, Hou J, Song S, et al. Lithology identification using well logs: a method by integrating artificial neural networks and sedimentary patterns[J]. Journal of Petroleum Science and Engineering, 2019, 182.DOI: 10.1016/j.petrol.2019.106336.
[8]
Zhang H, He Z, Li X, et al. Study on the intelligent identification method of formation lithology by element and gamma spectrum[J]. Neural Computing and Applications, 2022, 34: 1-9.
[9]
Jiang C, Zhang D, Chen S. Lithology identification from well-log curves via neural networks with additional geologic constraint[J]. Geophysics, 2021, 86(5): IM85-IM100.
[10]
Duan Y, Li J, Li B, et al. Lithology identification and reservoir characteristics of the mixed siliciclastic-carbonate rocks of the lower third member of the Shahejie formation in the south of the Laizhouwan Sag, Bohai Bay Basin, China[J]. Carbonates and Evaporites, 2020, 35: 1-19.
[11]
Lai J, Pang X, Chen G, et al. Prediction of reservoir quality in carbonates via porosity spectrum from image logs[J]. Journal of Petroleum Science and Engineering, 2019, 173: 197-208.
[12]
Kolbjørnsen O, Buland A, Hauge R, et al. Bayesian seismic inversion for stratigraphic horizon, lithology, and fluid prediction[J]. Geophysics, 2020, 85: R207-R221.
[13]
Liu S, Zhang Z, Zhao P. Machine learning methods for lithology classification based on well log data: a comparative study[J]. Journal of Petroleum Science and Engineering, 2019, 175: 342-355.
[14]
Ao Y, Zhang B, Wang T, et al. Probabilistic logging lithology characterization with random forest probability estimation[J]. Computers & Geosciences, 2020, 144.DOI: 10.1016/j.cageo.2020.104556.
[15]
黄安, 蔡文渊, 魏新路, 等. 基于改进随机森林的火山岩测井岩性识别[J]. 科学技术与工程, 2023, 23(9): 3696-3704.
Huang An, Cai Wenyuan, Wei Xinlu, et al. Lithology identification of volcanic logging based on improved random forest[J]. Science Technology and Engineering, 2023, 23(9): 3696-3704.
[16]
Zhang J, Li J, Chen X, et al. Seismic lithology/fluid prediction via a hybrid ISD-CNN[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 18(1): 13-17.
[17]
Gu Y Bao, Song X, et al. Complex lithology prediction using probabilistic neural network improved by continuous restricted Boltzmann machine and particle swarm optimization[J]. Journal of Petroleum Science and Engineering, 2019, 179: 966-978.
[18]
Imamverdiyev Y, Sukhostat L. Lithological facies classification using deep convolutional neural network[J]. Journal of Petroleum Science and Engineering, 2019, 174: 216-228.
[19]
Ao Y, Lu W, Hou Q, et al. Sequence-to-sequence borehole formation property prediction via multi-task deep networks with sparse core calibration[J]. Journal of Petroleum Science and Engineering, 2022, 208.DOI: 10.1016/j.petrol.2021.109637.
[20]
Chen Y, Zhang D. Physics-constrained deep learning of geomechanical logs[J]. IEEE Transactions on Geoscience and Remote Sensing, Aug. 2020, 58(8): 5932-5943.
[21]
王胜, 张拯, 谌强, 等. 基于振动与声音信号深度学习的岩性识别方法[J]. 科学技术与工程, 2023, 23(7): 2759-2767.
Wang Sheng, Zhang Zheng, Chen Qiang, et al. Lithology identification method based on deep learning of vibration and sound signals[J]. Science Technology and Engineering, 2023, 23(7): 2759-2767.
[22]
Zhao F, Zhou Z, Zhai H, et al. ResGAT: a residual graph attention network for lithology identification[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 22(3): 1-5.
[23]
Sun Y, Pang S, Zhang Y. Application of adaboost-transformer algorithm for lithology identification based on well logging data[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21(3): 1-5.
