Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 30, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Data-driven total organic carbon prediction using feature selection methods incorporated in an automated machine

Bruno da Silva Macêdo1, Dennis Delali Kwesi Wayo2,3, Deivid Campos4

  • 1Department of Computer Science, Federal University of Lavras, Lavras, MG, 37200-000, Brazil.

Scientific Reports
|March 28, 2025
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Data-driven design of hybrid graphene oxide-MXene polymeric membranes for water purification.

iScience·2026
Same author

Sulfuric acid-induced magnetic chitosan/graphene oxide composite hydrogel beads for pH-dependent adsorption of anionic and cationic dyes: Mechanisms, optimization, and reusability.

International journal of biological macromolecules·2026
Same author

A deep complementary learning framework for surface water temperature forecasting.

Scientific reports·2026
Same author

Does petroleum resource extraction and oceanic heat transfer increase geothermal heat flux? A global multi-sensor study of oil basins.

Innovation (Cambridge (Mass.))·2026
Same author

Synthesis and characterization of graphitic carbon nitride-doped carbon (Cu-Al/Biochar@g-C<sub>3</sub>N<sub>4</sub>) for quinoline yellow removal by the Fenton process: optimization by the response surface method.

Scientific reports·2026
Same author

The plastisphere as a nexus for antimicrobial resistance: micro(nano)plastics in pathogen colonization, gene transfer, and global health risks.

Biological reviews of the Cambridge Philosophical Society·2026

Automated Machine Learning (AutoML) accurately predicts Total Organic Carbon (TOC) in shale gas reservoirs using well log data. This approach streamlines analysis, saving time and costs associated with traditional laboratory methods.

Area of Science:

  • Geosciences
  • Petroleum Engineering
  • Data Science

Background:

  • Accurate Total Organic Carbon (TOC) assessment is crucial for sustainable shale gas resource development.
  • Traditional laboratory TOC analysis is time-consuming and expensive.
  • Data-driven models exist but require extensive parameter tuning in diverse sedimentary environments.

Purpose of the Study:

  • To develop an Automated Machine Learning (AutoML) strategy for predicting TOC using well log data.
  • To reduce the time and effort required for model development and parameter fine-tuning.
  • To provide an efficient and accurate method for TOC estimation in shale reservoirs.

Main Methods:

  • Utilized well log data as input for the predictive models.
  • Implemented an AutoML strategy to automate parameter searching and model selection.

Related Experiment Videos

Last Updated: Jun 30, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

  • Evaluated various machine learning algorithms, including Extremely Randomized Trees (XT).

    • Main Results:

    • The AutoML strategy successfully predicted TOC content from well log data.
    • Extremely Randomized Trees (XT) demonstrated the best performance with R = 0.8632 and MSE = 0.1806 on the test set.
    • The developed method significantly reduced execution time compared to traditional approaches.

    Conclusions:

    • AutoML offers a powerful and efficient data-driven approach for TOC estimation in shale gas exploration.
    • The proposed strategy facilitates real-world application in well data analysis and decision-making.
    • This method enhances the assessment of hydrocarbon source rock potential and shale gas resource evaluation.