IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v15y2022i10p3675-d817721.html
   My bibliography  Save this article

Well-Logging-Based Lithology Classification Using Machine Learning Methods for High-Quality Reservoir Identification: A Case Study of Baikouquan Formation in Mahu Area of Junggar Basin, NW China

Author

Listed:
  • Junlong Zhang

    (School of Geosciences, Yangtze University, Wuhan 430100, China)

  • Youbin He

    (School of Geosciences, Yangtze University, Wuhan 430100, China)

  • Yuan Zhang

    (Research Institute of Petroleum Exploration and Development, SINOPEC Jianghan Oilfield Company, Wuhan 430223, China)

  • Weifeng Li

    (School of Geosciences, Yangtze University, Wuhan 430100, China)

  • Junjie Zhang

    (Global Research, RBC Capital Markets, Toronto, ON M5J 2J5, Canada)

Abstract

The identification of underground formation lithology is fundamental in reservoir characterization during petroleum exploration. With the increasing availability and diversity of well-logging data, automated interpretation of well-logging data is in great demand for more efficient and reliable decision making for geologists and geophysicists. This study benchmarked the performances of an array of machine learning models, from linear and nonlinear individual classifiers to ensemble methods, on the task of lithology identification. Cross-validation and Bayesian optimization were utilized to optimize the hyperparameters of different models and performances were evaluated based on the metrics of accuracy—the area under the receiver operating characteristic curve (AUC), precision, recall, and F1-score. The dataset of the study consists of well-logging data acquired from the Baikouquan formation in the Mahu Sag of the Junggar Basin, China, including 4156 labeled data points with 9 well-logging variables. Results exhibit that ensemble methods (XGBoost and RF) outperform the other two categories of machine learning methods by a material margin. Within the ensemble methods, XGBoost has the best performance, achieving an overall accuracy of 0.882 and AUC of 0.947 in classifying mudstone, sandstone, and sandy conglomerate. Among the three lithology classes, sandy conglomerate, as in the potential reservoirs in the study area, can be best distinguished with accuracy of 97%, precision of 0.888, and recall of 0.969, suggesting the XGBoost model as a strong candidate machine learning model for more efficient and accurate lithology identification and reservoir quantification for geologists.

