Siamese-SR: A SiameseSuper-Resolution Modelfor Improved Petrophysical Parameter Estimation in Digital Rock

Digital rock involves scanning three-dimensional rock volumes using micro-CT scanners and using these volumes to estimate petrophysical parameters. Accurate estimation of these petrophysical parameters relies on acquiring high-resolution reconstruction volumes. Acquiring high-resolution reconstruction volumes is time consuming and challenging to cover the entire field of view. Therefore, there is a major emphasis on developing computational technique to enhance the resolution characteristics of the rock volumes.

Here a deep learning based super-resolution model, namely SIAMESE-SR was developed to improve the resolution of Digital Rock images. SIAMESE-SR model was capable of improving the resolution by a factor of 2, whilst preserving the texture and providing optimal denoising. Further the entire workflow of estimation of petrophysical parameter with and without super-resolution was taken up. Siamese-SR approach was found to generate petrophysical parameters close to the acquired HR image volumes compared to other state-of-the-art super-resolution techniques like SRGAN, ESRGAN.