Article(id=1307086246208107350, tenantId=1146029695717560320, journalId=1306274195778404443, issueId=1307086088166732376, articleNumber=null, orderNo=null, doi=10.12401/j.nwg.2025166, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1766678400000, receivedDateStr=2025-12-26, revisedDate=1769356800000, revisedDateStr=2026-01-26, acceptedDate=1769616000000, acceptedDateStr=2026-01-29, onlineDate=1789563245583, onlineDateStr=2026-09-16, pubDate=1787155200000, pubDateStr=2026-08-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1789563245583, onlineIssueDateStr=2026-09-16, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1789563245583, creator=13701087609, updateTime=1789563245583, updator=13701087609, issue=Issue{id=1307086088166732376, tenantId=1146029695717560320, journalId=1306274195778404443, year='2026', volume='59', issue='4', pageStart='1', pageEnd='386', issueExtLink='null', onlineDate='null', pubDate='1787155200000', pubDateStr='2026-08-20', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1789563207904, creator='13701087609', updateTime=1789616196824, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1307308339885531645, tenantId=1146029695717560320, journalId=1306274195778404443, issueId=1307086088166732376, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1307308339885531646, tenantId=1146029695717560320, journalId=1306274195778404443, issueId=1307086088166732376, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=109, endPage=121, ext={EN=ArticleExt(id=1307086246384268119, articleId=1307086246208107350, tenantId=1146029695717560320, journalId=1306274195778404443, language=EN, title=Research on Deep Tight Sandstone Parameter Prediction Based on XGBoost-MTL, columnId=null, journalTitle=Northwestern Geology, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Accurate prediction of deep tight sandstone reservoir property parameters is essential for reservoir evaluation and sweet spot prediction. However, existing models struggle to fully characterize the complex nonlinear relationships between parameters and cannot achieve simultaneous prediction of multiple parameters. Taking the Yangxia Formation tight sandstone reservoir in the Kuqa Depression of the Tarim Basin's Jurassic System as a case study, this paper conducted high-pressure mercury intrusion and nuclear magnetic resonance experiments on cores to extract reservoir micro-parameters. Average pore throat radius, displacement pressure, fractal dimension, and sorting coefficient are selected as feature parameters. A multi-task learning (MTL) framework was introduced based on a single-task XGBoost model, with an attention mechanism employed to enhance feature selection capabilities. This study proposes a joint prediction model combining Extreme Gradient Boosting (XGBoost) and MTL, suitable for small-sample datasets, to simultaneously predict permeability and porosity. Multiple comparative experiments were conducted to evaluate model performance from multiple perspectives, including prediction accuracy and error metrics. The research findings indicate: ① Both high-pressure mercury intrusion porosimetry and NMR fractal dimension curves exhibit a "three-segment" characteristic, indicating that deep tight sandstone reservoirs possess typical multifractal features; ② The XGBoost-MTL model achieved high correlation coefficients of 0.91 and 0.95 for predicted and actual values in pore-permeability prediction, respectively. Its root mean square error was reduced by approximately 70% compared to the single-task XGBoost model, demonstrating excellent predictive performance; ③ The pore throat scale in the study area is dominated by medium-sized pores. Using the attention score method, it was found that the fractal dimension has the most significant impact on reservoir permeability, while the average pore throat radius has the most significant impact on porosity. This study presents a reliable data-driven approach for predicting the physical properties of deep tight sandstone reservoirs. The findings have been successfully applied in reservoir evaluation of the Yangxia Formation in the Kuqa Depression, with prediction errors controlled within 8.3%. This approach holds significant implications for the efficient development of deep tight sandstone gas reservoirs.

, authors=Youyou CHENG1, 2, Yini GUO1, 2, *, Chengqian TAN1, 2, Yuhong CHENG3, Shaohua ZHANG1, 2, Liang LIANG4, authorsList=Youyou CHENG, Yini GUO, Chengqian TAN, Yuhong CHENG, Shaohua ZHANG, Liang LIANG, authorCompany=null, correspAuthors=Yini GUO, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Northwestern Geology. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1307086254890316690, articleId=1307086246208107350, tenantId=1146029695717560320, journalId=1306274195778404443, language=CN, title=基于XGBoost-MTL的深层致密砂岩储层物性预测研究, columnId=1307086183687811481, journalTitle=西北地质, columnName=人工智能在地质学领域的应用研究, runingTitle=null, highlight=null, articleAbstract=

深层致密砂岩储层物性参数的准确预测对于储层评价和“甜点”预测至关重要,但现有模型难以充分刻画参数之间复杂的非线性关系,且无法实现多参数同时预测。笔者以塔里木盆地库车坳陷侏罗系阳霞组致密砂岩储层为例,对岩心开展高压压汞和核磁共振实验,提取储层微观参数,选取平均孔喉半径、排驱压力、分形维数和分选系数作为特征参数,在单任务XGBoost模型基础上引入了多任务学习(MTL)框架,并使用注意力机制优化特征选择能力,提出了一种适用于小样本数据的基于极限梯度提升(XGBoost)与多任务学习(MTL)的联合预测模型,开展渗透率和孔隙度的同步预测,并设置多组对比实验,从预测精度、误差指标等多角度评估模型性能。研究结果表明:①高压压汞和核磁共振分形维数曲线都呈现出“三段式”特征,指示深层致密砂岩储层具有典型的多重分形特征;②XGBoost-MTL模型在致密砂岩孔渗预测中,预测值与真实值相关性指数分别高达0.91和0.95,均方根误差与单任务XGBoost模型相比降低约70%,表现出良好的预测效果;③研究区孔喉尺度以中孔为主,运用注意力分数方法,发现分形维数对储层渗透率影响最为显著,平均孔喉半径对孔隙度影响最为显著。本研究为深层致密砂岩储层物性预测提供了一种可靠的数据驱动方法,研究成果已在库车坳陷阳霞组储层评价中成功应用,预测误差控制在8.3%以内,对深层致密砂岩气藏高效开发具有重要指导意义。

, authors=成友友1, 2, 郭怡妮1, 2, *, 谭成仟1, 2, 成育红3, 张少华1, 2, 梁亮4, authorsList=成友友, 郭怡妮, 谭成仟, 成育红, 张少华, 梁亮, authorCompany=null, correspAuthors=郭怡妮, authorNote=

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

, correspAuthorsNote=
郭怡妮(2001−),女,硕士研究生,研究方向为非常规油气藏开发地质与开发工程。E−mail:。
, copyrightStatement=版权所有©《西北地质》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=E3eppvnsHGamsL3l47dH+A==, magXml=CyC5CfkOdVv9zdiDhW+YoQ==, pdfUrl=null, pdf=/OEaoWiZdDlL4DF0PhjciA==, pdfFileSize=1945934, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=beHapoHFkUnwIoowni9DKw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=FTPRJ7Ywe2Xu+mKgW60eGA==, mapNumber=null, fund=null)}, authors=[Author(id=1307086530741301364, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yycheng@xsyu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086530837770359, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530741301364, language=EN, stringName=Youyou CHENG, firstName=Youyou, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086530917462136, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530741301364, language=CN, stringName=成友友, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio={"content":"

