Application of Interpretable Machine-Learning Workflows To Identify Brittle, Fracturable, and Producible Rock in Horizontal Wells Using Surface Drilling Data
- Ngoc Lam Tran (University of Oklahoma) | Ishank Gupta (University of Oklahoma) | Deepak Devegowda (University of Oklahoma) | Vikram Jayaram (Pioneer Natural Resources) | Hamidreza Karami (University of Oklahoma) | Chandra Rai (University of Oklahoma) | Carl H. Sondergeld (University of Oklahoma)
- Document ID
- Society of Petroleum Engineers
- SPE Reservoir Evaluation & Engineering
- Publication Date
- August 2020
- Document Type
- Journal Paper
- 2020.Society of Petroleum Engineers
- natural fractures, SHAP, MSEEL, complex versus planar fractures, frac hits
- 49 in the last 30 days
- 49 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 35.00|
In this study, we demonstrate the application of an interpretable (or explainable) machine-learning workflow using surface drilling data to identify fracturable, brittle, and productive rock intervals along horizontal laterals in the Marcellus Shale. The results are supported by a thorough model-agnostic interpretation of the input/output relationships to make the model explainable to users. The methodology described here can easily be generalized to real-time processing of surface drilling data for optimal landing of laterals, placing of fracture stages, optimizing production, and minimizing fracture hits. In practice, this information is rarely available in real time and requires tedious and time-consuming processing of logs (including image logs), core, microseismic data, and fiber-optic-sensor data to provide post-job validation of fracture and well placement. Post-completion analyses are generally too late for corrective action, leading to wells with a low probability of success and increasing risk of fracture hits. Our workflow involves identifying geomechanical facies from core and well-log data. We verify that the geomechanical facies derived using core and well-log data have characteristically different brittleness, fracturability, and production characteristics. We test and investigate several different supervised classifiers to relate surface drilling data to the geomechanical facies. The data were divided into training and test data sets, with supervised classification techniques being able to accurately predict the geomechanical facies with 75% accuracy on the test data set. The clusters predicted on test well (unseen data) were qualitatively verified using the microseismic interpretation. The use of Shapley additive explanations (SHAP) helps explain the predictive models, rank the importance of various inputs in the prediction of the facies, and provides both local and global sensitivities. Our study demonstrates that pre-existing natural-fracture networks control both the hydraulic-fracture geometry as well as the production. Natural fractures promote the formation of complex fracture networks with shorter half-lengths, which increase well productivity while minimizing fracture hits and neighboring-well interactions. The natural-fracture network is itself controlled by the geomechanical properties of the rock. The ability of the surface drilling data to reliably predict the geomechanical rock facies provides a powerful tool for real-time optimization of wellbore trajectory and completions.
|File Size||9 MB||Number of Pages||15|
Abukhamsin, A. Y. 2017. Inflow Profiling and Production Optimization in Smart Wells Using Distributed Acoustic and Temperature Measurements. PhD dissertation, Stanford University, Stanford, California, USA (June 2017).
Alshaikh, A., Magana-Mora, A., Al Gharbi, S. et al. 2019. Machine Learning for Detecting Stuck Pipe Incidents: Data Analytics and Models Evaluation. Paper presented at the International Petroleum Technology Conference, Beijing, China, 26–28 March. IPTC-19394-MS. https://doi.org/10.2523/IPTC-19394-MS.
Altman, N. S. 1992. An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. Am Stat 46 (3): 175–185. https://doi.org/10.2307/2685209.
Barnett, V. and Lewis, T. 1995. Outliers in Statistical Data, third edition. Chichester, UK: John Wiley & Sons.
Birch, F. 1966. Compressibility, Elastic Constants. In Handbook of Physical Constants, Memoir 97, ed. S. P. Clark Jr., Chap. 7, 97–173. Boulder, Colorado, USA: Geological Society of America.
Breiman, L. 1997. Arcing the Edge. Technical Report 486, Statistics Department, University of California, Berkeley, Berkeley, California, USA.
Breiman, L. 2001. Random Forests. Machine Learning 45: 5–32. https://doi.org/10.1023/A:1010933404324.
