Skip to main content

Advertisement

SpringerLink
Log in

Carbonate / siliciclastic lithofacies classification aided by well-log derivative, volatility and sequence boundary attributes combined with machine learning

  • Research Article
  • Published:
Earth Science Informatics Aims and scope Submit manuscript

Abstract

Derivative and volatility attributes calculated for well-log versus depth sequences extract characteristics that can be usefully exploited by automated machine-learning (ML) lithofacies classification models. That information is valuable for wellbores that have a restricted suite of recorded well logs and no cores recovered, limiting the detailed geological information available. In this study, a ten-well dataset, calibrated with core information, from the large Panoma gas Field (Kansas, U.S.A), with a suite of five well logs through a complex Lower Permian carbonate and siliciclastic lithofacies sequence is evaluated with seven ML models. Detailed cross-validation. feature selection analysis identifies that the volatility of the neutron-density porosity log added to the five recorded well logs improves lithofacies classification performance with this dataset without recourse to geological input. The support vector classifier (SVC) provides the most accurate facies class prediction of the ML models tested, achieving prediction accuracy of 61.2% with this six feature dataset. However, the addition of calculated facies boundary influence attributes further improves the SVC’s facies class prediction accuracy to 77.2% (weighted average F1 score of 0,7620) for data unseen by the trained model. Training, validation and unseen data testing of the ML models reveals that the SVC model is less prone to overfitting than the other ML models evaluated with the attribute enhanced datasets. In the absence of detailed geological inputs, such attribute-enhanced well-log datasets can be used to reliably locate target reservoir lithofacies, such as high productivity zones associated with high porosity and permeability, with automated ML models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  • Abbas MA, Al-Mudhafar WJ (2021) Lithofacies classification of carbonate reservoirs using advanced machine learning: a case study from a Southern Iraqi oil field. Offshore Technology Conference, Virtual and Houston, Texas, U.S.A, August 2019. https://doi.org/10.4043/31114-MS

  • Agrawal R, Malik A, Samuel R, Saxena A (2022) Real-Time Prediction of litho-facies from drilling data using an artificial neural network: a comparative field data study with optimizing algorithms. J Energy Res Technol 144:043003. https://doi.org/10.1115/1.4051573

    Article  Google Scholar 

  • Al-Mudhafar WJ (2017) Integrating well log interpretations for lithofacies classification and permeability modeling through advanced machine learning algorithms. J Petrol Explor Prod Technol 7:1023–1033. https://doi.org/10.1007/s13202-017-0360-0

    Article  Google Scholar 

  • Al-Mudhafar WJ, Al Lawe EM, Noshi CI (2019) Clustering analysis for improved characterization of carbonate reservoirs in a Southern Iraqi oil field. Offshore Technology Conference, Houston, Texas, U.S.A. May 2019. https://doi.org/10.4043/29269-MS

  • Al-Mudhafar WJ (2020). Advanced supervised machine learning algorithms for efficient electrofacies classification of a carbonate reservoir in a giant Southern Iraqi oil field. Offshore Technology Conference, Houston, Texas, U.S.A. May 2020. https://doi.org/10.4043/30906-MS

  • Ameur-Zaimeche O, Aziez Z, Heddam S, Kechiched R (2020) Lithofacies prediction in non-cored wells from the Sif Fatima oil field (Berkine basin, southern Algeria): a comparative study of multilayer perceptron neural network and cluster analysis-based approaches. J Afr Earth Sci 166:103826. https://doi.org/10.1016/j.jafrearsci.2020.103826

    Article  Google Scholar 

  • Avseth P, Mukerji T (2002) Seismic lithofacies classification from well logs using statistical rock physics. Petrophysics 43(02):70–81. https://doi.org/10.2118/170748-MS

    Article  Google Scholar 

  • Bestagini P, Lipari V, Tubaro S (2017) A machine learning approach to facies classification using well logs. Proceedings of the SEG International Exposition and 87th Annual Meeting. 2137. https://doi.org/10.1190/segam2017-17729805.1

  • Bressan TS, Kehl de Souza M, Girelli TJ, Junior FC (2020) Evaluation of machine learning methods for lithology classification using geophysical data. Comput Geosci 139:104475. https://doi.org/10.1016/j.cageo.2020.104475

    Article  Google Scholar 

  • Busch J, Fortney W, Berry LN (1987) Determination of lithology from well logs by statistical analysis. SPE Form Eval 2:412–418. https://doi.org/10.2118/14301-PA