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

"}, bioImg=null, bioContent=

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086530971988090, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=g17691130626@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1307086531043291261, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530971988090, language=EN, stringName=Yini GUO, firstName=Yini, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531114594430, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530971988090, language=CN, stringName=郭怡妮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531173314688, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, 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=1307086531257200771, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531173314688, language=EN, stringName=Chengqian TAN, firstName=Chengqian, middleName=null, lastName=TAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531311726724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531173314688, language=CN, stringName=谭成仟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531370446982, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086531433361544, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531370446982, language=EN, stringName=Yuhong CHENG, firstName=Yuhong, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531500470409, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531370446982, language=CN, stringName=成育红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3中国石油长庆油田分公司第五采气厂,陕西 西安 710018, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530573529197, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=3, ext=[AuthorCompanyExt(id=1307086530581917806, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China), AuthorCompanyExt(id=1307086530590306415, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国石油长庆油田分公司第五采气厂,陕西 西安 710018)])]), Author(id=1307086531554996363, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086531630493838, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531554996363, language=EN, stringName=Shaohua ZHANG, firstName=Shaohua, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531693408399, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531554996363, language=CN, stringName=张少华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531764711569, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=5, 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=1307086531819237523, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531764711569, language=EN, stringName=Liang LIANG, firstName=Liang, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531882152084, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531764711569, language=CN, stringName=梁亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4西安石油大学石油工程学院,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530661609584, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=4, ext=[AuthorCompanyExt(id=1307086530669998193, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530678386802, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4西安石油大学石油工程学院,陕西 西安 710065)])])], keywords=[Keyword(id=1307086532012175509, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, orderNo=1, keyword=deep tight sandstone), Keyword(id=1307086532070895766, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, orderNo=2, keyword=reservoir physical properties), Keyword(id=1307086532138004631, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, orderNo=3, keyword=Extreme Gradient Boosting (XGBoost)), Keyword(id=1307086532205113496, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, orderNo=4, keyword=Multi-Task Learning (MTL)), Keyword(id=1307086532259639449, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, orderNo=5, keyword=Kuqa depression), Keyword(id=1307086532322554010, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, orderNo=1, keyword=深层致密砂岩), Keyword(id=1307086532381274267, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, orderNo=2, keyword=储层物性), Keyword(id=1307086532448383132, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, orderNo=3, keyword=极限梯度提升(XGBoost)), Keyword(id=1307086532502909085, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, orderNo=4, keyword=多任务学习(MTL)), Keyword(id=1307086532570017950, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, orderNo=5, keyword=库车坳陷)], refs=[Reference(id=1307086537028563143, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=安鹏, 曹丹平, 赵宝银, 等. 基于LSTM循环神经网络的储层物性参数预测方法研究[J]. 地球物理学进展, 2019, 34(5): 1849−1858., articleTitle=null, refAbstract=null), Reference(id=1307086537099866312, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=AN Peng, CAO Danping, ZHAO Baoyin, et al. Reservoir physical parameters prediction based on LSTM recurrent neural network[J]. Progress in Geophysics, 2019, 34(5): 1849−1858., articleTitle=null, refAbstract=null), Reference(id=1307086537179558089, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=程辉, 王付勇, 宰芸, 等. 基于高压压汞和核磁共振的致密砂岩渗透率预测[J]. 岩性油气藏, 2020, 32(3): 11., articleTitle=null, refAbstract=null), Reference(id=1307086538840502474, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=CHENG Hui, WANG Fuyong, ZAI Yun, et al. Prediction of tight sandstone permeability based on high-pressure mercury intrusion(HPMI)and nuclear magnetic resonance(NMR)[J]. Lithologic Reservoirs, 2020, 32(3): 11., articleTitle=null, refAbstract=null), Reference(id=1307086538920194251, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=程希, 周军, 傅海成, 等. 机器学习算法在地球物理测井中的适用性及应用[J]. 西北地质, 2023, 56(4): 336−348., articleTitle=null, refAbstract=null), Reference(id=1307086538983108812, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=CHENG Xi, ZHOU Jun, FU Haicheng, et al. Applicability and Application of Machine Learning Algorithm in Logging Interpretation[J]. Northwestern Geology, 2023, 56(4): 336−348., articleTitle=null, refAbstract=null), Reference(id=1307086539066994893, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=褚庆军, 葛云龙, 童茂松, 等. 基于XGBoost算法的岩性测井曲线预测方法[J]. 测井技术, 2024, 48(6): 748−754., articleTitle=null, refAbstract=null), Reference(id=1307086539125715150, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=CHU Qingjun, GE Yunlong, TONG Maosong, et al. Prediction Method of Lithology Log Based on XGBoost Algorithm[J]. Well Logging Technology, 2024, 48(6): 748−754., articleTitle=null, refAbstract=null), Reference(id=1307086539205406927, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=郭辉, 郭静纯. 基于混合共享机制的多任务深度学习方法[J]. 计算机工程与设计, 2023, 44(2): 556−562., articleTitle=null, refAbstract=null), Reference(id=1307086539276710096, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=GUO Hui, GUO Jingchun. Multi-task deep learning approach based on hybrid sharing mechanism[J]. Computer Engineering and Design, 2023, 44(2): 556−562., articleTitle=null, refAbstract=null), Reference(id=1307086539360596177, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=崔婷婷, 安雪莲, 孙德亮, 等. 基于SHAP的可解释机器学习的滑坡易发性评价模型[J]. 成都理工大学学报(自然科学版), 2025, 52(1): 153−172., articleTitle=null, refAbstract=null), Reference(id=1307086539444482258, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=CUI Tingting, AN Xuelian, SUN Deliang, et al. Explainable machine learning models for landslide susceptibility mapping based on SHAP[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2025, 52(1): 153−172., articleTitle=null, refAbstract=null), Reference(id=1307086539503202515, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=韩旭东, 张广智, 刘飞, 等. 基于虚拟样本生成的致密砂岩储层参数预测[J]. 矿产与地质, 2024, 38(1): 195−204., articleTitle=null, refAbstract=null), Reference(id=1307086539578699988, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=HAN Xudong, ZHANG Guangzhi, LIU Fei, et al. Prediction of tight sandstone reservoir parameters based on virtual sample generation[J]. Mineral Resources and Geology, 2024, 38(1): 195−204., articleTitle=null, refAbstract=null), Reference(id=1307086539645808853, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=贾爱林, 位云生, 郭智, 等. 中国致密砂岩气开发现状与前景展望[J]. 天然气工业, 2022, 42(1): 83−92., articleTitle=null, refAbstract=null), Reference(id=1307086539721306326, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=JIA Ailin, WEI Yunsheng, GUO Zhi, et al. Development status and prospect of tight sandstone gas in China[J]. Natural Gas Industry, 2022, 42(1): 83−92., articleTitle=null, refAbstract=null), Reference(id=1307086539796803799, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=贾承造, 庞雄奇, 宋岩. 全油气系统理论基本原理[J]. 石油勘探与开发, 2024, 51(4): 679−691., articleTitle=null, refAbstract=null), Reference(id=1307086539880689880, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=JIA Chengzao, PANG Xiongqi, SONG Yan. Basic principles of the whole petroleum system[J]. Petroleum Exploration and Development, 2024, 51(4): 679−691., articleTitle=null, refAbstract=null), Reference(id=1307086539943604441, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=刘军, 钟洁, 倪振, 等. 基于机器学习的低含油饱和度砂岩储层参数预测——以准噶尔盆地夏子街油田夏77井区下克拉玛依组为例[J]. 石油实验地质, 2024, 46(5): 1123−1134., articleTitle=null, refAbstract=null), Reference(id=1307086540006519002, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Jun, ZHONG Jie, NI Zhen, et al. Machine learning-based prediction of low oil saturation sandstone reservoir parameters: a case study of Lower Karamay Formation in Xia 77 well block of Xiazijie Oilfield, Junggar Basin[J]. Petroleum Geology and Experiment, 2024, 46(5): 1123−1134., articleTitle=null, refAbstract=null), Reference(id=1307086540086210779, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=罗功伟, 安小平, 姚卫华, 等. 非常规油气储层测井智能解释应用现状与发展趋势[J]. 石油科学通报, 2025, 10(5): 908−925., articleTitle=null, refAbstract=null), Reference(id=1307086540161708252, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO Gongwei, AN Xiaoping, YAO Weihua, et al. Application status and development trends of artificial intelligence in logging interpretation for unconventional oil and gas reservoirs[J]. Petroleum Science Bulletin, 2025, 10(5): 908−925., articleTitle=null, refAbstract=null), Reference(id=1307086540233011421, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=林琴, 郭永刚, 吴升杰, 等. 基于梯度提升的优化集成机器学习算法对滑坡易发性评价: 以雅鲁藏布江与尼洋河两岸为例[J]. 西北地质, 2024, 57(1): 12−22., articleTitle=null, refAbstract=null), Reference(id=1307086540333674718, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=LIN Qin, GUO Yonggang, WU Shengjie, et al. Evaluation of Landslide Susceptibility by Optimization Integrated Machine Learning Algorithm Based on Gradient Boosting: Take Both Banks of Yarlung Zangbo River and Niyang River as Examples[J]. Northwestern Geology, 2024, 57(1): 12−22., articleTitle=null, refAbstract=null), Reference(id=1307086540396589279, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=罗威. 构造驱动作用下的储层非均质性特征——以库车坳陷巴什基奇克组深层—超深层致密砂岩储层为例[J]. 复杂油气藏, 2026, 19(2): 137−143., articleTitle=null, refAbstract=null), Reference(id=1307086540459503840, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=LUO Wei. Reservoir heterogeneity characteristics driven by structural deformation: A case study of deep and ultra-deep tight sandstone reservoirs in the Bashijiqike Formation, Kuqa Depression[J]. Complex Hydrocarbon Reservoirs, 2026, 19(2): 137−143., articleTitle=null, refAbstract=null), Reference(id=1307086540539195617, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=马传杰, 孙宇贞, 彭道刚, 等. 基于XGBoost-MTL的综合能源系统多元负荷预测[J]. 电力工程技术, 2023, 42(5): 158−166., articleTitle=null, refAbstract=null), Reference(id=1307086540610498786, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=MA Chuanjie, SUN Yuzhen, PENG Daogang, et al. Multivariate load forecasting for integrated energy system based on XGBoost-MTL[J]. Electric Power Engineering Technology, 2023, 42(5): 158−166., articleTitle=null, refAbstract=null), Reference(id=1307086540677607651, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=沈禄银, 段太忠, 潘仁芳, 等. 基于支持向量机的测井物性评价——以巴西深海盐下湖相碳酸盐岩储层为例[J]. 中国科技论文, 2022, 17(5): 516−524., articleTitle=null, refAbstract=null), Reference(id=1307086540761493732, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=SHEN Luyin, DUAN Taizhong, PAN Renfang, et al. Logging physical property evaluation based on support vector machine: a case study of subsalt lacustrine carbonate reservoirs in Brazil[J]. China Sciencepaper, 2022, 17(5): 516−524., articleTitle=null, refAbstract=null), Reference(id=1307086540816019685, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=滕文航, 潘增锋, 王瑞. 基于机器学习的榍石微量元素特征判别岩浆岩类型[J]. 成都理工大学学报(自然科学版), 2025, 52(5): 873−887., articleTitle=null, refAbstract=null), Reference(id=1307086540870545638, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=TENG Wenhang, PAN Zengfeng, WANG Rui. Machine-learning-based classification of igneous rock type using titanite trace element data[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2025, 52(5): 873−887., articleTitle=null, refAbstract=null), Reference(id=1307086540941848807, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=王清华, 杨海军, 杨威. 塔里木盆地库车坳陷超深层碎屑岩油气地质研究新进展和下步勘探方向[J]. 石油勘探与开发, 2025, 52(1): 1−14., articleTitle=null, refAbstract=null), Reference(id=1307086541008957672, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Qinghua, YANG Haijun, YANG Wei. New progress and future exploration direction in oil and gas geological research of ultra-deep clastic rocks in the Kuqa Depression, Tarim Basin, NW China[J]. Petroleum Exploration and Development, 2025, 52(1): 1−14., articleTitle=null, refAbstract=null), Reference(id=1307086541071872233, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=王强强, 王元元, 鲁克改, 等. 库车坳陷日达里克地区铀成矿控矿要素与成因分析[J]. 西北地质, 2024, 57(5): 120−129., articleTitle=null, refAbstract=null), Reference(id=1307086541143175402, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG Qiangqiang, WANG Yuanyuan, LU Kegai, et al. Analysis on the Ore-controlling Factors and Genesis of Uranium Mineralization in the Ridalik Area of the Kuqa Depression[J]. Northwestern Geology, 2024, 57(5): 120−129., articleTitle=null, refAbstract=null), Reference(id=1307086541210284267, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=肖佃师, 卢双舫, 陆正元, 等. 联合核磁共振和恒速压汞方法测定致密砂岩孔喉结构[J]. 石油勘探与开发, 2016, 43(6): 961−970., articleTitle=null, refAbstract=null), Reference(id=1307086541310947564, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=XIAO Dianshi, LU Shuangfang, LU Zhengyuan, et al. Combining nuclear magnetic resonance and rate-controlled porosimetry to probe the pore-throat structure of tight sandstones[J]. Petroleum Exploration and Development, 2016, 43(6): 961−970., articleTitle=null, refAbstract=null), Reference(id=1307086541419999469, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=徐颖晋, 庞振宇. 基于改进支持向量机的致密砂岩储层参数预测研究[J]. 现代电子技术, 2024, 47(5): 132−138., articleTitle=null, refAbstract=null), Reference(id=1307086541503885550, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=XU Yingjin, PANG Zhenyu. Research on tight sandstone reservoir parameter prediction based on improved support vector machine[J]. Modern Electronic Technique, 2024, 47(5): 132−138., articleTitle=null, refAbstract=null), Reference(id=1307086541587771631, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=曾少军, 吴洪深, 蔡军, 等. 基于储层类别构建核磁伪毛管压力曲线及产能预测技术[J]. 科学术与工程, 2011, 11(25): 604−644., articleTitle=null, refAbstract=null), Reference(id=1307086541654880496, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=ZENG Shaojun, WU Hongshen, CAI Jun, et al. Capillary Pressure Curve Construction and Productivity Forecast from NMR Logging Based on Reservoir Category[J]. Science Technology and Engineering, 2011, 11(25): 604−644., articleTitle=null, refAbstract=null), Reference(id=1307086541717795057, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=张冰, 王晓婷, 徐福颖, 等. 基于XGBoost的孔隙压力预测方法研究[J]. 地球物理学进展, 2025, 40(2): 541−555., articleTitle=null, refAbstract=null), Reference(id=1307086543403905266, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Bing, WANG Xiaoting. XU Fuying, et al. Research on pore pressure prediction method based on XGBoost[J]. Progress in Geophysics, 2025, 40(2): 541−555., articleTitle=null, refAbstract=null), Reference(id=1307086543731060979, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=张可佳, 华浩南, 刘宗堡, 等. 融合CNN与GAT的储层物性参数预测方法[J]. 计算机技术与发展, 2025, 35(9): 64−70., articleTitle=null, refAbstract=null), Reference(id=1307086543810752756, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG Kejia, HUA Haonan, LIU Zongbao, et al. A Method for Predicting Reservoir Petrophysical Properties by Integrating CNN and GAT[J]. Computer Technology and Development, 2025, 35(9): 64−70., articleTitle=null, refAbstract=null), Reference(id=1307086544146297077, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=周露, 卓勤功, 罗翔, 等. 深层致密砂岩微观孔喉结构对气水相渗的控制机理[J]. 科学技术与工程, 2025, 25(1): 128−136., articleTitle=null, refAbstract=null), Reference(id=1307086544209211638, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHOU Lu, ZHUO Qingong, LUO Xiang, et al. Control Mechanism of Micro-pore Throat Structure of Deep Tight Sandstone on Gas-Water Relative Permeability Curves[J]. Science Technology and Engineering, 2025, 25(1): 128−136., articleTitle=null, refAbstract=null), Reference(id=1307086544272126199, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=朱碧兰, 操凡, 李昆, 等. 人工智能在深部油气勘探领域的应用展望[J]. 科技创新与应用, 2025, 15(34): 12−16., articleTitle=null, refAbstract=null), Reference(id=1307086544356012280, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHU Bilan, CAO Fan, LI Kun, et al. Prospect on the Application of Artificial Intelligence to Deep Oil and Gas Exploration[J]. Technology Innovation and Application, 2025, 15(34): 12−16., articleTitle=null, refAbstract=null), Reference(id=1307086544439898361, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=邹才能, 朱如凯, 吴松涛, 等. 常规与非常规油气聚集类型、特征、机理及展望——以中国致密油和致密气为例[J]. 石油学报, 2012, 33(2): 173−187., articleTitle=null, refAbstract=null), Reference(id=1307086544507007226, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=ZOU Caineng, ZHU Rukai, WU Songtao, et al. Types, characteristics, genesis and prospects of conventional and unconventional hydrocarbon accumulations: taking tight oil and tight gas in China as an instance[J]. Acta Petrolei Sinica, 2012, 33(2): 173−187., articleTitle=null, refAbstract=null), Reference(id=1307086544578310395, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Karimpouli S., Fathianpour N., Roohi J. A new approach to improve neural networks' algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (SCMNN)[J]. Journal of Petroleum Science and Engineering, 2010, 73: 227−238., articleTitle=null, refAbstract=null), Reference(id=1307086544695750908, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Lesniak G, Such P. Fractal aproch, analysis of images and diagenesis in pore space evaluation[J]. Natural Resources Research, 2005, 14(4): 317−324., articleTitle=null, refAbstract=null), Reference(id=1307086544771248381, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Tong D, Yuwei L. In-Situ Stress Prediction Model for Tight Sandstone Based on XGBoost Algorithm[J]. Journal of Mining Science, 2024, 60(2): 341−356., articleTitle=null, refAbstract=null), Reference(id=1307086544922243326, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiang L, Youyou C, Chengqian T. Calculation method of equivalent permeability of dual-porosity media considering fractal characteristics and fracture stress sensitivity[J]. Journal of Petroleum Exploration and Production Technology, 2023, 13(8): 1691−1701., articleTitle=null, refAbstract=null), Reference(id=1307086544980963583, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang G Y, Wang Z Z, Mohaghegh S. Pattern visualization and understanding of machine learning models for permeability prediction in tight sandstone reservoirs[J]. Journal of Petroleum Science and Engineering, 2020, 108142., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)]), AuthorCompany(id=1307086530573529197, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=3, ext=[AuthorCompanyExt(id=1307086530581917806, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China), AuthorCompanyExt(id=1307086530590306415, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国石油长庆油田分公司第五采气厂,陕西 西安 710018)]), AuthorCompany(id=1307086530661609584, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=4, ext=[AuthorCompanyExt(id=1307086530669998193, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530678386802, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4西安石油大学石油工程学院,陕西 西安 710065)])], figs=[ArticleFig(id=1307086532737790111, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.1, caption=Structural features of the Kuqa depression in the Tarim basin, figureFileSmall=3clrVozRC2AsHUQ1fCS4TQ==, figureFileBig=beHapoHFkUnwIoowni9DKw==, tableContent=null), ArticleFig(id=1307086534432288929, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图1, caption=塔里木盆地库车坳陷区域构造(罗威,2026), figureFileSmall=3clrVozRC2AsHUQ1fCS4TQ==, figureFileBig=beHapoHFkUnwIoowni9DKw==, tableContent=null), ArticleFig(id=1307086534532952226, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.2, caption=Fractal dimension fitting diagram of typical cores by MIP, figureFileSmall=iIF58YbNVyObxS4xR1HjFw==, figureFileBig=Ile5lnp8ir6Gtyrjh6sa3w==, tableContent=null), ArticleFig(id=1307086534595866787, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图2, caption=典型岩心压汞分形维数拟合图

