Title: Application of unsupervised deep learning to image segmentation and in-situ contact angle measurements in a CO₂-water-rock system

Abstract

Rock surface wettability is a critical property that regulates multiphase flows in porous media, which can be quantified using the surface contact angle (CA). X-ray micro-computed tomography (μCT) provides an effective approach to in-situ measurements of surface CAs. However, the CA measurement accuracy depends significantly on the quality of CT image segmentation, which is the clustering of CT pixels into separate phases. Inspired by this, we developed a deep learning (DL)-based CA measurement workflow. Motivated by the recent tremendous progress in unsupervised learning techniques and aiming to avoid expensive manual data annotations, an unsupervised DL pipeline for CT image segmentation was proposed and implemented, which includes unsupervised model training and post-processing. The unsupervised model training was driven by a novel loss function constrained with feature similarity and spatial continuity and implemented by iterative forward and backward paths; the former clustered the pixel-wise feature vectors extracted by convolution neural networks, whereas the latter updated the parameters using gradient descent. An over-segmentation strategy was adopted for model training. The post-processing steps based on agglomerative hierarchical clustering (AHC) were implemented to further merge the over-segmented model output to the desired cluster number, which is intended to improve the efficiency of image segmentation. Themore » developed unsupervised DL pipeline was compared with other commonly-used image segmentation methods using pixel-wise and physics-based evaluation metrics on a synthetic raw-image dataset, which had a known ground truth. The unsupervised DL pipeline showed the best performance. Next, the segmented images were input to an automatic CA measurement tool, and the results were validated by comparisons with manual measurements. The CA values from the manual and automatic measurements showed similar distributions and statistical properties. The automatic measurement demonstrated a wider spectrum because of the much larger number of measurement data points. The primary novelty of the unsupervised DL pipeline developed in this study lies in the novel loss function and the over-segmentation strategy associated with AHC post-processing. Finally, the workflow has been proven an efficient tool for pore-scale wettability characterization, which has a wide range of applications in fundamental studies of multiphase flows in natural porous media, which have critical implications to geological carbon sequestration, hydrocarbon energy recovery, and contaminant transport in groundwater.« less

Authors:

Wang, Hongsheng ^[1]; Dalton, Laura  ^[2];

• Search DOE PAGES for author "Dalton, Laura"
• Search DOE PAGES for ORCID "0000-0002-3230-8128"

Guo, Ruichang  ^[3];

• Search DOE PAGES for author "Guo, Ruichang"
• Search DOE PAGES for ORCID "0000-0003-0070-609X"

McClure, James ^[4]; Crandall, Dustin  ^[5];

• Search DOE PAGES for author "Crandall, Dustin"
• Search DOE PAGES for ORCID "0000-0001-7328-9464"

Chen, Cheng  ^[3]

• Search DOE PAGES for author "Chen, Cheng"
• Search DOE PAGES for ORCID "0000-0002-0815-0228"

---

+ Show Author Affiliations

1. Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)
2. Duke Univ., Durham, NC (United States)
3. Stevens Institute of Technology, Hoboken, NJ (United States)
4. Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States). National Security Institute
5. National Energy Technology Lab. (NETL), Morgantown, WV (United States)

Publication Date:

Wed Jan 18 00:00:00 EST 2023

Research Org.:

National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)

Sponsoring Org.:

USDOE Office of Fossil Energy (FE)

OSTI Identifier:

1923984

Report Number(s):

DOE/NETL-2023/3844
Journal ID: ISSN 0309-1708

Grant/Contract Number:  

FE0004000; FE0026825; S000038-USDOE

Resource Type:

Accepted Manuscript

Journal Name:

Advances in Water Resources

Additional Journal Information:

Journal Volume: 173; Journal ID: ISSN 0309-1708

Publisher:

Elsevier

Country of Publication:

United States

Language:

English

Subject:

42 ENGINEERING; unsupervised deep learning; image segmentation; in-situ contact angle measurement; CO2-water-rock system; geological carbon sequestration