    Article  Google Scholar 

  • Byrnes AP, Dubois MK, Magnuson M (2001) Western tight gas carbonates: comparison of Council Grove Group, Panoma Field, southwest Kansas, and western low permeability gas sands. Am Assoc Petrol Geol Annu Convention 10:A31

    Google Scholar 

  • Cant DJ (1992) Subsurface facies analysis. In: Walker RG, James NP, editors. Facies models, response to sea level changes. Geol Assoc Canada, pp 27–45

  • Dell’Aversana P (2019) Comparison of different machine learning algorithms for lithofacies classification from well logs. Bollettino di Geofisica Teorica ed Applicata 60(1):69–80. https://doi.org/10.4430/bgta0256

    Article  Google Scholar 

  • Dubois MK, Bohling GC, Chakrabarti S (2007a) Comparison of four approaches to a rock facies classification problem. Comput Geosci 33:599–617

    Article  Google Scholar 

  • Dubois MK, Byrnes AP, Bohling GC, Seals SC, Doveton JH (2003) Statistically-based lithofacies predictions for 3-D reservoir modeling: examples from the Panoma (Council Grove) Field, Hugoton Embayment, Southwest Kansas. In: Proceedings of the American Association of Petroleum Geologists annual convention 12:A44

  • Dubois MK, Byrnes AP, Bhattacharya S, Bohling GC, Doveton JH, Barba RE (2007b) Hugoton Asset Management Project (HAMP): Hugoton Geomodel Final Report. Kansas Geological Society Open File Report 2007b–6. http://www.kgs.ku.edu/PRS/publication/2007/OFR07_06/index.html. [Accessed 28th February 2022]

  • Fadokun DO, Oshilike IB, Onyekonwu MO (2020) Supervised and unsupervised machine learning approach in facies prediction. SPE-203726-MS. Nigeria Annual International Conference and (Virtual) Exhibition. 2020. https://doi.org/10.2118/203726-MS

  • Faga AT, Oyeneyin BM (2000) Effects of diagenesis on neural-network grain-size prediction. SPE-60305-MS. Rocky Mountain Regional/Low-Permeability Reservoirs Symposium and Exhibition, Denver, Colorado, March 2000. https://doi.org/10.2118/60305-MS

  • Farzi R, Bolandi V (2016) 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 Model Earth Syst Environ 2:105. https://doi.org/10.1007/s40808-016-0165-z

    Article  Google Scholar 

  • Goncalves CA, Harvey PK, Lovell MA (1995) Application of a multilayer neural network and statistical techniques in formation characterization. In: SPWLA 36th annual logging symposium, Paris, 26–29 Jun, Society of Petrophysicists and Well Log Analysts, Houston (U.S.A.) 12 pages

  • Gwinner DM, Laude LS, Olmos JL, Quirein JA, Reimer LJ (1991) Improved Reservoir Characterization By Integration Of Petrophysics, Geology And Core Analysis: An Example From The Hugoton Field, Kansas. SPWLA 32nd Annual Logging Symposium, Midland, Texas, June 1991.Paper SPWLA-1991-TT

  • Hall B (2016a) Facies Classification Using Machine Learning. Lead Edge 35(10):906–909. https://doi.org/10.1190/tle35100906.1

    Article  Google Scholar 

  • Hall M, Hall B (2017) Distributed collaborative prediction: results of the machine learning contest. Leading Edge 36(3):267–269. https://doi.org/10.1190/tle36030267.1

    Article  Google Scholar 

  • Hall B (2016b) Facies classification machine learning contest dataset. https://github.com/brendonhall/facies_classification/find/master. [Accessed 28th February, 2022]

  • Halotel J, Demyanov V, Gardiner A (2020) Value of geologically derived features in machine learning facies classification. Math Geosci 52:5–29. https://doi.org/10.1007/s11004-019-09838-0

    Article  Google Scholar 

  • Hemsell CC (1939) Geology of Hugoton Gas Field of Southwestern Kansas. AAPG Bull 23(7):1054–1067. https://doi.org/10.1306/3D9330DA-16B1-11D7-8645000102C1865D

    Article  Google Scholar 

  • Hossein TM, Watada J, Aziz IA, Hermana M (2020) Machine learning in electrofacies classification and subsurface lithology interpretation: a rough set theory approach. Appl Sci 10:5940. https://doi.org/10.3390/app10175940

