Deep-Learning-Based Vuggy Facies Identification from Borehole Images
- Jiajun Jiang (Baylor University) | Rui Xu (The University of Texas at Austin) | Scott C. James (Baylor University) | Chicheng Xu (Aramco Americas)
- Document ID
- Society of Petroleum Engineers
- SPE Reservoir Evaluation & Engineering
- Publication Date
- October 2020
- Document Type
- Journal Paper
- 2020.Society of Petroleum Engineers
- convolutional neural network, vuggy dolomite, facies classification, borehole image log
- 25 in the last 30 days
- 53 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 35.00|
Identification of vuggy intervals and understanding their connectivity are critical for predicting carbonate reservoir performance. Although core samples and conventional well logs have been traditionally used to classify vuggy facies, this process is labor intensive and often suffers from data inadequacies. Recently, convolutional neural network (CNN) algorithms have approached human-level performance at multiimage classification and identification tasks. In this study, CNNs were trained to identify vuggy facies from a well in the Arbuckle Group in Kansas, USA. Borehole-resistivity images were preprocessed into half-foot intervals; this complete data set was culled by removing poor-quality images to generate a cleaned data set for comparison. Core descriptions along with conventional gamma ray, neutron/density porosity, photoelectric factor (PEF), and nuclear magnetic resonance (NMR) T2 data were used to label these data sets for supervised learning. Hyperparameters defining the CNN network size (numbers of convolutional layers/filters and the numbers of fully connected layers/neurons) and minimize overfitting (dropout rates, patience, and minimum delta) were optimized. The median losses and accuracies from five Monte Carlo realizations of each hyperparameter combination were the metrics defining CNN performance. After hyperparameter optimization, median accuracy for vuggy/nonvuggy facies classification was 0.847 for the cleaned data set (0.813 for the complete data set). This study demonstrated the effectiveness of using microresistivity image logs in a CNN to classify facies as either vuggy or nonvuggy, while highlighting the importance of data quality control. This effort lays the foundation for developing CNNs to segment images to estimate vuggy porosity.
|File Size||7 MB||Number of Pages||12|
Adler, F. J., Caplan, W. M., Carlson, M. P. et al. 1971. Future Petroleum Provinces of the Mid-Continent, Region 7. In Future Petroleum Provinces of the United States—Their Geology and Potential, Vol. 2, 985–1042. Tulsa, Oklahoma, USA: American Association of Petroleum Geologists.
Alberti, M., Pondenkandath, V., Würsch, M. et al. 2018. DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments. Paper presented at the 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Niagara Falls, New York, USA, 5–8 August. https://doi.org/10.1109/ICFHR-2018.2018.00080.
Ausbrooks, R., Hurley, N. F., May, A. et al. 1999. Pore-Size Distributions in Vuggy Carbonates from Core Images, NMR, and Capillary Pressure. Paper presented at the SPE Annual Technical Conference and Exhibition, Houston, Texas, USA, 3–6 October. SPE-56506-MS. https://doi.org/10.2118/56506-MS.
Bergen, K. J., Johnson, P. A., de Hoop, M. V. et al. 2019. Machine Learning for Data-Driven Discovery in Solid Earth Geoscience. Science 363 (6433): eaau0323. https://doi.org/10.1126/science.aau0323.
Chen, M. C., Ball, R. L., Yang, L. et al. 2018. Deep Learning To Classify Radiology Free-Text Reports. Radiology 286 (3): 845–852. https://doi.org/10.1148/radiol.2017171115.
Choquette, P. W. and Pray, L. C. 1970. Geologic Nomenclature and Classification of Porosity in Sedimentary Carbonates. AAPG Bull 54 (2): 207–250. https://doi.org/10.1306/5D25C98B-16C1-11D7-8645000102C1865D.
Cole, V. B. 1975. Subsurface Ordovician-Cambrian Rocks in Kansas. Subsurface Geol Ser 2 2: P18. http://www.kgs.ku.edu/Publications/Bulletins/Sub2/.
Cunningham, K. J., Carlson, J. I., and Hurley, N. F. 2004. New Method for Quantification of Vuggy Porosity from Digital Optical Borehole Images as Applied to the Karstic Pleistocene Limestone of the Biscayne Aquifer, Southeastern Florida. J Appl Geophys 55 (1–2): 77–90. https://doi.org/10.1016/j.jappgeo.2003.06.006.
Deng, T., Xu, C., Jobe, D. et al. 2019. A Comparative Study of Three Supervised Machine-Learning Algorithms for Classifying Carbonate Vuggy Facies in the Kansas Arbuckle Formation. Petrophysics 60 (6): 838–853. SPWLA-2019-v60n6a8. https://doi.org/10.30632/pjv60n6-2019a8.
Doveton, J. and Watney, L. 2015. Textural and Pore Size Analysis of Carbonates from Integrated Core and Nuclear Magnetic Resonance Logging: An Arbuckle Study. Interpretation 3 (1): SA77–SA89. https://doi.org/10.1190/INT-2014-0050.1.
