A predictive estimation method for carbon dioxide transport by data-driven modeling with a physically-based data model

Jina Jeong, Eungyu Park, Weon Shik Han, Kue Young Kim, Seong Chun Jun, Sungwook Choung, Seong Taek Yun, Junho Oh, Hyun Jun Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In this study, a data-driven method for predicting CO2 leaks and associated concentrations from geological CO2 sequestration is developed. Several candidate models are compared based on their reproducibility and predictive capability for CO2 concentration measurements from the Environment Impact Evaluation Test (EIT) site in Korea. Based on the data mining results, a one-dimensional solution of the advective–dispersive equation for steady flow (i.e., Ogata-Banks solution) is found to be most representative for the test data, and this model is adopted as the data model for the developed method. In the validation step, the method is applied to estimate future CO2 concentrations with the reference estimation by the Ogata-Banks solution, where a part of earlier data is used as the training dataset. From the analysis, it is found that the ensemble mean of multiple estimations based on the developed method shows high prediction accuracy relative to the reference estimation. In addition, the majority of the data to be predicted are included in the proposed quantile interval, which suggests adequate representation of the uncertainty by the developed method. Therefore, the incorporation of a reasonable physically-based data model enhances the prediction capability of the data-driven model. The proposed method is not confined to estimations of CO2 concentration and may be applied to various real-time monitoring data from subsurface sites to develop automated control, management or decision-making systems.

Original languageEnglish
Pages (from-to)34-42
Number of pages9
JournalJournal of Contaminant Hydrology
Volume206
DOIs
Publication statusPublished - 2017 Nov 1

Fingerprint

estimation method
Carbon Dioxide
Data structures
carbon dioxide
modeling
Steady flow
Data mining
Data Mining
Decision making
Korea
data mining
steady flow
Uncertainty
prediction
Monitoring
Decision Making
carbon sequestration
method
decision making

Keywords

  • CO concentration
  • Cyber-physical system (CPS)
  • Data model
  • Data-driven model
  • Early warning system (EWS)
  • Process-based model

ASJC Scopus subject areas

  • Environmental Chemistry
  • Water Science and Technology

Cite this

A predictive estimation method for carbon dioxide transport by data-driven modeling with a physically-based data model. / Jeong, Jina; Park, Eungyu; Han, Weon Shik; Kim, Kue Young; Jun, Seong Chun; Choung, Sungwook; Yun, Seong Taek; Oh, Junho; Kim, Hyun Jun.

In: Journal of Contaminant Hydrology, Vol. 206, 01.11.2017, p. 34-42.

Research output: Contribution to journalArticle

Jeong, Jina ; Park, Eungyu ; Han, Weon Shik ; Kim, Kue Young ; Jun, Seong Chun ; Choung, Sungwook ; Yun, Seong Taek ; Oh, Junho ; Kim, Hyun Jun. / A predictive estimation method for carbon dioxide transport by data-driven modeling with a physically-based data model. In: Journal of Contaminant Hydrology. 2017 ; Vol. 206. pp. 34-42.
@article{e19bfd4b0bc84b908a8f4673a192f8d9,
title = "A predictive estimation method for carbon dioxide transport by data-driven modeling with a physically-based data model",
abstract = "In this study, a data-driven method for predicting CO2 leaks and associated concentrations from geological CO2 sequestration is developed. Several candidate models are compared based on their reproducibility and predictive capability for CO2 concentration measurements from the Environment Impact Evaluation Test (EIT) site in Korea. Based on the data mining results, a one-dimensional solution of the advective–dispersive equation for steady flow (i.e., Ogata-Banks solution) is found to be most representative for the test data, and this model is adopted as the data model for the developed method. In the validation step, the method is applied to estimate future CO2 concentrations with the reference estimation by the Ogata-Banks solution, where a part of earlier data is used as the training dataset. From the analysis, it is found that the ensemble mean of multiple estimations based on the developed method shows high prediction accuracy relative to the reference estimation. In addition, the majority of the data to be predicted are included in the proposed quantile interval, which suggests adequate representation of the uncertainty by the developed method. Therefore, the incorporation of a reasonable physically-based data model enhances the prediction capability of the data-driven model. The proposed method is not confined to estimations of CO2 concentration and may be applied to various real-time monitoring data from subsurface sites to develop automated control, management or decision-making systems.",
keywords = "CO concentration, Cyber-physical system (CPS), Data model, Data-driven model, Early warning system (EWS), Process-based model",
author = "Jina Jeong and Eungyu Park and Han, {Weon Shik} and Kim, {Kue Young} and Jun, {Seong Chun} and Sungwook Choung and Yun, {Seong Taek} and Junho Oh and Kim, {Hyun Jun}",
year = "2017",
month = "11",
day = "1",
doi = "10.1016/j.jconhyd.2017.09.011",
language = "English",
volume = "206",
pages = "34--42",
journal = "Journal of Contaminant Hydrology",
issn = "0169-7722",
publisher = "Elsevier",

