1887

Abstract

Summary

Hydrocarbon source rocks are rich in organic matter, and studying their spatial distribution is crucial for advancing deep oil and gas exploration. Key evaluation indices for hydrocarbon source rocks include Total Organic Carbon (TOC) content, specular body reflectance, and pyrolysis parameters. Traditionally, TOC has been measured as discrete points in the laboratory through geochemical methods, and the continuous TOC curve is typically derived using multi-parameter regression. However, this approach is limited to 1D well data and is not suitable for 3D spatial predictions of hydrocarbon source rocks. In this research, we developed a TOC prediction process for hydrocarbon source rocks based on the LightGBM algorithm, incorporating feature engineering, model interpretation, and evaluation. The reliability of this method was validated by comparing prediction accuracies. Field data test results demonstrate that the TOC predictions based on LightGBM exhibit high reliability, providing valuable data support for oil and gas exploration.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202510132
2025-06-02
2026-02-09

  • From This Site

    /content/papers/10.3997/2214-4609.202510132
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Jia, W., Z.Zong, D.Qin, and T.Lan. 2023a, Integrated well-log data and seismic inversion results for prediction of hydrocarbon source rock distribution in W segment, Pearl River Mouth Basin, China. Geoenergy Science and Engineering, 230,212233. doi: https://doi.org/10.1016/j.geoen.2023.212233.
     [Google Scholar]
  2. Jia, W., Z.Zong, D.Qin, and T.Lan. 2023b, A method for predicting the TOC in source rocks using a machine learning-based joint analysis of seismic multi-attributes. Journal of Applied Geophysics, 216,105143. doi: https://doi.org/10.1016/j.jappgeo.2023.105143.
     [Google Scholar]
  3. Jiang, M., D.Chen, X.Chang, L.Shu, and F.Wang. 2022, Controlling effect of tectonic-paleogeomorphology on deposition in the south of Lufeng sag, Pearl River Mouth Basin. Advances in Geo-Energy Research, 6, no. 5, 363–374.
     [Google Scholar]
  4. Ke, G., Q.Meng, T.Finley, T.Wang, W.Chen, W.Ma, Q.Ye, and T.-Y.Liu. 2017, Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
     [Google Scholar]
  5. Liu, G., Z.Niu, Z.Chen, X.Zhang, Y.Lei, M.Zhang, X.Wang, and X.Wang. 2019, Hydrocarbon accumulation patterns controlled by the migrated subsags in Lufeng sag. Pearl River Mouth Basin. ACTA PETROLET SINICA, 40, no. S1,26–40+216.
     [Google Scholar]
  6. Yu, S., Z.Zong, and X.Yin. 2021, Rock Physical Model and AVO Patterns for the Mud-Rich Source Rock. Frontiers in Earth Science, 9. doi: 10.3389/feart.2021.633930.
     https://doi.org/10.3389/feart.2021.633930 [Google Scholar]
/content/papers/10.3997/2214-4609.202510132
Loading
Integrated well Logging Data and Seismic Attributes Data for Prediction TOC with LightGBM Method
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202510132
/content/papers/10.3997/2214-4609.202510132
/content/papers/10.3997/2214-4609.202510132
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error