Abstract
Fractures play a crucial role in discovering and developing petroleum reserves. However, traditional logging techniques face significant challenges in identifying fractures. To address such challenges, this article proposes a new method that combines conventional logging data with a small amount of marker data from cores and image logs to identify fracture development in reservoirs with high accuracy and fast operation. The proposed method is based on the improved YOLOv5, which offers a new idea for fracture identification. The fracture data from the carbonate rocks of the Sulige gas field in the Ordos Basin were used for training and validation. Finally, positive experimental outcomes were achieved, demonstrating the usefulness of the improved YOLOv5 algorithm in detecting fracture development in carbonate rocks.
Similar content being viewed by others
Data availability
The data supporting the reserach results can be obtained from China Petroleum Changqing Oilfield Exploration and Development Research Institute, but the availability of these data is limited. These data are used under the permission of the current research, so they are not disclosed. However, the author can provide data according to reasonable requirements and with the permission of China Petroleum Changqing Oilfield Exploration and Development Research Institute. If anyone wants to obtain data from this study, please contact the corresponding author Zhang Yuanpei.
References
Chen, Y., Li, H., Gao, R., & Zhao, D. (2020). Boost 3-D object detection via point clouds segmentation and fused 3-D GIoU-Loss. IEEE Transactions on Neural Networks and Learning Systems, 33(2), 762–773.
Cong, R., Wu, J. Q., & Li, C. H. (2020). Analysis of conventional logging curve fracture identification in medium and high permeability reservoirs. Contemporary Chemical Industry, 49(03), 674–677.
Dong, S. Q., Zeng, L. B., & Che, X. H. (2022). Application of artificial intelligence in fracture logging identification of dense reservoirs. Earth Science, 1–23.
Dong, S. Q., Zeng, L. B., Lyu, W. Y., Xu, C., Liu, J., Mao, Z., Tian, H., & Sun, F. (2020). Fracture identification by semi-supervised learning using conventional logs in tight sandstones of Ordos Basin, China. Journal of Natural Gas Science and Engineering, 76(C), 103131.
Du, G. C., Hu, S. Q., & Cang, H. (2016). Identification method and application of conventional logging curves for low-angle fractures in carbonate reservoirs. Journal of Engineering Geophysics, 13(05), 590–594.
Han, G., He, F., & Zhang, H. J. (2019). Application of array acoustic logging in reservoir fracture identification - An example of K area in Ordos Basin. Oil and Gas Geology and Recovery, 26(03), 63–69.
Hu, S. (2013). Study on the classification method of fractured carbonate reservoirs in Puguang area. Western Prospecting Engineering, 25(05), 49–54.
Ji, Z. Y., & Wang, Y. S. (2022). An algorithm for water column signal detection at sea impact point based on improved YOLOV5. Electro-Optics and Control, 1–10.
Li, J. W., Wang, L., Chen, L. W., & Hua, A. J. (2013). Study of fracture identification techniques in carbonate reservoirs. Journal of Engineering Geophysics, 10(06), 885–890.
Lin, J. Q., Meng, X., & Li, Q. Q. (2022). Electrical imaging logging characterization method and application for conglomerate reservoirs-An example of conglomerate reservoirs in Mahu Depression, Junggar Basin. Petroleum Drilling Technology, 50(02), 126–131.
Qiu, T. H., Wang, L., Wang, P., & Bai, Y. E. (2022). Research on improved YOLOv5-based target detection algorithm. Computer Engineering and Applications, 58(13), 63–73.
Réda, S. Z. (2013). Fracture density estimation from core and conventional well logs data using artificial neural networks: The Cambro-Ordovician reservoir of Mesdar oil. Journal of African Earth Sciences, 83, 55–73.
Ren, J. (2020). Conventional logging evaluation method for fractured carbonate reservoirs. Fractured Reservoirs, 32(06), 129–137.
Su, G. L., & Deng, F. P. (2003). On the improvement algorithm of BP neural network based on MATLAB language. Science and Technology Bulletin, 02, 130–135.
Sun, L. Y., Ling, Z. B., & Wang, Y. Z. (2022). An improved YOLOv5-based method for identifying power transmission towers in remote sensing images. Experimental Technology and Management, 39(04), 19–24.
Tu, X. Y. (2020). Characterization of karst in the Eagle Mountain Formation based on imaging logging towers. Contemporary Chemical Industry, 49(04), 672–675.
Wang, Q., Cheng, M., Huang, S., Cai, Z., Zhang, J., & Yuan, H. (2022a). A deep learning approach incorporating YOLOv5 and attention mechanisms for field real-time detection of the invasive weed Solanum rostratum Dunal seedlings. Computers and Electronics in Agriculture, 199, 107194.
Wang, S. Q., Dong, W. C., & Huang, J. F. (2022b). Tile surface defect detection based on YOLOv5. Packaging Engineering, 43(09), 217–224.
Wu, Z. Y., Mo, X. W., Liu, J. H., & Hu, G. S. (2018). Convolutional neural network algorithm for classification evaluation of fractured reservoirs. Geophysical Prospecting for Petroleum, 57(4), 618–626.
Xiao, X. L., Jin, X. J., Zhang, X., Liu, H. L., & Jiang, Y. W. (2015). Fracture identification based on multi-information fusion of conventional logging and electrical imaging logging. Petroleum Geophysical Exploration, 50(03), 542–547.
Xu, P., Zhang, C. G., & Zhu, L. (2017). Reservoir fracture evaluation method based on core physical data and imaging data. Journal of Changjiang University (Self Science Edition), 14(03), 21–24.
Xu, J., Ma, Y., He, S., & Zhu, J. (2019). 3D-GIoU: 3D generalized intersection over union for object detection in point cloud. Sensors, 19(19), 4093.
Yang, L., Shi, C., Wei, L., Zhang, J., Wang, X., & Xu, S. (2020). Application of conventional logging interpretation fracture method based on neural network in offshore Oilfield L. IOP Conference Series: Earth and Environmental Science, 569(1), 12102. https://doi.org/10.1088/1755-1315/569/1/012102
Zhang, H. C., Zhang, M., Bian, L. M., Ge, Y. F., & Li, X. P. (2022). YOLOv5-based estimation and visualization of plant chlorophyll content. Journal of Agricultural Machinery, 1–14.
Acknowledgements
This work was supported by the Natural Science Foundation of Shandong Province (No. ZR2022MD033).
Funding
This work was supported by the Natural Science Foundation of Shandong Province (No. ZR2022MD033).
Author information
Authors and Affiliations
Contributions
Author 1 (First Author): Investigation, Formal Analysis, Writing - Original Draft; Author 2: Conceptualization, Methodology, Software, Data Curation, Writing - Original Draft; Author 3: Visualization, Investigation; Author 4: Resources, Supervision; Author 5: Software, Validation Author 6: Visualization, Writing - Review & Editing
Corresponding author
Ethics declarations
Conflict of interest
The authors have not disclosed any competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xie, J., Gao, R., Zhang, Y. et al. Carbonate Rock Fracture Identification Method Based on an Improved YOLOv5 Algorithm. Pure Appl. Geophys. 181, 189–201 (2024). https://doi.org/10.1007/s00024-023-03408-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00024-023-03408-6