Applicability of 2D algorithms for 3D characterization in digital rocks physics: an example of a machine learning-based super resolution image generation

• Autorzy: Karimpouli, Sadegh , Kadyrov, Rail , Siegert, Mirko , Saenger, Erik Hans
• Języki publikacji: EN

Abstrakty

EN

Digital rock physics is based on imaging, segmentation and numerical computations of rock samples. Due to challenges regarding the handling of a large 3-dimensional (3D) sample, 2D algorithms have always been attractive. However, in 2D algorithms, the efficiency of the pore structures in the third direction of the generated 3D sample is always questionable. We used four individually captured gCT-images of a given Berea sandstone with different resolutions (12.922, 9.499, 5.775, and 3.436 gm) to evaluate the super-resolution 3D images generated by multistep Super Resolution Double-U-Net (SRDUN), a 2D algorithm. Results show that unrealistic features form in the third direction due to section-wise reconstruction of 2D images. To overcome this issue, we suggest to generate three 3D samples using SRDUN in different directions and then to use one of two strategies: compute the average sample (reconstruction by averaging) or segment one-directional samples and combine them together (binary combination). We numerically compute rock physical properties (porosity, connected porosity, P- and S-wave velocity, permeability and formation factor) to evaluate these models. Results reveal that compared to one-directional samples, harmonic averaging leads to a sample with more similar properties to the original sample. On the other hand, rock physics trends can be calculated using a binary combination strategy by generating low, medium and high porosity samples. These trends are compatible with the properties obtained from one-directional and averaged samples as long as the scale difference between the input and output images of SRDUN is small enough (less than about 3 in our case). By increasing the scale difference, more dispersed results are obtained.

Słowa kluczowe

PL

super rozdzielczość; piaskowiec Berea; obliczenia numeryczne

EN

super resolution; Berea sandstone; numerical computation; SRDUN; 2D-to-3D

• Czasopismo: Acta Geophysica
• Rocznik: 2024
• Tom: Vol. 72, no. 2
• Strony: 861--874
• Opis fizyczny: Bibliogr. 34 poz.

Twórcy

autor

Karimpouli, Sadegh

• Helmholtz Centre Potsdam, GFZ German Research Centre for Geosciences, Potsdam, Germany,
• Mining Engineering Group, Engineering Faculty, University of Zanjan, Zanjan, Iran

autor

Kadyrov, Rail

• Institute of Geology and Petroleum Technologies, Kazan Federal University, Kazan, Russia

autor

Siegert, Mirko

• Bochum University of Applied Sciences, 44801 Bochum, Germany

autor

Saenger, Erik Hans

• Bochum University of Applied Sciences, 44801 Bochum, Germany
• Fraunhofer IEG, Fraunhofer Research Institution for Energy Infrastructure and Geothermal Systems, 44801 Bochum, Germany
• Ruhr-University Bochum, 44801 Bochum, Germany

