1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 72, Issue 1
  5. Article
Volume 72 Number 1
  • E-ISSN: 1365-2478
PDF

Abstract

ABSTRACT

Petrophysical interpretation and optimal correlation extraction of different measurements require accurate well log depth matching. We have developed a supervised multimodal machine learning alternative for the task of simultaneously matching raw logging while drilling and electrical wireline logging logs. Seven one‐dimensional convolutional neural networks are trained using different log measurements: gamma‐ray, resistivity, P‐ and S‐wave sonic, density, neutron and photoelectric factors, and their depth shift estimates are aggregated using different multimodal late fusion strategies. We test the late fusion average, late fusion weighted average, late fusion with linear and nonlinear learners and model‐level fusion. Depth matching results using the different fusion strategies applied to two unseen wells are compared using visual inspection and the mean Pearson correlation. All models perform well, increasing the correlation after depth matching. Late fusion weighted average achieves the highest scores for all log types. The late fusion weighted average results are compared to a cross‐correlation user‐assisted workflow and manual depth matching for validation. In general, the convolutional neural network fused method exhibits a lower performance than the traditional methods. For one of the wells, the cross‐correlation shows higher correlation values than the other methods but for the second well the manual depth match performs best. However, the differences in Pearson correlation values are small ranging from 0.01 to 0.1. The manual depth match performs very well for the sonic logs, which tend to require slightly larger depth shifts than the other measurements, thus a common depth shift might not always be suitable. Although our convolutional neural network fused approach is limited to estimating bulk shifts and uses constant fusion weights, its performance is similar to that of more time‐consuming methods. Our approach might be substantially improved by including dynamic shifts (stretch/squeeze) and depth‐dependent fusion weights via long‐short‐term memory recurrent neural networks.

© 2024 European Association of Geoscientists & Engineers. © 2022 The Authors. Geophysical Prospecting published by John Wiley & Sons Ltd on behalf of European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13200
2023-12-18
2025-05-23

  • From This Site

    /content/journals/10.1111/1365-2478.13200
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

/deliver/fulltext/gpr/72/1/gpr13200.html?itemId=/content/journals/10.1111/1365-2478.13200&mimeType=html&fmt=ahah

