Abstract
This study presents an intelligent identification method for shale crack networks based on transfer learning. Focuses on investigating the main physical parameters of shale similar materials based on the similarity theory and the physical parameters of shale. Fracture network images obtained from shale-like materials. The fracture network images are then preprocessed using image processing technology to generate a high-quality shale image dataset. A deep learning transfer recognition model, based on ResNet-50, is constructed to detect model performance using these shale fracture network images. Experimental results and reliability analyses demonstrate that the ResNet-50 based deep learning transfer model achieves an accuracy of 87% for shale images, indicating high recognition accuracy and fast model convergence. The proposed intelligent shale crack identification method exhibits robustness and generalization ability, making it suitable for efficient fracture identification in geological, road, and bridge deck projects.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analysed during the current study are not publicly available due [REASON WHY DATA ARE NOT PUBLIC] but are available from the corresponding author on reasonable request.
References
Guo XS, Hu DF, Wen ZD et al (2014) Major factors controlling the accumulation and high productivity in marine shale gas in the Lower Paleozoic of Sichuan Basin and its periphery: A case study of the Wufeng-Longmaxi Formation of Jiaoshiba area. J Geology in China 41(3):893–901. https://doi.org/10.3969/j.issn.1000-3657.2014.03.016
Wang CQ, Chen S, Huang DM et al (2023) Human carcinogenic risk analysis and utilization of shale gas water-based drilling cuttings in road materials. Environ Sci Pollut Res Int 30(5):12741–12768. https://doi.org/10.1007/s11356-022-23006-8
Zou C, Yang Z, Sun S et al (2020) “Exploring petroleum inside source kitchen”: Shale oil and gas in Sichuan Basin. Sci China Earth Sci 63:934–953. https://doi.org/10.1007/s11430-019-9591-5
Dai JX, Dong DZ, Ni YY (2020) Some essential geological and geochemical issues about shale gas research in China. J. Natural Gas Geoscience 31(6):745–760. https://doi.org/10.11764/j.issn.1672-1926.2020.05.016
Xiao ZK, Ding WL, Liu JS et al (2019) A fracture identification method for low-permeability sandstone based on R/S analysis and the finite difference method: A case study from the Chang 6 reservoir in Huaqing oilfield, Ordos Basin. J Journal of Petroleum Science and Engineering 174:1169–1178. https://doi.org/10.1016/j.petrol.2018.12.017
Pollastro RM (2007) Total petroleum system assessment of undiscovered resources in the giant Barnett shale continuous (unconventional) gas accumulation Fort Worth Basin Texas. J AAPG Bulletin 91(4):551–578. https://doi.org/10.1306/06200606007
Xu ST, Zhou YZ (2018) Artificial intelligence identification of ore minerals under microscope based on deep learning algorithm. Acta Petrologica Sinica 34(11):3244–3252 (CNKI:SUN:YSXB.0.2018-11-010)
Voulodimos A, Doulamis N, Doulamis A, Protopapadakis E (2018) Deep learning for computer vision: A brief review. J Computational Intelligence and Neuroscience. https://doi.org/10.1155/2018/7068349
Song Z (2020) English speech recognition based on deep learning with multiple features. Computing 102:663–682. https://doi.org/10.1007/s00607-019-00753-0
Liu HX, Li WS, Zha HY (2018) Method for surrounding rock mass classification of highway tunnels based on deep learning technology. J. Chinese Journal of Geotechnical Engineering 40(10):1809–1817. https://doi.org/10.11779/CJGE201810007
He Y, Zhu Y, Lin W (2019) HTTP tunnel Trojan detection model based on deep learning. C Journal of Physics: Conference Series. IOP Publishing 1187(4):042055. https://doi.org/10.1088/1742-6596/1187/4/042055
Yang W, Gao X, Zhang C et al (2021) Bridge extraction algorithm based on deep learning and high-resolution satellite image. J Scientific Programming 2021:1–8. https://doi.org/10.1155/2021/9961963
Jin CY, Ma ZY, Zhang YL et al (2006) Application of neural network to back analysis of mechanical parameters and initial stress field of rock masses. J Rock and Soil Mechanics 27(1263–1266):1271. https://doi.org/10.1016/S1872-1508(06)60035-1
Ibrahim A, Gamble P, Jaroensri R, Abdelsamea M, Mermel M, Chen CH, Chen PHC, Rakha EA (2020) Artificial Intelligence in Digital Breast Pathology: Techniques and Applications. J the Breast 49:267–273. https://doi.org/10.1016/j.breast.2019.12.007
Wang J, Zhu H, Wang SH, Zhang YD (2021) A Review of Deep Learning on Medical Image Analysis. Mobile Netw Appl 26:351–380. https://doi.org/10.1007/s11036-020-01672-7
Iwata H, Hayashi Y, Hasegawa A et al (2022) Classification of scanning electron microscope images of pharmaceutical excipients using deep convolutional neural networks with transfer learning. J International Journal of Pharmaceutics: X 4:100135. https://doi.org/10.1016/J.IJPX.2022.100135
Eldem H, Ülker E, Işıklı OY (2023) Alexnet architecture variations with transfer learning for classification of wound images. J. Engineering Science and Technology, an International Journal 45:101490. https://doi.org/10.1016/J.JESTCH.2023.101490
