Application of Deep Learning in Petrographic Coal Images Segmentation
Abstract
:1. Introduction
2. Materials and Methods
- The images which do not show the given maceral were excluded from the training set. For example, if the model was trained for vitrinite segmentation, all images where vitrinite was not present were excluded from the training set;
- Basic images augmentation was performed. The augmentation was limited to rotation by π/2, π, 3π/2 and mirroring horizontally and vertically.
3. Results and Discussion
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Dai, S.; Hower, J.C.; Finkelman, R.B.; Graham, I.T.; French, D.; Ward, C.R.; Eskenazy, G.; Wei, Q.; Zhao, L. Organic associations of non-mineral elements in coal: A review. Int. J. Coal Geol. 2019, 218, 103347. [Google Scholar] [CrossRef]
- Dai, S.; Finkelman, R.B. Coal as a promising source of critical elements: Progress and future prospects. Int. J. Coal Geol. 2018, 186, 155–164. [Google Scholar] [CrossRef]
- Finkelman, R.B.; Dai, S.; French, D. The importance of minerals in coal as the hosts of chemical elements: A review. Int. J. Coal Geol. 2019, 212. [Google Scholar] [CrossRef]
- Hower, J.C. Clean Coal Technologies and Clean Coal Technologies Roadmaps-by Colin Henderson, International Energy Agency, CCC/74 and CCC/75, 2003; and Trends in Emission Standards by Lesley L. Sloss, International Energy Agency, CCC/77, 2003. Int. J. Coal Geol. 2004, 4, 270–271. [Google Scholar] [CrossRef]
- Hower, J.C.; Ban, H.; Schaefer, J.L.; Stencel, J.M. Maceral/microlithotype partitioning through triboelectrostatic dry coal cleaning. Int. J. Coal Geol. 1997, 34, 277–286. [Google Scholar] [CrossRef]
- Hower, J.C.; Robl, T.L.; Thomas, G.A. Changes in the quality of coal delivered to Kentucky power plants, 1978 to 1997: Responses to Clean Air Act directives. Int. J. Coal Geol. 1999, 41, 125–155. [Google Scholar] [CrossRef]
- O’Keefe, J.M.; Bechtel, A.; Christanis, K.; Dai, S.; DiMichele, W.A.; Eble, C.F.; Esterle, J.; Mastalerz, M.; Raymond, A.L.; Valentim, B.; et al. On the fundamental difference between coal rank and coal type. Int. J. Coal Geol. 2013, 118, 58–87. [Google Scholar] [CrossRef]
- Hower, J.C.; Eble, C.F.; O’Keefe, J.M. Phyteral perspectives: Every maceral tells a story. Int. J. Coal Geol. 2021, 247, 103849. [Google Scholar] [CrossRef]
- ICCP, I. Handbook Coal Petr. Suppl. to 2nd Ed. ICCP. 1998. The New Vitrinite Classification (ICCP System 1994). Fuel 2001, 77, 349–358. [Google Scholar]
- Sỳkorová, I.; Pickel, W.; Christanis, K.; Wolf, M.; Taylor, G.; Flores, D. Classification of Huminite—ICCP System 1994. Int. J. Coal Geol. 2005, 62, 85–106. [Google Scholar] [CrossRef]
- Pickel, W.; Kus, J.; Flores, D.; Kalaitzidis, S.; Christanis, K.; Cardott, B.; Misz-Kennan, M.; Rodrigues, S.; Hentschel, A.; Hamor-Vido, M.; et al. Classification of Liptinite–ICCP System 1994. Int. J. Coal Geol. 2017, 169, 40–61. [Google Scholar] [CrossRef] [Green Version]
- Parzentny, H.R.; Róg, L. Dependences between Certain Petrographic, Geochemical and Technological Indicators of Coal Quality in the Limnic Series of the Upper Silesian Coal Basin (USCB), Poland. Arch. Min. Sci. 2020, 65, 665–684. [Google Scholar] [CrossRef]
- Kruszewska, K.; Dybowa-Jachowicz, S. Draft of Coal Pertology; Publishing House of the University of Silesia: Katowice, Poland, 1997. [Google Scholar]
- Parzentny, H.; Róg, L. Evaluation the Value of Some Petrographic, Physico-Chemical and Geochemical Indicators of Quality of Coal in Paralic Series of the Upper Silesian Coal Basin and Attempt to Find a Correlation Between Them. Gospod. Surowcami Miner. 2017, 33, 51–76. [Google Scholar] [CrossRef] [Green Version]