Franseen, E. K. and Byrnes, A. P. 2012. Great American Carbonate Bank: The Geology and Economic Resources of the Cambrian—Ordovician Sauk Megasequence of Laurentia. Tulsa, Oklahoma, USA: American Association of Petroleum Geologists.
He, K., Zhang, X., Ren, S. et al. 2016. Deep Residual Learning for Image Recognition. Paper presented at the 29th IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, 26 June–1 July. https://doi.org/10.1109/cvpr.2016.90.
Hu, F., Xia, G.-S., Hu, J. et al. 2015. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery. Remote Sens 7 (11): 14680–14707. https://doi.org/10.3390/rs71114680.
James, S. C., Zhang, Y., and O’Donncha, F. 2018. A Machine Learning Framework To Forecast Wave Conditions. Coastal Eng 137: 1–10. https://doi.org/10.1016/j.coastaleng.2018.03.004.
Jobe, T. D., Vital-Brazil, E., and Khait, M. 2018. Geological Feature Prediction Using Image-Based Machine Learning. Petrophysics 59 (6): 750–760. SPWLA-2018-v59n6a1. https://doi.org/10.30632/PJV59N6-2018a1.
Jungmann, M., Kopal, M., Clauser, C. et al. 2011. Multi-Class Supervised Classification of Electrical Borehole Wall Images Using Texture Features. Comput Geosci 37 (4): 541–553. https://doi.org/10.1016/j.cageo.2010.08.008.
Kalchbrenner, N., Grefenstette, E., and Blunsom, P. 2014. A Convolutional Neural Network for Modelling Sentences. Paper presented at the 52nd Annual Meeting of the Association for Confrontational Linguistics, Baltimore, Maryland, USA, 22 June. https://doi.org/10.3115/v1/p14-1062.
Keroher, R. P. and Kirby, J. J. 1948. Upper Cambrian and Lower Ordovician Rocks in Kansas. Lawrence, Kansas, USA: University of Kansas Publications.
Krizhevsky, A., Sutskever, I., and Hinton, G. E. 2012. ImageNet Classification with Deep Convolutional Neural Networks. Commun ACM 60 (6): 1097–1105. https://doi.org/10.1145/3065386.
Lary, D. J., Alavi, A. H., Gandomi, A. H. et al. 2016. Machine Learning in Geosciences and Remote Sensing. Geosci Front 7 (1): 3–10. https://doi.org/10.1016/j.gsf.2015.07.003.
LeCun, Y. and Bengio, Y. 1995. Convolutional Networks for Images, Speech, and Time Series. In The Handbook of Brain Theory and Neural Networks, ed. M. A. Arbib. Cambridge, Massachusetts, USA: MIT Press.
LeCun, Y., Bengio, Y., and Hinton, G. 2015. Deep Learning. Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Lee, H. and Kwon, H. 2017. Going Deeper with Contextual CNN for Hyperspectral Image Classification. IEEE Trans Image Process 26 (10): 4843–4855. https://doi.org/10.1109/TIP.2017.2725580.
Li, B., Tan, X., Wang, F. et al. 2017. Fracture and Vug Characterization and Carbonate Rock Type Automatic Classification Using X-Ray CT Images. J Pet Sci Eng 153: 88–96. https://doi.org/10.1016/j.petrol.2017.03.037.
Lønøy, A. 2006. Making Sense of Carbonate Pore Systems. AAPG Bull 90 (9): 1381–1405. https://doi.org/10.1306/03130605104.
Lucia, F. J. 1983. Petrophysical Parameters Estimated from Visual Descriptions of Carbonate Rocks: A Field Classification of Carbonate Pore Space. J Pet Technol 35 (3): 629–637. SPE-10073-PA. https://doi.org/10.2118/10073-PA.
Lucia, F. J. 1995. Rock-Fabric/Petrophysical Classification of Carbonate Pore Space for Reservoir Characterization. AAPG Bull 79 (9): 1275–1300. https://doi.org/10.1306/7834D4A4-1721-11D7-8645000102C1865D.
Marrone, S., Olivieri, S., Piantadosi, G. et al. 2019. Reproducibility of Deep CNN for Biomedical Image Processing across Frameworks and Architectures. Paper presented at the 27th European Signal Processing Conference (EUSIPCO), A Coruña, Spain, 2–6 September. https://doi.org/10.23919/EUSIPCO.2019.8902690.
Misra, S., Li, H., and He, J. 2019. Generalization of Machine Learning Assisted Segmentation of Scanning Electron Microscopy Images of Organic-Rich Shales. In Machine Learning for Subsurface Characterization, Chap. 11, 315–338. Houston, Texas, USA: Gulf Professional Publishing. https://doi.org/10.1016/C2018-0-01926-X.
Newberry, B. M., Grace, L. M., and Stief, D. O. 1996. Analysis of Carbonate Dual Porosity Systems from Borehole Electrical Images. Paper presented at the Permian Basin Oil and Gas Recovery Conference, Midland, Texas, USA, 27–29 March. SPE-35158-MS. https://doi.org/10.2118/35158-MS.
