Super-Resolution Carbonate Rock Image Beyond Instrument Limitations
Authors:
- Yang MengYMYang Meng
- Kunning TangKTKunning Tang
- Yuntian ChenYCYuntian Chen
- Senyou AnSASenyou An
- 1 July 2026
- journal article
- Published by Society of Petroleum Engineers (SPE) in SPE Journal
- Vol. 31 (09) , 1-8
Abstract
Summary: Carbonate rocks, as complex multiscale porous media, present major imaging challenges because of intricate structures and strong heterogeneity. To address the trade-off between field of view (FOV) and resolution, we introduce the Swin transformer for image restoration generative adversarial network (SwinIRGAN), a super-resolution (SR) framework based on sliding-window attention that captures long-range features efficiently. The model balances global consistency with high-frequency detail preservation and learns the mapping between low-resolution (LR) and high-resolution (HR) images. Using a biogenic carbonate data set, SwinIRGAN achieves 99.48% accuracy in Euler’s number and 97.05% accuracy in higher-resolution extrapolation. For the multiresolution complex carbonates micro-computed tomography (micro-CT, MRCCM) data set, the proposed reconstruction and extrapolation workflow improves Euler’s number by 15.59% compared with the baseline. Results show that SwinIRGAN preserves mineralogical and topological characteristics across scales and provides more reliable digital rocks for pore-scale analysis and flow simulation.Keywords
This publication has 35 references indexed in Scilit:
- Deep learning in pore scale imaging and modelingEarth-Science Reviews, 2021
- DeePore: A deep learning workflow for rapid and comprehensive characterization of porous materialsAdvances in Water Resources, 2020
- Rock properties from micro-CT images: Digital rock transforms for resolution, pore volume, and field of viewAdvances in Water Resources, 2019
- Enhancing Resolution of Digital Rock Images with Super Resolution Convolutional Neural NetworksJournal of Petroleum Science and Engineering, 2019
- Image super-resolution using a dilated convolutional neural networkNeurocomputing, 2018
- Multi-scale x-ray computed tomography analysis of coal microstructure and permeability changes as a function of effective stressInternational Journal of Coal Geology, 2016
- Imaging and image-based fluid transport modeling at the pore scale in geological materials: A practical introduction to the current state-of-the-artEarth-Science Reviews, 2016
- Micro-CT of rodents: State-of-the-art and future perspectivesPhysica Medica, 2014
- Digital rock physics benchmarks—Part I: Imaging and segmentationComputers & Geosciences, 2013
- Pore-scale imaging and modellingAdvances in Water Resources, 2013