基于改进SMOTE和随机森林算法的致密砂岩成岩相测井解释方法

doi:10.11885/j.issn.1674-5086.2022.05.04.01

西南石油大学学报(自然科学版) ›› 2025, Vol. 47 ›› Issue (4): 62-74.DOI: 10.11885/j.issn.1674-5086.2022.05.04.01

基于改进SMOTE和随机森林算法的致密砂岩成岩相测井解释方法

甄艳^1,2, 康锦涛^1,2, 赵晓明^1,2, 葛家旺^1,2, 代茂林^1,2

1. 西南石油大学地球科学与技术学院, 四川成都 610500;
2. 天然气地质四川省重点实验室, 四川成都 610500

收稿日期:2022-05-04 发布日期:2025-07-25
通讯作者: 赵晓明，E-mail:zhxim98@163.com
作者简介:甄艳，1985年生，女，汉族，四川绵竹人，副研究员，博士，主要从事人工智能与油气开发地质、时空大数据挖掘等方面的研究工作。E-mail:zhenyan0824@163.com
康锦涛，1997年生，男，汉族，山西吕梁人，硕士研究生，主要从事机器学习、人工智能与油气地质方面的研究工作。E-mail:863107879@qq.com
赵晓明，1982年生，男，汉族，山东安丘人，教授，主要从事油气田开发地质学、深水沉积学、非常规油气地质、二氧化碳封存与利用、人工智能与油气地质等方面的研究工作。E-mail:zhxim98@163.com
葛家旺，1988年生，男，汉族，湖北枝江人，副研究员，主要从事沉积学、层序地层学及开发沉积学等方面的研究工作。E-mail:gjwddn@163.com
代茂林，1997年生，男，汉族，四川仪陇人，硕士研究生，主要从事油气开发地质。E-mail:1503048438@qq.com
基金资助:
国家自然科学基金（42072183，41902124）

A Logging Interpretation Method for Tight Sandstone Diagenetic Facies Based on Improved SMOTE and Random Forest Algorithm

ZHEN Yan^1,2, KANG Jintao^1,2, ZHAO Xiaoming^1,2, GE Jiawang^1,2, DAI Maolin^1,2

1. School of Geoscience and Technology, Southwest Petroleum University, Chengdu, Sichuan 610500, China;
2. Sichuan Key Laboratory of Natural Gas Geology, Chengdu, Sichuan 610500, China

Received:2022-05-04 Published:2025-07-25

摘要/Abstract

摘要： 成岩相测井解释是致密砂岩优质储层预测的关键，相较于常规的数理统计学方法，机器学习方法可以有效提高成岩相测井解释精度，但受样品数量不足的影响，其解释结果仍存在一定的多解性。为有效解决成岩相测井解释中样本数据不平衡问题，在经典SMOTE算法的基础上，顾及新增样本的空间约束，提出了一种RESMOTE算法，对不平衡数据中的少类样本进行新增，并利用随机森林模型进行成岩相的识别与解释。结果表明，RESMOTE算法优于经典SMOTE算法、Borderline-SMOTE算法和ADASYN算法，随机森林模型的精度从原来的77.27%提升至91.06%。采用RESMOTE算法可保证新增数据的准确性，有效解决了常规测井岩相识别分类方法中的过拟合和准确性不高的问题，对致密砂岩优质储层预测具有重要的应用价值。

