Machine Learning Assisted Lithology Prediction Utilizing Toeplitz Inverse Covariance-Based Clustering (TICC)
Publication: Geo-Extreme 2021
ABSTRACT
The success of wells is heavily reliant on accurate identification of the formation being drilled. Lithology prediction allows us to foresee the target interval ahead of schedule to ensure maximum contact with the producing zone. By viewing the drilling process as a multivariate time series, algorithms such as Toeplitz Inverse Covariance-Based Clustering (TICC) can be deployed to generate a refined dataset for supervised deep learning models such as Long Short-Term Memory (LSTM). The present study combines labeled dataset generation through the TICC algorithm and predictive time-series classification via deep learning models to determine the formation ahead of the sensors. The well trajectory can be re-evaluated in real time to foresee what the drill bit will encounter in advance, allowing directional drillers to optimize well placement and ultimately production. This methodology can be implemented across all disciplines where real-time data analysis is necessary for immediate decision making such as anomaly detection, predictive modeling, and risk assessment.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Al-Khdheeawi, E. A., Mahdi, D. S., and Feng, R. (2019). ‘Lithology determination from drilling data using artificial neural network’, 53rd U.S. Rock Mechanics/Geomechanics Symposium.
Azike, O. (2011). ‘Multi-Well Real-Time 3D Structure Modeling and Horizontal Well Placement: An Innovative Workflow for Shale Gas Reservoirs’, in SPE Eastern Regional Meeting. Society of Petroleum Engineers. doi: https://doi.org/10.2118/148609-MS.
Bartosik, S., and Amirlatifi, A. (2020). ‘Machine Learning Assisted Geosteering’, in 54th U.S. Rock Mechanics/Geomechanics Symposium. American Rock Mechanics Association (ARMA). Available at: https://www.onepetro.org/conference-paper/ARMA-2020-1662.
Belozerov, B., et al. (2018). ‘Automatic well log analysis across priobskoe field using machine learning methods’, Society of Petroleum Engineers - SPE Russian Petroleum Technology Conference 2018, RPTC 2018. doi: https://doi.org/10.2118/191604-18rptc-ru.
Bond, C. E. (2015). ‘Uncertainty in structural interpretation: Lessons to be learnt’, Journal of Structural Geology. Elsevier Ltd, 74, pp. 185–200. doi: https://doi.org/10.1016/j.jsg.2015.03.003.
Gupta, A., and Soumya, U. (2020). ‘Well Log Interpretation Using Deep Learning Neural Networks’, (January), pp. 13–15. doi: https://doi.org/10.2523/iptc-19678-abstract.
Gupta, I., et al. (2020). ‘Looking Ahead of the Bit Using Surface Drilling and Petrophysical Data: Machine-Learning-Based Real-Time Geosteering in Volve Field’, SPE Journal, (June 2019), pp. 1–17. doi: https://doi.org/10.2118/199882-pa.
Hallac, D., et al. (2018). ‘Toeplitz inverse covariance-based clustering of multivariate time series data’, IJCAI International Joint Conference on Artificial Intelligence, 2018-July, pp. 5254–5258. doi: https://doi.org/10.24963/ijcai.2018/732.
Hallac, D., Nystrup, P., and Boyd, S. (2019). ‘Greedy Gaussian segmentation of multivariate time series’, Advances in Data Analysis and Classification, 13(3), pp. 727–751. doi: https://doi.org/10.1007/s11634-018-0335-0.
Hastie, T., Tibshirani, R., and Friedman, J. (2008). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd edn. Stanford, California: Springer. Available at: https://www.barnesandnoble.com/w/elements-of-statistical-learning-trevor-hastie/1100042550 (Accessed: 6 February 2021).
Hinton, G. E., Srivastava, N., and Swersky, K. (2012). Neural Networks for Machine Learning Lecture 6a Overview of mini-batch gradient descent., COURSERA: Neural Networks for Machine Learning. Toronto.
Hoeink, T., and Zambrano, C. (2017). ‘Shale discrimination with machine learning methods’, 51st US Rock Mechanics/Geomechanics Symposium 2017, 4, pp. 2840–2845.
Ma, Y. Z. (2011). ‘Lithofacies clustering using principal component analysis and neural network: Applications to wireline logs’, Mathematical Geosciences, 43(4), pp. 401–419. doi: https://doi.org/10.1007/s11004-011-9335-8.
Macpherson, J. D., et al. (2013). ‘Drilling-Systems Automation: Current State, Initiatives, and Potential Impact’, SPE Drilling & Completion, 28(04), pp. 296–308. doi: https://doi.org/10.2118/166263-PA.
Maus, S., et al. (2020). ‘Automated geosteering with fault detection and multi-solution tracking’, SPE/IADC Drilling Conference, Proceedings, 2020-March. doi: https://doi.org/10.2118/199660-ms.
Peyret, A.-P., Ambia, J., and Torres-Verdin, C. (2019). ‘a Machine Learning Framework for Automating Well’, Presented at the SPWLA 60th Annual Logging Symposium, Woodlands, June 15-19., pp. 1–10. doi: https://doi.org/10.30632/T60ALS-2019.
Pitcher, J., and Jackson, T. (2012). ‘Geosteering in unconventional shales: Current practice and developing methodologies’, in Society of Petroleum Engineers - SPE/EAGE European Unconventional Resources Conference and Exhibition 2012. doi: https://doi.org/10.2118/152580-ms.
Rogers, S. J., et al. (1992). ‘Determination of lithology from well logs using a neural network’, American Association of Petroleum Geologists Bulletin, 76(5). doi: https://doi.org/10.1016/0148-9062(93)90429-h.
Schuster, M., and Paliwal, K. K. (1997). ‘Bidirectional recurrent neural networks’, IEEE Transactions on Signal Processing, 45(11), pp. 2673–2681. doi: https://doi.org/10.1109/78.650093.
Valentín, M. B., et al. (2019). ‘A deep residual convolutional neural network for automatic lithological facies identification in Brazilian pre-salt oilfield wellbore image logs’, Journal of Petroleum Science and Engineering. Elsevier B.V., 179(April), pp. 474–503. doi: https://doi.org/10.1016/j.petrol.2019.04.030.
Wu, P. Y., et al. (2018). ‘Machine learning-based method for automated well log processing and interpretation’, 2018 SEG International Exposition and Annual Meeting, SEG 2018, pp. 2041–2045. doi: https://doi.org/10.1190/segam2018-2996973.1.
Zhang, T., et al. (2018). ‘TST3D: Automated structural interpretation in horizontal wellbores’, SPE/AAPG/SEG Unconventional Resources Technology Conference 2018, URTC 2018, pp. 1–15. doi: https://doi.org/10.15530/urtec-2018-2889444.
Information & Authors
Information
Published In
Geo-Extreme 2021
Pages: 232 - 241
Copyright
© 2021 American Society of Civil Engineers.
History
Published online: Nov 4, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.