a. 样品1压汞分形维数;b. 样品4压汞分形维数

, figureFileSmall=iIF58YbNVyObxS4xR1HjFw==, figureFileBig=Ile5lnp8ir6Gtyrjh6sa3w==, tableContent=null), ArticleFig(id=1307086534650392740, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.3, caption=Fractal dimension fitting diagram of typical cores by NMR, figureFileSmall=PI+NHn2HqiVQZIdTuEABgg==, figureFileBig=ls/QHDqgIm0uTHyokp8AJA==, tableContent=null), ArticleFig(id=1307086534725890213, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图3, caption=典型岩心核磁共振分形维数拟合图

a. 样品1核磁共振分形维数;b. 样品4核磁共振分形维数

, figureFileSmall=PI+NHn2HqiVQZIdTuEABgg==, figureFileBig=ls/QHDqgIm0uTHyokp8AJA==, tableContent=null), ArticleFig(id=1307086534805581990, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.4, caption=Micro-pore parameter vs. pore porosity-permeability fitting relationship diagram, figureFileSmall=CzyYzzgsSm0tgpbV9yX3Aw==, figureFileBig=9amAiHxK7spZsA/JqlWJqg==, tableContent=null), ArticleFig(id=1307086534885273767, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图4, caption=微观孔隙参数与孔渗拟合关系图

a. 平均孔喉半径;b. 排驱压力;c. 分选系数;d. 分形维数

, figureFileSmall=CzyYzzgsSm0tgpbV9yX3Aw==, figureFileBig=9amAiHxK7spZsA/JqlWJqg==, tableContent=null), ArticleFig(id=1307086534969159848, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.5, caption=XGBoost prediction model framework, figureFileSmall=GfJYRur7gr1UR7fbRFmKfQ==, figureFileBig=5KufjwMKTxbPLWiQnwA4VQ==, tableContent=null), ArticleFig(id=1307086535036268713, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图5, caption=XGBoost预测模型框架, figureFileSmall=GfJYRur7gr1UR7fbRFmKfQ==, figureFileBig=5KufjwMKTxbPLWiQnwA4VQ==, tableContent=null), ArticleFig(id=1307086535099183274, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.6, caption=XGBoost-MTL prediction model framework, figureFileSmall=zjD3lRBFiVW2zIIzPKLKLw==, figureFileBig=UH7ZqKPUnNAhBvP4j4Cvcg==, tableContent=null), ArticleFig(id=1307086535157903531, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图6, caption=XGBoost-MTL预测模型总体框架, figureFileSmall=zjD3lRBFiVW2zIIzPKLKLw==, figureFileBig=UH7ZqKPUnNAhBvP4j4Cvcg==, tableContent=null), ArticleFig(id=1307086535225012396, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.7, caption=Heatmap of hyperparameter combinations and R2, figureFileSmall=i277cWOroGUJ7ObUnqjUuQ==, figureFileBig=3HHUO1p0hZDBxTR8mYY8Cw==, tableContent=null), ArticleFig(id=1307086535287926957, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图7, caption=超参数组合与R2的热力关系图, figureFileSmall=i277cWOroGUJ7ObUnqjUuQ==, figureFileBig=3HHUO1p0hZDBxTR8mYY8Cw==, tableContent=null), ArticleFig(id=1307086535359230126, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.8, caption=Attention layer structure diagram, figureFileSmall=/9PD/+LVVr43KNr7/y+TSw==, figureFileBig=G/mEQ+gXRCtXrVDlzOQ5/g==, tableContent=null), ArticleFig(id=1307086535430533295, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图8, caption=注意力层结构图, figureFileSmall=/9PD/+LVVr43KNr7/y+TSw==, figureFileBig=G/mEQ+gXRCtXrVDlzOQ5/g==, tableContent=null), ArticleFig(id=1307086535493447856, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.9, caption=Porosity-permeability prediction results in different models, figureFileSmall=JAtUVhBpfou4dZhhEI7Tuw==, figureFileBig=0bSKV70tl/wClC0YUJeqwQ==, tableContent=null), ArticleFig(id=1307086535564751026, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图9, caption=不同模型孔渗预测效果图

a. XGBoost模型;b. XGBoost模型;c. XGBoost-MTL模型;d. XGBoost-MTL模型

, figureFileSmall=JAtUVhBpfou4dZhhEI7Tuw==, figureFileBig=0bSKV70tl/wClC0YUJeqwQ==, tableContent=null), ArticleFig(id=1307086535623471283, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.10, caption=XGBoost-MTL model training iteration curve, figureFileSmall=JinbB9iJ3j8j3I5ucvrM4w==, figureFileBig=1d7Yn0LAMzmKQ2nIP5RJLA==, tableContent=null), ArticleFig(id=1307086535677997237, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图10, caption=XGBoost-MTL模型训练迭代曲线

