Attention-enhanced RepBi-FPN YOLOv8 method for reservoir type identification in electrical imaging

JiaLiang ZHANG, ChuQiao GAO, Bin ZHAO

Prog Geophy ›› 2026, Vol. 41 ›› Issue (2) : 704-718.

PDF(3265 KB)
image
Home Journals Progress in Geophysics
Progress in Geophysics

Abbreviation (ISO4): Prog Geophy      Editor in chief:

About  /  Aim & scope  /  Editorial board  /  Indexed  /  Contact  / 
Online first  /  Current issue  /  All issues  /  Top access  /  RSS
PDF(3265 KB)
Prog Geophy ›› 2026, Vol. 41 ›› Issue (2) : 704-718. DOI: 10.6038/pg2026JJ0102

Attention-enhanced RepBi-FPN YOLOv8 method for reservoir type identification in electrical imaging

Author information +
History +

Abstract

At present, imaging logging image recognition mainly focuses on fracture recognition, while the research on the recognition of pore-like reservoir types is relatively lacking, and there has not been a systematic recognition method for layer-segment reservoir types. To this end, this paper proposes a reservoir type recognition method based on computer vision and deep learning, adopting YOLOv8-S as the model framework, and improving the recognition prediction ability of image reservoir types by introducing the attention mechanism and optimizing the Neck module. In addition, a sliding window method combined with edge detection is proposed to segment the layer segment images, which effectively reduces the loss of feature information and improves the accuracy of model recognition. Compared with the existing identification methods, this experimental research method significantly reduces the subjectivity and workload of manual operation, and is able to identify both fracture and hole reservoir types, with an identification accuracy of 83.3%, which has a certain reservoir type identification and prediction capability, providing a technical guarantee for the accurate evaluation of fracture and hole reservoirs

Key words

Electrical imaging logging / Reservoir type identification / Computer vision / Multi-scale feature fusion / Attention mechanism / Convolutional neural network

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations
JiaLiang ZHANG , ChuQiao GAO , Bin ZHAO. Attention-enhanced RepBi-FPN YOLOv8 method for reservoir type identification in electrical imaging[J]. Progress in Geophysics. 2026, 41(2): 704-718 https://doi.org/10.6038/pg2026JJ0102