Pan, S. J. and Yang, Q. 2010. A Survey on Transfer Learning. IEEE Trans Knowl Data Eng 22 (10): 1345–1359. https://doi.org/10.1109/TKDE.2009.191.
Ross, R. J. Jr. 1976. Ordovician Sedimentation in the Western United States. In The Ordovician System, ed. M. G. Bassett, 73–105. Cardiff, Wales, UK: University of Wales Press.
Russakovsky, O., Deng, J., Su, H. et al. 2015. ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vision 115 (3): 211–252. https://doi.org/10.1007/s11263-015-0816-y.
Simonyan, K. and Zisserman, A. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. https://arxiv.org/abs/1409.1556.
Srivastava, N., Hinton, G., Krizhevsky, A. et al. 2014. Dropout: A Simple Way To Prevent Neural Networks from Overfitting. J Mach Learn Res 15 (1): 1929–1958. https://dl.acm.org/doi/abs/10.5555/2627435.2670313.
Steinhauff, M., Franseen, E. K., and Byrnes, A. 1998. Arbuckle Reservoirs in Central Kansas—Relative Importance of Depositional Facies, Early Diagenesis and Unconformity Karst Processes on Reservoir Properties. Open-File Report, 98-55. Kansas Geological Survey, Lawrence, Kansas, USA.
Szegedy, C., Ioffe, S., Vanhoucke, V. et al. 2017. Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Paper presented at the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, California, USA, 4–9 February. https://arxiv.org/abs/1602.07261.
Tilke, P. G., Allen, D., and Gyllensten, A. 2006. Quantitative Analysis of Porosity Heterogeneity: Application of Geostatistics to Borehole Images. Math Geol 38 (2): 155–174. https://doi.org/10.1007/s11004-005-9011-y.
USGS. 2006. FGDC Digital Cartographic Standard for Geologic Map Symbolization (PostScript Implementation). USGS Numbered Series Report, USGS, Reston, Virginia, USA. https://doi.org/10.3133/tm11a2.
Vik, B., Djurhuus, K., Spildo, K. et al. 2007. Characterisation of Vuggy Carbonates. Paper presented at the SPE/EAGE Reservoir Characterization and Simulation Conference, Abu Dhabi, UAE, 28–31 October. SPE-111434-MS. https://doi.org/10.2118/111434-MS.
Walters, R. F. 1958. Differential Entrapment of Oil and Gas in Arbuckle Dolomite of Central Kansas. AAPG Bull 42 (9): 2133–2173. https://doi.org/10.1306/0BDA5BAF-16BD-11D7-8645000102C1865D.
Wilson, J. L., Fritz, R. D., and Medlock, P. L. 1991. The Arbuckle Group: Relationship of Core and Outcrop Analyses to Cyclic Stratigraphy and Correlation. Special Publication 91-3, Oklahoma Geological Survey, Norman, Oklahoma, USA.
Witten, I. H., Frank, E., Hall, M. A. et al. 2016. Data Mining: Practical Machine Learning Tools and Techniques. Burlington, Massachusetts, USA: Morgan Kaufmann.
Wu, X., Liang, L., Shi, Y. et al. 2019. FaultSeg3D: Using Synthetic Data Sets To Train an End-to-End Convolutional Neural Network for 3D Seismic Fault Segmentation. Geophysics 84 (3): IM35–IM45. https://doi.org/10.1190/geo2018-0646.1.
Wu, Y. and Misra, S. 2020. Intelligent Image Segmentation for Organic-Rich Shales Using Random Forest, Wavelet Transform, and Hessian Matrix. IEEE Geosci Remote Sens Lett 17 (7): 1144–1147. https://doi.org/10.1109/LGRS.2019.2943849.
Xu, C., Misra, S., Srinivasan, P. et al. 2019. When Petrophysics Meets Big Data: What Can Machine Do? Paper presented at the SPE Middle East Oil and Gas Show and Conference, Manama, Bahrain, 18–21 March. SPE-195068-MS. https://doi.org/10.2118/195068-MS.
Xu, R., Deng, T., Jiang, J. et al. 2020. Integration of NMR and Conventional Logs for Vuggy Facies Classification in the Arbuckle Formation: A Machine Learning Approach. SPE Res Eval & Eng 23 (3): 917–929. SPE-201102-PA. https://doi.org/10.2118/201102-PA.
Yamashita, R., Nishio, M., Do, R. K. G. et al. 2018. Convolutional Neural Networks: An Overview and Application in Radiology. Insights Imaging 9 (4): 611–629. https://doi.org/10.1007/s13244-018-0639-9.
Zhang, P. Y., Sun, J. M., Jiang, Y. J. et al. 2017. Deep Learning Method for Lithology Identification from Borehole Images. Paper presented at the EAGE Conference and Exhibition, Paris, France, 12–15 June. https://doi.org/10.3997/2214-4609.201700945.