Carr, T., Ghahfarokhi, P., Carney, B. J. et al. 2019. Marcellus Shale Energy and Environmental Laboratory (MSEEL) Results and Plans: Improved Subsurface Reservoir Characterization and Engineered Completions. Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Denver, Colorado, USA, 22–24 July. URTEC-2019-415-MS. https://doi.org/10.15530/urtec-2019-415.
Carr, T. R., Wilson, T., Kavousi, P. et al. 2017. Insights from the Marcellus Shale Energy and Environment Laboratory (MSEEL). Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Austin, Texas, USA, 24–26 July. URTEC-2670437-MS. https://doi.org/10.15530/URTEC-2017-2670437.
El Sgher, M., Aminian, K., and Ameri, S. 2018. Contribution of Hydraulic Fracture Stage on the Gas Recovery from the Marcellus Shale. Paper presented at the SPE/AAPG Eastern Regional Meeting, Pittsburgh, Pennsylvania, USA, 7–11 October. SPE-191778-18ERM-MS. https://doi.org/10.2118/191778-18ERM-MS.
El Sgher, M., Aminian, K., and Ameri, S. 2019. The Stress Shadowing Impact on the Production Performance of Marcellus Shale. Paper presented at the SPE Annual Technical Conference and Exhibition, Calgary, Alberta, Canada, 30 September–2 October. SPE-196005-MS. https://doi.org/10.2118/196005-MS.
Evans, K., Toth, R., Ore, T. et al. 2019. Fracture Analysis Before and After Hydraulic Fracturing in the Marcellus Shale Using the Mohr-Coulomb Failure Criteria. Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Denver, Colorado, USA, 22–24 July. URTEC-2019-650-MS. https://doi.org/10.15530/urtec-2019-650.
Fawcett, T. 2006. An Introduction to ROC Analysis. Pattern Recognit Lett 27 (8): 861–874. https://doi.org/10.1016/j.patrec.2005.10.010.
Friedman, J. H. 2001. Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat. 5: 1189–1232. https://doi.org/10.1214/aos/1013203451.
Gupta, I. 2017. Rock Typing in Organic Shales: Eagle Ford, Woodford, Barnett and Wolfcamp Formations. Master's thesis, University of Oklahoma, Norman, Oklahoma, USA.
Gupta, I., Devegowda, D., Jayaram, V. et al. 2019b. Machine Learning Regressors and Their Metrics To Predict Synthetic Sonic and Mechanical Properties. Interpretation 7 (3): 1A-T725. https://doi.org/10.1190/INT-2018-0255.1.
Gupta, I., Rai, C., Sondergeld, C. et al. 2017. Rock Typing in Wolfcamp Formation. Paper presented at the SPWLA 58th Annual Logging Symposium, Oklahoma City, Oklahoma, USA, 17–21 June. SPWLA-2017-D.
Gupta, I., Tran, N., Devegowda, D. et al. 2019a. Looking Ahead of the Bit Using Surface Drilling and Petrophysical Data: Machine-Learning-Based Real-Time Geosteering in Volve Field. SPE J. 25 (2): 990–1006. SPE-199882-PA. https://doi.org/10.2118/199882-PA.
Han, J., Sun, Y., and Zhang, S. 2019. A Data Driven Approach of ROP Prediction and Drilling Performance Estimation. Paper presented at the International Petroleum Technology Conference, Beijing, China, 26–28 March. IPTC-19430-MS. https://doi.org/10.2523/IPTC-19430-MS.
Jacobs, T. 2018. Three Unconventional Startups Offer New Clues on Shale’s Biggest Well Spacing Mysteries. J Pet Technol 70 (9): 47–52. SPE-0918-0047-JPT. https://doi.org/10.2118/0918-0047-JPT.
Jacobs, T. 2019. To Solve Frac Hits, Unconventional Engineering Must Revolve Around. J Pet Technol 71 (4): 27–31. SPE-0419-0027-JPT. https://doi.org/10.2118/0419-0027-JPT.
James, G., Witten, D., Hastie, T. et al. 2013. An Introduction to Statistical Learning with Applications in R. New York, New York, USA: Springer.
