Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation
This study proposes three-phase saturation identification using X-ray computerized tomography (CT) images of gas hydrate (GH) experiments considering critical GH saturation (S<sub>GH,C</sub>) based on the machine-learning method of random forest. Eight GH samples were categorized into th...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-11-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/13/21/5844 |
id |
doaj-4614a43ada234a5cac20132dfff5a5d6 |
---|---|
record_format |
Article |
spelling |
doaj-4614a43ada234a5cac20132dfff5a5d62020-11-25T03:59:15ZengMDPI AGEnergies1996-10732020-11-01135844584410.3390/en13215844Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate SaturationSungil Kim0Kyungbook Lee1Minhui Lee2Taewoong Ahn3Petroleum and Marine Research Division, Korea Institute of Geoscience and Mineral Resources, Daejeon 34132, KoreaPetroleum and Marine Research Division, Korea Institute of Geoscience and Mineral Resources, Daejeon 34132, KoreaGEOLAB Co., Ltd., Sejong 30121, KoreaPetroleum and Marine Research Division, Korea Institute of Geoscience and Mineral Resources, Daejeon 34132, KoreaThis study proposes three-phase saturation identification using X-ray computerized tomography (CT) images of gas hydrate (GH) experiments considering critical GH saturation (S<sub>GH,C</sub>) based on the machine-learning method of random forest. Eight GH samples were categorized into three low and five high GH saturation (S<sub>GH</sub>) groups. Mean square error of test results in the low and the high groups showed decreases of 37% and 33%, respectively, compared to that of the total eight. Additionally, a universal test set was configured from the total eight and tested with two trained machines for the low and high GH groups. Results revealed a boundary at ~50% of S<sub>GH</sub> signifying different saturation identification performance and the ~50% was estimated as S<sub>GH,C</sub> in this study. The trained machines for the low and high S<sub>GH</sub> groups had less performance on the larger and smaller values, respectively, of S<sub>GH,C</sub>. These findings conclude that we can take advantage of suitable separation of obtained training data, such as GH CT images, under the criteria of S<sub>GH,C</sub>. Moreover, the proposed data-driven method not only serves as a saturation identification method for GH samples in real time, but also provides a guideline to make decisions for data acquirement priorities.https://www.mdpi.com/1996-1073/13/21/5844X-ray CT imagecritical gas hydrate saturationsaturation identificationrandom forestdata managementmachine-learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Sungil Kim Kyungbook Lee Minhui Lee Taewoong Ahn |
spellingShingle |
Sungil Kim Kyungbook Lee Minhui Lee Taewoong Ahn Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation Energies X-ray CT image critical gas hydrate saturation saturation identification random forest data management machine-learning |
author_facet |
Sungil Kim Kyungbook Lee Minhui Lee Taewoong Ahn |
author_sort |
Sungil Kim |
title |
Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation |
title_short |
Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation |
title_full |
Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation |
title_fullStr |
Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation |
title_full_unstemmed |
Data-Driven Three-Phase Saturation Identification from X-ray CT Images with Critical Gas Hydrate Saturation |
title_sort |
data-driven three-phase saturation identification from x-ray ct images with critical gas hydrate saturation |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2020-11-01 |
description |
This study proposes three-phase saturation identification using X-ray computerized tomography (CT) images of gas hydrate (GH) experiments considering critical GH saturation (S<sub>GH,C</sub>) based on the machine-learning method of random forest. Eight GH samples were categorized into three low and five high GH saturation (S<sub>GH</sub>) groups. Mean square error of test results in the low and the high groups showed decreases of 37% and 33%, respectively, compared to that of the total eight. Additionally, a universal test set was configured from the total eight and tested with two trained machines for the low and high GH groups. Results revealed a boundary at ~50% of S<sub>GH</sub> signifying different saturation identification performance and the ~50% was estimated as S<sub>GH,C</sub> in this study. The trained machines for the low and high S<sub>GH</sub> groups had less performance on the larger and smaller values, respectively, of S<sub>GH,C</sub>. These findings conclude that we can take advantage of suitable separation of obtained training data, such as GH CT images, under the criteria of S<sub>GH,C</sub>. Moreover, the proposed data-driven method not only serves as a saturation identification method for GH samples in real time, but also provides a guideline to make decisions for data acquirement priorities. |
topic |
X-ray CT image critical gas hydrate saturation saturation identification random forest data management machine-learning |
url |
https://www.mdpi.com/1996-1073/13/21/5844 |
work_keys_str_mv |
AT sungilkim datadriventhreephasesaturationidentificationfromxrayctimageswithcriticalgashydratesaturation AT kyungbooklee datadriventhreephasesaturationidentificationfromxrayctimageswithcriticalgashydratesaturation AT minhuilee datadriventhreephasesaturationidentificationfromxrayctimageswithcriticalgashydratesaturation AT taewoongahn datadriventhreephasesaturationidentificationfromxrayctimageswithcriticalgashydratesaturation |
_version_ |
1724454950800457728 |