IMAGE-BASED YOLOV4 ARCHITECTURE FOR DETECTING MINERAL IN SEDIMENTARY ROCKS THIN SECTION
DOI:
https://doi.org/10.11113/aej.v14.19904Keywords:
YOLOv4, Deep learning, Mineral, Sedimentary rock, ImageAbstract
Thin section analysis of sedimentary rocks is the basis for identifying minerals and textures. In general, quantitative analysis of thin sections of rock often requires many hours of work when done manually. In today's era, mineralogical interpretation and percentage calculations must be carried out automatically using more practical applications. The research method begins with the identification of 44 thin section samples in parallel plane polarized (PPL) and crossed polarized (XPL) conditions with thin section analysis then mineralogy detection is carried out using a computational approach, namely the use of image-based Deep Learning YoloV4 architecture with 2D RGB image objects from the thin section of sedimentary rock. The results of this study show the best values of Average Precision in Quartz, Feldspar, and lithic are 39.21% in the XPL model, 26.53% in the XPL model, and 15.75% in combined mode, according to the training and testing of YoloV4 Models for the identification of rock minerals in thin sections. Based on the complexity of the mineral types, the granularity of the detection, and the specific geological objectives, establishing a meaningful benchmark or baseline for comparison is always challenging. Additionally, consider discussing the trade-offs between precision and recall, as a higher precision may be more critical in some geological applications. It is expected that the application of this research can produce practical, fast and accurate interpretation of the determination of minerals in sedimentary rocks from all thin-section images of rocks and thus provide a complete understanding of geological views automatically.
References
Dutton, S.P., Loucks, R.G. and Day-Stirrat, R.J., 2012. Impact of regional variation in detrital mineral composition on reservoir quality in deep to ultradeep lower Miocene sandstones, western Gulf of Mexico. Marine and Petroleum Geology, 35(1): 139-153. https://doi.org/10.1016/j.marpetgeo.2012.01.006
Folk, R.L., 1974. Petrology of sedimentary rocks: Austin, Texas.
Pettijohn, F.J., 1975. Sedimentary rocks. 3: 628. New York: Harper & Row.
Lander, R.H. and Walderhaug, O., 1999. Predicting porosity through simulating sandstone compaction and quartz cementation. AAPG bulletin, 83(3): 433-449.
Nasseri, M.H.B. and Mohanty, B., 2008. Fracture toughness anisotropy in granitic rocks. International Journal of Rock Mechanics and Mining Sciences. 45(2): 167 193. https://doi.org/10.1016/j.ijrmms.2007.04.005
de Lima, R.P., Duarte, D., Nicholson, C., Slatt, R. and Marfurt, K.J., 2020. Petrographic microfacies classification with deep convolutional neural networks. Computers & geosciences, 142: 104481. https://doi.org/10.1016/j.cageo.2020.104481
Srisutthiyakorn, N., Hunter, S., Sarker, R., Hofmann, R. and Espejo, I., 2018. Predicting elastic properties and permeability of rocks from 2D thin sections. The Leading Edge, 37(6): 421-427. https://doi.org/10.1190/tle37060421.1
Stehli, F.G. and Webb, S.D. eds., 2013. The great American biotic interchange. 4. Springer Science & Business Media.
Lander, R.H., Larese, R.E. and Bonnell, L.M., 2008. Toward more accurate quartz cement models: The importance of euhedral versus noneuhedral growth rates. AAPG bulletin, 92(11): 1537-1563. https://doi.org/10.1306/07160808037
Ciregan, D., Meier, U. and Schmidhuber, J., 2012, June. Multi-column deep neural networks for image classification. In 2012 IEEE conference on computer vision and pattern recognition. 3642-3649. IEEE. https://doi.org/10.1109/CVPR.2012.6248110
Budennyy, S., Pachezhertsev, A., Bukharev, A., Erofeev, A., Mitrushkin, D. and Belozerov, B., 2017, October. Image processing and machine learning approaches for petrographic thin section analysis. In SPE Russian Petroleum Technology Conference. OnePetro. https://doi.org/10.2118/187885-RU
Ma, Z. and Gao, S., 2017, May. Image analysis of rock thin section based on machine learning. In International Geophysical Conference, Qingdao, China, 17-20 April 2017. 844-847. Society of Exploration Geophysicists and Chinese Petroleum Society. https://doi.org/10.1190/IGC2017-213
Maitre, J., Bouchard, K. and Bédard, L.P., 2019. Mineral grains recognition using computer vision and machine learning. Computers & Geosciences. 130: 84 93. https://doi.org/10.1016/j.cageo.2019.05.009
Saxena, N., Day-Stirrat, R.J., Hows, A. and Hofmann, R., 2021. Application of deep learning for semantic segmentation of sandstone thin sections. Computers & Geosciences, 152: 104778. https://doi.org/10.1016/j.cageo.2021.104778
Tang, D.G., Milliken, K.L. and Spikes, K.T., 2020. Machine learning for point counting and segmentation of arenite in thin section. Marine and Petroleum Geology, 120: 104518. https://doi.org/10.1016/j.marpetgeo.2020.104518
Miao, J., Hirakawa, T., Yamashita, T. and Fujiyoshi, H., 2021, February. 3D Object Detection with Normal-map on Point Clouds. In VISIGRAPP 5: 569-576. https://doi.org/10.5220/0010304305690576
Pratama, B.G. and Yuliani, O., 2021, October. Monitoring and Controlling Thermal Comfort in Air Conditioner Using YoloV4 And Predicted Mean Vote. In 2021 7th International Conference on Electrical, Electronics and Information Engineering (ICEEIE). 460-465. IEEE.
https://doi.org/10.1109/ICEEIE52663.2021.9616849
Bochkovskiy, A., Wang, C.Y. and Liao, H.Y.M., 2020. Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934.
Tzutalin, 2015, LabelImg. Git code. https://github.com/tzutalin/labelImg
Pratama, B. G., Qodri, M. F., & Sugarbo, O. (2023, March). Building YoloV4 models for identification of rock minerals in thin section. In IOP Conference Series: Earth and Environmental Science. 1151(1): 012046. IOP Publishing.
Wu, D., Lv, S., Jiang, M. and Song, H., 2020. Using channel pruning-based YOLO v4 deep learning algorithm for the real-time and accurate detection of apple flowers in natural environments. Computers and Electronics in Agriculture. 178: 105742. https://doi.org/10.1016/j.compag.2020.105742