- Vasconcelos, L.D.S.E. The petrographic composition of world coals. Statistical results obtained from a literature survey with reference to coal type (maceral composition). Int. J. Coal Geol. 1999, 40, 27–58. [Google Scholar] [CrossRef]
- Permana, A.K.; Ward, C.R.; Gurba, L.W. Maceral Characteristics and Vitrinite Reflectance Variation of The High Rank Coals, South Walker Creek, Bowen Basin, Australia. Indones. J. Geosci. 2013, 8. [Google Scholar] [CrossRef]
- Denge, E.; Baiyegunhi, C. Maceral Types and Quality of Coal in the Tuli Coalfield: A Case Study of Coal in the Madzaringwe Formation in the Vele Colliery, Limpopo Province, South Africa. Appl. Sci. 2021, 11, 2179. [Google Scholar] [CrossRef]
- Suárez-Ruiz, I.; Ward, C.R. Basic Factors Controlling Coal Quality and Technological Behavior of Coal. In Applied Coal Petrology; Elsevier: Amsterdam, The Netherlands, 2008; pp. 19–59. [Google Scholar]
- Cutruneo, C.M.; Oliveira, M.; Ward, C.; Hower, J.C.; de Brum, I.A.; Sampaio, C.H.; Kautzmann, R.M.; Taffarel, S.R.; Teixeira, E.C.; Silva, L. A mineralogical and geochemical study of three Brazilian coal cleaning rejects: Demonstration of electron beam applications. Int. J. Coal Geol. 2014, 130, 33–52. [Google Scholar] [CrossRef]
- Mastalerz, M.; Padgett, P.L. From in situ coal to the final coal product: A case study of the Danville Coal Member (Indiana). Int. J. Coal Geol. 1999, 41, 107–123. [Google Scholar] [CrossRef]
- Méndez, L.; Borrego, A.; Martinez-Tarazona, M.; Menéndez, R. Influence of petrographic and mineral matter composition of coal particles on their combustion reactivity. Fuel 2003, 82, 1875–1882. [Google Scholar] [CrossRef]
- Jelonek, I.; Jelonek, Z. Influence of petrographic properties of bituminous coal on the quality of metallurgical coke. Sci. J. Inst. Miner. Energy Econ. Pol. Acad. Sci. 2017, 100, 49–66. [Google Scholar]
- Jelonek, I.; Mirkowski, Z. Petrographic and geochemical investigation of coal slurries and of the products resulting from their combustion. Int. J. Coal Geol. 2015, 139, 228–236. [Google Scholar] [CrossRef]
- Bielowicz, B. Petrographic Characteristics of Coal Gasification and Combustion by-Products from High Volatile Bituminous Coal. Energies 2020, 13, 4374. [Google Scholar] [CrossRef]
- Bielowicz, B. Petrographic Composition of Coal from the Janina Mine and Char Obtained as a Result of Gasification in the CFB Gasifier. Miner. Resour. Manag. 2019, 35, 99–116. [Google Scholar] [CrossRef]
- Mirkowski, Z.; Jelonek, I. Petrographic composition of coals and products of coal combustion from the selected combined heat and power plants (CHP) and heating plants in Upper Silesia, Poland. Int. J. Coal Geol. 2018, 201, 102–108. [Google Scholar] [CrossRef] [Green Version]
- Bielowicz, B.; Misiak, J. The Impact of Coal’s Petrographic Composition on Its Suitability for the Gasification Process: The Example of Polish Deposits. Resources 2020, 9, 111. [Google Scholar] [CrossRef]
- Róg, L. Vitrinite reflectance as a measure of the range of influence of the temperature of a georeactor on rock mass during underground coal gasification. Fuel 2018, 224, 94–100. [Google Scholar] [CrossRef]
- Büçkün, Z.; Inaner, H.; Oskay, R.G.; Christanis, K. Palaeoenvironmental Reconstruction of Hüsamlar Coal Seam, SW Turkey. J. Earth Syst. Sci. 2015, 124, 729–746. [Google Scholar] [CrossRef] [Green Version]
- Oskay, R.; Christanis, K.; Inaner, H.; Salman, M.; Taka, M. Palaeoenvironmental reconstruction of the eastern part of the Karapınar-Ayrancı coal deposit (Central Turkey). Int. J. Coal Geol. 2016, 163, 100–111. [Google Scholar] [CrossRef]