关键词: 致密砂岩, 成岩相, RESMOTE算法, 随机森林, 测井解释

Abstract: Diagenetic logging interpretation is the key to predict high-quality tight sandstone reservoirs. Compared with conventional mathematical statistical methods, machine learning methods can effectively improve the accuracy of diagenetic facies logging interpretation. However, due to the insufficient number of samples, there are still some multi-solutions in the interpretation results. In order to effectively solve the problem of sample data imbalance in the logging interpretation of diagenetic facies, this paper considers the spatial constraints of new samples on the basis of the classical SMOTE (Synthetic Minority Over-sampling Technique) algorithm. This paper puts forward a RESMOTE (Repeat SMOTE) algorithm, which adds the few class samples in the imbalanced data, and uses the random forest model to identify and explain the diagenetic facies. The experimental results show that the RESMOTE algorithm is better than classical SMOTE algorithm, Borderline-SMOTE algorithm and ADASYN algorithm, and the accuracy of random forest model is improved from 77.27% to 91.06%. The RESMOTE algorithm can ensure the accuracy of new data, effectively solve the problem of over-fitting and low accuracy in conventional logging lithofacies identification and classification methods, and has important application value for the prediction of high quality tight sandstone reservoirs.

Key words: tight sandstone, diagenetic facies, RESMOTE algorithm, random forest, log interpretation

中图分类号:

TE122

甄艳, 康锦涛, 赵晓明, 葛家旺, 代茂林. 基于改进SMOTE和随机森林算法的致密砂岩成岩相测井解释方法[J]. 西南石油大学学报(自然科学版), 2025, 47(4): 62-74.

ZHEN Yan, KANG Jintao, ZHAO Xiaoming, GE Jiawang, DAI Maolin. A Logging Interpretation Method for Tight Sandstone Diagenetic Facies Based on Improved SMOTE and Random Forest Algorithm[J]. Journal of Southwest Petroleum University(Science & Technology Edition), 2025, 47(4): 62-74.

0
/ / 推荐

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://journal15.magtechjournal.com/Jwk_xnzk/CN/10.11885/j.issn.1674-5086.2022.05.04.01