[24]
Gu J, Lu S. An effective intrusion detection approach using SVM with naïve Bayes feature embedding[J]. Computers & Security, Mar. 2021, 103.DOI: 10.1016/j.cose.2020.102158.
[25]
Yang K, Yu Z, Chen C P, et al. Progressive hybrid classifier ensemble for imbalanced data[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(4): 2464-2478.
[26]
Jin J, Qin Z, Yu D, et al. Regularized discriminative broad learning system for image classification[J]. Knowledge-Based Systems, 2022, 251.DOI: 10.1016/j.knosys.2022.109306.
[27]
Mayabadi S, Saadatfar H. Two density-based sampling approaches for imbalanced and overlap data[J]. Knowledge-Based Systems, 2022, 241.DOI: 10.1016/j.knosys.2022.108217.
[28]
Lin C, Tsai C F, Lin W C. Towards hybrid over-and under-sampling combination methods for class imbalanced datasets: an experimental study[J]. Artificial Intelligence Review, 2023, 56(2): 845-863.
[29]
Xu Z, Liu R, Yang S, et al. Learning imbalanced data with vision transformers[C]// Proceedings of the IEEE/CVF Conference on Computer Visionand Pattern Recognition. Piscataway: IEEE, 2023: 15793-15803.
[30]
He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 770-778.
[31]
Ma L, Wu H, Samundeeswari P. GoogLeNet-AL: a fully automated adaptive model for lung cancer detection[J]. Pattern Recognition, 2024.DOI: 10.1016/j.patcog.2024.110657.
[32]
Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2020: 11534-11542.
[33]
Ross T Y, Dollár G K H P. Focal loss for dense object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 2980-2988.
[34]
Ren J, Yu C, Ma X, et al. Balanced meta-softmax for long-tailed visual recognition[J]. NeurIPS, Red Hook: Curran Associates, Inc, 2020, 33: 4175-4186.
[35]
Zhang H, Wang L, Liu Y. Simulated annealing-based optimization of loss function for deep learning in geological data analysis[J]. Journal of Machine Learning Research, 2022, 23(7): 1234-1249.
[36]
Dubois M K, Bohling G C, Chakrabarti S.An integrated application of neural network and Markov chain techniques to prediction of lithofacies from well logs[EB/OL]. [2025-01-07]. https://www.kaggle.com/datasets/imeintanis/well-log-facies-dataset.
[37]
Ahmed U, Jiangbin Z, Almogren A, et al. Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems[J]. Scientific Reports, 2024, 14(1).DOI: 10.1038/s41598-024-81151-1.
[38]
Silva R, Brito J, Dhir R. Establishing a relationship between modulus of elasticity and compressive strength of recycled aggregate concrete[J]. Journal of Cleaner Production, 2016, 112: 2171-2186.
[39]
魏杰, 杨斌, 刘锋, 等. 基于岩性识别的BP神经网络孔隙度预测[J]. 石油化工应用, 2020, 39(3): 105-110.
Wei Jie, Yang Bin, Liu Feng, et al. Porosity prediction based on BP neural network for lithology identification[J]. Petrochemical Application, 2020, 39(3): 105-110.
[40]
Zhang X, Wen J, Sun Q, et al. Lithology identification technology of logging data based on deep learning model[J]. Earth Science Informatics, 2023, 16(3): 2545-2557.
2025年第25卷第22期
PDF下载
148
65
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2407182
  • 接收时间:2024-09-25
  • 首发时间:2026-02-11
  • 出版时间:2025-08-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-25
  • 修回日期:2025-05-13
基金
长庆油田校企合作项目(2022-10897)
作者信息
    1 中南民族大学计算机学院, 武汉 430074
    2 长江大学资源与环境学院, 武汉 430100

通讯作者:

* 李波(1975—),男,汉族,湖北宜都人,博士,教授。研究方向:机器学习及模式识别。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2407182
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