a. 迭代200次;b. 迭代500次;c. 迭代700次

, figureFileSmall=JinbB9iJ3j8j3I5ucvrM4w==, figureFileBig=1d7Yn0LAMzmKQ2nIP5RJLA==, tableContent=null), ArticleFig(id=1307086535740911798, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.11, caption=Feature importance distribution chart, figureFileSmall=2P08u1dCMR+CJhszXliiYA==, figureFileBig=3AxDw0Oacj0RCCK7e9DhnA==, tableContent=null), ArticleFig(id=1307086535791243447, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图11, caption=特征重要性分布图, figureFileSmall=2P08u1dCMR+CJhszXliiYA==, figureFileBig=3AxDw0Oacj0RCCK7e9DhnA==, tableContent=null), ArticleFig(id=1307086535845769401, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.12, caption=Relationship of fractal dimension and permeability, figureFileSmall=IP8/3wrXuiJAAQdS5fuCRw==, figureFileBig=b/LERUgAyNHoQhK4vtu96g==, tableContent=null), ArticleFig(id=1307086535900295354, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图12, caption=分形维数与渗透率关系图

a. 小孔隙;b. 中孔隙;c. 大孔隙

, figureFileSmall=IP8/3wrXuiJAAQdS5fuCRw==, figureFileBig=b/LERUgAyNHoQhK4vtu96g==, tableContent=null), ArticleFig(id=1307086535971598523, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.13, caption=Pore type statistics chart, figureFileSmall=YU6iUgJnOqPBGYt8ffcv2g==, figureFileBig=fODG8ttf79cMc8mtrBYj+w==, tableContent=null), ArticleFig(id=1307086536042901692, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图13, caption=孔隙类型统计图, figureFileSmall=YU6iUgJnOqPBGYt8ffcv2g==, figureFileBig=fODG8ttf79cMc8mtrBYj+w==, tableContent=null), ArticleFig(id=1307086536105816253, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Fig.14, caption=Relationship diagram of dractal dimension and porosity, figureFileSmall=MALO+3aHGEst9+AEADCaVQ==, figureFileBig=LHOyKqNmvz7U4fHbad8XYw==, tableContent=null), ArticleFig(id=1307086536189702334, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=图14, caption=分形维数与孔隙度关系图

a. 小孔隙;b. 中孔隙;c.大孔隙

, figureFileSmall=MALO+3aHGEst9+AEADCaVQ==, figureFileBig=LHOyKqNmvz7U4fHbad8XYw==, tableContent=null), ArticleFig(id=1307086536261005503, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Tab.1, caption=

Basic information form of sample

, figureFileSmall=null, figureFileBig=null, tableContent=
样品编号岩性深度(m)层位孔隙度(%)渗透率(mD)
1细砂岩4071.2J2kz9.350.0501
2细砂岩4555.7J1y7.850.0285
3中砂岩4674.2J1a8.920.0389
4含油砂岩4676.4J1a8.050.0489
5细砂岩4678.0J1a7.320.0456
6砂岩4681.7J1a7.800.0479
7细砂岩5281.3J1y10.490.0315
8中砂岩5284.9J1y8.180.0377
9粉砂岩5294.0J1y8.100.0352
10粉砂岩5294.7J1y8.450.0435
), ArticleFig(id=1307086536336502976, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=表1, caption=

岩心样品基本信息表

, figureFileSmall=null, figureFileBig=null, tableContent=
样品编号岩性深度(m)层位孔隙度(%)渗透率(mD)
1细砂岩4071.2J2kz9.350.0501
2细砂岩4555.7J1y7.850.0285
3中砂岩4674.2J1a8.920.0389
4含油砂岩4676.4J1a8.050.0489
5细砂岩4678.0J1a7.320.0456
6砂岩4681.7J1a7.800.0479
7细砂岩5281.3J1y10.490.0315
8中砂岩5284.9J1y8.180.0377
9粉砂岩5294.0J1y8.100.0352
10粉砂岩5294.7J1y8.450.0435
), ArticleFig(id=1307086536453943489, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Tab.2, caption=

Sample parameter statistics table

, figureFileSmall=null, figureFileBig=null, tableContent=
样品
编号
渗透率
(mD)
孔隙度
(%)
平均孔
喉半径
(μm)
排驱
压力
(MPa)
分选
系数
DNMR
10.05019.350.0881.782.832.94
20.02857.850.0482.382.592.93
30.03898.920.0682.052.682.55
40.04898.050.0622.742.702.60
50.04567.320.0411.982.522.55
60.04797.80.1411.502.572.62
70.031510.490.0841.502.622.45
80.03778.180.0411.993.112.55
90.03528.10.0582.212.622.64
100.04358.450.0711.922.922.75
), ArticleFig(id=1307086536525246658, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=表2, caption=

样品参数统计表

, figureFileSmall=null, figureFileBig=null, tableContent=
样品
编号
渗透率
(mD)
孔隙度
(%)
平均孔
喉半径
(μm)
排驱
压力
(MPa)
分选
系数
DNMR
10.05019.350.0881.782.832.94
20.02857.850.0482.382.592.93
30.03898.920.0682.052.682.55
40.04898.050.0622.742.702.60
50.04567.320.0411.982.522.55
60.04797.80.1411.502.572.62
70.031510.490.0841.502.622.45
80.03778.180.0411.993.112.55
90.03528.10.0582.212.622.64
100.04358.450.0711.922.922.75
), ArticleFig(id=1307086536609132739, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Tab.3, caption=

Model configuration table

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数名称超参数设置
损失函数RMSE
树最大深度6
学习率0.02
迭代次数500
正则化参数0.1
树构建方法Hist
), ArticleFig(id=1307086536684630212, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=表3, caption=

预测模型配置表

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数名称超参数设置
损失函数RMSE
树最大深度6
学习率0.02
迭代次数500
正则化参数0.1
树构建方法Hist
), ArticleFig(id=1307086536776904901, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=EN, label=Tab.4, caption=

Prediction Model Evaluation Parameters Table

, figureFileSmall=null, figureFileBig=null, tableContent=
迭代次数渗透率预测R2孔隙度预测R2
2000.560.67
5000.910.95
7000.920.95
), ArticleFig(id=1307086536864985286, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, language=CN, label=表4, caption=

预测模型评价参数表

, figureFileSmall=null, figureFileBig=null, tableContent=
迭代次数渗透率预测R2孔隙度预测R2
2000.560.67
5000.910.95
7000.920.95
)], attaches=null, journal=Journal(id=1306267142871679062, delFlag=0, nameCn=西北地质, nameEn=Northwestern Geology, nameHistory1=null, nameHistory2=null, issn=1009-6248, eissn=null, cn=61-1149/P, coden=null, periodic=1, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=g2W/dgWgrdfgFI9n2w7LWA==, journalPrice=null, startedYear=null, abbrevIsoEn=Northwestern Geology, journalRemark=null, publicationField=null, createdTime=1789367956135, updatedTime=1789370261553, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=X, firstLetterEn=X, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=g2W/dgWgrdfgFI9n2w7LWA==, picEn=HA+pr3B5s55cMNFqTCcq7w==, jcr=null, cjcr=null, exts=[JournalExt(id=1306276812607213966, language=CN, name=西北地质, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1789370261575, updatedTime=1789370261575, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/xbdz, submissionEditorUrl=http://www.manuscripts.com.cn/xbdz, submissionReviewUrl=http://www.manuscripts.com.cn/xbdz, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1306276812661739919, language=EN, name=Northwestern Geology, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1789370261588, updatedTime=1789370261588, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.manuscripts.com.cn/xbdz, submissionEditorUrl=http://www.manuscripts.com.cn/xbdz, submissionReviewUrl=http://www.manuscripts.com.cn/xbdz, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1306274195778404443, websiteList=[Website(id=1306284065330586563, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1306274195778404443, 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/xbdz/CN, language=CN, createTime=1789371990838, createBy=18614031015, updateTime=1789373679297, updateBy=18614031015, name=西北地质-中文, tplId=1146099689490845704, title=西北地质, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1306291362576495313, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=articleTextType, value=kx, createTime=1789373730558, updateTime=1789373730558, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362555523790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=banner, value=null, createTime=1789373730553, updateTime=1789373730553, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362614244052, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=grayFlag, value=0, createTime=1789373730567, updateTime=1789373730567, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362547135181, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=logo, value=https://castjournals.cast.org.cn/joweb/xbdz/CN/file/pic?fileId=xvVA02G0wplFZSMI4Nm5tw==, createTime=1789373730551, updateTime=1789373730551, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362631021270, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=minRunFlag, value=0, createTime=1789373730571, updateTime=1789373730571, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362572301008, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xbdz/CN/file/pic, createTime=1789373730557, updateTime=1789373730557, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362622632661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=silenceFlag, value=0, createTime=1789373730569, updateTime=1789373730569, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362563912399, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1789373730555, updateTime=1789373730555, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362584883922, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=themeColor, value=null, createTime=1789373730560, updateTime=1789373730560, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291362593272531, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065330586563, code=themeStyle, value=null, createTime=1789373730562, updateTime=1789373730562, creator=18614031015, updator=18614031015)]), Website(id=1306284065741628379, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1306274195778404443, 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/xbdz/EN, language=EN, createTime=1789371990857, createBy=18614031015, updateTime=1789373700339, updateBy=18614031015, name=西北地质-英文, tplId=1146101810881728533, title=Northwestern Geology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1306291335716172484, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=articleTextType, value=kx, createTime=1789373724154, updateTime=1789373724154, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335695200961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=banner, value=null, createTime=1789373724149, updateTime=1789373724149, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335745532615, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=grayFlag, value=0, createTime=1789373724161, updateTime=1789373724161, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335686812352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=logo, value=https://castjournals.cast.org.cn/joweb/xbdz/EN/file/pic?fileId=xvVA02G0wplFZSMI4Nm5tw==, createTime=1789373724147, updateTime=1789373724147, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335762309833, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=minRunFlag, value=0, createTime=1789373724165, updateTime=1789373724165, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335707783875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xbdz/EN/file/pic, createTime=1789373724152, updateTime=1789373724152, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335753921224, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=silenceFlag, value=0, createTime=1789373724163, updateTime=1789373724163, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335703589570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1789373724151, updateTime=1789373724151, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335728755397, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=themeColor, value=null, createTime=1789373724157, updateTime=1789373724157, creator=18614031015, updator=18614031015), WebsiteProps(id=1306291335737144006, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1306284065741628379, code=themeStyle, value=null, createTime=1789373724159, updateTime=1789373724159, creator=18614031015, updator=18614031015)])], journalTitle=西北地质, weixinUrl=null, journalUrl=https://www.xbdz.net.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Northwestern Geology, journalPhotoCn=g2W/dgWgrdfgFI9n2w7LWA==, journalPhotoEn=HA+pr3B5s55cMNFqTCcq7w==, journalFirstLetter=X, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/xbdz/CN/10.12401/j.nwg.2025166, detailUrlEn=https://castjournals.cast.org.cn/joweb/xbdz/EN/10.12401/j.nwg.2025166, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xbdz/CN/PDF/10.12401/j.nwg.2025166, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xbdz/EN/PDF/10.12401/j.nwg.2025166, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1787155200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于XGBoost-MTL的深层致密砂岩储层物性预测研究
收藏切换
PDF下载
成友友 1, 2 , 郭怡妮 1, 2, * , 谭成仟 1, 2 , 成育红 3 , 张少华 1, 2 , 梁亮 4
西北地质 | 人工智能在地质学领域的应用研究 2026,59(4): 109-121
收起
收藏切换
西北地质 |人工智能在地质学领域的应用研究 2026 , 59 (4) : 109 -121
基于XGBoost-MTL的深层致密砂岩储层物性预测研究
全屏
[Author(id=1307086530741301364, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yycheng@xsyu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086530837770359, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530741301364, language=EN, stringName=Youyou CHENG, firstName=Youyou, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086530917462136, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530741301364, language=CN, stringName=成友友, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio={"content":"