http://journal15.magtechjournal.com/Jwk_xnzk/CN/Y2025/V47/I4/62

参考文献

[1] 张国生，赵文智，杨涛，等. 我国致密砂岩气资源潜力、分布与未来发展地位[J]. 中国工程科学， 2012， 14（6）:87-93. doi: 10.3969/j.issn.1009-1742.2012.06.012 ZHANG Guosheng, ZHAO Wenzhi, YANG Tao, et al. Resource evaluation, position and distribution of tight sandstone gas in China[J]. Chinese Engineering Science, 2012, 14（6）: 87-93. doi: 10.3969/j.issn.1009-1742.2012.06.012
[2] 李明强，张立强，李政宏，等. 塔里木盆地下侏罗统阿合组下砂砾岩段致密砂岩成岩相划分及测井识别——以库车坳陷依奇克里克地区为例[J]. 天然气地球科学， 2021， 32（10）:1559-1570. doi: 10.11764/j.issn.1672-1926.2021.03.001 LI Mingqiang, ZHANG Liqiang, LI Zhenghong, et al. Diagenetic facies division and logging identification of tight sandstone in the lower conglomerate member of Lower Jurassic Ahe Formation in Tarim Basin: Case study of Yiqikelike Area in Kuqa Depression[J]. Natural Gas Geoscience, 2021, 32(10): 1559-1570. doi: 10.11764/j.is sn.1672-1926.2021.03.001
[3] CUI Yufeng, WANG Guiwen, JONES S J, et al. Prediction of diagenetic facies using well logs: A case study from the upper Triassic Yanchang Formation, Ordos Basin, China[J]. Marine and Petroleum Geology, 2017, 81: 5065. doi: 10.1016/j.marpetgeo.2017.01.001
[4] LI Bin, ZHANG Hanbing, XIA Qingsong, et al. Quantitative evaluation of tight sandstone reservoir based on diagenetic facies: A case of Lower Silurian Kepingtage Formation in Shuntuoguole Low Uplift, Tarim Basin, China[J]. Frontiers in Earth Science, 2021, 8: 2020. doi: 10.3389/feart.2020.597535
[5] REN Dazhong, SUN Liang, LI Rongxi, et al. The impacts of diagenetic facies on reservoir quality in tight sandstones[J]. Open Geosciences, 2020, 12(1): 1060-1082. doi: 10.1515/geo-2020-0174
[6] 白云云，孙卫，任大忠，等. 鄂尔多斯盆地苏里格气田西区苏48区块盒8 段砂岩成岩相定量划分及特征差异[J]. 天然气地球科学， 2018， 29（12）:1739-1747. doi: 10.11764/j.issn.1672-1926.2018.08.002 BAI Yunyun, SUN Wei, REN Dazhong, et al. Quantitative classification and characteristic difference of diagenetic facies in He 8 Reservoir of the Su 48 Block, west area of Sulige Gas Field, Ordos Basin[J]. Natural Gas Geoscience, 2018, 29(12): 1739-1747. doi: 10.11764/j.issn.1672-1926.2018.08.002
[7] 余瑜，林良彪，高健，等. Q型聚类分析在四川盆地南部上三叠统须二段成岩相研究中的应用[J]. 地质科技情报， 2017， 36（2）:133-140. YU Yu, LIN Liangbiao, GAO Jian, et al. Application of Q type cluster analysis in the study of quantitative diagenetic facies of Member 2 of Xujiahe Formation in southern Sichuan[J]. Geological Science and Technology Information, 2017, 36(2): 133-140.
[8] 白薷，王世玉，张璐，等. 基于 MAE神经网络的测井曲线地层自动识别方法[J]. 天然气勘探与开发， 2024， 47（4）:63-71. doi: 10.12055/gaskk.issn.16733177.2024.04.007 BAI Ru, WANG Shiyu, ZHANG Lu, et al. An automatic identifying method for strata via logging curves based on MAE neural network[J]. Natural Gas Exploration and Development, 2024, 47(4): 63-71. doi: 10.12055/ gaskk.issn.1673-3177.2024.04.007
[9] 赵峦啸，刘金水，姚云霞，等. 基于随机森林算法的陆相沉积烃源岩定量地震刻画:以东海盆地长江坳陷为例[J]. 地球物理学报， 2021， 64（2）:700-715. doi: 10.6038/cjg2021O0123. ZHAO Luanxiao, LIU Jinshui, YAO Yunxia, et al. Quantitative seismic characterization of source rocks in lacustrine depositional setting using the Random Forest method: An example from the Changjiang Sag in East China Sea Basin[J]. Chinese Journal of Geophysics, 2021, 64(2): 700-715. doi: 10.6038/cjg2021O0123.
[10] QI Ming, HAN Changcheng, MA Cunfei, et al. Identification of diagenetic facies logging of tight oil reservoirs based on deep learning: A case study in the permian Lucaogou Formation of the Jimsar Sag, Junggar Basin[J]. Minerals, 2022, 12(7): 917. doi: 10.3390/min12070913
[11] SARKAR S, PRAMANIK A, MAITI J, et al. Predicting and analyzing injury severity: A machine learning-based approach using class-imbalanced proactive and reactive data[J]. Safety Science, 2020, 125(1): 104616. doi: 10.1016/j.ssci.2020.104616
[12] FERNANDEZ A, GARCIA S, HERRERA F, et al. SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary[J]. Journal of Artificial Intelligence Research, 2018, 61: 863-905. doi: 10.1613/jair.1.11192
