Stratigraphy and lithology
| Article # 11_2024 | submitted on 04/02/2024 displayed on website on 05/06/2024 |
| 9 p. | Zhuravlev A.V., Gruzdev D.A. |
| Automated diagnostics of carbonate rocks from microphotographs of thin sections based on machine learning | |
| On the basis of machine learning technology, a computer model for diagnosing carbonate rocks from thin section images has been developed. The model uses the Dunham' classification and identifies four types of carbonates - mudstone, wackestone, packstone, grainstone, with 98% accuracy. The ability to use the model and software based on it is currently limited to the given carbonate classes. Any images outside of these classes will be misdiagnosed. The pros of the model include its high speed of operation and reproducibility of results. It can be used as a human assistant when working with large volumes of material. Keywords: carbonates, thin sections, machine learning, image classification. |
|
| article citation | Zhuravlev A.V., Gruzdev D.A. Avtomatizirovannaya diagnostika karbonatnykh porod po mikrofotografiyam shlifov na osnove mashinnogo obucheniya [Automated diagnostics of carbonate rocks from microphotographs of thin sections based on machine learning]. Neftegazovaya Geologiya. Teoriya I Praktika, 2024, vol. 19, no. 2, available at: https://www.ngtp.ru/rub/2024/11_2024.html EDN: YUQJXC |
References
Babenko V.V., Telnova O.P. Problems and prospects of digital identification of Devonian spores for the stratigraphy // Paleontological journal. - 2022. - Vol. 56. - P. 1067-1073. DOI: 10.1134/S0031030122090040
Baraboshkin E.E., Ismailova L.S., Orlov D.M., Zhukovskaya E.A., Kalmykov G.A., Khotylev O.V., Baraboshkin E.Y., Koroteev D.A. Deep convolutions for indepth automated rock typing // Computers and Geosciences. - 2020. - Vol. 135. - 104330. DOI: 10.1016/j.cageo.2019.104330
Duan X. Automatic identification of conodont species using fine-grained convolutional neural networks // Frontiers in Earth Science. - 2023. - Vol. 10. - № 1. DOI: 10.3389/feart.2022.1046327
Dunham R.J. Classification of carbonate rocks according to depositional texture // AAPG Memoir. - 1962. - № 1. - P. 108-121.
El-Omairi M.A., El Garouani A. A review on advancements in lithological mapping utilizing machine learning algorithms and remote sensing data // Heliyon. - 2023. - № 9. DOI: 10.1016/j.heliyon.2023.e20168
Jia L.Q., Yang M., Meng F., He M.Y., Liu H.M. Mineral photos recognition based on feature fusion and online hard sample mining // Minerals. - 2021. - Vol.11. - 1354. DOI: 10.3390/min11121354
Li D., Zhao J., Ma J. Experimental studies on rock thin-section image classification by deep learning-based approaches // Mathematics. - 2022. - № 10. - 2317. DOI: 10.3390/math10132317
Lokier S.W., Al Junaibi M. The petrographic description of carbonate facies: are we all speaking the same language? // Sedimentology. - 2016. - Vol. 63. - P. 1843-1885. DOI: 10.1111/sed.12293
Ma H., Han G.Q., Peng L., Zhu L.Y., Shu J. Rock thin sections identification based on improved squeeze-and-excitation networks model // Computers & Geosciences. - 2021. - Vol. 152. - 104780. DOI: 10.1016/j.cageo.2021.104780
Marmo R., Amodio S., Tagliaferri R., Ferreri V., Longo G. Textural identification of carbonate rocks by image processing and neural network: methodology proposal and examples // Computers & Geosciences. - 2005. - Vol. 31. - Issue 5. - P. 649-659. DOI: 10.1016/j.cageo.2004.11.016
Su C., Xu S.J., Zhu K.Y., Zhang X.C. Rock classification in petrographic thin section images based on concatenated convolutional neural networks // Earth Sci. Inform. - 2020. - Vol. 13. - P. 1477-1484. DOI: 10.1007/s12145-020-00505-1
Suzuki K. Vision Detector. - 2022. - https://apps.apple.com/us/app/vision-detector/id6443729650
Tetard M., Carlsson V., Meunier M., Danelian T. Merging databases for CNN image recognition, increasing bias or improving results? // Marine Micropaleontology. - 2023. - Vol. 185. - 102296. DOI: 10.1016/j.marmicro.2023.102296
Wang H., Cao W., Zhou Y., Yu P., Yang W. Multitarget intelligent recognition of petrographic thin section images based on faster RCNN // Minerals. - 2023. - Vol. 13. - 872. DOI: 10.3390/min13070872