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

"}, bioImg=null, bioContent=

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086530971988090, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=g17691130626@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1307086531043291261, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530971988090, language=EN, stringName=Yini GUO, firstName=Yini, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531114594430, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086530971988090, language=CN, stringName=郭怡妮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531173314688, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, 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=1307086531257200771, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531173314688, language=EN, stringName=Chengqian TAN, firstName=Chengqian, middleName=null, lastName=TAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531311726724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531173314688, language=CN, stringName=谭成仟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531370446982, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086531433361544, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531370446982, language=EN, stringName=Yuhong CHENG, firstName=Yuhong, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531500470409, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531370446982, language=CN, stringName=成育红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3中国石油长庆油田分公司第五采气厂,陕西 西安 710018, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530573529197, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=3, ext=[AuthorCompanyExt(id=1307086530581917806, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China), AuthorCompanyExt(id=1307086530590306415, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530573529197, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3中国石油长庆油田分公司第五采气厂,陕西 西安 710018)])]), Author(id=1307086531554996363, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1307086531630493838, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531554996363, language=EN, stringName=Shaohua ZHANG, firstName=Shaohua, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531693408399, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531554996363, language=CN, stringName=张少华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1西安石油大学地球科学与工程学院,陕西 西安 710065
2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530409951335, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=1, ext=[AuthorCompanyExt(id=1307086530418339944, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530426728553, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530409951335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西安石油大学地球科学与工程学院,陕西 西安 710065)]), AuthorCompany(id=1307086530481254506, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=2, ext=[AuthorCompanyExt(id=1307086530489643115, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530498031724, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530481254506, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065)])]), Author(id=1307086531764711569, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, orderNo=5, 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=1307086531819237523, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531764711569, language=EN, stringName=Liang LIANG, firstName=Liang, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1307086531882152084, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, authorId=1307086531764711569, language=CN, stringName=梁亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4西安石油大学石油工程学院,陕西 西安 710065, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1307086530661609584, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, xref=4, ext=[AuthorCompanyExt(id=1307086530669998193, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China), AuthorCompanyExt(id=1307086530678386802, tenantId=1146029695717560320, journalId=1306274195778404443, articleId=1307086246208107350, companyId=1307086530661609584, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4西安石油大学石油工程学院,陕西 西安 710065)])])]
成友友1, 2 , 郭怡妮1, 2, * , 谭成仟1, 2, 成育红3, 张少华1, 2, 梁亮4
作者信息
  • 1西安石油大学地球科学与工程学院,陕西 西安 710065
  • 2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065
  • 3中国石油长庆油田分公司第五采气厂,陕西 西安 710018
  • 4西安石油大学石油工程学院,陕西 西安 710065
通讯作者:
郭怡妮(2001−),女,硕士研究生,研究方向为非常规油气藏开发地质与开发工程。E−mail:。
作者简介:

成友友(1988−),男,博士,副教授,长期从事非常规油气藏开发地质与开发工程。E−mail:

Research on Deep Tight Sandstone Parameter Prediction Based on XGBoost-MTL
Youyou CHENG1, 2 , Yini GUO1, 2, * , Chengqian TAN1, 2, Yuhong CHENG3, Shaohua ZHANG1, 2, Liang LIANG4
Affiliations
  • 1School of Earth Sciences and Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
  • 2Shaanxi Key Laboratory of Petroleum Accumulation Geology, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
  • 3No.5 Oil Production Plant, PetroChina Changqing Oil Field, Xi’an 710018, Shaanxi, China
  • 4School of Petroleum Engineering, Xi’an Petroleum University, Xi’an 710065, Shaanxi, China
出版时间: 2026-08-20 doi: 10.12401/j.nwg.2025166
文章导航
收藏切换

深层致密砂岩储层物性参数的准确预测对于储层评价和“甜点”预测至关重要,但现有模型难以充分刻画参数之间复杂的非线性关系,且无法实现多参数同时预测。笔者以塔里木盆地库车坳陷侏罗系阳霞组致密砂岩储层为例,对岩心开展高压压汞和核磁共振实验,提取储层微观参数,选取平均孔喉半径、排驱压力、分形维数和分选系数作为特征参数,在单任务XGBoost模型基础上引入了多任务学习(MTL)框架,并使用注意力机制优化特征选择能力,提出了一种适用于小样本数据的基于极限梯度提升(XGBoost)与多任务学习(MTL)的联合预测模型,开展渗透率和孔隙度的同步预测,并设置多组对比实验,从预测精度、误差指标等多角度评估模型性能。研究结果表明:①高压压汞和核磁共振分形维数曲线都呈现出“三段式”特征,指示深层致密砂岩储层具有典型的多重分形特征;②XGBoost-MTL模型在致密砂岩孔渗预测中,预测值与真实值相关性指数分别高达0.91和0.95,均方根误差与单任务XGBoost模型相比降低约70%,表现出良好的预测效果;③研究区孔喉尺度以中孔为主,运用注意力分数方法,发现分形维数对储层渗透率影响最为显著,平均孔喉半径对孔隙度影响最为显著。本研究为深层致密砂岩储层物性预测提供了一种可靠的数据驱动方法,研究成果已在库车坳陷阳霞组储层评价中成功应用,预测误差控制在8.3%以内,对深层致密砂岩气藏高效开发具有重要指导意义。

深层致密砂岩  /  储层物性  /  极限梯度提升(XGBoost)  /  多任务学习(MTL)  /  库车坳陷

Accurate prediction of deep tight sandstone reservoir property parameters is essential for reservoir evaluation and sweet spot prediction. However, existing models struggle to fully characterize the complex nonlinear relationships between parameters and cannot achieve simultaneous prediction of multiple parameters. Taking the Yangxia Formation tight sandstone reservoir in the Kuqa Depression of the Tarim Basin's Jurassic System as a case study, this paper conducted high-pressure mercury intrusion and nuclear magnetic resonance experiments on cores to extract reservoir micro-parameters. Average pore throat radius, displacement pressure, fractal dimension, and sorting coefficient are selected as feature parameters. A multi-task learning (MTL) framework was introduced based on a single-task XGBoost model, with an attention mechanism employed to enhance feature selection capabilities. This study proposes a joint prediction model combining Extreme Gradient Boosting (XGBoost) and MTL, suitable for small-sample datasets, to simultaneously predict permeability and porosity. Multiple comparative experiments were conducted to evaluate model performance from multiple perspectives, including prediction accuracy and error metrics. The research findings indicate: ① Both high-pressure mercury intrusion porosimetry and NMR fractal dimension curves exhibit a "three-segment" characteristic, indicating that deep tight sandstone reservoirs possess typical multifractal features; ② The XGBoost-MTL model achieved high correlation coefficients of 0.91 and 0.95 for predicted and actual values in pore-permeability prediction, respectively. Its root mean square error was reduced by approximately 70% compared to the single-task XGBoost model, demonstrating excellent predictive performance; ③ The pore throat scale in the study area is dominated by medium-sized pores. Using the attention score method, it was found that the fractal dimension has the most significant impact on reservoir permeability, while the average pore throat radius has the most significant impact on porosity. This study presents a reliable data-driven approach for predicting the physical properties of deep tight sandstone reservoirs. The findings have been successfully applied in reservoir evaluation of the Yangxia Formation in the Kuqa Depression, with prediction errors controlled within 8.3%. This approach holds significant implications for the efficient development of deep tight sandstone gas reservoirs.