    Article  Google Scholar 

  • Hurst A (1990) Natural gamma-ray spectroscopy in hydrocarbon bearing sandstones from the Norwegian continental shelf, in Geological Applications of Wireline Logs. Geological Society, London, Special Publication, eds. Hurst A, Lovell MA, Morton AC 48:211–222

  • Ippolito M, Ferguson J, Jenson F (2021) Improving facies prediction by combining supervised and unsupervised learning methods. J Petrol Sci Eng 200:108300. https://doi.org/10.1016/j.petrol.2020.108300

    Article  Google Scholar 

  • Kesslar L, Sachs SD (1995) Depositional setting and sequence stratigraphic implications of the Upper Sinemurian (Lower Jurassic) sandstone interval, North Celtic Sea/St George’s Channel Basins, offshore Ireland. Geol Soc Lond Spec Publ 93(1):171–92. https://doi.org/10.1144/GSL.SP.1995.093.01.13

    Article  Google Scholar 

  • Krumbein WC, Sloss LL (1951) Stratigraphy and sedimentation. W.H.Freeman and Co, San Francisco (USA) 497 pages. https://doi.org/10.1002/gj.3350010110

  • SciKit Learn (2022a) Supervised and unsupervised machine learning models in Python. 2022a. https://scikit-learn.org/stable/ [Accessed 28th February 2022a].

  • SciKit Learn (2022b) GridSearchCV: Exhaustive search over specified parameter values for an estimator in Python. https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.GridSearchCV.html. [Accessed 28th February 2022b].

  • SciKit Learn (2022c) Bayesian optimization of hyperparameters in Python.. https://scikit-optimize.github.io/stable/modules/generated/skopt.BayesSearchCV.html [Accessed 28th February 2022c].

  • SciKit Learn (2022d) Cross-validation: evaluating estimator performance.https://scikit-learn.org/stable/modules/cross_validation.html[Accessed 28th February 2022d].

  • Lee SH, Datta-Gupta A (1999) Electrofacies characterization and permeability predictions in carbonate reservoirs: role of multivariate analysis and nonparametric regression. In: SPE annual technical conference and exhibition (3–6 October), Houston, Texas. https://doi.org/10.2118/56658-MS

  • Mandal PP, Rezaee R (2019) Facies classification with different machine learning algorithm – An efficient artificial intelligence technique for improved classification. ASEG Extended Abstracts 1:1–6. https://doi.org/10.1080/22020586.2019.12072918

    Article  Google Scholar 

  • Merembayev T, Kurmangaliyev D, Bekbauov B, Amanbek YA (2021) Comparison of machine learning algorithms in predicting lithofacies: Case studies from Norway and Kazakhstan. Energies 14:1896. https://doi.org/10.3390/en14071896

    Article  Google Scholar 

  • Olson TM, Babcock JA, Prasad KVK, Boughton SD, Wagner PD, Franklin MH, Thompson KA (1997) Reservoir characterization of the giant Hugoton gas field, Kansas. AAPG Bull 81(11):1785–1803

    Google Scholar 

  • Potratz GL, Canchumuni SWA, Castro JDB, Potratz J, Pacheco MAC (2021) Automatic Lithofacies Classification with t-SNE and K-Nearest Neighbors Algorithm. Anuário Do Instituto De Geociências 44:35024. https://doi.org/10.11137/2021_44_35024

    Article  Google Scholar 

  • Puskarczyk E (2019) Artificial neural networks as a tool for pattern recognition and electrofacies analysis in Polish palaeozoic shale gas formations. Acta Geophys 67:1991–2003. https://doi.org/10.1007/s11600-019-00359-2

    Article  Google Scholar 

  • Reverdy X, Argaud M, Walgenwitz F (1983) Minerological analysis required for log interpretation in complex lithologies. Paper H, Transactions of the SPWLA 8th European Symposium

  • Rider MH (1990) Gamma-ray log shape used as a facies indicator: critical analysis of an oversimplified methodology. Geol Soc Lond Spec Publ 48:27–37. https://doi.org/10.1144/GSL.SP.1990.048.01.04

    Article  Google Scholar 

  • Rogers SJ, Fang J, Karr C, Stanley D (1992) Determination of lithology from well logs using a neural network (1). AAPG Bull 76:731–739

