Journal
TRANSPORT IN POROUS MEDIA
Volume 143, Issue 2, Pages 497-525Publisher
SPRINGER
DOI: 10.1007/s11242-022-01781-9
Keywords
Carbonate rocks; Segmentation; Microporosity; Super-resolution; Deep learning; Digital rock
Categories
Funding
- CAUL
Ask authors/readers for more resources
Reliable quantitative analysis of digital rock images, especially in heterogeneous rocks like carbonates with complex pore size distributions, requires precise segmentation and identification. In recent years, deep learning algorithms have provided efficient and automated solutions for digital rock super-resolution and segmentation. This study presents a framework that uses convolutional neural networks (CNNs) to achieve super-resolved segmentations of carbonate rock images in order to identify sub-resolution porosity. Comparison of voxel-wise segmentation accuracy metrics, topological features, and effective properties confirms the accuracy of the trained model and highlights the value of integrating deep learning frameworks in digital rock analysis.
Reliable quantitative analysis of digital rock images requires precise segmentation and identification of the macroporosity, sub-resolution porosity, and solid\mineral phases. This is highly emphasized in heterogeneous rocks with complex pore size distributions such as carbonates. Multi-label segmentation of carbonates using classic segmentation methods such as multi-thresholding is highly sensitive to user bias and often fails in identifying low-contrast sub-resolution porosity. In recent years, deep learning has introduced efficient and automated algorithms that are capable of handling hard tasks with precision comparable to human performance, with application to digital rocks super-resolution and segmentation emerging. Here, we present a framework for using convolutional neural networks (CNNs) to produce super-resolved segmentations of carbonates rock images for the objective of identifying sub-resolution porosity. The volumes used for training and testing are based on two different carbonates rocks imaged in-house at low and high resolutions. We experiment with various implementations of CNNs architectures where super-resolved segmentation is obtained in an end-to-end scheme and using two networks (super-resolution and segmentation) separately. We show the capability of the trained model of producing accurate segmentation by comparing multiple voxel-wise segmentation accuracy metrics, topological features, and measuring effective properties. The results underline the value of integrating deep learning frameworks in digital rock analysis.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available