Wang Y, Niu F, Zhang X et al (2022) Super resolution reconstruction of digital core image based on transfer learning. J Energy Reports 8:87–94. https://doi.org/10.1016/J.EGYR.2022.10.069
Chi P, Sun JM, Luo X (2023) Reconstruction of 3D digital rocks with controllable porosity using CVAE-GAN. Geoenergy Science and Engineering 230:212264. https://doi.org/10.1016/j.geoen.2023.212264
Shams R, Masihi M, Ramin BB et al (2020) Coupled generative adversarial and auto-encoder neural networks to reconstruct three-dimensional multi-scale porous media. J Petrol Sci Eng 186:106794. https://doi.org/10.1016/j.petrol.2019.106794
Syed AQ, Jothi JAA, Anusree K (2022) Crack identification from concrete structure images using deep transfer learning C 2nd International Conference on Artificial Intelligence and Signal Processing (AISP). IEEE, 2022: 1–7. https://doi.org/10.1109/AISP53593.2022.9760670
Yazid MDM, Senin SF (2022) Automated system form concrete damage classification identification using pretrained deep learning model. C. AIP Conference Proceedings. AIP Publishing, 2532(1) https://doi.org/10.1063/5.0110080
Kim IH, Jeon H, Baek SC et al (2018) Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle. Sensors 18:1881. https://doi.org/10.3390/s18061881
Gui R, Sun Q, Wu WQ et al (2023) Transfer learning for cross-scene 3D pavement crack detection based on enhanced deep edge features. J. Engineering Applications of Artificial Intelligence, 123(PC):106452, https://doi.org/10.1016/J.ENGAPPAI.2023.106452
Lim S, Chi S et al (2021) Damage prediction on bridge decks considering environmental effects with the application of deep neural networks. J KSCE Journal of Civil Engineering 25(2):371–385. https://doi.org/10.1007/s12205-020-5669-4
Prasanna P, Dana K, Gucunski N, Basily B (2012) Computer-vision based crack detection and analysis. In Sensors and smart structures technologies for civil, mechanical, and aerospace systems 2012 (Vol. 8345, pp. 1143–1148). SPIE. https://doi.org/10.1117/12.915384
Liu FY, Liu J, Wang LB (2022) Deep learning and infrared thermography for asphalt pavement crack severity classification. J Automation in Construction 140:104383. https://doi.org/10.1016/J.AUTCON.2022.104383
Zheng Q, Zhang D (2022) RockGPT: reconstructing three-dimensional digital rocks from single two-dimensional slice with deep learning. Comput Geosci 26:677–696. https://doi.org/10.1007/s10596-022-10144-8
Li G, Ren XL, Qiao WT et al (2020) Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing. J Structural Control and Health Monitoring 27(11):e2620. https://doi.org/10.1002/stc.2620
Li YD (2021) Bridge crack morphological classification using GAN anddeep transfer-learning. D. Chang’an University. https://doi.org/10.26976/d.cnki.gchau.2020.001382
Qi W, Wang YC, Jiang B et al (2023) Geomechanics model test research on large deformation control mechanism of roadway disturbed by strong dynamic pressure. J. Geohazard Mechanics, 1(2). https://doi.org/10.1016/J.GHM.2023.06.002
Oji DN, I. SO, J. UO et al (2022) Application of buckingham theorem in the prediction of sand production rate for unconsolidated sandstone reservoirs bounded by active water aquifer. J. Advances in Petroleum Exploration and Development, 21(1). https://doi.org/10.3968/12560
Wang YY, Gan XN, Fan XY et al (2017) Research on preparation and mechanical properties of a kind of material similar to shale. J Shandong Science 30(04):50–57. https://doi.org/10.3976/j.issn.1002-4026.2017.04.009
Wang YY, Zhu YM, Fan XY et al (2016) Experimental study of the effect of porosity on the damage of shale-like materials. J. Chinese Journal of Applied Mechanics 33(04):695–700+743. https://doi.org/10.11776/cjam.33.04.B067
Sun GL, Hu JC, Wang HF, Li DW (2022) Electrochemical experiment to evaluate the impact of multistage load and osmotic pressure on anchor bolt. J. Geofluids, 1–13. https://doi.org/10.1155/2022/9405262
Sun GL, Hu JC, Wang HF, Li. PF (2021) Experimental study on the deformation and failure characteristics of anchor under graded loading and corrosion. J. Advances in Materials Science and Engineering, 1–11. https://doi.org/10.1155/2021/8701180
Jie C 2019 Research on image enhancement based on colour information. D. Nanjing University of Posts and Telecommunications. CNKI:CDMD:1.1018.891603
Acknowledgements
Qin Wang: Data curation, Writing—original draft, Writing—review & editing. Jiangchun Hu: Resources, Methodology, Investigation, Writing—review & editing, Funding support. PengFei Liu: Writing—review & editing. GuangLin Sun: Conceptualization, Formal analysis.
Funding
The research leading to these results received funding from [the Experimental study and mechanism analysis of rheological aging characteristics of deep engineering anchored solid with stress-seepage-coupled rheology] under Grant Agreement No[5157, 4296].
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interest
The authors declare no competing interests.
Additional information
Communicated by: H. Babaie
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, Q., Hu, J., Liu, P. et al. Intelligent recognition of shale fracture network images based on transfer learning. Earth Sci Inform 17, 797–812 (2024). https://doi.org/10.1007/s12145-023-01202-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12145-023-01202-5