Gamma-ray log derivative and volatility attributes assist facies characterization in clastic sedimentary sequences for formulaic and machine learning analysis
Abstract view|225|times PDF download|90|times Supplements download|35|times
Abstract
Rate of change, second derivative and volatility of gamma-ray (GR) well-log curves provide useful indicators with which to characterize lithofacies in clastic sedimentary sequences. Rolling averages of these variables, as they change with depth, are also able to distinguish certain lithofacies features. These attributes make it possible to accurately distinguish key facies by using only gamma-ray data, both with formulaic calculations and employing machine-learning (ML) algorithms. This is useful in the many wellbores for which only basic logging suites are available. As well as enhancing lithofacies classification more generally using well-log variables, these GR attributes can be used to forecast facies in real time based on logging-while-drilling data. The application is demonstrated with simple formula using synthetic GR logs featuring common clastic lithofacies and their transitions. Seven widely used ML methods are each trained and validated with a synthetic GR curve (1450 data points) displaying six distinct facies. The ability of the ML model to distinguish those facies using seven GR attributes is compared and further tested with an independent GR data set (800 data points). The random forest algorithm outperforms the other ML models in this facies prediction task, achieving a mean absolute error of 0.25 (on a facies class range of 1 to 6) for the independent testing dataset. The results highlight the benefit of this technique in providing reliable facies analysis based only on GR data. Random forest, support vector classification and eXtreme Gradient Boost are the ML models that provide the most reliable facies classification from the GR attributes defined. Annotated confusion matrices assist in revealing the details of facies class prediction accuracy and precision achieved by the ML and models and classification formulas.
Cited as: Wood, D.A. Gamma-ray log derivative and volatility attributes assist facies characterization in clastic sedimentary sequences for formulaic and machine learning analysis. Advances in Geo-Energy Research, 2022, 6(1): 69-85. https://doi.org/10.46690/ager.2022.01.06
Keywords
References
Bestagini, P., Lipari, V., Tubaro, S. A machine learning approach to facies classification using well logs. Paper SEG-2017-17729805 Presented at the 2017 SEG International Exposition and Annual Meeting, Houston, Texas, 24-29 September, 2017.
Busch, J. M., Fortney, W. G., Berry, L. N. Determination of lithology from well logs by statistical analysis. SPE Formation Evaluation, 1987, 2(4): 412-418.
Danielsson, J., Valenzuela, M., Zer, I. Learning from history: Volatility and financial crises. The Review of Financial Studies, 2018, 31(7): 2774-2805.
Dubois, M. K., Bohling, G. C., Chakrabarti, S. Comparison of four approaches to a rock facies classification problem. Computers & Geosciences, 2007, 33(5): 599-617.
Dypvik, H., Eriksen, D. Natural radioactivity of clastic sediments and the contributions of U, Th and K. Journal of Petroleum Geology, 1983, 5(4): 409-416.
Emery, D., Myers, K. Sequence Stratigraphy. Blackwell Science, Oxford, UK, 1996.
Fadokun, D. O., Oshilike, I. B., Onyekonwu, M. O. Supervised and unsupervised machine learning approach in facies prediction. Paper SPE-203726-MS Presented at the SPE Nigeria Annual International Conference and Exhibition, Virtual, 11-13 August, 2020.
Faga, A. T., Oyeneyin, B. M. Effects of diagenesis on neural-network grain-size prediction. Paper SPE-60305-MS Presented at the SPE Rocky Mountain Regional/Low-Permeability Reservoirs Symposium and Exhibition, Denver, Colorado, 12-15 March, 2000.
Farzi, R., Bolandi, V. Estimation of organic facies using ensemble methods in comparison with conventional intelligent approaches: A case study of the South Pars Gas Field, Persian Gulf, Iran. Modeling Earth Systems and Environment, 2016, 2: 105.
Glantz, M., Kissel, R. Multi-Asset Risk Modeling: Techniques for a Global Economy in an Electronic and Algorithmic Trading Era. Academic Press, New York, USA, 2014.
Goncalves, C. A., Harvey, P. K., Lovell, M. A. Application of a multilayer neural network and statistical techniques in formation characterization. Paper SPWLA-1995-FF Presented at the SPWLA 36th Annual Logging Symposium, Paris, France, 26-29 June, 1995.