[13] HE Haibo, BAI Yang, EDWARDO A G, et al. ADASYN: Adaptive synthetic sampling approach for imbalanced learning[C]. Hong Kong: Proceedings of the International Joint Conference on Neural Networks, 2008. doi: 10.1109/ijcnn.2008.4633969
[14] TAEJUN L, MINJU K, SUNG-PHIL K, et al. Data augmentation effects using Borderline-SMOTE on classification of a P300-based BCI[C]. Berlin: Proceedings of the 8th International Winter Conference on Brain-Computer Interface(BCI), 2020. doi: 10.1109/BCI48061.2020.9061656
[15] 赵清华，张艺豪，马建芬，等. 改进SMOTE的非平衡数据集分类算法研究[J]. 计算机工程与应用， 2018， 54（18）:168-173. doi: 10.3778/j.issn.1002-8331.1705-0334 ZHAO Qinghua, ZHANG Yihao, MA Jianfen, et al. Research on classification algorithm of imbalanced datasets based on improved SMOTE[J]. Computer Engineering and Applications, 2018, 54(18): 168-173. doi: 10.3778/j.issn.1002-8331.1705-0334
[16] 梅大成，陈江，郑涛. 边界与密度适应的SMOTE算法研究[J]. 计算机应用研究， 2022， 39（5）:1478-1482. doi: 10.19734/j.issn.1001-3695.2021.09.0410 MEI Dacheng, CHEN Jiang, ZHENG Tao. Research on SMOTE algorithm based on boundary and density adaptation[J]. Computer Application Research, 2022, 39(5):1478-1482. doi: 10.19734/j.issn.1001-3695.2021.09.0410
[17] LI Junnan, ZHU Qingsheng, WU Quanwang, et al. A novel oversampling technique for class-imbalanced learning based on SMOTE and natural neighbors[J]. Information Sciences, 2021, 565: 438-455. doi: 10.1016/j.ins.2021. 03.041
[18] XU Fanghao, XU Guosheng, LIU Yong, et al. Factors controlling the development of tight sandstone reservoirs in the Huagang Formation of the central inverted structural belt in Xihu Sag, East China Sea Basin[J]. Petroleum Exploration and Development, 2020, 47(1): 101-113. doi: 10.1016/S1876-3804(20)60009-X
[19] 李顺利，李竞，陈彬滔，等. 西湖凹陷渐新统花港组大型沿岸砂坝沉积特征及主控因素[J]. 古地理学报， 2020， 22（3）:493-503. doi: 10.7605/gdlxb.2020.03.034. LI Shunli, LI Jing, CHEN Bintao, et al. Sedimentary characteristics and controlling factors of large-scale longshore bar in the Oligocene Huagang Formation, Xihu Sag[J]. Chinese Journal of Palaeogeography, 2020, 22(3): 493-503. doi: 10.7605/gdlxb.2020.03.034.
[20] DUAN Dongping, ZHANG Xianguo, LIU Binbin, et al. The relationship between chlorite and reservoir quality in the Huagang Formation, Xihu Depression, China[J]. Energies, 2022, 15(9): 1-16. doi: 10.3390/en15093438
[21] QIAN Wendao, YIN Taiju, ZHANG Changmin, et al. Diagenetic evolution of the oligocene Huagang Formation in Xihu Sag, the East China Sea Shelf Basin[J]. Scientific Reports, 2020, 10(1): 19402. doi: 10.1038/s41598020-76481-9
[22] VERBIEST N, RAMENTOL E, CORNELIS C, et al. Preprocessing noisy imbalanced datasets using SMOTE enhanced with fuzzy rough prototype selection[J]. Applied Soft Computing, 2014, 22: 511-517. doi: 10.1016/j.asoc.2014.05.023
[23] MOORTHY K, MOHAMAD M S. Random forest for gene selection and microarray data classification[J]. Biomedical Informatics, 2011, 7(3): 142-146. doi: 10.1007/978-3-642-32826-8_18
[24] SCHONLAU M, ZOU Yuyan. The random forest algorithm for statistical learning[J]. Stata Journal, 2020, 20(1): 3-29. doi: 10.1177/1536867X20909688
[25] 钟原，张泰，李平，等. 随机森林的融合模型在压井方法分类中的研究[J]. 西南石油大学学报（自然科学版）， 2022， 44（1）:165-173. doi: 10.11885/j.issn.16745086.2020.05.12.02. ZHONG Yuan, ZHANG Tai, LI Ping, et al. Research on classification of well killing method based on random forest fusion model[J]. Journal of Southwest Petroleum University (Science & Technology Edition), 2022, 44(1): 165-173. doi: 10.11885/j.issn.1674-5086.2020.05.12.02.
[26] AUSKALNIS J, PAULAUSKAS N, BASKYS A. Application of local outlier factor algorithm to detect anomalies in computer network[J]. Telecommunications Engineering, 2018, 24(3): 96-99. doi: 10.5755/j01.eie.24.3.20972
[27] SU Shubin, XIAO Limin, LI Ruan, et al. An efficient density-based local outlier detection approach for scattered data[J]. IEEE Access, 2018, 7: 1006-1020. doi: 10.1109/ACCESS.2018.2886197

