Automation of interwell correlation using dynamic time scale transformation algorithm: application experience

Author details

Abstract

The article presents an approach to automation of interwell correlation based on the Dynamic Time Warping algorithm for dynamic time scale transformation. This method is an effective tool for analyzing and comparing time series (in this case, well logging curves). The key stages of implementing this approach are described, starting with preliminary data preparation: selecting the most informative well logging curves, processing gaps, smoothing and standardizing the data. Then, clustering methods (for example, k-means using PCA) are applied to determine reference wells that cover all possible behavior options for well logging curves from the available data. At the next stage, the Dynamic Time Warping algorithm is used to calculate the similarity between reference and target wells, which allows finding the optimal match between them. Finally, the position of formation intersections in target wells is predicted based on expert marks in reference wells. Experience shown high consistency of the algorithm results with expert estimates in 85% of cases, confirming its effectiveness. Discrepancies were noted, which in some cases were caused by subjective factors in expert interpretation, while the Dynamic Time Warping algorithm demonstrated effectiveness in correctly recognizing the assigned behavior patterns of well logging curves. The proposed approach based on Dynamic Time Warping not only improves the accuracy and objectivity of data interpretation, but also serves as a tool for identifying and correcting subjective errors associated with the human factor. This is especially important when working with large volumes of data, where traditional analysis methods become extremely labor-intensive and vulnerable to errors. Thus, the use of Dynamic Time Warping opens up new opportunities for automating the processes of data analysis and correlation in geophysical research, contributing to the increased efficiency of specialists in this field.

Keywords

interwell correlationautomatic well correlationautocorrelationgeophysical well logginglogginggeophysicsdynamic time scale transformation algorithmalgorithmprogrammingclusteringdata analysisstatisticsdata processing

Bibliography

  1. 1.Keogh E., Pazzani M. Scaling up Dynamic Time Warping for Datamining Applications. Proceedings of the 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2002, pp. 285-289. DOI: 10.1145/347090.347153 Scholar
  2. 2.Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 2011, no. 12, pp. 2825-2830. DOI: 10.48550/arXiv.1201.0490 Scholar
  3. 3.McKinney W. Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference, 2010, pp. 1-6. DOI: 10.25080/Majora-92bf1922-00a Scholar
  4. 4.Hunter J.D. Matplotlib: A 2D graphics environment. Computing in Science & Engineering, 2007, no. 9 (3), pp. 90-95. Scholar
  5. 5.Semenov I.A., Shishkin M.D. Ispol'zovanie vozmozhnostei biblioteki Matplotlib dlia vizualizatsii dannykh v rabote inzhenerov i issledovatelei [Using the potential of the Matplotlib library for data visualization in the work of engineers and researchers]. Sovremennye tekhnologii i nauchno-tekhnicheskii progress, 2024, no. 11, pp. 169-170. Scholar
  6. 6.Tarshkhoeva Zh.T. Iazyk programmirovaniia Python. Biblioteki Python [Python programming language. Python libraries]. Molodoi uchenyi, 2021, no. 5 (347), pp. 20-21. Scholar
  7. 7.Galimullin N.R. Python: ispol'zovanie Python dlia avtomatizatsii povsednevnykh zadach [Python: using Python to automate everyday tasks]. Ekonomika i upravlenie: problemy, resheniia, 2024, vol. 9, no. 9 (150), pp. 69-76. DOI: 10.36871/ek.up.p.r.2024.09.09.010 Scholar
  8. 8.Efremov E.A. Razrabotka graficheskikh interfeisov s pomoshch'iu graficheskoi biblioteki Tkinter [Developing GUIs with the Tkinter GUI Library]. Molodezhnyi nauchno-tekhnicheskii vestnik, 2017, no. 6, 44 p. Scholar
  9. 9.Driankova D.A. Obrabotka propushchennykh znachenii i dublikatov v dannykh s pomoshch'iu biblioteki Pandas dlia iazyka programmirovaniia Python [Processing of missing values and duplicates in data using the Pandas library for the Python programming language]. Dnevnik nauki, 2023, no. 6 (78). DOI: 10.51691/2541-8327_2023_6_11 Scholar
  10. 10.Van der Walt S., Colbert S.C., Varoquaux G. The NumPy array: A structure for efficient numerical computation. Computing in Science & Engineering, 2011, no. 13 (2), pp. 22-30. DOI: 10.1109/MCSE.2011.37 Scholar
Download PDF

Article information

Published
1 April 2025
Issue date
1 April 2025
Issue
Vol. 25, No. 2 (2025)
Share