Bibliografia

• 1. Ahuja VR, Gupta U, Rapole SR et al (2022) Siamese-SR: A siamese super-resolution model for boosting resolution of digital rock images for improved petrophysical property estimation. IEEE Trans Image Process 31:3479-3493. https://doi.org/10.1109/TIP. 2022.3172211
• 2. Andrä H, Combaret N, Dvorkin J et al (2013a) Digital rock physics benchmarks—Part I: imaging and segmentation. Comput Geosci 50:25-32. https://doi.org/10.1016/j.cageo.2012.09.005
• 3. Andrä H, Combaret N, Dvorkin J et al (2013b) Digital rock physics benchmarks-part II: computing effective properties. Comput Geo-sci 50:33-43. https://doi.org/10.1016/j.cageo.2012.09.008
• 4. Archie GE (1942) The electrical resistivity log as an aid in determining some reservoir characteristics. Transactions of the AIME 146:54-62. https://doi.org/10.2118/942054-G
• 5. Chen H, He X, Teng Q et al (2020) Super-resolution of real-world rock microcomputed tomography images using cycle-consistent generative adversarial networks. Phys Rev E 101:023305. https:// doi.org/10.1103/PhysRevE.101.023305
• 6. Churcher PL, French PR, Shaw JC, Schramm LL (1991) Rock properties of Berea sandstone, Baker dolomite, and Indiana limestone. In: SPE international conference on oilfield chemistry. SPE, pp. SPE-21044
• 7. da Wang Y, Armstrong RT, Mostaghimi P (2019) Enhancing resolution of digital rock images with super resolution convolutional neural networks. J Pet Sci Eng 182:106261. https://doi.org/10.1016/j. petrol.2019.106261
• 8. Darcy H (1856) Les fontaines publiques de la ville de Dijon: Exposition et application des principes a suivre et des formules a employer dans les questions de distribution d’eau: Ouvrage terminé par un appendice relatif aux fournitures d’eau de plusieurs villes, au fil-trage des eaux et a la fabrication des tuyaux de fonte, de plomb, de tole et de bitume
• 9. Dvorkin J, Nur A (1996) Elasticity of high-porosity sandstones: theory for two North Sea data sets. Geophysics 61:1363-1370. https:// doi.org/10.1190/1.1444059
• 10. Gong L, Nie L, Xu Y (2020) Geometrical and topological analysis of pore space in sandstones based on X-ray computed tomography. Energies 13(15):3774. https://doi.org/10.3390/en13153774
• 11. Hussaini SR, Dvorkin J (2022) Permeability in the thin section. J Pet Sci Eng 218:110959. https://doi.org/10.1016/j.petrol.2022.110959
• 12. Kadyrov R, Nurgaliev D, Saenger EH et al (2022) Digital rock physics: Defining the reservoir properties on drill cuttings. J Pet Sci Eng 210:110063. https://doi.org/10.1016/J.PETROL.2021.110063
• 13. Kamrava S, Tahmasebi P, Sahimi M (2020) Linking morphology of porous media to their macroscopic permeability by deep learning. Transp Porous Media 131:427-448. https://doi.org/10.1007/ s11242-019-01352-5
• 14. Karimpouli S, Faraji A, Balcewicz M, Saenger EH (2020) Computing heterogeneous core sample velocity using digital rock physics: a multiscale approach. Comput Geosci 135:104378
• 15. Karimpouli S, Kadyrov R (2022) Multistep Super Resolution DoubleU-net (SRDUN) for enhancing the resolution of Berea sandstone images. J Pet Sci Eng 216:110833. https://doi.org/10.1016/j.pet-rol.2022.110833
• 16. Karimpouli S, Tahmasebi P (2019a) Coal Fractures Segmentation Using Machine Learning. Natural Resources Research Under Review
• 17. Karimpouli S, Tahmasebi P (2019b) Segmentation of digital rock images using deep convolutional autoencoder networks. Comput Geosci 126:142-150. https://doi.org/10.1016/j.cageo.2019.02.003
• 18. Karimpouli S, Tahmasebi P, Saenger EH (2018) Estimating 3D elastic moduli of rock from 2D thin-section images using differential effective medium theory. GEOPHYSICS 83:MR211-MR219. https://doi.org/10.1190/geo2017-0504.1
• 19. Khalifa NE, Loey M, Mirjalili S (2022) A comprehensive survey of recent trends in deep learning for digital images augmentation. Artif Intell Rev 55:2351-2377. https://doi.org/10.1007/ s10462-021-10066-4
• 20. Li B, Nie X, Cai J et al (2022) U-Net model for multi-component digital rock modeling of shales based on CT and QEMSCAN images. J Pet Sci Eng 216:110734. https://doi.org/10.1016/j.petrol.2022. 110734
• 21. Liu J, Pereira GG, Liu Q, Regenauer-Lieb K (2016) Computational challenges in the analyses of petrophysics using microtomography and upscaling: a review. Comput Geosci 89:107-117. https://doi. org/10.1016/j.cageo.2016.01.014
• 22. Mavko G, Mukerji T, Dvorkin J (2009) The rock physics handbook: Tools for seismic analysis of porous media. Cambridge university press
• 23. Niu Y, Jackson SJ, Alqahtani N et al (2022) Paired and unpaired deep learning methods for physically accurate super-resolution carbonate rock images. Transp Porous Media 144:825-847. https://doi. org/10.1007/s11242-022-01842-z
• 24. Phan J, Ruspini LC, Lindseth F (2021) Automatic segmentation tool for 3D digital rocks by deep learning. Sci Rep 11:19123. https:// doi.org/10.1038/s41598-021-98697-z
• 25. Saenger EH, Gold N, Shapiro SA (2000) Modeling the propagation of elastic waves using a modified finite-difference grid. Wave Motion 31:77-92. https://doi.org/10.1016/S0165-2125(99)00023-2
• 26. Saenger EH, Kruger OS, Shapiro SA et al (2004) Effective elastic properties of randomly fractured soils: 3D numerical experiments. Geophys Prospect 52:183-195. https://doi.org/10.1111/j. 1365-2478.2004.00407.x
• 27. Saslow WM (2002) Ohm’s law: electric current is driven by emf, and limited by electrical resistance. Electricity, Magnetism, and Light 281-335
• 28. Saxena N, Hofmann R, Hows A et al (2019) Rock compressibility from microcomputed tomography images: controls on digital rock simulations. GEOPHYSICS. https://doi.org/10.1190/geo20 18-0499.1
• 29. Saxena N, Mavko G (2016) Estimating elastic moduli of rocks from thin sections: digital rock study of 3D properties from 2D images. Comput Geosci 88:9-21. https://doi.org/10.1016/j.cageo.2015.12. 008
• 30. Saxena N, Mavko G, Hofmann R, Srisutthiyakorn N (2017) Estimating permeability from thin sections without reconstruction: digital rock study of 3D properties from 2D images. Comput Geosci 102:79-99. https://doi.org/10.1016/j.cageo.2017.02.014
• 31. Schön J (2015) Pore Space Properties. In Developments in Petroleum Science (Vol. 65, pp. 21-84). Elsevier. https://doi.org/10.1016/ B978-0-08-100404-3.00002-0
• 32. Siegert M, Gurris M, Lebedev M, Saenger EH (2022) Numerical modeling of the permeability in Bentheim sandstone under confining pressure. 1-62. https://doi.org/10.1190/GEO2021-0718.1
• 33. Tembely M, AlSumaiti AM, Alameri WS (2021) Machine and deep learning for estimating the permeability of complex carbonate rock from X-ray micro-computed tomography. Energy Reports 7:1460-1472. https://doi.org/10.1016/j.egyr.2021.02.065
• 34. Zhu J-Y, Park T, Isola P, Efros AA (2017) Unpaired Image-To-Image Translation Using Cycle-Consistent Adversarial Networks. 2223-2232

Identyfikatory

DOI

10.1007/s11600-023-01149-7