- Mastalerz, M.; Hower, J.; Taulbee, D. Variations in Chemistry of Macerals as Refl Ected by Micro-Scale Analysis of a Spanish Coal. Geol. Acta 2013, 11, 483–493. [Google Scholar]
- Querol, X.; Cabrera, L.; Pickel, W.; López-Soler, A.; Hagemann, H.; Fernandez-Turiel, J.-L. Geological controls on the coal quality of the Mequinenza subbituminous coal deposit, northeast Spain. Int. J. Coal Geol. 1996, 29, 67–91. [Google Scholar] [CrossRef]
- Suarez-Ruiz, I.; Jimenez, A.; Iglesias, M.J.; Laggoun-Defarge, F.; Prado, J.G. Influence of Resinite on Huminite Properties. Energy Fuels 1994, 8, 1417–1424. [Google Scholar] [CrossRef]
- Oestreich, J.; Tolley, W.; Rice, D. The development of a color sensor system to measure mineral compositions. Miner. Eng. 1995, 8, 31–39. [Google Scholar] [CrossRef]
- Singh, V.; Rao, S.M. Application of image processing and radial basis neural network techniques for ore sorting and ore classification. Miner. Eng. 2005, 18, 1412–1420. [Google Scholar] [CrossRef]
- Tessier, J.; Duchesne, C.; Bartolacci, G. A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor belts. Miner. Eng. 2007, 20, 1129–1144. [Google Scholar] [CrossRef]
- Iwaszenko, S.; Nurzynska, K. Rock Grains Segmentation Using Curvilinear Structures Based Features. In Proceedings of the Real-Time Image Processing and Deep Learning 2019. SPIE Int. Soc. Opt. Eng. 2019, 10996, 109960V. [Google Scholar]
- Zhang, Z.; Yang, J.; Su, X.; Ding, L.; Wang, Y. Multi-Scale Image Segmentation of Coal Piles on a Belt Based on the Hessian Matrix. Particuology 2013, 11, 549–555. [Google Scholar] [CrossRef]
- Perez, C.A.; Estévez, P.A.; Vera, P.A.; Castillo, L.E.; Aravena, C.M.; Schulz, D.A.; Medina, L.E. Ore grade estimation by feature selection and voting using boundary detection in digital image analysis. Int. J. Miner. Process. 2011, 101, 28–36. [Google Scholar] [CrossRef]
- Iwaszenko, S.; Smoliński, A. Texture features for bulk rock material grain boundary segmentation. J. King Saud Univ.—Eng. Sci. 2020, 33, 95–103. [Google Scholar] [CrossRef]
- Mertens, G.; Elsen, J. Use of computer assisted image analysis for the determination of the grain-size distribution of sands used in mortars. Cem. Concr. Res. 2006, 36, 1453–1459. [Google Scholar] [CrossRef]
- Kazak, A.; Simonov, K.; Kulikov, V. Machine-Learning-Assisted Segmentation of Focused Ion Beam-Scanning Electron Microscopy Images with Artifacts for Improved Void-Space Characterization of Tight Reservoir Rocks. SPE J. 2021, 26, 1739–1758. [Google Scholar] [CrossRef]
- Zhou, Y.; Starkey, J.; Mansinha, L. Segmentation of petrographic images by integrating edge detection and region growing. Comput. Geosci. 2004, 30, 817–831. [Google Scholar] [CrossRef]
- Sethian, J. Fast Marching Methods and Level Set Methods for Propagating Interfaces. In Proceedings of the 29th Computational Fluid Dynamics, Rhode-Saint-Genese, Belgium, 23–27 February 1998. [Google Scholar]
- Lu, B.; Cui, M.; Liu, Q.; Wang, Y. Automated Grain Boundary Detection Using the Level Set Method. Comput. Geosci. 2009, 35, 267–275. [Google Scholar] [CrossRef]
- Chao, E.; Minkin, J.; Thompson, C. Application of automated image analysis to coal petrography. Int. J. Coal Geol. 1982, 2, 113–150. [Google Scholar] [CrossRef]
- Crelling, J.C. Automated petrographic characterization of coal lithotypes. Int. J. Coal Geol. 1982, 1, 347–359. [Google Scholar] [CrossRef]
- Kuili, J.; Jian, X.; Duohu, H. The use of automated coal petrography in determining maceral group composition and the reflectance of vitrinite. Int. J. Coal Geol. 1988, 9, 385–395. [Google Scholar] [CrossRef]