    Google Scholar 

  • Russell WL (1944) The total gamma ray activity of sedimentary rocks as indicated by Geiger counter determinations. Geophysics 9(2):180–216. https://doi.org/10.1190/1.1445076

    Article  Google Scholar 

  • Sarkar S, Majundar C (2020) A comparative analysis of supervised classification algorithms for lithofacies characterization. EAGE Digitalization Conference and Exhibition, Nov 2020. European Association of Geoscientists & Engineers 1–5. https://doi.org/10.3997/2214-4609.202032090

  • Scholle PA, Spearing D (1982) Sandstone depositional environments. American Association of Petroleum Geologists Memoir 31:410 pages. ISBN: 9780891813071

  • Selley RC (1978) Concepts and Methods of Subsurface Facies Analysis. American Association of Petroleum Geologists Education Course Notes Series #9. https://doi.org/10.1306/CE9397

  • Shashank S, Mahapatra MP (2018) Boosting rock facies prediction: weighted ensemble of machine learning classifiers. Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE. SPE-192930-MS. https://doi.org/10.2118/192930-MS

  • Tang H, White C, Zeng X, Gani MR, Bhattacharya JP (2004) Comparison of multivariate statistical algorithms for wireline log facies classification. AAPG Ann Meet Abstr 88:13

    Google Scholar 

  • Tran TV, Ngo HH, Hoang SK, Tran HN, Lambiase JL (2020) Depositional Facies Prediction Using Artificial Intelligence to Improve Reservoir Characterization in a Mature Field of Nam Con Son Basin, Offshore Vietnam. Offshore Technology Conference Asia, Kuala Lumpur, Malaysia, November 2020 OTC-30086-MS. https://doi.org/10.4043/30086-MS

  • Wood DA (2019) Lithofacies and stratigraphy prediction methodology exploiting an optimized nearest-neighbour algorithm to mine well-log data. Mar Pet Geol 110:347–367. https://doi.org/10.1016/j.marpetgeo.2019.07.026

    Article  Google Scholar 

  • Wood DA (2020) Bakken stratigraphic and type well log learning network for transparent prediction and rigorous data mining. Nat Resour Res 29(2):1329–1349. https://doi.org/10.1007/s11053-019-09525-1

    Article  Google Scholar 

  • Wood DA (2022) Gamma-ray log derivative and volatility attributes assist facies characterization in clastic sedimentary sequences for formulaic and machine learning analysis. Adv Geoenergy Res 6(1):69–85. https://doi.org/10.46690/ager.2022.01.06

    Article  Google Scholar 

  • Wrona T, Pan I, Gawthorpe RL, Fossen H (2018) Seismic facies analysis using machine learning. Geophysics 83(5):O83–O95. https://doi.org/10.1190/GEO2017-0595.1

    Article  Google Scholar 

  • Xie Y, Zhu C, Lu Y, Zhu Z (2019) Towards optimization of boosting models for formation lithology identification. Math Problems Eng 5309852. https://doi.org/10.1155/2019/5309852

Download references

Funding

No funding was received for this study.

Author information

Authors and Affiliations

  1. DWA Energy Limited, Lincoln, UK

    David A. Wood

Authors
  1. David A. Wood
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to David A. Wood.

Ethics declarations

Conflicts of interest

The author has no conflicts of interest associated with this study.

Additional information

Communicated by H. Babaie

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• Well-log derivative, volatility and boundary attributes aid complex lithology facies classification where limited geological data is available

• Support vector classifier is able to avoid overfitting complex attribute-enhanced dataset making it more generalizable to unseen data than other machine learning models evaluated

• Neutron-density log volatility combined with boundary influence attributes form an effective facies discriminator for complex carbonate / siliciclastic sequences.

Appendix A. Metrics used to predict lithofacies classification performance

Appendix A. Metrics used to predict lithofacies classification performance

A combination of traditional regression-type error metrics and classification accuracy metrics are used in this study to assess the performance of machine-learning models in predicting complex limestone lithofacies. These are displayed in Fig. 13. 

Fig. 13
figure 13

Classification prediction performance measures assessed in this study

Full size image

13.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wood, D.A. Carbonate / siliciclastic lithofacies classification aided by well-log derivative, volatility and sequence boundary attributes combined with machine learning. Earth Sci Inform 15, 1699–1721 (2022). https://doi.org/10.1007/s12145-022-00829-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-022-00829-0

Keywords

Search

Navigation