Journal
PHYSICAL REVIEW APPLIED
Volume 17, Issue 3, Pages -Publisher
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevApplied.17.034048
Keywords
-
Categories
Funding
- Tyree X-ray CT Facility - UNSW Research Infras-tructure Scheme
- U.S. Department of Energy (DOE) Office of Sci-ence User Facility operated for the DOE Office of Science by Argonne National Laboratory [DE-AC02-06CH11357]
Ask authors/readers for more resources
Mitigating greenhouse gas emissions and finding solutions for future energy is essential. Understanding geochemical reactions and flow behavior at the interface is important for successful underground storage. This study introduces an image-processing workflow using synchrotron-based μCT and CNNs to extract quantitative data and analyze porous materials for energy applications. The results show the need for comprehensive assessment beyond pixel-wise accuracy.
Mitigating greenhouse gas emissions by underground carbon dioxide storage or by coupling intermittent renewable energy with underground hydrogen storage are solutions essential to the future of energy. Of particular importance to the success of underground storage is the fundamental understanding of geochemical reactions with mineralogical phases and flow behavior at the length scale at which interfaces are well resolved. Fast synchrotron-based three-dimensional x-ray microcomputed tomography (mu CT) of rocks is a widely used technique that provides real-time visualization of fluid flow and transport mechanisms. However, fast imaging results in significant noise and artifacts that complicate the extraction of quantitative data beyond the basic identification of solid and void regions. To address this issue, an image-processing workflow is introduced that begins with unpaired domain transfer by cycle-consistent adversarial network, which is used to transfer synchrotron-based mu CT images containing fast-imaging-associated noise to long-scan high-quality mu CT images that have paired ground truth labels for all phases. The second part of the workflow is multimineral segmentation of images using convolutional neural networks (CNNs). Four CNNs are trained using the transferred dynamic-style mu CT images. A quantitative assessment of physically meaningful parameters and material properties is carried out. In terms of physical accuracy, the results show a high variance for each network output, which indicates that the segmentation performance cannot be fully revealed by pixel-wise accuracy alone. Overall, the integration of unpaired domain transfer with CNN-based multimineral segmentation provides a generalizable digital material framework to study the physics of porous materials for energy-related applications, such as underground CO2 and H2 storage.
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