Hall, B. Facies classification using machine learning. The Lead Edge, 2016, 35(10): 906-909.
Halotel, J., Demyanov, V., Gardiner, A. Value of geologically derived features in machine learning facies classification. Mathematical Geosciences, 2020, 52: 5-29.
Hossain, T. M., Watada, J., Aziz, I. A., et al. Machine learning in electrofacies classification and subsurface lithology interpretation: A rough set theory approach. Applied Sciences, 2020, 10(17): 5940.
Hurst, A. Natural gamma-ray spectroscopy in hydrocarbon bearing sandstones from the Norwegian continental shelf. Geological Society, 1990, 48(1): 211-222.
Ippolito, M., Ferguson, J., Jenson, F. Improving facies prediction by combining supervised and unsupervised learning methods. Journal of Petroleum Science and Engineering, 2021, 200: 108300.
Krumbein, W. C., Sloss, L. L. Stratigraphy and Sedimentation. W H Freeman & Co, London, UK, 1951.
Mandal, P. P., Rezaee, R. Facies classification with different machine learning algorithm–An efficient artificial intelligence technique for improved classification. ASEG Extended Abstracts, 2019, 1: 1-6.
Merembayev, T., Kurmangaliyev, D., Bekbauov, B., et al. A Comparison of machine learning algorithms in predicting lithofacies: Case studies from Norway and Kazakhstan. Energies, 2021, 14(7): 1896.
Reverdy, X., Argaud, M., Walgenwitz, F. Minerological analysis required for log interpretation in complex lithologies. Transactions of the SPWLA 8th European Symposium, 1983.
Rider, M. H. Geological Interpretation of Well Logs. Blackie, New York, USA, 1986.
Rider, M. H. Gamma-ray log shape used as a facies indicator: Critical analysis of an oversimplified methodology. Geological Society, 1990, 48(1): 27-37.
Rogers, S. J., Fang, J., Karr, C., et al. Determination of lithology from well logs using a neural network. AAPG Bulletin, 1992, 76(5): 731-739.
Russell, W. L. The total gamma ray activity of sedimentary rocks as indicated by Geiger counter determinations. Geophysics, 1944, 9(2): 180-216.
Scholle, P. A., Spearing, D. Sandstone Depositional Environments. American Association of Petroleum Geologists, tulsa, UAS, 1982.
Schwert, G. W. Why does stock market price volatility change over time. The Journal of Finance, 1989, 154 (5): 1115-1153.
SciKit Learn. Cross-validation: evaluating estimator performance 2021a.
https://scikit-learn.org/stable/
SciKit Learn. Bayesian optimization of hyperparameters in Python 2021c.
Selley, R. C. Concepts and Methods of Subsurface Facies Analysis. American Association of Petroleum Geologists Education Course Notes, Tulsa, USA, 1978.
Shashank, S., Mahapatra, M. P. Boosting rock facies prediction: weighted ensemble of machine learning classifiers. Paper SPE-192930-MS Presented at the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 12-15 November, 2018.
Tran, T. V., Ngo, H. H., Hoang, S. K., et al. Depositional facies prediction using artificial intelligence to improve reservoir characterization in a mature field of Nam Con Son Basin, Offshore Vietnam. Paper OTC-30086-MS Presented at the Offshore Technology Conference Asia, Kuala Lumpur, Malaysia, 17-19 August, 2020.
Wood, D. A. A transparent Open-Box learning network provides insight to complex systems and a performance benchmark for more-opaque machine learning algorithms. Advances in Geo-Energy Research, 2018, 2(2): 148-162.
Wood, D. A. Lithofacies and stratigraphy prediction methodology exploiting an optimized nearest-neighbour algorithm to mine well-log data. Marine and Petroleum Geology, 2019, 110: 347-367.
Wood, D. A. Bakken stratigraphic and type well log learning network for transparent prediction and rigorous data mining. Natural Resources Research, 2020, 29(2): 1329-1349.
Wrona, T., Pan, I., Gawthorpe, R. L., et al. Seismic facies analysis using machine learning. Geophysics, 2018, 83(5): O83-O95.
DOI: https://doi.org/10.46690/ager.2022.01.06
Refbacks
- There are currently no refbacks.
Copyright (c) 2021 The Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.