Kale, S., Rai, C., and Sondergeld, C. 2010. Rock Typing in Gas Shales. Paper presented at the SPE Annual Technical Conference, Florence, Italy, 19–22 September. SPE-134539-MS. https://doi.org/10.2118/134539-MS.
Kalinec, J., Paryani, M., and Ouenes, A. 2019. Estimation of 3D Distribution of Pore Pressure from Surface Drilling Data—Application to Optimal Drilling and Frac Hit Prevention in the Eagle Ford. Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Denver, Colorado, USA, 22–24 July. URTEC-2019-511-MS. https://doi.org/10.15530/urtec-2019-511.
King, G. E. 2014. 60 Years of Multi-Fractured Vertical, Deviated and Horizontal Wells: What Have We Learned? Paper presented at the SPE Annual Technical Conference and Exhibition, Amsterdam, The Netherlands, 27–29 October. SPE-170952-MS. https://doi.org/10.2118/170952-MS.
King, G. E. and Valencia, R. L. 2016. Well Integrity for Fracturing and Re-Fracturing: What is Needed and Why? Presented at the SPE Hydraulic Fracturing Technology Conference, The Woodlands, Texas, USA, 9–11 February. SPE-179120-MS. https://doi.org/10.2118/179120-MS.
King, G. E., Rainbolt, M. F., and Swanson, C. 2017. Frac Hit Induced Production Losses: Evaluating Root Causes, Damage Location, Possible Prevention Methods and Success of Remedial Treatments. Paper presented at the SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA, 9–11 October. SPE-187192-MS. https://doi.org/10.2118/187192-MS.
Kohonen, T. and Honkela, T. 2007. Kohonen Network. Scholarpedia 2 (1): 1568. https://doi.org/10.4249/scholarpedia.1568.
Kuhn, M. 2008. Building Predictive Models in R Using the caret Package. J Stat Softw 28 (5): 1–26. https://doi.org/10.18637/jss.v028.i05.
Lawal, H., Abolo, N., Jackson, G. et al. 2014. A Quantitative Approach To Analyze Fracture Area Loss in Shale Gas Reservoirs. Paper presented at the SPE Latin America and Caribbean Petroleum Engineering Conference, Maracaibo, Venezuela, 21–23 May. SPE-169406-MS. https://doi.org/10.2118/169406-MS.
Lecun, Y., Bottou, L., Bengio, Y. et al. 1998. Gradient-Based Learning Applied To Document Recognition. Proc. IEEE 86 (11): 2278–2324. https://doi.org/10.1109/5.726791.
Litchfield, T. and Lehman, J. 2013. Inter-Well Interference During Stimulation, Flowback and Production History. SPE Slide Presentation, SPE ATW on Flowback, San Antonio, Texas, USA, 6–7 November.
Lundberg, S. M. and Lee, S. I. 2017. A Unified Approach to Interpreting Model Predictions. Proc., 31st Conference on Neural Information Processing Systems, Long Beach, California, USA, 4–9 December.
Maechler, M., Rousseeuw, P., Struyf, A. et al. 2019. Cluster: Cluster Analysis Basics and Extensions. R Package Version 2.1.0, https://cran.r-project.org/web/packages/cluster/citation.html.
Marx, T., Reid, G. W., Leung, H. et al. 2014. Methods and Systems for Improved Drilling Operations Using Real-Time and Historical Drilling Data. US Patent No. 2,014,011,677,6A1.
MSEEL. 2015. Marcellus Shale Energy and Environment Laboratory, http://mseel.org/ (accessed 5 January 2019).
Nielson, M. A. 2015. Neural Networks and Deep Learning. http://neuralnetworksanddeeplearning.com (accessed 27 April 2019).
Noshi, C. I. 2019. Application of Data Science and Machine Learning Algorithms for ROP Prediction: Turning Data into Knowledge. Paper presented at the Offshore Technology Conference, Houston, Texas, USA, 6–9 May. OTC-29288-MS. https://doi.org/10.4043/29288-MS.
Pankaj, P., Shukla, P., Kavousi, P. et al. 2018. Integrated Well Interference Modeling Reveals Optimized Well Completion and Spacing in the Marcellus Shale. Paper presented at the SPE Annual Technical Conference and Exhibition, Dallas, Texas, USA, 24–26 September. SPE-191393-MS. https://doi.org/10.2118/191393-MS.