deep tight sandstone  /  reservoir physical properties  /  Extreme Gradient Boosting (XGBoost)  /  Multi-Task Learning (MTL)  /  Kuqa depression
成友友, 郭怡妮, 谭成仟, 成育红, 张少华, 梁亮. 基于XGBoost-MTL的深层致密砂岩储层物性预测研究. 西北地质, 2026 , 59 (4) : 109 -121 . DOI: 10.12401/j.nwg.2025166
Youyou CHENG, Yini GUO, Chengqian TAN, Yuhong CHENG, Shaohua ZHANG, Liang LIANG. Research on Deep Tight Sandstone Parameter Prediction Based on XGBoost-MTL[J]. Northwestern Geology, 2026 , 59 (4) : 109 -121 . DOI: 10.12401/j.nwg.2025166
致密砂岩气在全球范围内的资源量约为210×1012 m3,约占非常规天然气总量的75%(贾爱林等,2022),伴随油气勘探由盆地中浅层向深层迈进,深层致密砂岩气藏更是当前油气勘探的前沿领域和重点方向。致密砂岩储层在微观上呈孔隙结构复杂、孔喉连通性差及非均质性强等特征,进而导致其在宏观上表现出气水关系复杂等特征(邹才能等,2012;贾承造等,2024)。与常规气藏相比,深层致密砂岩气藏还具有孔喉细小、裂缝发育等特点,使得储层物性预测难度极大。因此,开展储层物性预测对于指导深层致密砂岩气藏高效开发至关重要。
国内外学者在储层物性参数预测方面已经取得了丰富的成果。传统预测方法是利用回归分析建立预测模型,基于高压压汞和核磁共振实验,能够实现对渗透率的定量预测(曾少军等,2011;程辉等,2020)。随着人工智能的快速发展,基于各类机器学习算法的储层预测模型得到广泛应用(程希等,2023)。早期研究多采用神经网络(Karimpouli,2010; 安鹏等,2019)、遗传算法(Zhang et al.,2020)等构建预测模型;近年来,支持向量机(SVM)(沈禄银等,2022;徐颖晋等,2024)、BP神经网络(刘军,2024)及多种机器学习算法组合(张可佳等,2025)等方法在储层预测方面大量应用。刘军等(2024)使用BP神经网络构建预测模型对物性参数进行预测,结果表明预测精度高于80%,展现出较高的精度和良好的可行性。
尽管储层参数预测方法一直在推进优化,但在实际应用过程中仍存在诸多挑战。①深层致密砂岩储层的岩心样品数量有限,导致一部分的预测模型由于训练样本过少而出现过拟合从而影响预测结果精度等问题(韩旭东等,2024);②储层物性受孔隙结构、地层压力等多个因素共同影响,传统的线性回归方法难以精确刻画多因素之间复杂的非线性关系;③目前所提出的预测模型仅针对单任务进行预测,没有考虑到多个目标参数同时预测。XGBoost算法具有强大的正则化能够有效防止小样本下地过拟合,同时能够提供特征重要性评估,对参数之间复杂的非线性关系进行准确刻画,为小样本区域的储层参数预测提供新方法。
在此背景下,笔者以塔里木盆地库车坳陷致密砂岩储层为研究对象,收集整理研究区岩心样品,通过高压压汞和核磁共振实验获得排驱压力、分形维数等参数作为特征参数,在极限梯度提升(XGBoost)的模型基础上引入多任务学习(MTL),实现对渗透率和孔隙度的同时预测。同时在训练过程中加入注意力分数机制,量化各特征参数分别对预测目标的重要性,揭示库车坳陷深层致密砂岩储层物性的影响因素。笔者旨在构建一种精度高、效率高且泛化能力强的储层物性预测模型,为深层致密砂岩储层高效开发提供一种可靠的数据驱动方法。
塔里木盆地北部的库车坳陷,面积约为3.1×104 km2,是中新生代发育起来的前陆坳陷(王强强等2024;王清华等,2025)。受南天山逆冲推覆作用影响,区内发育大量断背斜、断层传播褶皱等相关构造,形成了一系列近东西向展布的构造圈闭,为油气富集提供了良好的构造条件(图1,罗威,2026)。
研究区位于南天山山前的第二排构造带克拉苏构造带,目的层系为侏罗系下统阳霞组,岩性以砂岩为主,砂体厚度为450~650 m。该层系经历了强烈的压实和成岩作用,埋深多超过4 500 m,储层裂缝较为发育,主要发育次生孔隙型、裂缝–次生孔隙型,属于典型的深层致密砂岩储层。
笔者取得致密砂岩岩心样品10块,均来自库车坳陷克拉苏构造带,埋深范围4071.2~5295 m,砂体厚度介于200~300 m,横向分布稳定;岩性大多为灰色细粉砂岩以及中砂岩,孔隙度介于7.32%~10.49%,渗透率介于0.0285~0.0501 mD(表1)。
本研究利用高压压汞以及核磁共振技术,实现对岩心样品的微观表征。
(1)高压压汞实验:采用全自动压汞仪AutoPore IV 9500开展高压压汞测试,成功获取大量的微观表征参数。根据拉普拉斯方程推导出基于压汞法的分形维数表达式为公式(1)(Lesniak, 2005)。
$ \mathrm{\lg }\left(1-{S}_{\text{Hg}}\right)=\left({D}_{\text{MIP}}-3\right)\mathrm{\lg }{p}_{\text{c}}-\left({D}_{\text{MIP}}-3\right)\mathrm{\lg }{p}_{\text{cmin}} $
式中:SHg为汞饱和度(%);pc为毛管压力(MPa);pcmin为最小毛管压力(MPa);DMIP为压汞法分形维数。
样品1和样品4的压汞法分形维数回归结果(图2)显示,从图像中可以看出研究区的压汞分形曲线具有明显的“三段式”特征,表明不同级别孔喉微观特征具有明显差异。以曲线拐点为界点,压汞分形维数中的DMIP1、DMIP2和DMIP3分别表示大孔、中孔和小孔的分形维数。
(2)核磁共振实验:核磁共振T2谱是一种非常有效的孔隙微观特征表征方法,使用核磁共振岩样分析仪MiNiMR-HTH开展核磁共振测试,基于核磁共振的分形维数表达式可表示为公式(2)(肖佃师等,2016;周露等,2025)。
$ \mathrm{\lg }{S}_{\text{T}}=\left(3-{D}_{\text{NMR}}\right)\mathrm{\lg }{T}_{2}-\left(3-{D}_{\text{NMR}}\right)\mathrm{\lg }{T}_{2\max } $
式中:ST为弛豫时间小于T2的孔隙体积占比;T2为横向弛豫时间(ms);T2max为最大横向弛豫时间(ms);DNMR为核磁共振分形维数。
样品1和样品4的核磁共振分形维数回归结果显示,其结果同样呈现出了“三段式”特征,且拟合系数略高于压汞分形维数拟合系数,DNMR1、DNMR2和DNMR3分别表示小孔、中孔和大孔的分形维数(图3)。
根据压汞法和核磁法获得的分形维数具有分段的特点,通过不同孔喉类别对应的分形维数进行加权平均计算对应储层的总分形维数(Xiang et al.,2023)。压汞法和核磁共振总分形维数计算方法表达为公式(3)和公式(4)。
$ \begin{split} &{D}_{\text{MIP}}={D}_{\text{MIP1}}\frac{{\varphi }_{\text{MIP1}}}{{\varphi }_{\text{MIP1}}+{\varphi }_{\text{MIP2}}+{\varphi }_{\text{MIP3}}}+\\&{D}_{\text{MIP2}}\frac{{\varphi }_{\text{MIP2}}}{{\varphi }_{\text{MIP1}}+{\varphi }_{\text{MIP2}}+{\varphi }_{\text{MIP3}}}+\\&{D}_{\text{MIP3}}\frac{{\varphi }_{\text{MIP3}}}{{\varphi }_{\text{MIP1}}+{\varphi }_{\text{MIP2}}+{\varphi }_{\text{MIP3}}}\end{split} $
$ \begin{split} &{D}_{\text{NMR}}={D}_{\text{NMR1}}\frac{{\varphi }_{\text{NMR1}}}{{\varphi }_{\text{NMR1}}+{\varphi }_{\text{NMR2}}+{\varphi }_{\text{NMR3}}}+\\&{D}_{\text{NMR2}}\frac{{\varphi }_{\text{NMR2}}}{{\varphi }_{\text{NMR1}}+{\varphi }_{\text{NMR2}}+{\varphi }_{\text{NMR3}}}+\\&{D}_{\text{NMR3}}\frac{{\varphi }_{\text{NMR3}}}{{\varphi }_{\text{NMR1}}+{\varphi }_{\text{NMR2}}+{\varphi }_{\text{NMR3}}}\end{split} $
式中:$ {\varphi }_{\text{MIP}} $为压汞法孔隙度(%);$ {\varphi }_{\text{NMR}} $为核磁共振孔隙度(%)。
根据所做实验以及相关的计算分析,统计典型岩心样品的参数(表2)。平均孔喉半径数值普遍较小,且对应的排驱压力数值较大,说明该致密砂岩样品的孔喉较细。样品分选系数在2.52~3.11,均远大于1,表明所有样品的孔喉大小极不均匀,呈现出典型的多尺度特征。
基于以上实验所获得的岩心数据,分别考虑平均孔喉半径、排驱压力、分选系数和分形维数与孔渗之间的关系。拟合关系图(图4)显示,各参数与孔隙度和渗透率之间的线性相关性极低,与渗透率的相关性拟合系数最高仅有0.1,与孔隙度的相关性拟合系数最高只有0.2,这表明单个参数不能够有效表征对储层物性的影响,应综合考虑多参数对储层物性影响。
目前,机器学习方法不断发展,根据具体要解决的问题也在不断优化创新。对于孔隙度和渗透率的预测也出现了许多新方法(朱碧兰等,2025;罗功伟等,2025),笔者将同时预测岩心孔隙度和渗透率的值,预测对象增加至两个,且考虑到岩心数据通常获取成本极高、样品量有限且噪声较大,笔者选择的机器学习算法应当适合小样本数据且能够进行非线性拟合回归分析,给出比较高的预测精度,确保该方法的可应用性。XGBoost算法满足本次研究的算法要求(褚庆军等,2024;张冰等,2025;崔婷婷等,2025),对于预测多个参数,笔者在XGBoost算法的基础上加入多任务的联合学习,以此来提升小样本任务的性能。
