Skip to main content
Journal cover image

Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM

Publication ,  Journal Article
Wang, H; Dalton, L; Fan, M; Guo, R; McClure, J; Crandall, D; Chen, C
Published in: Journal of Petroleum Science and Engineering
August 1, 2022

Three-dimensional (3D) X-ray micro-computed tomography (μCT) has been widely used in petroleum engineering because it can provide detailed pore structural information for a reservoir rock, which can be imported into a pore-scale numerical model to simulate the transport and distribution of multiple fluids in the pore space. The partial volume blurring (PVB) problem is a major challenge in segmenting raw μCT images of rock samples, which impacts boundaries and small targets near the resolution limit. We developed a deep-learning (DL)-based workflow for accurate and fast partial volume segmentation. The DL model's performance depends primarily on the training data quality and model architecture. This study employed the entropy-based-masking indicator kriging (IK-EBM) to segment 3D Berea sandstone images as training datasets. The comparison between IK-EBM and manual segmentation using a 3D synthetic sphere pack, which had a known ground truth, showed that IK-EBM had higher accuracy on partial volume segmentation. We then trained and tested the UNet++ model, a state-of-the-art supervised encoder-decoder model, for binary (i.e., void and solid) and four-class segmentation. We compared the UNet++ with the commonly used U-Net and wide U-Net models and showed that the UNet++ had the best performance in terms of pixel-wise and physics-based evaluation metrics. Specifically, boundary-scaled accuracy demonstrated that the UNet++ architecture outperformed the regular U-Net architecture in the segmentation of pixels near boundaries and small targets, which were subjected to the PVB effect. Feature map visualization illustrated that the UNet++ bridged the semantic gaps between the feature maps extracted at different depths of the network, thereby enabling faster convergence and more accurate extraction of fine-scale features. The developed workflow significantly enhances the performance of supervised encoder-decoder models in partial volume segmentation, which has extensive applications in fundamental studies of subsurface energy, water, and environmental systems.

Duke Scholars

Published In

Journal of Petroleum Science and Engineering

DOI

ISSN

0920-4105

Publication Date

August 1, 2022

Volume

215

Related Subject Headings

  • Energy
  • 4019 Resources engineering and extractive metallurgy
  • 4012 Fluid mechanics and thermal engineering
  • 3705 Geology
  • 0914 Resources Engineering and Extractive Metallurgy
  • 0904 Chemical Engineering
  • 0403 Geology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Wang, H., Dalton, L., Fan, M., Guo, R., McClure, J., Crandall, D., & Chen, C. (2022). Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM. Journal of Petroleum Science and Engineering, 215. https://doi.org/10.1016/j.petrol.2022.110596
Wang, H., L. Dalton, M. Fan, R. Guo, J. McClure, D. Crandall, and C. Chen. “Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM.” Journal of Petroleum Science and Engineering 215 (August 1, 2022). https://doi.org/10.1016/j.petrol.2022.110596.
Wang H, Dalton L, Fan M, Guo R, McClure J, Crandall D, et al. Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM. Journal of Petroleum Science and Engineering. 2022 Aug 1;215.
Wang, H., et al. “Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM.” Journal of Petroleum Science and Engineering, vol. 215, Aug. 2022. Scopus, doi:10.1016/j.petrol.2022.110596.
Wang H, Dalton L, Fan M, Guo R, McClure J, Crandall D, Chen C. Deep-learning-based workflow for boundary and small target segmentation in digital rock images using UNet++ and IK-EBM. Journal of Petroleum Science and Engineering. 2022 Aug 1;215.
Journal cover image

Published In

Journal of Petroleum Science and Engineering

DOI

ISSN

0920-4105

Publication Date

August 1, 2022

Volume

215

Related Subject Headings

  • Energy
  • 4019 Resources engineering and extractive metallurgy
  • 4012 Fluid mechanics and thermal engineering
  • 3705 Geology
  • 0914 Resources Engineering and Extractive Metallurgy
  • 0904 Chemical Engineering
  • 0403 Geology