Wardaya P.D., Khairy H., Chow W.S. Extracting physical properties from thin section: another neural network contribution in rock physics // Paper presented at the International Petroleum Technology Conference, Beijing, China. - 2013a. DOI: 10.2523/IPTC-16977-MS
Wardaya P.D., Khairy H., Chow W.S. Integrating digital image processing and artificial neural network for estimating porosity from thin section // Paper presented at the International Petroleum Technology Conference, Beijing, China. - 2013b. DOI: 10.2523/IPTC-16959-MS
Wu B.K., Ji X.H., He M.Y., Yang M., Zhang Z.C., Chen Y., Wang Y.Z., Zheng X.Q. Mineral identification based on multi-label mage classification // Minerals. - 2022. - Vol. 12. - 1338. DOI: 10.3390/min12111338
Baraboshkin E.E., Ismailova L.S., Orlov D.M., Zhukovskaya E.A., Kalmykov G.A., Khotylev O.V., Baraboshkin E.Y., Koroteev D.A. Deep convolutions for indepth automated rock typing // Computers and Geosciences. - 2020. - Vol. 135. - 104330. DOI: 10.1016/j.cageo.2019.104330
Duan X. Automatic identification of conodont species using fine-grained convolutional neural networks // Frontiers in Earth Science. - 2023. - Vol. 10. - № 1. DOI: 10.3389/feart.2022.1046327
Dunham R.J. Classification of carbonate rocks according to depositional texture // AAPG Memoir. - 1962. - № 1. - P. 108-121.
El-Omairi M.A., El Garouani A. A review on advancements in lithological mapping utilizing machine learning algorithms and remote sensing data // Heliyon. - 2023. - № 9. DOI: 10.1016/j.heliyon.2023.e20168
Jia L.Q., Yang M., Meng F., He M.Y., Liu H.M. Mineral photos recognition based on feature fusion and online hard sample mining // Minerals. - 2021. - Vol.11. - 1354. DOI: 10.3390/min11121354
Li D., Zhao J., Ma J. Experimental studies on rock thin-section image classification by deep learning-based approaches // Mathematics. - 2022. - № 10. - 2317. DOI: 10.3390/math10132317
Lokier S.W., Al Junaibi M. The petrographic description of carbonate facies: are we all speaking the same language? // Sedimentology. - 2016. - Vol. 63. - P. 1843-1885. DOI: 10.1111/sed.12293
Ma H., Han G.Q., Peng L., Zhu L.Y., Shu J. Rock thin sections identification based on improved squeeze-and-excitation networks model // Computers & Geosciences. - 2021. - Vol. 152. - 104780. DOI: 10.1016/j.cageo.2021.104780
Marmo R., Amodio S., Tagliaferri R., Ferreri V., Longo G. Textural identification of carbonate rocks by image processing and neural network: methodology proposal and examples // Computers & Geosciences. - 2005. - Vol. 31. - Issue 5. - P. 649-659. DOI: 10.1016/j.cageo.2004.11.016
Su C., Xu S.J., Zhu K.Y., Zhang X.C. Rock classification in petrographic thin section images based on concatenated convolutional neural networks // Earth Sci. Inform. - 2020. - Vol. 13. - P. 1477-1484. DOI: 10.1007/s12145-020-00505-1
Suzuki K. Vision Detector. - 2022. - https://apps.apple.com/us/app/vision-detector/id6443729650
Tetard M., Carlsson V., Meunier M., Danelian T. Merging databases for CNN image recognition, increasing bias or improving results? // Marine Micropaleontology. - 2023. - Vol. 185. - 102296. DOI: 10.1016/j.marmicro.2023.102296
Wang H., Cao W., Zhou Y., Yu P., Yang W. Multitarget intelligent recognition of petrographic thin section images based on faster RCNN // Minerals. - 2023. - Vol. 13. - 872. DOI: 10.3390/min13070872
Wardaya P.D., Khairy H., Chow W.S. Extracting physical properties from thin section: another neural network contribution in rock physics // Paper presented at the International Petroleum Technology Conference, Beijing, China. - 2013a. DOI: 10.2523/IPTC-16977-MS
Wardaya P.D., Khairy H., Chow W.S. Integrating digital image processing and artificial neural network for estimating porosity from thin section // Paper presented at the International Petroleum Technology Conference, Beijing, China. - 2013b. DOI: 10.2523/IPTC-16959-MS
Wu B.K., Ji X.H., He M.Y., Yang M., Zhang Z.C., Chen Y., Wang Y.Z., Zheng X.Q. Mineral identification based on multi-label mage classification // Minerals. - 2022. - Vol. 12. - 1338. DOI: 10.3390/min12111338