XGBoost是梯度提升算法的一种高效实现,通过二阶泰勒级数展开来扩展损失函数,使模型快速收敛(Tong et al.,2024;林琴等,2024;滕文航等,2025)。其核心思想是通过不断地拟合残差,构建一系列弱学习器,并将它们组合起来形成一个强学习器,在传统的梯度提升算法基础上进行了一系列的优化,在准确性和速度上都有提升,适合用来预测孔隙度和渗透率。使用XGBoost模型进行预测,对实际获取的岩心数据进行数据预处理,建立两个XGBoost模型分别对渗透率和孔隙度进行训练预测,分别输出渗透率和孔隙度的预测值,整个过程需要对其中一个参数预测结束才能开展对另一个参数的预测(图5)。该模型虽然能够顺利预测目标值,但从结构框架图中也可以看出整个过程比较复杂且不能够同时输出两个预测值。
为了能够同时进行多个目标值的预测,笔者在XGBoost算法的基础上引入多任务学习(MTL)。MTL是一种联合多个任务同时学习来增加模型表示和泛化能力的一种方式(郭辉等,2023;马传杰等,2023),其任务之间共享优化学习引起的参数正则化相比普通训练模型拟合的正则化有着先天性的优势。
文中所提到的XGBoost-MTL预测模型总体框架(图6)包括:①对实际获得的岩心参数进行数据加载,接着对数据进行特征值(平均孔喉半径、排驱压力、分选系数、分形维数)和目标值(孔隙度、渗透率)的选择并对其进行数据预处理;②使用XGBoost模型进行训练;③基于MTL的共享机制搭建预测模型;④基于该预测模型对孔隙度和渗透率进行联合预测,同时输出两个预测值。
在数据预处理的初始阶段,需要明确特征变量和目标变量。在本实验中,特征变量包括:R(平均孔喉半径)、Pd(排驱压力)、D(分选系数)和S(分形维数);目标变量包括:PERM(渗透率)和PORO(孔隙度)。
数据标准化是将特征值缩放到相同范围的重要步骤。通过标准化,可以消除不同特征之间的量纲差异,使模型更快收敛,并提高预测性能。如公式(5)所示,本实验中使用StandardScaler对特征进行缩放,将不同特征的取值缩放到同一尺度上,从而提高模型训练的稳定性和性能。
$ {z}_{i}=\frac{{x}_{i}-\mu }{\sigma } $
式中:zi是标准化后的值;xi是原始特征值;μ是该特征的均值;σ是该特征的标准差。
致密砂岩储层的孔隙度和渗透率分布不均匀,通过权重平衡,可以确保模型在训练时不会过于偏向某些常见值,从而更全面地学习每个值的特征。本实验用到 Equalization Loss v2函数来进行平衡权重,平衡权重计算过程表达为公式(6)。
$ {L}_{EQL\text{v2}}=-\frac{1}{N}\sum\limits_{\text{i}=1}^{N}\sum\limits_{\text{j=}1}^{C}{\omega }_{\text{j}}\cdot SFL({p}_{\text{i,j}},{y}_{\text{i,j}}) $
式中:N是样本数量;C是类别数量;pi,j模型预测样本i属于类别j的概率;yi,j是样本i在类别j上的真实标签;ωj是类别权重因子。
超参数是模型在训练前设定的参数,其选择对模型的性能至关重要。该模型的超参数选择基于网格搜索与5折交叉验证确定,搜索范围包括树深度(3~10)、学习率(0.01~0.1)、迭代次数(200~1 000),最终选择在验证集上RMSE最小的参数组合。由超参数组合与R2的热力关系图(图7)可以确定,树最大深度选择6,学习率选择0.02(表3)。
为校验XGBoost-MTL联合学习孔渗预测模型性能,文中采用均方根误差(root mean square error, RMSE)、平均绝对误差(mean absolute error,MAE)和决定系数(coefficient of determination,R2)3项指标来进行评估。RMSE和MAE的值越小,表示模型预测越精准;R2的取值在0到1之间,值越接近于1,表示模型预测越精准,其表达式为公式(7)~公式(9)。
$ {X}_{MA}=\frac{1}{T}\sum\limits_{\text{t}=1}^{T}\left| {y}_{t}-\widehat{{y}_{t}}\right| $
$ {X}_{RMS}=\sqrt{\frac{1}{T}\sum\limits_{t=1}^{T}{\left({y}_{t}-\widehat{{y}_{t}}\right)}^{2}} $
$ {R}^{2}=1-\frac{\displaystyle\sum\limits_{t=1}^{T}{\left({y}_{\text{t}}-\hat{{y}_{t}}\right)}^{2}}{\displaystyle\sum\limits_{t=1}^{T}{\left({y}_{\text{t}}-\overline{y}\right)}^{2}} $
式中:$ \mathrm{T} $为样本数量;$ {y}_{t} $为实际值;$ {\hat{y}}_{t} $为预测值。
在模型训练过程中,本实验还引入了注意力分数机制,它通过计算输入特征之间的相似性来生成注意力分数。这些分数决定了模型在处理输入时,应该关注哪些部分。模型可以根据输入的不同动态调整关注点,提高了灵活性和表达能力。注意力机制在文中的具体应用流程如下:①输入特征通过线性层映射为查询矩阵Q(Query)、键矩阵K(Key)和值矩阵V(Value);②在注意力机制中,Q、K、V通过映射矩阵得到相应的向量,计算Q与K的点积相似度;③经过softmax归一化得到权重,通过注意力分数加权特征,生成新的特征表示;④使用这些权重对V进行加权求和得到输出。注意力分数计算依据公式(10),注意力层结构图如图8所示。
$ AttentionScore\text=soft\max \left(\frac{Q{K}^{T}}{\sqrt{{d}_{k}}}\right)V $
式中:Q是查询矩阵,K是键矩阵,dk是键向量的维度,用于缩放,V是权重值矩阵。
本实验建立样本容量为50组的数据集,其中40组作为训练集(train),将前文提到的典型样品的10组数据作为验证组(test),分别使用XGBoost和XGBoost-MTL两种模型进行训练预测。预测效果图中的R2值对比结果(图9)显示,单独使用XGBoost模型来进行预测孔渗的R2值分别为0.80和0.81,而使用XGBoost-MTL模型进行孔渗预测的R2值为0.91和0.95,联合训练模型的效果优于单独使用XGBoost训练模型的效果。对两种模型的训练误差值进行对比,使用联合训练模型预测的RMSE值比单独使用XGBoost模型的RMSE值降低约70%,MAE值降低约85%,联合训练模型的预测效果更好。
对XGBoost-MTL模型分别设置迭代次数为200、500和700,获取各批次预测的相关系数(表4)。将迭代次数由200次增加至500次,准确度有大幅度提升,渗透率相关性系数由0.56上升到0.91,孔隙度相关性系数由0.67上升到0.95;将迭代次数增加到700次后准确度几乎没有发生改变,渗透率相关性系数变化不大,由0.91升至0.92,孔隙度相关性系数没发生变化。不同迭代次数的收敛曲线(图10)显示,迭代次数为200次时,误差值RMSE已经显著降低但曲线并未收敛;迭代次数为500次时,迭代曲线已经收敛;迭代次数增加至700次时,相较于500次时误差值并没有明显变化,曲线仍然收敛。综合考虑模型计算性能,选择迭代次数500次来进行训练预测。
根据注意力分数机制得到的渗透率和孔隙度特征重要性分布图(图11)可以看出,在预测渗透率过程中,分形维数和平均孔喉半径重要性较高,其次是排驱压力和分选系数,特征重要性分别为0.38、0.26、0.19和0.17;而在对孔隙度的预测过程中,平均孔喉半径和排驱压力的重要性占比较高,其次是分选系数和分形维数,特征重要性分别为0.51、0.24、0.14和0.11。
致密砂岩储层的孔隙结构均服从分形特征,分形维数拟合曲线呈现出明显的“三段式”特征。分形维数本质上是反映连通孔隙网络的复杂程度,是孔隙结构的综合表现。以核磁共振分形维数曲线中的拐点作为小孔、中孔和大孔的区分边界,分析各类型孔隙对应的分形维数特征,训练预测样品小中大3种尺度孔隙分形维数与渗透率之间的关系(图12)。结果表明,3种孔隙的分形维数与渗透率之间都呈现出较好的负相关关系,即分形维数越大,孔隙的结构越复杂、非均质性越强,相应的渗透率会越低。其中,小孔分形维数与渗透率相关性最高,其次为大孔和中孔。这一结果说明,在深层致密砂岩中,小尺度孔隙结构的复杂性对储层渗流能力的制约作用最为显著,可能是由于小孔喉更容易受成岩作用和压实作用影响,导致孔隙连通性变差。
孔喉半径直接反映孔隙的发育程度。各尺度孔隙统计结果(图13)显示,中孔在研究区目的层所占比例最高,达62%,表明中孔是主要的储集空间类型。进一步分析大、中、小3类孔隙分形维数与孔隙度之间的关系(图14),发现中孔分形维数与孔隙度之间的相关性最高,小孔分形维数与孔隙度之间的相关性最小,大孔介于两者之间,表明中孔不仅在数量上占据优势,其结构特征对孔隙度的影响也最明显。值得注意的是,孔隙度预测的特征重要性分布图中,平均孔喉半径的注意力分数高达0.51,远高于其他参数。这可能是因为孔喉半径越大,表明储层的储集空间发育程度越好,相应的孔隙度越高。
(1)通过高压压汞和核磁共振实验,两种方法拟合的分形维数曲线均呈现出“三段式”特征,表明深层致密砂岩储层具有典型的多重分形特征,其中核磁共振分形维数(DNMR)曲线拟合程度略高于高压压汞分形维数(DMIP)曲线,表明核磁共振分形维数对微观孔喉结构的刻画更为精细。
(2)在XGBoost模型的基础上引入多任务学习(MTL)模型进行储层物性参数预测,解决了不能同时对多个参数进行预测的问题,有效提高了致密砂岩储层物性参数预测精度,联合预测模型的预测相关系数分别高达0.91和0.95。
(3)根据注意力分数机制,影响渗透率的特征参数由高到低分别是分形维数、平均孔喉半径、排驱压力和分选系数,影响孔隙度的特征参数从高到低分别是平均孔喉半径、排驱压力、分选系数和分形维数。

