Vol. 337 No. 10 (2026)
DOI https://doi.org/10.18799/24131830/2026/10/5369
Application of machine learning algorithms for predicting missing well log data in the X Field, Vietnam
Relevance. Well logs provide essential information about the properties of reservoir rocks and formation fluids. However, at certain depth intervals, well log data might be missing due to technical limitations during logging or economic constraints. Aim. To develop and select the optimal machine learning model for predicting missing acoustic log data in well X-5 of X field (Vietnam). Object. The optimal model using efficient machine learning algorithms and selected input logs for predicting missing acoustic log data. Methods. The model was developed using three machine learning algorithms – Random Forest, Extreme Gradient Boosting and Artificial Neural Networks – to predict missing acoustic log values based on other available well logs. Results and conclusions. A total of 27 predictive models were constructed using nine different input variable combinations. Data from three wells with complete log suites were divided into training and testing datasets in a ratio of 80:20. The statistical analysis showed that the Random Forest and Extreme Gradient Boosting algorithms achieved the highest predictive accuracy, with coefficients of determination R2 equal to 0.84, confirming their effectiveness for imputation missing well log data. The optimal model, Extreme Gradient Boosting, utilizing density, gamma ray, neutron porosity, electric and acoustic logs, was applied to predict the missing intervals of the acoustic log in Well X-5. The proposed approach is automatic, objective, and fully data-driven, offering a potential and practical solution for filling incomplete well log datasets in geophysical analysis.
For citation: Bui N.T., Nguyen M.D., Tran O.T. Application of machine learning algorithms for predicting missing well log data in the X Field, Vietnam. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2026, vol. 337, no. 10, pp. 204–213. http://doi.org/10.18799/24131830/2026/10/5369
Keywords:
acoustic log, predicting missing well log data , machine learning algorithms: Artificial Neural Network, Extreme Gradient Boosting, Random Forest
References:
1. Tiab D., Donaldson E.C. Petrophysics. Theory and practice of measuring reservoir rock and fluid transport properties. Houston, Gulf Professional Publishing, 1996. 928 p.
2. Darling T. Well logging and formation evaluation. Amsterdam, Elsevier, 2005. 336 p.
3. Mavko G., Mukerji T., Dvorkin J. The rock physics handbook. Cambridge, Cambridge University Press, 2009. 524 p.
4. Lai J. Toward the scientific interpretation of geophysical well logs: typical misunderstandings and countermeasures. Surveys in Geophysics, 2023, vol. 44, pp. 463–494. DOI: 10.1007/s10712-022-09746-9.
5. Saggaf M., Nebrija Ed. Estimation of missing logs by regularized neural networks. Aapg Bulletin, 2003, vol. 87, pp. 1377–1389. DOI: 10.1306/03110301030.
6. Berry J.E. Acoustic velocity in porous media. Transactions of the AIME, 1959, vol. 216, pp. 262–270. DOI: 10.2118/1231-G.
7. Strelchenko V.V. Geophysical research of sea wells. Мoscow, Neft i gaz Publ., 2005. 68p. (In Russ.)
8. Hastie T., Tibshirani R., Friedman J., Franklin J. The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer, 2005, vol. 27, pp. 83–85.
9. Mukherjee B., Sain K., Wu X. Missing log prediction using machine learning perspectives: a case study from upper Assam basin. Earth Sci Inform, 2024, vol. 17, pp. 3071–3093. DOI: https://doi.org/10.1007/s12145-024-01323-5.
10. Akhmetsafin R.D., Akhmetsafina R.Z. Applying machine learning methods to predict or replace missing logging data. Journal of Instrument Engineering, 2021, vol. 64, pp. 532–541 (In Russ.)
11. Feng R., Grana D., Balling N. Imputation of missing well log data by random forest and its uncertainty analysis. Computers & Geosciences, 2021, vol. 152, pp. 104763. DOI: 10.1016/j.cageo.2021.104763.
12. Gonzalez K., Brusova O., Valenciano A. Valenciano. A machine learning workflow for log data prediction at the basin scale. First Break, 2023, vol. 41, pp. 73–80. DOI: 10.3997/1365-2397.fb2023015.
13. Hakam A., Utama W., Garini S.A., Jabar O.A., Insani A.N.F., Rosandi Y. Sonic log prediction based on Extreme Gradient Boosting (XGBoost) Machine Learning Algorithm by using well log data. BIO Web Conf., 2024. DOI: 10.1051/bioconf/20248909003.
14. Mohammed A.K.A., Dhaidan M.K. Prediction of well logs data and estimation of petrophysical parameters of Mishrif Formation, Nasiriya Field, South of Iraq using Artificial Neural Network (ANN). Iraqi Journal of Science, 2023, pp. 253–268. DOI: 10.24996/ijs.2023.64.1.24.
15. Schmidt W.J., Bui H.B, Handschy J.W., Vu T.H, Trinh X.C., Nguyen T.T. Tectonic evolution and regional setting of the Cuu Long Basin, Vietnam. Tectonophysics, 2019, vol. 757, pp. 36–57. DOI: https://doi.org/10.1016/j.tecto.2019.03.001.
16. Liu Y., Wang Y., Zhang J. New machine learning algorithm: Random Forest. International Conference on Information Computing and Applications, 2012. vol. 7473, pp. 246–252. DOI: 10.1007/978-3-642-34062-8_32.
17. Natekin A., Knoll A. Gradient boosting machines a tutorial. Front. Neurorobot, 2013, vol. 7, pp. 21. DOI: 10.3389/fnbot.2013.00021.
18. Mohaghegh S. Virtual-intelligence applications in petroleum engineering: Part 1 – Artificial Neural Networks. Journal of Petroleum Technology, 2000, vol. 52, pp. 64–73. DOI: 10.2118/58046-MS.
19. Aggarwal C.C., Yu P.S. Outlier detection for high dimensional data. ACM SIGMOD Record, 2002, vol. 30. DOI: 10.1145/376284.375668.
20. Wang H., Bah M.J., Hammad M. Progress in outlier detection techniques: a survey. IEEE Access, 2019, vol. 7, pp. 107964–108000. DOI: 10.1109/ACCESS.2019.2932769.
21. Hodge V., Austin J. A survey of outlier detection methodologies. Artificial Intelligence Review, 2004, vol. 22, pp. 85–126. DOI: 10.1023/B:AIRE.0000045502.10941.a9.
22. Misra S., Osogba O., Powers M. Unsupervised outlier detection techniques for well logs and geophysical data. Machine Learning for Subsurface Characterization, 2020, pp. 1–37. DOI: 10.1016/B978-0-12-817736-5.00001-6.
23. Dash Ch.S.K., Behera A.K., Dehuri S., Ghosh A. An outliers detection and elimination framework in classification task of data mining. Decision Analytics Journal, 2023, vol. 6, pp. 100164. DOI: 10.1016/j.dajour.2023.100164.
24. Hair J.F. Multivariate data analysis. Upper Saddle River, Prentice Hall, 2009. 816 p.
25. Asquith G.B., Krygowski D. Basic well log analysis. Tulsa, AAPG, 2004. 244 p.