- Hou, X.; Ren, D.; Mao, H.; Lei, J.; Jin, K.; Chu, P.K.; Reich, F.; Wayne, D.H. Application of imaging TOF-SIMS to the study of some coal macerals. Int. J. Coal Geol. 1995, 27, 23–32. [Google Scholar] [CrossRef]
- Alpana; Mohapatra, S. Automated Coal Characterization Using Computational Intelligence and Image Analysis Techniques; IEEE: Piscataway, NJ, USA, 2015; pp. 176–180. [Google Scholar] [CrossRef]
- O’Brien, G.; Jenkins, B.; Esterle, J.; Beath, H. Coal characterisation by automated coal petrography. Fuel 2003, 82, 1067–1073. [Google Scholar] [CrossRef]
- O’Brien, G.; Gu, Y.; Adair, B.; Firth, B. The use of optical reflected light and SEM imaging systems to provide quantitative coal characterisation. Miner. Eng. 2011, 24, 1299–1304. [Google Scholar] [CrossRef]
- Crelling, J.; Glasspool, I.; Gibbins, J.; Seitz, M. Bireflectance imaging of coal and carbon specimens. Int. J. Coal Geol. 2005, 64, 204–216. [Google Scholar] [CrossRef]
- Lester, E.; Watts, D.; Cloke, M. A novel automated image analysis method for maceral analysis. Fuel 2002, 81, 2209–2217. [Google Scholar] [CrossRef]
- Tiwary, A.K.; Ghosh, S.; Singh, R.; Mukherjee, D.P.; Shankar, B.U.; Dash, P.S. Automated coal petrography using random forest. Int. J. Coal Geol. 2020, 232, 103629. [Google Scholar] [CrossRef]
- Wang, H.; Lei, M.; Chen, Y.; Li, M.; Zou, L. Intelligent Identification of Maceral Components of Coal Based on Image Segmentation and Classification. Appl. Sci. 2019, 9, 3245. [Google Scholar] [CrossRef] [Green Version]
- Wang, Y.; Bai, X.; Wu, L.; Zhang, Y.; Qu, S. Identification of maceral groups in Chinese bituminous coals based on semantic segmentation models. Fuel 2021, 308, 121844. [Google Scholar] [CrossRef]
- Vranjes-Wessely, S.; Misch, D.; Kiener, D.; Cordill, M.; Frese, N.; Beyer, A.; Horsfield, B.; Wang, C.; Sachsenhofer, R. High-speed nanoindentation mapping of organic matter-rich rocks: A critical evaluation by correlative imaging and machine learning data analysis. Int. J. Coal Geol. 2021, 247, 103847. [Google Scholar] [CrossRef]
- Mlynarczuk, M.; Skiba, M. The application of artificial intelligence for the identification of the maceral groups and mineral components of coal. Comput. Geosci. 2017, 103, 133–141. [Google Scholar] [CrossRef]
- Skiba, M.; Młynarczuk, M. Identification of macerals of the inertinite group using neural classifiers, based on selected textural features. Arch. Min. Sci. 2018, 63, 827–837. [Google Scholar] [CrossRef]
- Busse, J.; de Dreuzy, J.; Torres, S.G.; Bringemeier, D.; Scheuermann, A. Image processing based characterisation of coal cleat networks. Int. J. Coal Geol. 2016, 169, 1–21. [Google Scholar] [CrossRef] [Green Version]
- Maxwell, K.; Rajabi, M.; Esterle, J. Automated classification of metamorphosed coal from geophysical log data using supervised machine learning techniques. Int. J. Coal Geol. 2019, 214. [Google Scholar] [CrossRef]
- Garcia-Garcia, A.; Orts-Escolano, S.; Oprea, S.; Villena-Martinez, V.; Garcia-Rodriguez, J. A Review on Deep Learning Techniques Applied to Semantic Segmentation. arXiv 2017, arXiv:1704.06857. [Google Scholar]
- Taghanaki, S.A.; Abhishek, K.; Cohen, J.P.; Cohen-Adad, J.; Hamarneh, G. Deep semantic segmentation of natural and medical images: A review. Artif. Intell. Rev. 2020, 54, 137–178. [Google Scholar] [CrossRef]
- De Lima, R.P.; Bonar, A.; Coronado, D.D.; Marfurt, K.; Nicholson, C. Deep convolutional neural networks as a geological image classification tool. Sediment. Rec. 2019, 17, 4–9. [Google Scholar] [CrossRef]
- Pu, Y.; Apel, D.B.; Szmigiel, A.; Chen, J. Image Recognition of Coal and Coal Gangue Using a Convolutional Neural Network and Transfer Learning. Energies 2019, 12, 1735. [Google Scholar] [CrossRef] [Green Version]
