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

Journal Article · Wed May 04 00:00:00 EDT 2022 · Journal of Petroleum Science and Engineering

DOI:https://doi.org/10.1016/j.petrol.2022.110596· OSTI ID:1870206

Wang, Hongsheng ^[1]; Dalton, Laura ^[2]; Fan, Ming ^[3]; Guo, Ruichang ^[1]; McClure, James ^[1]; Crandall, Dustin ^[4]; Chen, Cheng ^[5]

---

1. Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)
2. North Carolina State Univ., Raleigh, NC (United States)
3. Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
4. National Energy Technology Lab. (NETL), Morgantown, WV (United States)
5. Environmental and Ocean Engineering, Hoboken, NJ (United States)

We report 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.

• Research Organization: National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE; USDOE Office of Fossil Energy (FE)
• Grant/Contract Number: AC05-00OR22725; FE0004000; FE0026825
• OSTI ID: 1870206
• Alternate ID(s): OSTI ID: 1875462
• Journal Information: Journal of Petroleum Science and Engineering, Journal Name: Journal of Petroleum Science and Engineering Journal Issue: A Vol. 215; ISSN 0920-4105
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

02 PETROLEUM
IK-EBM
UNet++
boundary and small targets
digital rock physics
image segmentation
partial volume blurring
supervised deep learning