Lateral scanning logging while drilling data processing using convolutional neural networks
https://doi.org/10.18303/2619-1563-2021-2-24
Abstract
This article discusses a new approach to processing lateral scanning logging while drilling data based on a combination of three-dimensional numerical modeling and convolutional neural networks. We prepared dataset for training neural networks. Dataset contains realistic synthetic resistivity images and geoelectric layer boundary layouts, obtained based on true values of their spatial orientation parameters. Using convolutional neural networks two algorithms have been developed and programmatically implemented: suppression of random noise and detection of layer boundaries on the resistivity images. The developed algorithms allow fast and accurate processing of large amounts of data, while, due to the absence of full-connection layers in the neural networks’ architectures, it is possible to process resistivity images of arbitrary length.
About the Authors
K. N. Danilovskii
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Russian Federation
Russian Federation
Koptyug Ave., 3, Novosibirsk, 630090
Loginov G. N.
Trofimuk Institute of Petroleum Geology and Geophysics SB RAS
Russian Federation
Russian Federation
Koptyug Ave., 3, Novosibirsk, 630090
References
1. Danilovskiy K., Glinskikh V., Nechaev O. 3D modelling of the new resistivity microimaging tool signals for logging while drilling // The 80th EAGE Conference and Exhibition (Copenhagen, Denmark, June 11–14, 2018): Extended abstracts. – Copenhagen, 2018. – Tu SP2 01, doi: 10.3997/2214-4609.201801679.
2. Danilovskiy K.N., Dudaev A.R., Glinskikh V.N., Nikitenko M.N., Moskaev I.A. Web-technologies based software for oil and gas wells geosteering // Vestnik NSU. Series: Information Technologies. – 2019. – Vol. 17 (2). – P. 5–17.
3. Danilovskiy K., Loginov G., Nechaev O. Automatic geoelectric boundaries detection on the resistivity images based on 3D numerical simulation and convolutional neural network // The 9th Saint Petersburg International Conference and Exhibition (Saint Petersburg, Russia, November 16–19, 2020): Extended abstracts. – St. Petersburg, 2020. – Paper 15, doi: 10.3997/2214-4609.202053015.
4. Danilovskiy K.N., Petrov A.M., Leonenko A.R., Sukhorukova K.V. Capabilities of convolutional neural networks based algorithms for solving resistivity logging tasks // Data Science in Oil and Gas 2021 (Novosibirsk, Russia, 4–6 August 2021): Extended abstracts. – Novosibirsk, 2021. – Paper 39, doi: 10.3997/2214-4609.202156039.
5. Glinskikh V.N., Nikitenko M.N., Danilovskiy K.N., Eremin V.N., Moskaev I.A. Telemetry logging systems: software and methodological support in the process of drilling inclined-horizontal wells // Neftegaz.RU. – 2017. – No. 10. – P. 42–49.
6. Glinskikh V.N., Danilovsky K.N., Nechaev O.V. 3D numerical simulation of the azimuthal microlateral LWD signals // Geology, Geophysics and Development of Oil and Gas Fields. – 2018. – No. 10. – P. 32–39.
7. Goodfellow I., Bengio Y., Courville A. Deep Learning. – MIT Press, Cambridge, 2016. – Vol. 1. – 774 p.
8. Kayurov K.N., Eremin V.N., Epov M.I., Glinskikh V.N., Sukhorukova K.V., Nikitenko M.N. Electromagnetic-logging-while-drilling equipment and numerical inversion software // Oil industry. – 2014. – No. 12. – P. 112–115.
9. К.Н. Даниловский, Г.Н. Логинов, Геофизические технологии, 2021, 2, 24–35
10.
11. Kingma D.P., Ba J. Adam: A method for stochastic optimization // 3rd International conference for learning representations (California, USA, May 7–9, 2015): Transactions. – San Diego, 2015. – Document ID: arxiv.org/abs/1412.6980.
12. Krizhevsky A., Sutskever I., Hilton G.E. Imagenet classification with deep convolutional neural networks // Advances in Neural Information Processing Systems. – 2012. – Vol. 25. – P. 1097–1105.
13. Larsen D., Antonov Y., Luxey P., Skillings J., Skaug M., Wagner V. Navigating the horizontal section in a heterogeneous formation while using Extra Deep Azimuthal Resistivity for optimizing the wellbore placement within a narrow TVD window // SPWLA 57th Annual Logging Symposium (Reykjavik, Iceland, June 25–29, 2016): Transactions. – Reykjavik, 2016. – SPWLA-2016-Paper IIII. Loginov G.N., Petrov A.M. Automatic detection of geoelectric boundaries according to lateral logging sounding data by applying a deep convolutional neural network // Russ. Geol. Geophys. – 2019. – Vol. 60 (11). – P. 1319–1325, doi: 10.15372/RGG2019134.
14. Perlin K. An image synthesizer // SIGGRAPH Computer Graphics – 1985. – Vol. 19 (3). – P. 287–296, doi: 10.1145/325165.325247.
15. Sasaki Y. The truth of the F-measure // Teach. Tutor. Mater. – 2007. – Vol. 1 (5). – P. 1–5.
16. Wang Z., Bovik A.C., Sheikh H.R., Simoncelli E.P. Image quality assessment: from error visibility to structural similarity // IEEE Transactions on Image Processing. – 2004. – Vol. 13 (4). – P. 600–612, doi: 10.1109/TIP.2003.819861.
Review
For citations:
Danilovskii K.N., N. L.G. Lateral scanning logging while drilling data processing using convolutional neural networks. Russian Journal of Geophysical Technologies. 2021;(2):24-35. (In Russ.) https://doi.org/10.18303/2619-1563-2021-2-24
Views:
427
Email this article 