- Li, D.; Zhang, Z.; Xu, Z.; Xu, L.; Meng, G.; Li, Z.; Chen, S. An Image-Based Hierarchical Deep Learning Framework for Coal and Gangue Detection. IEEE Access 2019, 7, 184686–184699. [Google Scholar] [CrossRef]
- Lei, M.; Rao, Z.; Wang, H.; Chen, Y.; Zou, L.; Yu, H. Maceral groups analysis of coal based on semantic segmentation of photomicrographs via the improved U-net. Fuel 2021, 294, 120475. [Google Scholar] [CrossRef]
- Long, J.; Shelhamer, E.; Darrell, T. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015; pp. 3431–3440. [Google Scholar] [CrossRef] [Green Version]
- Van Krevelen, D.W.; Schuyer, J. Coal. Coal Chemistry and Its Structure; Państwowe Wydawnictwo Naukowe: Warsaw, Poland, 1959. [Google Scholar]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, 5–9 October 2015; Springer: Berlin/Heidelberg, Germany, 2015; pp. 234–241. [Google Scholar]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. arXiv 2017, arXiv:1412.6980. [Google Scholar]
- Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G.S.; Davis, A.; Dean, J.; Devin, M.; et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. arXiv 2015, arXiv:1603.04467. [Google Scholar]
- Glorot, X.; Bengio, Y. Understanding the Difficulty of Training Deep Feedforward Neural Networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy, 13–15 May 2010; pp. 249–256. [Google Scholar]
Origin Samples | Numer of Samples | Maceral Groups (% vol.) | Vitrinite Reflectance (%) | ||
---|---|---|---|---|---|
Vitrinite | Liptinite | Inertinite | |||
Upper Silesian Coal Basin | 12 | 45–79 | 7–12 | 17–31 | 0.51–0.80 |
Lublin Coal Basin | 10 | 58–72 | 6–15 | 18–35 | 0.58–0.75 |
Layer | Shape | Activation |
---|---|---|
Input | 512 × 512 × 3 | - |
Convolutional 2D | 512 × 512 × 16 | ReLU |
Convolutional 2D | 512 × 512 × 16 | ReLU |
Max Pooling | 256 × 256 × 16 | |
Convolutional 2D | 256 × 512 × 32 | ReLU |
Convolutional 2D | 256 × 512 × 32 | ReLU |
Max Pooling | 128 × 128 × 32 | |
Convolutional 2D | 128 × 128 × 64 | ReLU |
Convolutional 2D | 128 × 128 × 64 | ReLU |
Max Pooling | 64 × 64 × 64 | |
Convolutional 2D | 64 × 64 × 128 | ReLU |
Convolutional 2D | 64 × 64 × 128 | ReLU |
Max Pooling | 32 × 32 × 128 | |
Convolutional 2D | 32 × 32 × 256 | ReLU |
Convolutional 2D | 32 × 32 × 256 | ReLU |
Up Sampling | 64 × 64 × 256 | |
Convolutional 2D | 64 × 64 × 128 | ReLU |
Convolutional 2D | 64 × 64 × 128 | ReLU |
Up Sampling | 128 × 128 × 128 | |
Convolutional 2D | 128 × 128 × 64 | ReLU |
Convolutional 2D | 128 × 128 × 64 | ReLU |
Up Sampling | 256 × 256 × 64 | |
Convolutional 2D | 256 × 256 × 32 | ReLU |
Convolutional 2D | 256 × 256 × 32 | ReLU |
Up Sampling | 512 × 512 × 32 | |
Convolutional 2D | 512 × 512 × 16 | ReLU |
Convolutional 2D | 512 × 512 × 16 | ReLU |
Convolutional 2D | 512 × 512 × 1 | Sigmoid |
Macerals’ Group | PA | IoU | MIoU |
---|---|---|---|
Inertinite | 0.9385 | 0.79 | 0.85 |
Liptinite | 0.9791 | 0.18 | 0.58 |
Vitrinite | 0.9176 | 0.78 | 0.75 |
Mean | 0.9451 | 0.58 | 0.79 |
Mean without liptinite | 0.9280 | 0.73 | 0.80 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Iwaszenko, S.; Róg, L. Application of Deep Learning in Petrographic Coal Images Segmentation. Minerals 2021, 11, 1265. https://doi.org/10.3390/min11111265
Iwaszenko S, Róg L. Application of Deep Learning in Petrographic Coal Images Segmentation. Minerals. 2021; 11(11):1265. https://doi.org/10.3390/min11111265
Chicago/Turabian StyleIwaszenko, Sebastian, and Leokadia Róg. 2021. "Application of Deep Learning in Petrographic Coal Images Segmentation" Minerals 11, no. 11: 1265. https://doi.org/10.3390/min11111265