Advances in Earth Science ›› 2024, Vol. 39 ›› Issue (5): 476-488. doi: 10.11867/j.issn.1001-8166.2024.036

Previous Articles     Next Articles

Deep Learning SEM Image Segmentation of Shale Pyrite and Environmental Indications: A Study of Luzhou Block, Sichuan Basin

Naier DENG 1( ), Hao XU 2( ), Wen ZHOU 2, Xiaochuan TANG 3, Yulu CHEN 1, Yongyang LIU 4, Shaojun LIU 4, Yi ZHANG 5, Ke JIANG 1, Ruiyin LIU 6, Weiguo SONG 1   

  1. 1.College of Energy (College of Modern Shale Gas Industry), Chengdu University of Technology, Chengdu 610059, China
    2.State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Chengdu University of Technology, Chengdu 610059, China
    3.College of Computer Science and Cyber Security(Demonstrative Software College), Chengdu University of Technology, Chengdu 610059, China
    4.Research Institute of Shale Gas, PetroChina Southwest Oil & Gasfield Company, Chengdu 610051, China
    5.College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China
    6.Guizhou Geological Survery, Guiyang 550081, China
  • Received:2024-01-24 Revised:2024-04-29 Online:2024-05-10 Published:2024-06-03
  • Contact: Hao XU E-mail:2516101958@qq.com;xuhao19@cdut.edu.cn
  • About author:DENG Naier, Master student, research area includes unconventional reservoir fine evaluation. E-mail: 2516101958@qq.com
  • Supported by:
    the National Natural Science Foundation of China(42202189);The Natural Science Foundation of Sichuan Province(24NSFSC4997)

Naier DENG, Hao XU, Wen ZHOU, Xiaochuan TANG, Yulu CHEN, Yongyang LIU, Shaojun LIU, Yi ZHANG, Ke JIANG, Ruiyin LIU, Weiguo SONG. Deep Learning SEM Image Segmentation of Shale Pyrite and Environmental Indications: A Study of Luzhou Block, Sichuan Basin[J]. Advances in Earth Science, 2024, 39(5): 476-488.

Pyrite, a significant heavy mineral in shale, aids in the comprehension of shale depositional environments. Referencing the Wufeng-Long1 subsection Formation of the Luzhou Block in Sichuan Basin, a network model for pyrite SEM image segmentation was established via core mineral experiments, SEM observations, network model refinement, and feature parameter analysis. The model assesses the sedimentary environment of the study block using pyrite framboid parameters. Our findings indicated that enhancement of the UNet-Im model for pyrite framboid SEM images resulted in a segmentation precision of 0.863, demonstrating the effectiveness of the enhancement measures. Pyrite content varied from 2.95% in the Long 1 1 ~ 3 minor layer to 0.83% in the Wufeng Formation, with the Long 1 4 minor layer at 2.03%. Pyrite depositional environments are deduced as deep-water sulfide environments, strong reducing environments, strong-weak reduction environments, and reductive-suboxidative environments based on pyrite framboid characteristics. This study accurately segmented pyrite SEM images to enhance the exploration and development of intelligence in this industry.

No related articles found!
Viewed
Full text


Abstract