参考文献 引证文献
排序方式:
1
安鹏, 曹丹平, 赵宝银, 等. 基于LSTM循环神经网络的储层物性参数预测方法研究[J]. 地球物理学进展, 2019, 34(5): 1849−1858.
AN Peng, CAO Danping, ZHAO Baoyin, et al. Reservoir physical parameters prediction based on LSTM recurrent neural network[J]. Progress in Geophysics, 2019, 34(5): 1849−1858.
2
程辉, 王付勇, 宰芸, 等. 基于高压压汞和核磁共振的致密砂岩渗透率预测[J]. 岩性油气藏, 2020, 32(3): 11.
CHENG Hui, WANG Fuyong, ZAI Yun, et al. Prediction of tight sandstone permeability based on high-pressure mercury intrusion(HPMI)and nuclear magnetic resonance(NMR)[J]. Lithologic Reservoirs, 2020, 32(3): 11.
3
程希, 周军, 傅海成, 等. 机器学习算法在地球物理测井中的适用性及应用[J]. 西北地质, 2023, 56(4): 336−348.
CHENG Xi, ZHOU Jun, FU Haicheng, et al. Applicability and Application of Machine Learning Algorithm in Logging Interpretation[J]. Northwestern Geology, 2023, 56(4): 336−348.
4
褚庆军, 葛云龙, 童茂松, 等. 基于XGBoost算法的岩性测井曲线预测方法[J]. 测井技术, 2024, 48(6): 748−754.
CHU Qingjun, GE Yunlong, TONG Maosong, et al. Prediction Method of Lithology Log Based on XGBoost Algorithm[J]. Well Logging Technology, 2024, 48(6): 748−754.
5
郭辉, 郭静纯. 基于混合共享机制的多任务深度学习方法[J]. 计算机工程与设计, 2023, 44(2): 556−562.
GUO Hui, GUO Jingchun. Multi-task deep learning approach based on hybrid sharing mechanism[J]. Computer Engineering and Design, 2023, 44(2): 556−562.
6
崔婷婷, 安雪莲, 孙德亮, 等. 基于SHAP的可解释机器学习的滑坡易发性评价模型[J]. 成都理工大学学报(自然科学版), 2025, 52(1): 153−172.
CUI Tingting, AN Xuelian, SUN Deliang, et al. Explainable machine learning models for landslide susceptibility mapping based on SHAP[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2025, 52(1): 153−172.
7
韩旭东, 张广智, 刘飞, 等. 基于虚拟样本生成的致密砂岩储层参数预测[J]. 矿产与地质, 2024, 38(1): 195−204.
HAN Xudong, ZHANG Guangzhi, LIU Fei, et al. Prediction of tight sandstone reservoir parameters based on virtual sample generation[J]. Mineral Resources and Geology, 2024, 38(1): 195−204.
8
贾爱林, 位云生, 郭智, 等. 中国致密砂岩气开发现状与前景展望[J]. 天然气工业, 2022, 42(1): 83−92.
JIA Ailin, WEI Yunsheng, GUO Zhi, et al. Development status and prospect of tight sandstone gas in China[J]. Natural Gas Industry, 2022, 42(1): 83−92.
9
贾承造, 庞雄奇, 宋岩. 全油气系统理论基本原理[J]. 石油勘探与开发, 2024, 51(4): 679−691.
JIA Chengzao, PANG Xiongqi, SONG Yan. Basic principles of the whole petroleum system[J]. Petroleum Exploration and Development, 2024, 51(4): 679−691.
10
刘军, 钟洁, 倪振, 等. 基于机器学习的低含油饱和度砂岩储层参数预测——以准噶尔盆地夏子街油田夏77井区下克拉玛依组为例[J]. 石油实验地质, 2024, 46(5): 1123−1134.
LIU Jun, ZHONG Jie, NI Zhen, et al. Machine learning-based prediction of low oil saturation sandstone reservoir parameters: a case study of Lower Karamay Formation in Xia 77 well block of Xiazijie Oilfield, Junggar Basin[J]. Petroleum Geology and Experiment, 2024, 46(5): 1123−1134.
11
罗功伟, 安小平, 姚卫华, 等. 非常规油气储层测井智能解释应用现状与发展趋势[J]. 石油科学通报, 2025, 10(5): 908−925.
LUO Gongwei, AN Xiaoping, YAO Weihua, et al. Application status and development trends of artificial intelligence in logging interpretation for unconventional oil and gas reservoirs[J]. Petroleum Science Bulletin, 2025, 10(5): 908−925.
12
林琴, 郭永刚, 吴升杰, 等. 基于梯度提升的优化集成机器学习算法对滑坡易发性评价: 以雅鲁藏布江与尼洋河两岸为例[J]. 西北地质, 2024, 57(1): 12−22.
LIN Qin, GUO Yonggang, WU Shengjie, et al. Evaluation of Landslide Susceptibility by Optimization Integrated Machine Learning Algorithm Based on Gradient Boosting: Take Both Banks of Yarlung Zangbo River and Niyang River as Examples[J]. Northwestern Geology, 2024, 57(1): 12−22.
13
罗威. 构造驱动作用下的储层非均质性特征——以库车坳陷巴什基奇克组深层—超深层致密砂岩储层为例[J]. 复杂油气藏, 2026, 19(2): 137−143.
LUO Wei. Reservoir heterogeneity characteristics driven by structural deformation: A case study of deep and ultra-deep tight sandstone reservoirs in the Bashijiqike Formation, Kuqa Depression[J]. Complex Hydrocarbon Reservoirs, 2026, 19(2): 137−143.
14
马传杰, 孙宇贞, 彭道刚, 等. 基于XGBoost-MTL的综合能源系统多元负荷预测[J]. 电力工程技术, 2023, 42(5): 158−166.
MA Chuanjie, SUN Yuzhen, PENG Daogang, et al. Multivariate load forecasting for integrated energy system based on XGBoost-MTL[J]. Electric Power Engineering Technology, 2023, 42(5): 158−166.
15
沈禄银, 段太忠, 潘仁芳, 等. 基于支持向量机的测井物性评价——以巴西深海盐下湖相碳酸盐岩储层为例[J]. 中国科技论文, 2022, 17(5): 516−524.
SHEN Luyin, DUAN Taizhong, PAN Renfang, et al. Logging physical property evaluation based on support vector machine: a case study of subsalt lacustrine carbonate reservoirs in Brazil[J]. China Sciencepaper, 2022, 17(5): 516−524.
16
滕文航, 潘增锋, 王瑞. 基于机器学习的榍石微量元素特征判别岩浆岩类型[J]. 成都理工大学学报(自然科学版), 2025, 52(5): 873−887.
TENG Wenhang, PAN Zengfeng, WANG Rui. Machine-learning-based classification of igneous rock type using titanite trace element data[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2025, 52(5): 873−887.
17
王清华, 杨海军, 杨威. 塔里木盆地库车坳陷超深层碎屑岩油气地质研究新进展和下步勘探方向[J]. 石油勘探与开发, 2025, 52(1): 1−14.
WANG Qinghua, YANG Haijun, YANG Wei. New progress and future exploration direction in oil and gas geological research of ultra-deep clastic rocks in the Kuqa Depression, Tarim Basin, NW China[J]. Petroleum Exploration and Development, 2025, 52(1): 1−14.
18
王强强, 王元元, 鲁克改, 等. 库车坳陷日达里克地区铀成矿控矿要素与成因分析[J]. 西北地质, 2024, 57(5): 120−129.
WANG Qiangqiang, WANG Yuanyuan, LU Kegai, et al. Analysis on the Ore-controlling Factors and Genesis of Uranium Mineralization in the Ridalik Area of the Kuqa Depression[J]. Northwestern Geology, 2024, 57(5): 120−129.
19
肖佃师, 卢双舫, 陆正元, 等. 联合核磁共振和恒速压汞方法测定致密砂岩孔喉结构[J]. 石油勘探与开发, 2016, 43(6): 961−970.
XIAO Dianshi, LU Shuangfang, LU Zhengyuan, et al. Combining nuclear magnetic resonance and rate-controlled porosimetry to probe the pore-throat structure of tight sandstones[J]. Petroleum Exploration and Development, 2016, 43(6): 961−970.
20
徐颖晋, 庞振宇. 基于改进支持向量机的致密砂岩储层参数预测研究[J]. 现代电子技术, 2024, 47(5): 132−138.
XU Yingjin, PANG Zhenyu. Research on tight sandstone reservoir parameter prediction based on improved support vector machine[J]. Modern Electronic Technique, 2024, 47(5): 132−138.
21
曾少军, 吴洪深, 蔡军, 等. 基于储层类别构建核磁伪毛管压力曲线及产能预测技术[J]. 科学术与工程, 2011, 11(25): 604−644.
ZENG Shaojun, WU Hongshen, CAI Jun, et al. Capillary Pressure Curve Construction and Productivity Forecast from NMR Logging Based on Reservoir Category[J]. Science Technology and Engineering, 2011, 11(25): 604−644.
22
张冰, 王晓婷, 徐福颖, 等. 基于XGBoost的孔隙压力预测方法研究[J]. 地球物理学进展, 2025, 40(2): 541−555.
ZHANG Bing, WANG Xiaoting. XU Fuying, et al. Research on pore pressure prediction method based on XGBoost[J]. Progress in Geophysics, 2025, 40(2): 541−555.
23
张可佳, 华浩南, 刘宗堡, 等. 融合CNN与GAT的储层物性参数预测方法[J]. 计算机技术与发展, 2025, 35(9): 64−70.
ZHANG Kejia, HUA Haonan, LIU Zongbao, et al. A Method for Predicting Reservoir Petrophysical Properties by Integrating CNN and GAT[J]. Computer Technology and Development, 2025, 35(9): 64−70.
24
周露, 卓勤功, 罗翔, 等. 深层致密砂岩微观孔喉结构对气水相渗的控制机理[J]. 科学技术与工程, 2025, 25(1): 128−136.
ZHOU Lu, ZHUO Qingong, LUO Xiang, et al. Control Mechanism of Micro-pore Throat Structure of Deep Tight Sandstone on Gas-Water Relative Permeability Curves[J]. Science Technology and Engineering, 2025, 25(1): 128−136.
25
朱碧兰, 操凡, 李昆, 等. 人工智能在深部油气勘探领域的应用展望[J]. 科技创新与应用, 2025, 15(34): 12−16.
ZHU Bilan, CAO Fan, LI Kun, et al. Prospect on the Application of Artificial Intelligence to Deep Oil and Gas Exploration[J]. Technology Innovation and Application, 2025, 15(34): 12−16.
26
邹才能, 朱如凯, 吴松涛, 等. 常规与非常规油气聚集类型、特征、机理及展望——以中国致密油和致密气为例[J]. 石油学报, 2012, 33(2): 173−187.
ZOU Caineng, ZHU Rukai, WU Songtao, et al. Types, characteristics, genesis and prospects of conventional and unconventional hydrocarbon accumulations: taking tight oil and tight gas in China as an instance[J]. Acta Petrolei Sinica, 2012, 33(2): 173−187.
27
Karimpouli S., Fathianpour N., Roohi J. A new approach to improve neural networks' algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (SCMNN)[J]. Journal of Petroleum Science and Engineering, 2010, 73: 227−238.
28
Lesniak G, Such P. Fractal aproch, analysis of images and diagenesis in pore space evaluation[J]. Natural Resources Research, 2005, 14(4): 317−324.
29
Tong D, Yuwei L. In-Situ Stress Prediction Model for Tight Sandstone Based on XGBoost Algorithm[J]. Journal of Mining Science, 2024, 60(2): 341−356.
30
Xiang L, Youyou C, Chengqian T. Calculation method of equivalent permeability of dual-porosity media considering fractal characteristics and fracture stress sensitivity[J]. Journal of Petroleum Exploration and Production Technology, 2023, 13(8): 1691−1701.
31
Zhang G Y, Wang Z Z, Mohaghegh S. Pattern visualization and understanding of machine learning models for permeability prediction in tight sandstone reservoirs[J]. Journal of Petroleum Science and Engineering, 2020, 108142.
2026年第59卷第4期
PDF下载
163
72
引用本文
BibTeX
文章信息
doi: 10.12401/j.nwg.2025166
  • 接收时间:2025-12-26
  • 首发时间:2026-09-16
  • 出版时间:2026-08-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-12-26
  • 修回日期:2026-01-26
  • 录用日期:2026-01-29
基金
作者信息
    1西安石油大学地球科学与工程学院,陕西 西安 710065
    2西安石油大学,陕西省油气成藏地质学重点实验室,陕西 西安 710065
    3中国石油长庆油田分公司第五采气厂,陕西 西安 710018
    4西安石油大学石油工程学院,陕西 西安 710065

通讯作者:

郭怡妮(2001−),女,硕士研究生,研究方向为非常规油气藏开发地质与开发工程。E−mail:。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xbdz/CN/10.12401/j.nwg.2025166
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