References

  1. Abdoli, S., Cardinal, P. and Koerich, A.L. (2019) End‐to‐end environmental sound classification using a 1D convolutional neural network. Expert Systems with Applications, 136, 252–263. DOI: 10.1016/j.eswa.2019.06.040
     [Google Scholar]
  2. Arundo Analytics, Inc. Revision 8d539c82. . (2020) tsaug documentation: Examples of augmenters. Available at: https://tsaug.readthedocs.io/en/stable/notebook/Examples%20of%20augmenters.html [Accessed 20 April 2021].
  3. Baltrušaitis, T., Ahuja, C. and Morency, L.‐P. (2018) Multimodal machine learning: a survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423–443. DOI: 10.1109/TPAMI.2018.2798607
     [Google Scholar]
  4. Bateman, R.M. (1986) Openhole Log Analysis and Formation Evaluation. Society of Petroleum Engineers.
     [Google Scholar]
  5. Bolt, H. (2016) Wireline logging depth quality improvement: methodology review and elastic‐stretch correction. Petrophysics, 57(3), 294–310.
     [Google Scholar]
  6. Bolt, H. (2019) Correction of driller's depth: field example using driller's way‐point depth correction methodology. Petrophysics, 60(1), 76–91. DOI: 10.30632/PJV60N1‐2019a7.
     [Google Scholar]
  7. Brazell, S., Bayeh, A., Ashby, M. and Burton, D. (2019) A machine‐learning‐based approach to assistive well‐log correlation. Petrophysics, 60(4), 469–479. DOI: 10.30632/PJV60N4‐2019a1
     [Google Scholar]
  8. Bulmer, M.G. (1979) Principles of Statistics, Courier Corporation.
     [Google Scholar]
  9. Chen, S. and Jin, Q. (2016) Multi‐modal conditional attention fusion for dimensional emotion prediction.Proceedings of the 24th ACM International Conference on Multimedia, Amsterdam, the Netherlands, 15‐19 October 2016. ACM. pp. 571–575. DOI: 10.1145/2964284.2967286
  10. Chia, C.R., LaastadH., KostinA.V., HjortlandF., and BordakovG.A. (2006) A new method for improving LWD logging depth. Paper 102175‐MS, SPE Annual Technical Conference and Exhibition, San Antonio, TX, 24–27 September, 2006. DOI: 10.2118/102175‐MS.
  11. Chollet, F. (2015) Keras. Available at https://keras.io[Accessed 24 September 2021].
  12. Deng, T., Xu, C., Lang, X. and Doveton, J. (2021) Diagenetic facies classification in the Arbuckle formation using deep neural networks. Mathematical Geosciences, 53 (7) 1491–1512. DOI: 10.1007/s11004‐021‐09918‐0
     [Google Scholar]
  13. Gadzicki, K., Khamsehashari, R. and Zetzsche, C. (2020) Early vs late fusion in multimodal convolutional neural networks. Proceedings of the 23rd International Conference on Information Fusion (FUSION IEEE), Rustenburg, South Africa, 6‐9 July 2020. IEEE. pp 1–6. DOI: 10.23919/FUSION45008.2020.9190246
  14. Gareth, J., Daniela, W., Trevor, H. and Robert, T. (2013) An Introduction to Statistical Learning: with Applications in R. Springer.
     [Google Scholar]
  15. Imamverdiyev, Y. and Sukhostat, L. (2019) Lithological facies classification using deep convolutional neural network. Journal of Petroleum Science and Engineering, 174, 216–228. DOI: 10.1016/j.petrol.2018.11.023.
     [Google Scholar]
  16. Ioffe, S. and Szegedy, C. (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning, Lille, France, 7–9 July 2015. Proceedings of Machine Learning Research, 37, 448‐456
     [Google Scholar]
  17. Kerzner, M.G. (1984) A solution to the problem of automatic depth matching. Paper SPWLA‐1984‐VV, Proceedings of the SPWLA 25th Annual Logging Symposium, New Orleans, LA, 10–13 June 1984.
  18. Kingma, D.P. and Ba, J. (2015) Adam: A method for stochastic optimization. Proceedings of the Third International Conference for Learning Representations (ICRL), San Diego, CA, 7–9 May 2015.
  19. Le Nir, I., Van Gysel, N. and Rossi, D. (1998) Cross‐section construction from automated well log correlation: A dynamic programming approach using multiple well logs. Paper SPWLA‐1998‐DDDm Proceedings of the SPWLA 39th Annual Logging Symposium, Keyston, CO, 26–28 May 1998.
  20. Le, T., LiangL., ZimmermannT., ZerougS., and HeliotD. (2019) A machine‐learning framework for automating well‐log depth matching. Petrophysics, 60(5), 585–595. DOI:10.30632/PJV60N5‐2019a3.
     [Google Scholar]
  21. Lecun, Y., Bengio, Y. and Hinton, G. (2015) Deep learning. Nature, 521(7553), 436–444. DOI: 10.1038/nature14539.
     [Google Scholar]
  22. Li, L., Jamieson, K., Desalvo, G., Rostamizadeh, A. and Talwalkar, A. (2017) Hyperband: a novel bandit based approach to hyperparameter optimization. The Journal of Machine Learning Research, 18(1), 6765–6816.
     [Google Scholar]
  23. Lineman, D., Mendelson, J. and Toksoz, M.N. (1987) Well to well log correlation using knowledge‐based systems and dynamic depth warping. Paper SPWLA‐1987‐UU, Proceedings of the SPWLA 28th Annual Logging Symposium, London, UK, 29 June–2 July 1987.
  24. Liu, K., Li, Y., Xu, N. and Natarajan, P. (2018) Learn to combine modalities in multimodal deep learning. arXiv preprint arXiv:1805.11730.
  25. Luthi, S.M. and Bryant, I.D. (1997) Well‐log correlation using a back‐propagation neural network. Mathematical Geology, 29(3), 413–425.
     [Google Scholar]