References

List( Publishing order | Descend order by publishing year | Descend order by cited within ) Chart analysis
Dong S Q , Zeng L B , Che X H , et al. Application of artificial intelligence in fracture identification using well logs in tight reservoirs. Earth Science, 2023, 48(7): 2443- 2461.
https://doi.org/10.3799/dqkx.2022.088
Du X Q , Liu X , Xue Z B , et al. Preliminary study on automatic identification method of electric imaging logging fracture based on deep learning. Chemical Enterprise Management, 2019,(24): 204- 205.
Fan Y D , Pang H W , Jin Y , et al. Intelligent segmentation and recognition of pores and fractures based on imaging logging. Oil Drilling & Production Technology, 2022, 44(4): 500- 505.
https://doi.org/10.13639/j.odpt.2022.04.015
Han B H , Wang F , Liu Q R , et al. Review of research progress on evaluation of logging reservoir classification methods. Progress in Geophysics, 2021, 36(5): 1966- 1974.
https://doi.org/10.6038/pg2021EE0431
He K M, Zhang X Y, Ren S Q, et al. 2016. Deep residual learning for image recognition. //Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 770-778.
Cited in this article [1]
He Y . The role and influence of acoustic remote detection technology in oil reservoir identification. China Petroleum and Chemical Standard and Quality, 2023, 43(24): 175- 177.
Huangfu Z M , Li S Q . Lightweight you only look once v8: An upgraded you only look once v8 algorithm for small object identification in unmanned aerial vehicle images. Applied Sciences, 2023, 13(22): 12369
https://doi.org/10.3390/app132212369
Cited in this article [1]
Jiang P F , Deng F , Yan X . Microseismic first break picking based on Swin Transformer feature extraction. Progress in Geophysics, 2023, 38(3): 1132- 1142.
https://doi.org/10.6038/pg2023GG0357
Li B T , Wang Z Z , Kong C X , et al. A new intelligent method of fracture recognition based on imaging logging. Well Logging Technology, 2019, 43(3): 257- 262.
https://doi.org/10.16489/j.issn.1004-1338.2019.03.007
Li C Y, Li L L, Geng Y F, et al. 2023. YOLOv6 v3.0: A full-scale reloading. arXiv preprint arXiv: 2301.05586.
Li Y W , Zhang X X . Object detection for UAV images based on improved YOLOv6. IAENG International Journal of Computer Science, 2023, 50(2): 759- 768.
Cited in this article [3]
Lin T Y, Dollár P, Girshick R, et al. 2017. Feature pyramid networks for object detection. //Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 936-944.
Cited in this article [1]
Liu S, Qi L, Qin H F, et al. 2018. Path aggregation network for instance segmentation. //Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 8759-8768.
Cited in this article [1]
Liu X , Zhao H J , Wu S W . Application of U-Net based rock formation image crack detection algorithm. Computer Technology and Development, 2021, 31(5): 73- 78.
https://doi.org/10.3969/j.issn.1673-629X.2021.05.013
Liu Y , Wang L , Luo Y , et al. Log-based identification of the types of the Maokou Formation carbonate reservoirs in the central Sichuan Basin. Geophysical and Geochemical Exploration, 2024, 48(3): 629- 639.
https://doi.org/10.11720/wtyht.2024.1289
Liu Y C, Shao Z R, Hoffmann N. 2021. Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv: 2112.05561.
Cited in this article [1]
Lu J A , Wu Z L , Guan X C , et al. Automatically extract fracture parameters from resistivity images by using Hough transform. Well Logging Technology, 2004, 28(2): 115- 117. 115-117, 179
https://doi.org/10.16489/j.issn.1004-1338.2004.02.008
Ma C , Huang H D , Liang S Y , et al. An overview of prediction methods for complex oil and gas reservoirs. China Offshore Oil and Gas, 2024, 36(2): 87- 97.
https://doi.org/10.11935/j.issn.1673-1506.2024.02.008
