View in EDS HTML Full Text PDF Full Text

Prediction of Minimum Horizontal Stress Using Machine Learning for Unconventional Reservoir Applications.

Saved in:
Bibliographic Details
Title: Prediction of Minimum Horizontal Stress Using Machine Learning for Unconventional Reservoir Applications.
Authors: Odekanle, Ebenezer Leke1 (AUTHOR), Olowookere, AbdulQoyum Adegoke1 (AUTHOR), Ajediti, Omolara Busayo1 (AUTHOR), Adeyanju, Bambo Ayo2 (AUTHOR), Ajagbe, Sunday Adeola3 (AUTHOR) saajagbe@pgschool.lautech.edu.ng, Adigun, Matthew O.4 (AUTHOR), Biswas, Arnab (AUTHOR) arnbiswas@wiley.com
Source: International Journal of Chemical Engineering (1687806X). 5/18/2026, Vol. 2026, p1-15. 15p.
Subjects: Machine learning, Strains & stresses (Mechanics), Ensemble learning, Shale, Shale gas reservoirs, Random forest algorithms, Hydraulic fracturing, Boosting algorithms
Geographic Terms: Marcellus Shale
Abstract: This study presents a leakage‐aware machine learning framework for predicting minimum horizontal stress (σhmin) using structured geomechanical and fracture‐related parameters. A dataset comprising 21,499 records from approximately 200 horizontal wells in the Marcellus Shale was preprocessed using a strictly leakage‐controlled pipeline, including feature refinement, outlier capping, and training‐fold–based transformations. Three ensemble models—random forest (RF), gradient boosting regressor (GBR), and extreme gradient boosting (XGBoost)—along with a stacking regressor and artificial neural network (ANN), were evaluated using root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The RF model achieved the best baseline performance (RMSE = 6.5846, R2 = 0.9988), while gradient boosting showed improved performance after tuning (RMSE ≈ 6.59). The stacking model delivered competitive results (RMSE = 7.4963), whereas the ANN showed lower performance (RMSE = 55.5008), indicating limited suitability for structured tabular data. A scenario‐based evaluation using Nigerian reservoir data demonstrated reasonable pr3332edictive consistency but was not treated as external validation due to data limitations. The results confirm that leakage‐aware ensemble learning provides a robust and physically consistent approach for predicting minimum horizontal stress, with potential application in reservoir characterization and hydraulic fracturing design. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Chemical Engineering (1687806X) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 193836852
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prediction of Minimum Horizontal Stress Using Machine Learning for Unconventional Reservoir Applications.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Odekanle%2C+Ebenezer+Leke%22">Odekanle, Ebenezer Leke</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Olowookere%2C+AbdulQoyum+Adegoke%22">Olowookere, AbdulQoyum Adegoke</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ajediti%2C+Omolara+Busayo%22">Ajediti, Omolara Busayo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Adeyanju%2C+Bambo+Ayo%22">Adeyanju, Bambo Ayo</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ajagbe%2C+Sunday+Adeola%22">Ajagbe, Sunday Adeola</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> saajagbe@pgschool.lautech.edu.ng</i><br /><searchLink fieldCode="AR" term="%22Adigun%2C+Matthew+O%2E%22">Adigun, Matthew O.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Biswas%2C+Arnab%22">Biswas, Arnab</searchLink> (AUTHOR)<i> arnbiswas@wiley.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Chemical+Engineering+%281687806X%29%22">International Journal of Chemical Engineering (1687806X)</searchLink>. 5/18/2026, Vol. 2026, p1-15. 15p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Strains+%26+stresses+%28Mechanics%29%22">Strains & stresses (Mechanics)</searchLink><br /><searchLink fieldCode="DE" term="%22Ensemble+learning%22">Ensemble learning</searchLink><br /><searchLink fieldCode="DE" term="%22Shale%22">Shale</searchLink><br /><searchLink fieldCode="DE" term="%22Shale+gas+reservoirs%22">Shale gas reservoirs</searchLink><br /><searchLink fieldCode="DE" term="%22Random+forest+algorithms%22">Random forest algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Hydraulic+fracturing%22">Hydraulic fracturing</searchLink><br /><searchLink fieldCode="DE" term="%22Boosting+algorithms%22">Boosting algorithms</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Marcellus+Shale%22">Marcellus Shale</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study presents a leakage‐aware machine learning framework for predicting minimum horizontal stress (σhmin) using structured geomechanical and fracture‐related parameters. A dataset comprising 21,499 records from approximately 200 horizontal wells in the Marcellus Shale was preprocessed using a strictly leakage‐controlled pipeline, including feature refinement, outlier capping, and training‐fold–based transformations. Three ensemble models—random forest (RF), gradient boosting regressor (GBR), and extreme gradient boosting (XGBoost)—along with a stacking regressor and artificial neural network (ANN), were evaluated using root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The RF model achieved the best baseline performance (RMSE = 6.5846, R2 = 0.9988), while gradient boosting showed improved performance after tuning (RMSE ≈ 6.59). The stacking model delivered competitive results (RMSE = 7.4963), whereas the ANN showed lower performance (RMSE = 55.5008), indicating limited suitability for structured tabular data. A scenario‐based evaluation using Nigerian reservoir data demonstrated reasonable pr3332edictive consistency but was not treated as external validation due to data limitations. The results confirm that leakage‐aware ensemble learning provides a robust and physically consistent approach for predicting minimum horizontal stress, with potential application in reservoir characterization and hydraulic fracturing design. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of International Journal of Chemical Engineering (1687806X) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193836852
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1155/ijce/5409400
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 15
        StartPage: 1
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Strains & stresses (Mechanics)
        Type: general
      – SubjectFull: Ensemble learning
        Type: general
      – SubjectFull: Shale
        Type: general
      – SubjectFull: Shale gas reservoirs
        Type: general
      – SubjectFull: Random forest algorithms
        Type: general
      – SubjectFull: Hydraulic fracturing
        Type: general
      – SubjectFull: Boosting algorithms
        Type: general
      – SubjectFull: Marcellus Shale
        Type: general
    Titles:
      – TitleFull: Prediction of Minimum Horizontal Stress Using Machine Learning for Unconventional Reservoir Applications.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Odekanle, Ebenezer Leke
      – PersonEntity:
          Name:
            NameFull: Olowookere, AbdulQoyum Adegoke
      – PersonEntity:
          Name:
            NameFull: Ajediti, Omolara Busayo
      – PersonEntity:
          Name:
            NameFull: Adeyanju, Bambo Ayo
      – PersonEntity:
          Name:
            NameFull: Ajagbe, Sunday Adeola
      – PersonEntity:
          Name:
            NameFull: Adigun, Matthew O.
      – PersonEntity:
          Name:
            NameFull: Biswas, Arnab
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 18
              M: 05
              Text: 5/18/2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 1687806X
          Numbering:
            – Type: volume
              Value: 2026
          Titles:
            – TitleFull: International Journal of Chemical Engineering (1687806X)
              Type: main
ResultId 1