Abstract

Digital rock images have been widely used for rock core analysis in petroleum industry. Petroleum engineers are interested in high resolution digital rock images which are fine enough for them to overcome complex real-world problems. The higher resolution of digital rock images, the more accurate the parameters they can get, such as porosity and permeability which statistically describe porous materials. We applied Fast Super-Resolution Convolutional Neural Networks (FSRCNN) to increase resolution for Digital Rock Images. And we compared it with the benchmark named Super-Resolution Convolutional Neural Networks (SRCNN) which is the first deep learning method for image super resolution. The results demonstrate that the FSRCNN can produce high resolution digital rock images in a faster speed and it is valuable processing step for digital rock workflow.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.