Generation of Synthetic Sonic Profiles for Drilled Wells in the Sergipe Basin: A Linearity Analysis Using Regression

• José Gabriel da S. Carvalho UFS
• Vitor Hugo Simon UFS
• Rodolfo B. de B. Garcia UFS

DOI: https://doi.org/10.5753/erbase.2025.13784

Abstract

The prediction of sonic logs is essential in the oil industry, as it allows the estimation of geological properties without direct measurements, which are often costly or unfeasible. This work applies linear regression to generate synthetic sonic logs based on other geophysical logs from the ANP database for the Sergipe Onshore Basin. The methodology uses Pearson correlation to select relevant variables for the prediction. The model achieved an r² of 0.77, indicating its viability to reduce costs by replacing direct measurements with statistical predictions.

References

Ahammod, S., Hai, M. A., Islam, M. R., and Abu, S. (2014). Petro-physical analysis of reservoir rock of fenchuganj gas field (well 03) using wireline log. American Journal of Engineering Research (AJER), 3(8):37–48.

Akinyemi, O. D., Elsaadany, M., Siddiqui, N. A., Elkurdy, S., Olutoki, J. O., and Islam, M. M. (2023). Machine learning application for prediction of sonic wave transit time-a case of niger delta basin. Results in Engineering, 20:101528.

Alhelfia, L. M., Ali, H. M., and Ahmed, S. H. (2021). P-wave sonic log predictive modeling with optimal artificial neural networks topology. Journal of Al-Qadisiyah for computer science and mathematics, 13(3):Page–142.

Archie, G. E. (1950). Introduction to petrophysics of reservoir rocks. AAPG bulletin, 34(5):943–961.

Augusto, F. d. O. A. and Martins, J. L. (2009). A well-log regression analysis for p-wave velocity prediction in the namorado oil field, campos basin. Revista Brasileira de Geofisica, 27:595–608.

Cao, J., Shi, Y., Wang, D., and Zhang, X. (2017). Acoustic log prediction on the basis of kernel extreme learning machine for wells in gjh survey, erdos basin. Journal of Electrical and Computer Engineering, 2017(1):3824086.

Cranganu, C. and Breaban, M. (2013). Using support vector regression to estimate sonic log distributions: a case study from the anadarko basin, oklahoma. Journal of Petroleum Science and Engineering, 103:1–13.

Ellis, D. V. and Singer, J. M. (2007). Well logging for earth scientists, volume 692. Springer.

Gressling, T. (2020). Data Science in chemistry: artificial intelligence, big data, chemometrics and quantum computing with jupyter. Walter de Gruyter GmbH & Co KG.

Montgomery, D. C., Peck, E. A., and Vining, G. G. (2021). Introduction to linear regression analysis. John Wiley & Sons.

Nero, C., Aning, A. A., Danuor, S. K., and Mensah, V. (2023). Prediction of compressional sonic log in the western (tano) sedimentary basin of ghana, west africa using supervised machine learning algorithms. Heliyon, 9(9).

Ogbamikhumi, A., Salami, S., and Uwadiae, W. (2020). Neural network prediction of p-wave log for reservoir characterization in the niger delta basin. Nigerian Journal of Technological Development, 17(1):28–32.

Pratikna, K., Rahman, M., Torabi, A., and Mondol, N. (2022). Machine learning application for compressional wave velocity log prediction in sleipner co2 storage, offshore norway. In 83rd EAGE Annual Conference & Exhibition, volume 2022, pages 1–5. European Association of Geoscientists & Engineers.

Selley, R. C. (1998). Elements of petroleum geology. Gulf Professional Publishing.

SOUSA, A. (2024). Validação externa dos agrupamentos de eletrofácies com aprendizado não supervisionado utilizando litologias interpretadas em poços de petróleo. 107 páginas.

Tissot, B. P. and Welte, D. H. (2013). Petroleum formation and occurrence. Springer Science & Business Media.