Kazan, Kazan, Russian Federation
Russian Federation
Russian Federation
VAK Russia 1.6
UDC 55
UDC 550.34
UDC 550.383
CSCSTI 38.15
CSCSTI 38.39
CSCSTI 37.01
CSCSTI 37.15
CSCSTI 37.25
CSCSTI 37.31
CSCSTI 38.01
CSCSTI 36.00
CSCSTI 37.00
CSCSTI 38.00
CSCSTI 39.00
CSCSTI 52.00
Russian Classification of Professions by Education 05.03.01
Russian Classification of Professions by Education 05.00.00
Russian Library and Bibliographic Classification 263
Russian Library and Bibliographic Classification 26
Russian Trade and Bibliographic Classification 6332
Russian Trade and Bibliographic Classification 63
BISAC SCI SCIENCE
Petrographic analysis of thin sections of terrigenous rocks plays a key role in characterizing reservoir properties, enabling the assessment of textural and structural features as well as porosity—essential for reconstructing depositional environments and post-sedimentary alterations. Conventional manual analysis of thin sections is time-consuming and subjective, necessitating its automation. This study proposes an automated method for analyzing thin-section areas of quartz sandstone with carbonate cement based on deep learning, combining instance segmentation using the Mask R-CNN model with semantic segmentation employing SemanticFPN. This ensemble approach achieves high segmentation accuracy, as confirmed by Pixel Accuracy and Intersection over Union metrics, significantly accelerating petrographic data processing while enhancing objectivity and reproducibility. The method holds practical value for geological and petroleum exploration studies.
petrographic thin section, mineral grain segmentation, sedimentary petrography, deep learning, artificial intelligence
1. Gmid L. P. Lithological aspects of the carbonate reservoir rocks study // Petroleum Geology – Theoretical and Applied Studies. — 2006. — Vol. 1. — P. 9. — (In Russian).
2. Danilova T. E. Terrigenous rocks of the Devonian and Lower Carboniferous. — Kazan : Pluton, 2008. — 436 p. — (In Russian).
3. Morozov V. P. Educational and methodological manual for laboratory classes in the course "Lithology". — Kazan : Kazan university, 2012. — 40 p. — (In Russian).
4. Muslimov R. Kh., Abdulmazitov R. G., Khisamov R. B., et al. Oil and gas potential of the Republic of Tatarstan. Geology and development of oil fields. Volume 1. — Kazan : FEN AN RT, 2007. — 316 p. — (In Russian).
5. Rykus M. V. Carbonate cementation in sandstone reservoirs: an overview of views // Neftegazovoe delo. — 2020. — Vol. 18, no. 5. — P. 15–26. — https://doi.org/10.17122/ngdelo-2020-5-15-26 — (In Russian).
6. Caeser H., Uijlings J. and Ferrari V. COCO-Stuff: Thing and Stuff Classes in Context // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. — Salt Lake City, UT, USA : IEEE, 2018. — P. 1209–1218. — https://doi.org/10.1109/cvpr.2018.00132
7. Dabek P., Chudy K., Nowak I., et al. Grain segmentation in sandstone thin-section based on computer analysis of microscopic images // IOP Conference Series: Earth and Environmental Science. — 2023. — Vol. 1189, no. 1. — P. 012026. — https://doi.org/10.1088/1755-1315/1189/1/012026
8. Dell’Aversana P. An Integrated Deep Learning Framework for Classification of Mineral Thin Sections and Other Geo-Data, a Tutorial // Minerals. — 2023. — Vol. 13, no. 5. — P. 584. — https://doi.org/10.3390/min13050584
9. Gadhiya Ravindra and Kalani Nilesh. Deep learning architectures for semantic segmentation of 2D image: A review // 1st International Conference on Advances in Signal Processing, VLSI, Commenications and Embedded Systems: ICSVCE-2021. Vol. 2407. — AIP Publishing, 2021. — P. 020032. — https://doi.org/10.1063/5.0074633
10. González-Vargas T. and Gutiérrez-Castorena M. D. C. Brightness Values-Based Discriminant Functions for Classification of Degrees of Organic Matter Decomposition in Soil Thin Sections // Spanish Journal of Soil Science. — 2022. — Vol. 12. — https://doi.org/10.3389/sjss.2022.10348
11. He K., Gkioxari G., Dollár P., et al. Mask R-CNN // IEEE International Conference on Computer Vision (ICCV). — arXiv, 2017. — P. 2980–2988. — https://doi.org/10.48550/ARXIV.1703.06870
12. Kerr P. F. Optical Mineralogy. — McGraw-Hill, 1977. — 492 p. Kirillov A., Girshick R., He K., et al. Panoptic Feature Pyramid Networks // IEEE Computer Vision and Pattern Recognition Conference (CVPR). — Long Beach, CA, USA : arXiv, 2019. — P. 6392–6401. — https://doi.org/10.4 8550/ARXIV.1901.02446
13. Kirillov A., Wu Yu., He K., et al. PointRend: Image Segmentation as Rendering // IEEE Computer Vision and Pattern Recognition Conference (CVPR). — arXiv, 2020. — P. 9799–9808. — https://doi.org/10.48550/ARXIV.1912.08193
14. Leichter A., Almeev R. R., Wittich D., et al. Automated Segmentation of Olivine Phenocrysts in a Volcanic Rock Thin Section Using a Fully Convolutional Neural Network // Frontiers in Earth Science. — 2022. — Vol. 10. — https://doi.org/10.3389/feart.2022.740638
15. Lin T. Y., Maire M., Belongie S., et al. Microsoft COCO: Common Objects in Context // Computer Vision – ECCV 2014. — Cham : Springer International Publishing, 2014. — P. 740–755. — https://doi.org/10.1007/978-3-319-10602-1_48
16. Padilla R., Netto S. L. and Silva E. A. B. da. A Survey on Performance Metrics for Object-Detection Algorithms // 2020 International Conference on Systems, Signals and Image Processing (IWSSIP). — Niteroi, Brazil : IEEE, 2020. — P. 237–242. — https://doi.org/10.1109/iwssip48289.2020.9145130
17. Ren S., He K., Girshick R., et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks // IEEE Transactions on Pattern Analysis and Machine Intelligence. — 2017. — Vol. 39, no. 6. — P. 1137–1149. — https://doi.org/10.1109/tpami.2016.2577031
18. Su C., Xu S. J., Zhu K. Y., et al. Rock classification in petrographic thin section images based on concatenated convolutional neural networks // Earth Science Informatics. — 2020. — Vol. 13, no. 4. — P. 1477–1484. — https://doi.org/10.1007/s12145-020-00505-1
19. Wang H., Cao W., Zhou Y., et al. Multitarget Intelligent Recognition of Petrographic Thin Section Images Based on Faster RCNN // Minerals. — 2023. — Vol. 13, no. 7. — P. 872. — https://doi.org/10.3390/min13070872