Paryani, M., Smaoui, R., Poludasu, S. et al. 2017. Adaptive Fracturing To Avoid Frac Hits and Interference: A Wolfcamp Shale Case Study. Paper presented at the SPE Unconventional Resources Conference, Calgary, Alberta, Canada, 15–16 February. SPE-185044-MS. https://doi.org/10.2118/185044-MS.
Rainbolt, M. F. and Esco, J. 2018. Frac Hit Induced Production Losses: Evaluating Root Causes, Damage Location, Possible Prevention Methods and Success of Remediation Treatments, Part II. Paper presented at the SPE Hydraulic Fracturing Technology Conference and Exhibition, The Woodlands, Texas, USA, 23–25 January. SPE-189853-MS. https://doi.org/10.2118/189853-MS.
Rassenfoss, S. 2018. A Look into What Fractures Really Look Like. J Pet Technol 70 (11): 28–36. SPE-1118-0028-JPT. https://doi.org/10.2118/1118-0028-JPT.
Rickman, R., Mullen, M. J., Petre, J. E. et al. 2008. A Practical Use of Shale Petrophysics for Stimulation Design Optimization: All Shale Plays Are Not Clones of the Barnett Shale. Paper presented at the SPE Annual Technical Conference and Exhibition, Denver, Colorado, USA, 21–24 September. SPE-115258-MS. https://doi.org/10.2118/115258-MS.
Warpinski, N. R. 2009. Integrating Microseismic Monitoring with Well Completions, Reservoir Behavior, and Rock Mechanics. Paper presented at the SPE Tight Gas Completions Conference, San Antonio, Texas, USA, 15–17 June. SPE-125239-MS. https://doi.org/10.2118/125239-MS.
Warpinski, N. R. and Teufel, L. W. 1987. Influence of Geologic Discontinuities on Hydraulic Fracture Propagation (includes associated papers 17011 and 17074). J Pet Technol 39 (2): 209–220. SPE-13224-PA. https://doi.org/10.2118/13224-PA.
Warpinski, N. R., Branagan, P. T., Sattler, A. R. et al. 1990. Case Study of a Stimulation Experiment in a Fluvial, Tight-Sandstone Gas (includes associated papers 23475 and 23567). SPE Prod Eng 5 (4): 403–410. SPE-18258-PA. https://doi.org/10.2118/18258-PA.
Yu, Y., Liu, Q., and Chambon, S. 2019. Using Deep Kalman Filter To Predict Drilling Time Series. Paper presented at the International Petroleum Technology Conference, Beijing, China, 26–28 March. IPTC-19207-MS. https://doi.org/10.2523/IPTC-19207-MS.
Zhang, S. and Zhu, D. 2019. Inversion of Downhole Temperature Measurements in Multistage Fracturing Stimulation of Horizontal Wells in Unconventional Reservoirs. SPE Prod & Oper 35 (2): 231–244. SPE-187322-PA. https://doi.org/10.2118/187322-MS.
Zhao, T., Jayaram, V., Roy, A. et al. 2015. A Comparison of Classification Techniques for Seismic Facies Recognition. Interpretation 3 (4): SAE29–SAE58. https://doi.org/10.1190/INT-2015-0044.1.
Zheng, A. and Casari, A. 2018. Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists, first edition. Sebastopol, California, USA: O’Reilly Media.
Zhu, Y. and Carr, T. 2018. Estimation of Fracability of the Marcellus Shale: A Case Study from the MIP3H in Monongalia County, West Virginia University. Paper presented at the SPE/AAPG Eastern Regional Meeting, Pittsburgh, Pennsylvania, USA, 7–11 October. SPE-191818-18ERM-MS. https://doi.org/10.2118/191818-18ERM-MS.
Zorn, E. V., Harbert, W., Hammack, R. et al. 2017. Geomechanics of the Microseismic Response in Devonian Organic Shales at the Marcellus Shale Energy and Environment Laboratory (MSEEL) Site, West Virginia. Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Austin, Texas, USA, 24–26 July. URTEC-2669946-MS. https://doi.org/10.15530/URTEC-2017-2669946.