LAPSE:2023.25064
Published Article
LAPSE:2023.25064
Research on Image Identification Method of Rock Thin Slices in Tight Oil Reservoirs Based on Mask R-CNN
Tao Liu, Chunsheng Li, Zongbao Liu, Kejia Zhang, Fang Liu, Dongsheng Li, Yan Zhang, Zhigang Liu, Liyuan Liu, Jiacheng Huang
March 28, 2023
Terrestrial tight oil has extremely strong diagenesis heterogeneity, so a large number of rock thin slices are needed to reveal the real microscopic pore-throat structure characteristics. In addition, difficult identification, high cost, long time, strong subjectivity and other problems exist in the identification of tight oil rock thin slices, and it is difficult to meet the needs of fine description and quantitative characterization of the reservoir. In this paper, a method for identifying the characteristics of rock thin slices in tight oil reservoirs based on the deep learning technique was proposed. The present work has the following steps: first, the image preprocessing technique was studied. The original image noise was removed by filtering, and the image pixel size was unified by a normalization technique to ensure the quality of samples; second, the self-labeling image data augmentation technique was constructed to solve the problem of sparse samples; third, the Mask R-CNN algorithm was introduced and improved to synchronize the segmentation and recognition of rock thin slice components in tight oil reservoirs; Finally, it was demonstrated through experiments that the SMR method has significant advantages in accuracy, execution speed and migration.
Keywords
characteristics identification, deep learning, rock thin slices, tight oil reservoir, unconventional oil and gas
Suggested Citation
Liu T, Li C, Liu Z, Zhang K, Liu F, Li D, Zhang Y, Liu Z, Liu L, Huang J. Research on Image Identification Method of Rock Thin Slices in Tight Oil Reservoirs Based on Mask R-CNN. (2023). LAPSE:2023.25064
Author Affiliations
Liu T: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Li C: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Liu Z: School of Earth Sciences, Northeast Petroleum University, Daqing 163318, China
Zhang K: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Liu F: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Li D: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Zhang Y: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Liu Z: School of Computer & Information Technology, Northeast Petroleum University, Daqing 163318, China
Liu L: School of Earth Sciences, Northeast Petroleum University, Daqing 163318, China
Huang J: School of Earth Sciences, Northeast Petroleum University, Daqing 163318, China
Journal Name
Energies
Volume
15
Issue
16
First Page
5818
Year
2022
Publication Date
2022-08-10
Published Version
ISSN
1996-1073
Version Comments
Original Submission
Other Meta
PII: en15165818, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2023.25064
This Record
External Link

doi:10.3390/en15165818
Publisher Version
Download
Files
[Download 1v1.pdf] (4.8 MB)
Mar 28, 2023
Main Article
License
CC BY 4.0
Meta
Record Statistics
Record Views
60
Version History
[v1] (Original Submission)
Mar 28, 2023
 
Verified by curator on
Mar 28, 2023
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2023.25064
 
Original Submitter
Auto Uploader for LAPSE
Links to Related Works
Directly Related to This Work
Publisher Version