The University of Southampton
University of Southampton Institutional Repository

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

Comparison of methods to segment variable-contrast XCT images of methane-bearing sand using U-nets trained on single dataset sub-volumes
Comparison of methods to segment variable-contrast XCT images of methane-bearing sand using U-nets trained on single dataset sub-volumes
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.
U-Net, Methane hydrates, Microtomography, Sediment microstructure, Semantic segmentation
2674-0389
Alvarez Borges, Fernando J.
5512cdfd-6ad3-475f-8aec-2fc767607314
King, Oliver N.F.
2bfc86d6-849f-4725-9ae5-abb96fb8868d
Madhusudhan, Bangalore M.
e139e3d3-2992-4579-b3f0-4eec3ddae98c
Connolley, Thomas
baeb481e-885f-4ac9-ad83-fc6537ac5337
Basham, Mark
55739b97-162a-4d37-bee8-a392948fcbcc
Ahmed, Sharif
ddc6bab1-9d76-4391-b7ea-ae68d6f3924d
Alvarez Borges, Fernando J.
5512cdfd-6ad3-475f-8aec-2fc767607314
King, Oliver N.F.
2bfc86d6-849f-4725-9ae5-abb96fb8868d
Madhusudhan, Bangalore M.
e139e3d3-2992-4579-b3f0-4eec3ddae98c
Connolley, Thomas
baeb481e-885f-4ac9-ad83-fc6537ac5337
Basham, Mark
55739b97-162a-4d37-bee8-a392948fcbcc
Ahmed, Sharif
ddc6bab1-9d76-4391-b7ea-ae68d6f3924d

Alvarez Borges, Fernando J., King, Oliver N.F., Madhusudhan, Bangalore M., Connolley, Thomas, Basham, Mark and Ahmed, Sharif (2023) Comparison of methods to segment variable-contrast XCT images of methane-bearing sand using U-nets trained on single dataset sub-volumes. Methane, 2 (1). (doi:10.3390/methane2010001).

Record type: Article

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.

Text
methane-02-00001-v2 - Version of Record
Available under License Creative Commons Attribution.
Download (7MB)

More information

Accepted/In Press date: 5 December 2022
e-pub ahead of print date: 20 December 2022
Published date: 2023
Keywords: U-Net, Methane hydrates, Microtomography, Sediment microstructure, Semantic segmentation

Identifiers

Local EPrints ID: 475135
URI: http://eprints.soton.ac.uk/id/eprint/475135
ISSN: 2674-0389
PURE UUID: 5656c3e2-8a3e-4699-98aa-4c8c7ae16b8e
ORCID for Fernando J. Alvarez Borges: ORCID iD orcid.org/0000-0002-6940-9918
ORCID for Bangalore M. Madhusudhan: ORCID iD orcid.org/0000-0002-2570-5934

Catalogue record

Date deposited: 10 Mar 2023 17:42
Last modified: 12 Jun 2024 02:04

Export record

Altmetrics

Contributors

Author: Fernando J. Alvarez Borges ORCID iD
Author: Oliver N.F. King
Author: Thomas Connolley
Author: Mark Basham
Author: Sharif Ahmed

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×