Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock images

Journal Article · Thu Jul 20 00:00:00 EDT 2023 · Geoenergy Science and Engineering

DOI:https://doi.org/10.1016/j.geoen.2023.212160· OSTI ID:1997802

Liu, Siyan ^[1]; Fan, Ming ^[1]; Lu, Dan ^[1]

---

1. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Rock permeability is one of the most crucial properties affecting subsurface fluid flow behaviors. To accurately and robustly estimate the permeability, Digital Rock Physics, including micro-CT scanning technology and direct flow simulations on scanned images, has prevailed in recent years. Besides, machine learning techniques such as convolutional neural networks (CNNs) have been widely adopted and achieved success in permeability estimations directly from rock images. However, existing ML methods used for permeability estimation from rock images lack uncertainty quantification that causes unreliable predictions and overconfident estimations on out-of-distribution (OOD) samples. Here, in this work, we propose a PI3NN-CNN framework to address this problem. PI3NN-CNN consists of a CNN model for absolute permeability estimation and a PI3NN method to quantify the estimation uncertainty. It is able to quantify the uncertainty for in-distribution (InD) data with a desired confidence level, and identify OOD samples to avoid overconfident predictions. We demonstrate the method using micro-CT scanned images from two sandstone and two carbonate rocks. We found that PI3NN-CNN generates accurate predictions for InD samples, while producing high-quality prediction uncertainties regardless of the prediction accuracy. Meanwhile, PI3NN-CNN identifies OOD samples using its special network initialization scheme. The unique feature of PI3NN-CNN makes it applicable to more complex real-world image-based data for robust learning and predictions without overconfident estimations when the ground-truth information is unavailable.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: USDOE Laboratory Directed Research and Development (LDRD) Program
• Grant/Contract Number: AC05-00OR22725
• OSTI ID: 1997802
• Journal Information: Geoenergy Science and Engineering, Journal Name: Geoenergy Science and Engineering Journal Issue: 1 Vol. 230; ISSN 2949-8910
• Publisher: Elsevier
• Country of Publication: United States
• Language: English

Related Subjects

58 GEOSCIENCES
Convolutional neural networks
Digital rock physics
Machine learning
Permeability
Uncertainty quantification