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

• Published in: Advances in water resources Vol. 173; p. 104385
• Main Authors: Wang, Hongsheng, Dalton, Laura, Guo, Ruichang, McClure, James, Crandall, Dustin, Chen, Cheng
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01-03-2023; Elsevier
• Subjects: CO2-water-rock syste; CO2-water-rock system; ENGINEERING; Geological carbon sequestration; Image segmentation; In-situ contact angle measurement; Unsupervised deep learning; Unsupervised deep learning; Image segmentation; CO2-water-rock syste; In-situ contact angle measurement; Geological carbon sequestration
• ISSN: 0309-1708; 1872-9657
• DOI: 10.1016/j.advwatres.2023.104385

•An unsupervised deep learning method for digital rock image segmentation was proposed, 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.•The proposed deep learning method provides an effective approach to in-situ measurements of surface contact angles for two-phase flow in porous media.
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. The 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. 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.