}

TY - JOUR

T1 - A predictive estimation method for carbon dioxide transport by data-driven modeling with a physically-based data model

AU - Jeong, Jina

AU - Park, Eungyu

AU - Han, Weon Shik

AU - Kim, Kue Young

AU - Jun, Seong Chun

AU - Choung, Sungwook

AU - Yun, Seong Taek

AU - Oh, Junho

AU - Kim, Hyun Jun

PY - 2017/11/1

Y1 - 2017/11/1

N2 - In this study, a data-driven method for predicting CO2 leaks and associated concentrations from geological CO2 sequestration is developed. Several candidate models are compared based on their reproducibility and predictive capability for CO2 concentration measurements from the Environment Impact Evaluation Test (EIT) site in Korea. Based on the data mining results, a one-dimensional solution of the advective–dispersive equation for steady flow (i.e., Ogata-Banks solution) is found to be most representative for the test data, and this model is adopted as the data model for the developed method. In the validation step, the method is applied to estimate future CO2 concentrations with the reference estimation by the Ogata-Banks solution, where a part of earlier data is used as the training dataset. From the analysis, it is found that the ensemble mean of multiple estimations based on the developed method shows high prediction accuracy relative to the reference estimation. In addition, the majority of the data to be predicted are included in the proposed quantile interval, which suggests adequate representation of the uncertainty by the developed method. Therefore, the incorporation of a reasonable physically-based data model enhances the prediction capability of the data-driven model. The proposed method is not confined to estimations of CO2 concentration and may be applied to various real-time monitoring data from subsurface sites to develop automated control, management or decision-making systems.

AB - In this study, a data-driven method for predicting CO2 leaks and associated concentrations from geological CO2 sequestration is developed. Several candidate models are compared based on their reproducibility and predictive capability for CO2 concentration measurements from the Environment Impact Evaluation Test (EIT) site in Korea. Based on the data mining results, a one-dimensional solution of the advective–dispersive equation for steady flow (i.e., Ogata-Banks solution) is found to be most representative for the test data, and this model is adopted as the data model for the developed method. In the validation step, the method is applied to estimate future CO2 concentrations with the reference estimation by the Ogata-Banks solution, where a part of earlier data is used as the training dataset. From the analysis, it is found that the ensemble mean of multiple estimations based on the developed method shows high prediction accuracy relative to the reference estimation. In addition, the majority of the data to be predicted are included in the proposed quantile interval, which suggests adequate representation of the uncertainty by the developed method. Therefore, the incorporation of a reasonable physically-based data model enhances the prediction capability of the data-driven model. The proposed method is not confined to estimations of CO2 concentration and may be applied to various real-time monitoring data from subsurface sites to develop automated control, management or decision-making systems.

KW - CO concentration

KW - Cyber-physical system (CPS)

KW - Data model

KW - Data-driven model

KW - Early warning system (EWS)

KW - Process-based model

UR - http://www.scopus.com/inward/record.url?scp=85030475847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030475847&partnerID=8YFLogxK

U2 - 10.1016/j.jconhyd.2017.09.011

DO - 10.1016/j.jconhyd.2017.09.011

M3 - Article

C2 - 28969864

AN - SCOPUS:85030475847

VL - 206

SP - 34

EP - 42

JO - Journal of Contaminant Hydrology

JF - Journal of Contaminant Hydrology

SN - 0169-7722

ER -