«Automation and Informatization of the fuel and energy complex»

Application of deep learning methods in current tasks of processing micro-CT images of core plugs. Segmentation, restoration and synthesis of digital core

UDC: 004.8
DOI: 10.33285/2782-604X-2023-12(605)-34-43

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: micro-CT, deep learning, machine learning, computer vision, digital core plug, segmentation, mineralogical segmentation, lost sections restoration, 3D image synthesis of digital cores

Annotation:

The article considers the application of deep learning (DL) based methods when processing core plugs micro-CT data. Specifically, the study demonstrates the potential of DL for tasks such as segmentation, lost sections restoration, and 3D image synthesis. The results suggest that DL methods can provide efficient solutions to these challenges in core plug analysis, which could have significant implications for geological and petro-physical research.

Bibliography:

1. Arsen'ev-Obraztsov S.S., Plyushch G.O. Primenenie metodov glubokogo obucheniya v aktual'nykh zadachakh obrabotki mikroKT obraztsov kerna. Reshenie obratnoy zadachi, interpolyatsiya razrezhennykh sinogramm, fil'tratsiya izobrazheniy srezov // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 10(603). – S. 48–58. – DOI: 10.33285/2782-604X-2023-10(603)-48-58
2. Jasim W.N., Mohammed R.J. A Survey on Segmentation Techniques for Image Processing // Iraqi J. for Electrical and Electronic Engineering. – 2021. – Vol. 17, Issue 2. – P. 73–93. – DOI: 10.37917/ijeee.17.2.10
3. Rapid quantitative mineral and phase analysis using automated scanning electron microscopy (QemSCAN); potential applications in forensic geoscience / D. Pirrie, A.R. Butcher, M.R. Power [et al.] // Geological Society London Special Publications. – 2004. – Vol. 232, Issue 1. – P. 123–136. – DOI: 10.1144/GSL.SP.2004.232.01.12
4. Physical Accuracy of Deep Neural Networks for 2d and 3d Multi-Mineral Segmentation of Rock micro-CT Images: A Preprint / Ying Da Wang, M. Shabaninejad, R.T. Armstrong, P. Mostaghimi. – 2020. – DOI: 10.48550/arXiv.2002.05322
5. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. – 2015. – DOI: 10.48550/ARXIV.1505.04597
6. Badrinarayanan V., Kendall A., Cipolla R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2017. – Vol. 39, Issue 12. – P. 2481–2495. – DOI: 10.1109/TPAMI.2016.2644615
7. Deep Residual Learning for Image Recognition / Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun // IEEE Conf. on Computer Vision and Pattern Recognition. – 2015. – P. 770–778. – URL: https://arxiv.org/pdf/1512.03385.pdf
8. U-ReSNet: Ultimate Coupling of Registration and Segmentation with Deep Nets / T. Estienne, M. Vakalopoulou, S. Christodoulidis [et al.] // Lecture Notes in Computer Science. Vol. 11766. Medical Image Computing and Computer Assisted Intervention. – Cham: Springer, 2019. – P. 310–319. – DOI: 10.1007/978-3-030-32248-9_35
9. Arsenyev-Obraztsov S.S., Plusch G.O. Deep learning based restoration of lost sections in MicroCT core plugs // IOP Conf. Series: Materials Science and Engineering. – 2021. – Vol. 1201. Third Conf. of Computational Methods & Ocean Technology (COTech 2021), Stavanger, Norway and Second Conf. of Oil & Gas Technologies in Cold Climate (OGTech 2021), Nov. 25–26, 2021, Moscow, Russia. – P. 012070. – DOI: 10.1088/1757-899X/1201/1/012070
10. Klette R. Concise Computer Vision: An Introduction into Theory and Algorithms. – London: Springer-Verlag, 2014. – XVIII, 429 p.
11. Akima H. A New Method of Interpolation and Smooth Curve Fitting Based on Local Procedures // J. of the ACM. – 1970. – Vol. 17, Issue 4. – P. 589–602. – DOI: 10.1145/321607.321609
12. A practical guide to performing multiple-point statistical simulations with the Direct Sampling algorithm / E. Meerschman, G. Pirot, G. Mariethoz [et al.] // Computers & Geosciences. – 2013. – Vol. 52. – P. 307–324. – DOI: 10.1016/j.cageo.2012.09.019
13. Mariethoz G., Renard P., Straubhaar J. The direct sampling method to perform multiple-point geostatistical simulations // Water Resources Research. – 2010. – Vol. 46, Issue 11. – DOI: 10.1029/2008WR007621
14. Mosser L., Dubrule O., Blunt M.J. Reconstruction of three-dimensional porous media using generative adversarial neural networks // Physical Review E. – 2017. – Vol. 96, Issue 4. – P. 043309-1–043309-17. – DOI: 10.1103/PhysRevE.96.043309
15. Arsen'ev-Obraztsov S.S., Plyushch G.O. Primenenie metodov komp'yuternoy tomografii dlya vosstanovleniya utrachennykh chastey kerna // Nanoyavleniya v geoekologii i pri razrabotke mestorozhdeniy uglevodorodnogo syr'ya: ot nanomineralogii i nanokhimii k nanotekhnologiyam: materialy VII Mezhdunar. konf. "NANOTECHOILGAS-2022", M., 22–23 noyab. 2022 g. – M.: Tvorcheskaya masterskaya, 2022. – S. 345–354.
16. Van den Oord A., Vinyals O., Kavukcuoglu K. Neural Discrete Representation Learning // 31st Conf. on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA. – 2017. – DOI: 10.48550/ARXIV.1711.00937
17. Conditional Image Generation with PixelCNN Decoders / A. van den Oord, N. Kalchbrenner, O. Vinyals [et al.]. – 2016. – DOI: 10.48550/ARXIV.1606.05328
18. High-Resolution Image Synthesis with Latent Diffusion Models / R. Rombach, A. Blattmann, D. Lorenz [et al.] // IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). – 2022. – DOI: 10.48550/arXiv.2112.10752
19. Razavi A., van den Oord A., Vinyals O. Generating Diverse High-Fidelity Images with VQ-VAE-2. – 2019. – DOI: 10.48550/ARXIV.1906.00446
20. Sudakov O., Burnaev E., Koroteev D. Driving Digital Rock towards Machine Learning: Predicting Permeability with Gradient Boosting and Deep Neural Networks // Computers & Geosciences. – 2019. – Vol. 127. – P. 91–98. – DOI: 10.1016/j.cageo.2019.02.002