基于改进SMOTE和随机森林算法的致密砂岩成岩相测井解释方法

A Logging Interpretation Method for Tight Sandstone Diagenetic Facies Based on Improved SMOTE and Random Forest Algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	赵元良, 虞兵, 郭克才, 王美玲, 帅士辰. 超深层非均质低孔砂岩储层复杂流体识别方法[J]. 西南石油大学学报(自然科学版), 2025, 47(4): 10-22.
[2]	段冬平, 刘彬彬, 庞榆, 时琼, 李文俊, 唐洪明. 西湖凹陷HY气田储层孔隙结构差异对其渗流特征的影响[J]. 西南石油大学学报(自然科学版), 2025, 47(4): 75-86.
[3]	李皋, 张毅, 李红涛, 孟英峰, 杨旭. 致密砂岩气藏气体钻井高效建产的机理分析及展望[J]. 西南石油大学学报(自然科学版), 2025, 47(4): 87-95.
[4]	林潼, 赵振宇, 武超, 张华. 台北凹陷侏罗系含铁碳酸盐胶结物特征及对致密砂岩储层的影响[J]. 西南石油大学学报(自然科学版), 2025, 47(2): 32-49.
[5]	师修琳, 黎平, 李剑波, 王淳, 任海侠. 基于叠前反演技术的须家河组孔隙甜点储层预测[J]. 西南石油大学学报(自然科学版), 2025, 47(2): 50-69.
[6]	邓文龙, 衡勇, 冉旭. 中江气田沙溪庙组致密砂岩气藏地层水微观赋存状态及产出特征[J]. 西南石油大学学报(自然科学版), 2024, 46(5): 19-28.
[7]	杨凤来, 陈蓉, 周庆, 王俊, 代力. 油基泥浆下深层储层裂缝表征及有效性评价[J]. 西南石油大学学报(自然科学版), 2024, 46(4): 51-64.
[8]	冯林杰, 蒋裕强, 曹脊翔, 杨长城, 宋林珂. 川中北部须家河组烃源岩测井解释及评价[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 31-42.
[9]	刘言, 刘露. 新场JS₂致密砂岩气藏开发中后期加密界限研究[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 103-110.
[10]	陈林, 黎棚武, 张绍俊, 李志杰, 杜小勇. 基于机器学习的岩芯渗透率及裂缝开度预测[J]. 西南石油大学学报(自然科学版), 2023, 45(4): 155-163.
[11]	葛亮, 滕怡, 肖国清, 肖小汀, 邓红霞. 基于井下环空参数的溢流智能预警技术研究[J]. 西南石油大学学报(自然科学版), 2023, 45(2): 126-134.
[12]	刘言. 中江气田致密砂岩气藏“一体化”甜点评价技术[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 12-25.
[13]	王荐, 段文燊, 毕有益. 川西致密砂岩气藏“暗点”型河道砂岩识别方法[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 37-46.
[14]	熊亮, 衡勇. 中江沙溪庙组致密砂岩气藏气水分布及主控因素[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 47-58.
[15]	刘成川, 陈俊, 程洪亮. 川西致密砂岩气藏测井评价技术及其发展展望[J]. 西南石油大学学报(自然科学版), 2022, 44(3): 59-69.