Advances in the application of deep learning methods to digital rock technology
Xiao-Bin Li, Bingke Li, Fangzhou Liu, Tingting Li, Xin Nie
Abstract
Digital rock technology is becoming essential in reservoir engineering and petrophysics. Three-dimensional digital rock reconstruction, image resolution enhancement, image segmentation, and rock parameters prediction are all crucial steps in enabling the overall analysis of digital rocks to overcome the shortcomings and limitations of traditional methods. Artificial intelligence technology, which has started to play a significant role in many different fields, may provide a new direction for the development of digital rock technology. This work presents a systematic review of the deep learning methods that are being applied to tasks within digital rock analysis, including the reconstruction of digital rocks, high-resolution image acquisition, grayscale image segmentation, and parameter prediction. The results of these applications prove that state-of-the-art deep learning methods can help advance and provide a new approach to scientific knowledge in the field of digital rocks. This work also discusses future research and developments on the application of deep learning methods to digital rock technology. Cited as: Li, X., Li, B., Liu, F., Li, T., Nie, X. Advances in the application of deep learning methods to digital rock technology. Advances in Geo-Energy Research, 2023, 8(1): 5-18. https://doi.org/10.46690/ager.2023.04.02