Suggested Citation

  • Junlong Zhang & Youbin He & Yuan Zhang & Weifeng Li & Junjie Zhang, 2022. "Well-Logging-Based Lithology Classification Using Machine Learning Methods for High-Quality Reservoir Identification: A Case Study of Baikouquan Formation in Mahu Area of Junggar Basin, NW China," Energies, MDPI, vol. 15(10), pages 1-15, May.
  • Handle: RePEc:gam:jeners:v:15:y:2022:i:10:p:3675-:d:817721
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/15/10/3675/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/15/10/3675/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yunxin Xie & Chenyang Zhu & Yue Lu & Zhengwei Zhu, 2019. "Towards Optimization of Boosting Models for Formation Lithology Identification," Mathematical Problems in Engineering, Hindawi, vol. 2019, pages 1-13, August.
    2. Timur Merembayev & Darkhan Kurmangaliyev & Bakhbergen Bekbauov & Yerlan Amanbek, 2021. "A Comparison of Machine Learning Algorithms in Predicting Lithofacies: Case Studies from Norway and Kazakhstan," Energies, MDPI, vol. 14(7), pages 1-16, March.
    3. Antonio Mucherino & Petraq J. Papajorgji & Panos M. Pardalos, 2009. "Data Mining in Agriculture," Springer Optimization and Its Applications, Springer, number 978-0-387-88615-2, September.
    4. Matthias Schonlau & Rosie Yuyan Zou, 2020. "The random forest algorithm for statistical learning," Stata Journal, StataCorp LP, vol. 20(1), pages 3-29, March.
    5. Zhixue Sun & Baosheng Jiang & Xiangling Li & Jikang Li & Kang Xiao, 2020. "A Data-Driven Approach for Lithology Identification Based on Parameter-Optimized Ensemble Learning," Energies, MDPI, vol. 13(15), pages 1-15, July.
    6. Laura Auria & Rouslan A. Moro, 2008. "Support Vector Machines (SVM) as a Technique for Solvency Analysis," Discussion Papers of DIW Berlin 811, DIW Berlin, German Institute for Economic Research.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Sascha O. Becker, Sascha O & Voth, Hans-Joachim, 2023. "From the Death of God to the Rise of Hitler," The Warwick Economics Research Paper Series (TWERPS) 1478, University of Warwick, Department of Economics.
    2. Hui Zou & Zhihong Zou & Xiaojing Wang, 2015. "An Enhanced K-Means Algorithm for Water Quality Analysis of The Haihe River in China," IJERPH, MDPI, vol. 12(11), pages 1-14, November.
    3. Aurelia Rybak & Aleksandra Rybak & Spas D. Kolev, 2023. "Modeling the Photovoltaic Power Generation in Poland in the Light of PEP2040: An Application of Multiple Regression," Energies, MDPI, vol. 16(22), pages 1-17, November.
    4. Kyuhan Lee & Jinsoo Park & Iljoo Kim & Youngseok Choi, 2018. "Predicting movie success with machine learning techniques: ways to improve accuracy," Information Systems Frontiers, Springer, vol. 20(3), pages 577-588, June.
    5. Odile Carisse & Mamadou Lamine Fall, 2021. "Decision Trees to Forecast Risks of Strawberry Powdery Mildew Caused by Podosphaera aphanis," Agriculture, MDPI, vol. 11(1), pages 1-16, January.
    6. Orkida Ilollari & Petraq Papajorgji & Adrian Civici & Howard Moskowitz, 2022. "Measuring Client’s Feelings on Mobile Banking," Review of Applied Socio-Economic Research, Pro Global Science Association, vol. 23(1), pages 28-39, June.
    7. Sascha O. Becker & Hans-Joachim Voth, 2023. "From the Death of God to the Rise of Hitler," CESifo Working Paper Series 10730, CESifo.
    8. Tomasz Rymarczyk & Konrad Niderla & Edward Kozłowski & Krzysztof Król & Joanna Maria Wyrwisz & Sylwia Skrzypek-Ahmed & Piotr Gołąbek, 2021. "Logistic Regression with Wave Preprocessing to Solve Inverse Problem in Industrial Tomography for Technological Process Control," Energies, MDPI, vol. 14(23), pages 1-21, December.
    9. Yoon-Joo Park, 2018. "Predicting the Helpfulness of Online Customer Reviews across Different Product Types," Sustainability, MDPI, vol. 10(6), pages 1-20, May.
    10. Abdulkadir Atalan, 2023. "Forecasting drinking milk price based on economic, social, and environmental factors using machine learning algorithms," Agribusiness, John Wiley & Sons, Ltd., vol. 39(1), pages 214-241, January.
    11. Forbes, Kevin F., 2023. "Demand for grid-supplied electricity in the presence of distributed solar energy resources: Evidence from New York City," Utilities Policy, Elsevier, vol. 80(C).
    12. Ni, Ji & Chen, Bowei & Allinson, Nigel M. & Ye, Xujiong, 2020. "A hybrid model for predicting human physical activity status from lifelogging data," European Journal of Operational Research, Elsevier, vol. 281(3), pages 532-542.
    13. Christian B. Hansen & Mark E. Schaffer & Thomas Wiemann & Achim Ahrens, 2022. "ddml: Double/debiased machine learning in Stata," Swiss Stata Conference 2022 02, Stata Users Group.
    14. Muhammad Islam & Muhammad Usman & Azhar Mahmood & Aaqif Afzaal Abbasi & Oh-Young Song, 2020. "Predictive analytics framework for accurate estimation of child mortality rates for Internet of Things enabled smart healthcare systems," International Journal of Distributed Sensor Networks, , vol. 16(5), pages 15501477209, May.
    15. Petrakova Aleksandra & Merkurjeva Galina & Affenzeller Michael, 2015. "Heterogeneous versus Homogeneous Machine Learning Ensembles," Information Technology and Management Science, Sciendo, vol. 18(1), pages 135-140, December.
    16. Danijel Jevtic & Romain Deleze & Joerg Osterrieder, 2022. "AI for trading strategies," Papers 2208.07168, arXiv.org.
    17. Hillebrecht, Michael & Klonner, Stefan & Pacere, Noraogo A., 2020. "Dynamic Properties of Poverty Targeting," Working Papers 0696, University of Heidelberg, Department of Economics.
    18. Wang, Xinlin & Ahn, Sung-Hoon, 2020. "Real-time prediction and anomaly detection of electrical load in a residential community," Applied Energy, Elsevier, vol. 259(C).
    19. Söhnke M. Bartram & Jürgen Branke & Mehrshad Motahari, 2020. "Artificial intelligence in asset management," Working Papers 20202001, Cambridge Judge Business School, University of Cambridge.
    20. Ivan Brandić & Alan Antonović & Lato Pezo & Božidar Matin & Tajana Krička & Vanja Jurišić & Karlo Špelić & Mislav Kontek & Juraj Kukuruzović & Mateja Grubor & Ana Matin, 2023. "Energy Potentials of Agricultural Biomass and the Possibility of Modelling Using RFR and SVM Models," Energies, MDPI, vol. 16(2), pages 1-10, January.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:15:y:2022:i:10:p:3675-:d:817721. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.