  26. Münzner, S., Schmidt, P., Reiss, A., Hanselmann, M., Stiefelhagen, R. and Dürichen, R. (2017) CNN‐based sensor fusion techniques for multimodal human activity recognition. Proceedings of the ACM International Symposium on Wearable Computers, Maui, Hawaii, 11‐15 September 2017. ACM. pp. 158–165 DOI: 10.1145/3123021.3123046
  27. Norwegian Petroleum Directorate (NPD) , (2019) Guidelines for reporting well data to authorities after completion "Blue Book". Available at https://www.npd.no/globalassets/1npd/regelverk/forskrifter/en/b_og_b_digital_rapportering_e.pdf [Accessed 10 April 2021].
  28. Oliphant, Travis, and contributors (2021) Scipy.signal.correlate, https://docs.scipy.org/doc/scipy/reference/generated/scipy.signal.correlate.html, [Accessed 24 September 2021].
  29. O'Malley, T., Bursztein, E., Long, J., Chollet, F., Jin, H. and Invernizzi, L. (2019) Keras Tuner, Github, [Accessed on 28 November 2020].
  30. Opitz, D. and Maclin, R. (1999), Popular ensemble methods: An empirical study. Journal of Artificial Intelligence Research, 11, 169–198. DOI: 10.1613/jair.614
     [Google Scholar]
  31. Pedersen, B.K., Constable, M.V. and Risbakken, J.K. (2006) Operational procedures and methodology for improving LWD and WL depth control, Kristin field. Paper SPWLA‐2006‐XXX, Proceedings of the SPWLA 47th Annual Logging Symposium, Veracruz, Mexico, 4‐7 June 2006.
  32. Perrone, M.P. and Cooper, L.N. (1992) When networks disagree: ensemble methods for hybrid neural networks, , Institute for Brain and Neural Systems Brown University, Providence RI.
  33. Rider, M.H. (1986) The Geological Interpretation of Well Logs, Rider‐French Consulting Ltd.
     [Google Scholar]
  34. Sollie, F.O. and RodgersS.G. (1994), Towards better measurements of logging depth. Paper SPWLA‐1994‐D, Proceedings of the SPWLA 35th Annual Logging Symposium, Tulsa, OK, 19–22 June 1994.
  35. Spalburg, M. (1989) An algorithm for simultaneous deconvolution, squaring and depth‐matching of logging data. Paper SPWLA‐1989‐P, Proceedings of the SPWLA 30th Annual Logging Symposium, Denver, Colorado, USA, 11‐14 June.
  36. Startzman, R. and Kuo, T. (1986) An artificial intelligence approach to well log correlation. Paper SPWLA‐1986‐WW, Proceedings of the SPWLA 27th Annual Logging Symposium, Houston, TX, 9–13 June 1986.
  37. Storn, R. and Price, K. (1997) Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11(4), 341–359.
     [Google Scholar]
  38. The SciPy community , (2021) Scipy.optimize.differential_evolution. Available at https://docs.scipy.org/doc/scipy/reference/generated/scipy.optimize.differential_evolution.html [Accessed 26 April 2021].
  39. Theys, P.P. (1999) Log Data Acquisition and Quality Control. Editions Technip.
     [Google Scholar]
  40. Torres Caceres, V.A., Duffaut, K., Westad, F.O., Stovas, A., Johansen, Y.B. and Jenssen, A. (2022a) Automated log data analytics workflow–the value of data access and management to reduced turnaround time for log analysis. Petrophysics, 63(1), 35–60. DOI:10.30632/PJV63N1‐2022a3
     [Google Scholar]
  41. Torres Caceres, V.A., Duffaut, K., Yazidi, A., Westad, F.O. and Johansen, Y.B. (2022b) Automated well‐log depth matching–1d convolutional neural networks vs. classic cross correlation. Petrophysics, 63(1), 12–34. DOI:10.30632/PJV63N1‐2022a2
     [Google Scholar]
  42. Wang, S., Shen, Q., Wu, X. and Chen, J. (2020) Automated gamma‐ray log pattern alignment and depth matching by machine learning. Interpretation, 8(3), SL25–SL34. DOI: 10.1190/INT‐2019‐0193.1
     [Google Scholar]
  43. Wilson, H., LoftsJ., PageG., BrooksA., and WalderD. (2004) Depth control: reconciliation of LWD and wireline depths, standard practice and an alternative simple but effective method. Paper SPE‐89899‐MS, Proceedings of the SPE Annual Technical Conference and Exhibition, Houston, TX, 26‐29 September 2004. DOI: 10.2118/89899‐MS.
  44. Wolpert, D.H. (1992) Stacked generalization. Neural Networks, 5(2), 241–259.
     [Google Scholar]
  45. Yamashita, R., Nishio, M., Do, R.K.G. and Togashi, K. (2018) Convolutional neural networks: An overview and application in radiology. Insights into Imaging, 9(4), 611–629. DOI: 10.1007/s13244‐018‐0639‐9.
     [Google Scholar]
  46. Zangwill, J. (1982) Depth matching ‐ a computerized approach. Paper SPWLA‐1982‐EE, Proceedings of the SPWLA 23rd Annual Logging Symposium, Corpus Christi, TX, 6‐9 July, 1982.
  47. Zimmermann, T., Liang, L. and Zeroug, S. (2018) Machine‐learning‐based automatic well‐log depth matching. Petrophysics, 59(6), 863–872. DOI:10.30632/PJV59N6‐2018a10.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13200
Loading
Automated well log depth matching: Late fusion multimodal deep learning
Geophysical Prospecting 72, 155 (2023); https://doi.org/10.1111/1365-2478.13200
/content/journals/10.1111/1365-2478.13200
/content/journals/10.1111/1365-2478.13200
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): Depth matching; Logging; Machine learning; one‐dimensional Convolutional neural networks; Petrophysics

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error