Ma T L , Liu H Q , Liao H B , et al. Fracture identification method combining channel and spatial cross attention. Progress in Geophysics, 2024, 39(2): 727- 736.
https://doi.org/10.6038/pg2024HH0144
Peng C , Zou C C . Automatic extraction method for imaging logs crack based on improved ant colony algorithm. Computer Engineering, 2015, 41(8): 196- 201.
Redmon J, Divvala S, Girshick R, et al. 2016. You only look once: Unified, real-time object detection. //Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 779-788.
Cited in this article [1]
Sun Z L , Li Z M , Shen B J , et al. NMR technology in reservoir evaluation for shale oil and gas. Petroleum Geology & Experiment, 2022, 44(5): 930- 940.
https://doi.org/10.11781/sysydz202205930
Tan M X, Pang R M, Le Q V. 2020. EfficientDet: Scalable and efficient object detection. //Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA: IEEE, 10778-10787.
Cited in this article [1]
Woo S, Park J, Lee J Y, et al. 2018. CBAM: Convolutional block attention module. //Proceedings of the 15th European Conference on Computer Vision. Munich, Germany: Springer, 3-19.
Cited in this article [1]
Xia W H , Zhu Z H , Han Y J , et al. Intelligent identification and segmentation method of wellbore fractures in resistivity logging imaging map. Oil Geophysical Prospecting, 2023, 58(5): 1042- 1052.
https://doi.org/10.13810/j.cnki.issn.1000-7210.2023.05.002
Yang F, Zhang S D, Li Y X, et al. 2023. Logging classification and evaluation method for deep fracture-vuggy carbonate reservoir. //2023 International Conference on Exploration and Development of Oil and Gas Fields II (in Chinese). Wuhan, 330-337, doi: 10.26914/c.cnkihy.2023.059458.
Yang X Q , Zhang P , Xiong Z D , et al. Fracture identification of electrical imaging logging based on target detection and transfer learning. Computer Knowledge and Technology, 2021, 17(36): 32- 36.
https://doi.org/10.14004/j.cnki.ckt.2021.3549
Ye C T , Qiu H T . Research on the application of petroleum logging technology in reservoir description. Petrochemical Industry Technology, 2024, 31(6): 132- 134.
Zhang H , Wang L , Sima L Q , et al. Characterization of fractures and vugs by electrical imaging based on image region segmentation and convolutional neural network. Oil Geophysical Prospecting, 2021, 56(4): 698- 706. 698-706, 735
https://doi.org/10.13810/j.cnki.issn.1000-7210.2021.04.003
Zhang H J , Zhou L Y . Research on the extraction of incline fracture of ultrasonic logging image. Journal of Optoelectronics·Laser, 2019, 30(6): 654- 658.
https://doi.org/10.16136/j.joel.2019.06.0349
Zhang M Z . Identification method for oil-gas reservoirs based on fluid elastic impedance inversion. Progress in Geophysics, 2016, 31(6): 2717- 2723.
https://doi.org/10.6038/pg20160648
Zhang Q , Zhu X M , Mao L , et al. Pore evolution and genesis of secondary pores in the Paleogene Dainan Formation, Jinhu Sag, Subei Basin. Earth Science Frontiers, 2021, 28(1): 190- 201.
https://doi.org/10.13745/j.esf.sf.2020.5.18
Zhang Q H , Shi Y P , Chen Y L . Automatic identification of crack in imaging logging based on cellular automaton. Journal of Xi'an University of Science and Technology, 2012, 32(6): 772- 775.
https://doi.org/10.13800/j.cnki.xakjdxxb.2012.06.005
Zhang S Y , Fan Y R , Li H Y . Karst carbonate reservoir division and contrast based on natural gamma ray spectrometry logging in Tahe Oilfield. Journal of China University of Petroleum, 2006, 30(6): 35- 41.
Zhang T , Zhang X L , Yang L J . Research on recognizing the types of oil and gas reservoirs by resilient BP neural network. Sci-Tech Information Development and Economy, 2010, 20(6): 142- 144.
Zhang X B , Cheng G D , Zhao J L , et al. Research on classification and evaluation of Chang 3 reservoir in H area based on BP neural network technology. Progress in Geophysics, 2023, 38(3): 1272- 1281.
