Comparison of methods to segment variable-contrast XCT images of methane-bearing sand using U-nets trained on single dataset sub-volumes

DOI: 10.3390/methane2010001

Authors: Fernando Alvarez-Borges (University of Southampton; Diamond Light Source) , Oliver N. F. King (Diamond Light Source) , Bangalore N. Madhusudhan (University of Southampton) , Thomas Connolley (Diamond Light Source) , Mark Basham (The Rosalind Franklin Institute) , Sharif I. Ahmed (Diamond Light Source)
Co-authored by industrial partner: No

Type: Journal Paper
Journal: Methane , VOL 2 , PAGES 1 - 23

State: Published (Approved)
Published: December 2022
Diamond Proposal Number(s): 16205

Abstract: Methane (CH4) hydrate dissociation and CH4 release are potential geohazards currently investigated using X-ray computed tomography (XCT). Image segmentation is an important data processing step for this type of research. However, it is often time consuming, computing resource-intensive, operator-dependent, and tailored for each XCT dataset due to differences in greyscale contrast. In this paper, an investigation is carried out using U-Nets, a class of Convolutional Neural Network, to segment synchrotron XCT images of CH4-bearing sand during hydrate formation, and extract porosity and CH4 gas saturation. Three U-Net deployments previously untried for this task are assessed: (1) a bespoke 3D hierarchical method, (2) a 2D multi-label, multi-axis method and (3) RootPainter, a 2D U-Net application with interactive corrections. U-Nets are trained using small, targeted hand-annotated datasets to reduce operator time. It was found that the segmentation accuracy of all three methods surpass mainstream watershed and thresholding techniques. Accuracy slightly reduces in low-contrast data, which affects volume fraction measurements, but errors are small compared with gravimetric methods. Moreover, U-Net models trained on low-contrast images can be used to segment higher-contrast datasets, without further training. This demonstrates model portability, which can expedite the segmentation of large datasets over short timespans.

Journal Keywords: U-Net; methane hydrates; microtomography; sediment microstructure; semantic segmentation

Subject Areas: Earth Science, Technique Development, Information and Communication Technology


Instruments: I13-2-Diamond Manchester Imaging

Added On: 24/12/2022 08:36

Documents:
methane-02-00001.pdf

Discipline Tags:

Technique Development - Earth Sciences & Environment Earth Sciences & Environment Artificial Intelligence Information & Communication Technologies Geology Geophysics Data processing

Technical Tags:

Imaging Tomography