https://doi.org/10.6038/pg2023HH0111
董 少群 , 曾 联波 , 车 小花 , 等. 人工智能在致密储层裂缝测井识别中的应用. 地球科学, 2023, 48(7): 2443- 2461.
https://doi.org/10.3799/dqkx.2022.088
Cited in this article [1]
杜 小强 , 刘 鑫 , 薛 志波 , 等. 基于深度学习的电成像测井裂缝自动识别方法初探. 化工管理, 2019,(24): 204- 205.
Cited in this article [1]
樊 永东 , 庞 惠文 , 金 衍 , 等. 基于成像测井的孔缝智能分割与识别. 石油钻采工艺, 2022, 44(4): 500- 505.
https://doi.org/10.13639/j.odpt.2022.04.015
Cited in this article [1]
韩 博华 , 王 飞 , 刘 倩茹 , 等. 测井储层分类评价方法研究进展综述. 地球物理学进展, 2021, 36(5): 1966- 1974.
https://doi.org/10.6038/pg2021EE0431
Cited in this article [1]
何 艺 . 声波远探测技术在石油储层识别中的作用与影响. 中国石油和化工标准与质量, 2023, 43(24): 175- 177.
Cited in this article [1]
蒋 沛凡 , 邓 飞 , 严 星 . 基于Swin Transformer特征提取的微地震初至拾取方法. 地球物理学进展, 2023, 38(3): 1132- 1142.
https://doi.org/10.6038/pg2023GG0357
Cited in this article [1]
李 冰涛 , 王 志章 , 孔 垂显 , 等. 基于成像测井的裂缝智能识别新方法. 测井技术, 2019, 43(3): 257- 262.
https://doi.org/10.16489/j.issn.1004-1338.2019.03.007
Cited in this article [1]
刘 鑫 , 赵 慧杰 , 武 苏雯 . 基于U-Net的岩层图像裂缝检测算法应用. 计算机技术与发展, 2021, 31(5): 73- 78.
https://doi.org/10.3969/j.issn.1673-629X.2021.05.013
Cited in this article [1]
刘 宇 , 王 亮 , 罗 洋 , 等. 川中地区茅口组碳酸盐岩储层类型测井识别. 物探与化探, 2024, 48(3): 629- 639.
https://doi.org/10.11720/wtyht.2024.1289
Cited in this article [1]
陆 敬安 , 伍 忠良 , 关 晓春 , 等. 成像测井中的裂缝自动识别方法. 测井技术, 2004, 28(2): 115- 117. 115-117, 179
https://doi.org/10.16489/j.issn.1004-1338.2004.02.008
Cited in this article [1]
马 晨 , 黄 捍东 , 梁 书义 , 等. 复杂油气藏储层预测方法综述. 中国海上油气, 2024, 36(2): 87- 97.
https://doi.org/10.11935/j.issn.1673-1506.2024.02.008
Cited in this article [1]
马 同乐 , 刘 红岐 , 廖 海博 , 等. 融合通道和空间交叉注意力的裂缝识别方法. 地球物理学进展, 2024, 39(2): 727- 736.
https://doi.org/10.6038/pg2024HH0144
Cited in this article [1]
彭 诚 , 邹 长春 . 基于改进蚁群算法的成像测井裂缝自动提取方法. 计算机工程, 2015, 41(8): 196- 201.
Cited in this article [1]
孙 中良 , 李 志明 , 申 宝剑 , 等. 核磁共振技术在页岩油气储层评价中的应用. 石油实验地质, 2022, 44(5): 930- 940.
https://doi.org/10.11781/sysydz202205930
Cited in this article [1]
夏 文鹤 , 朱 喆昊 , 韩 玉娇 , 等. 电阻率测井成像图井壁裂缝智能识别与分割方法. 石油地球物理勘探, 2023, 58(5): 1042- 1052.
https://doi.org/10.13810/j.cnki.issn.1000-7210.2023.05.002
Cited in this article [4]
杨帆, 张树东, 李亚旭, 等. 2023. 深层缝洞型碳酸盐岩储层测井分类评价方法. //2023油气田勘探与开发国际会议论文集Ⅱ. 武汉, 330-337, doi: 10.26914/c.cnkihy.2023.059458.
Cited in this article [1]
杨 晓倩 , 张 萍 , 熊 振东 , 等. 基于目标检测和迁移学习的电成像测井裂缝识别. 电脑知识与技术, 2021, 17(36): 32- 36.
https://doi.org/10.14004/j.cnki.ckt.2021.3549
Cited in this article [1]
叶 传涛 , 邱 海涛 . 石油测井技术在油藏描述中的应用研究. 石化技术, 2024, 31(6): 132- 134.
Cited in this article [1]
张 浩 , 王 亮 , 司马 立强 , 等. 基于图像区域分割和卷积神经网络的电成像缝洞表征. 石油地球物理勘探, 2021, 56(4): 698- 706. 698-706, 735
https://doi.org/10.13810/j.cnki.issn.1000-7210.2021.04.003
Cited in this article [1]
张 豪洁 , 周 箩鱼 . 超声测井图像过井裂缝提取算法研究. 光电子·激光, 2019, 30(6): 654- 658.
https://doi.org/10.16136/j.joel.2019.06.0349
Cited in this article [1]
张 明振 . 基于流体弹性阻抗反演的储层含油气性识别方法. 地球物理学进展, 2016, 31(6): 2717- 2723.
https://doi.org/10.6038/pg20160648
Cited in this article [1]
张 琴 , 朱 筱敏 , 毛 凌 , 等. 苏北盆地金湖凹陷古近系戴南组孔隙演化及次生孔隙成因分析. 地学前缘, 2021, 28(1): 190- 201.
https://doi.org/10.13745/j.esf.sf.2020.5.18
Cited in this article [1]
张 群会 , 师 玉璞 , 陈 有兰 . 成像测井裂缝自动识别元胞自动机方法研究. 西安科技大学学报, 2012, 32(6): 772- 775.
https://doi.org/10.13800/j.cnki.xakjdxxb.2012.06.005
Cited in this article [1]
张 松扬 , 范 宜仁 , 李 会银 . 基于自然伽马能谱测井的岩溶型碳酸盐岩储层层位划分与对比. 中国石油大学学报(自然科学版), 2006, 30(6): 35- 41.
Cited in this article [1]
张 涛 , 张 小莉 , 杨 立娟 . 弹性BP神经网络识别油气储层类型的研究. 科技情报开发与经济, 2010, 20(6): 142- 144.
Cited in this article [1]
张 晓博 , 程 国栋 , 赵 军龙 , 等. 基于BP神经网络技术的H区长3储层分类评价研究. 地球物理学进展, 2023, 38(3): 1272- 1281.
https://doi.org/10.6038/pg2023HH0111
Cited in this article [1]

感谢审稿专家提出的修改意见和编辑部的大力支持！

RIGHTS & PERMISSIONS

Copyright ©2026 Progress in Geophysics. All rights reserved.
PDF(3265 KB)

Accesses

Citation

Detail
Sections
Recommended

/

〈 〉