⚠ Official Notice: www.ijisrt.com is the official website of the International Journal of Innovative Science and Research Technology (IJISRT) Journal for research paper submission and publication. Please beware of fake or duplicate websites using the IJISRT name.



Ensemble Machine Learning for Seismic Attribute-Based Porosity Prediction and Lithofacies Classification in Clastic Hydrocarbon Reservoirs: A Comparative Workflow with Uncertainty Assessment


Authors : Pronab Chowdhury

Volume/Issue : Volume 11 - 2026, Issue 7 - July

Google Scholar : https://tinyurl.com/smw3y3cb

Scribd : https://tinyurl.com/49nkf8n7

DOI : https://doi.org/10.38124/ijisrt/26jul1413

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Accurate prediction of reservoir porosity and reliable lithofacies classification are fundamental to hydrocarbon exploration and reservoir development because they directly influence reserve estimation, well placement, and production optimization. Conventional seismic interpretation methods often struggle to capture the complex nonlinear relationships between seismic attributes and reservoir properties, particularly in heterogeneous clastic formations. This study presents an integrated machine learning workflow for simultaneous porosity prediction and lithofacies classification using post-stack seismic attributes calibrated with well-log observations. Twenty seismic attributes representing amplitude, frequency, phase, geometric, and textural characteristics were extracted from a three-dimensional seismic volume and screened using a systematic feature-selection strategy. Four supervised machine learning algorithms, namely Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Artificial Neural Networks (ANN), were developed and compared for porosity estimation, while corresponding classification models were evaluated for lithofacies prediction. Model performance was assessed using k-fold cross-validation and blind-well validation to ensure robust generalization. Predictive uncertainty was quantified through ensemble-based confidence estimation and incorporated into the final reservoir property volumes. Illustrative placeholder results indicate that ensemble learning algorithms consistently outperform conventional regression approaches by effectively capturing nonlinear relationships among seismic attributes while providing improved porosity prediction accuracy and more reliable lithofacies discrimination. The proposed workflow integrates feature selection, comparative machine learning evaluation, blind-well validation, and uncertainty assessment into a unified framework that can be readily adapted to other clastic hydrocarbon reservoirs. This study demonstrates the potential of modern machine learning techniques for quantitative seismic reservoir characterization while providing confidence-aware predictions for exploration and field-development decision making.

Keywords : Machine Learning; Seismic Attributes; Reservoir Characterization; Porosity Prediction; Lithofacies Classification; Random Forest; Artificial Neural Network; Gradient Boosting; Support Vector Regression; Uncertainty Assessment.

References :

  1. P. Avseth, T. Mukerji, and G. Mavko, Quantitative Seismic Interpretation: Applying Rock Physics Tools to Reduce Interpretation Risk. Cambridge University Press, 2005.
  2. P. M. Doyen, Seismic Reservoir Characterization: An Earth Modelling Perspective. EAGE Publications, 2007.
  3. G. Mavko, T. Mukerji, and J. Dvorkin, The Rock Physics Handbook, 2nd ed. Cambridge University Press, 2009.
  4. M. T. Taner, F. Koehler, and R. E. Sheriff, "Complex seismic trace analysis," Geophysics, vol. 44, no. 6, pp. 1041–1063, 1979.
  5. S. Chopra and K. J. Marfurt, Seismic Attributes for Prospect Identification and Reservoir Characterization. SEG, 2007.
  6. D. P. Hampson, J. S. Schuelke, and J. A. Quirein, "Use of multiattribute transforms to predict log properties from seismic data," Geophysics, vol. 66, no. 1, pp. 220–236, 2001.
  7. R. A. Elbarouni, "A review of AI-driven seismic interpretation, digital twin technology and intelligent reservoir characterization for hydrocarbon exploration," World Journal of Advanced Engineering Technology and Sciences, vol. 9, no. 1, pp. 513–519, 2023.
  8. R. A. Elbarouni, "AI-driven digital twin framework for real-time seismic reservoir monitoring and predictive hydrocarbon production optimization," World Journal of Advanced Engineering Technology and Sciences, vol. 11, no. 2, pp. 712–720, 2024.
  9. R. A. Elbarouni, "Advanced 3D seismic interpretation techniques for accurate subsurface structural mapping and reservoir characterization," International Journal of Science and Research Archive, vol. 18, no. 3, pp. 992–1002, 2026.
  10. R. A. Elbarouni, "Seismic attribute-based fault detection and structural mapping in 3D seismic data for hydrocarbon exploration," World Journal of Advanced Engineering Technology and Sciences, vol. 18, no. 3, pp. 320–329, 2026.
  11. R. A. Elbarouni, "Integrated seismic and petrophysical analysis for improved hydrocarbon reservoir characterization," World Journal of Advanced Engineering Technology and Sciences, vol. 20, no. 1, pp. 196–207, 2026.
  12. R. A. Elbarouni, "Machine learning-based seismic attribute analysis for porosity prediction and lithofacies classification in clastic hydrocarbon reservoirs," World Journal of Advanced Engineering Technology and Sciences, vol. 20, no. 1, pp. 231–240, 2026.
  13. R. A. Elbarouni, "Uncertainty-aware reservoir characterization using probabilistic seismic–petrophysical integration," World Journal of Advanced Engineering Technology and Sciences, vol. 20, no. 1, pp. 219–230, 2026.
  14. L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
  15. C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
  16. J. H. Friedman, "Greedy function approximation: A gradient boosting machine," Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
  17. T. Chen and C. Guestrin, "XGBoost: A scalable tree boosting system," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785–794.
  18. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, pp. 436–444, 2015.
  19. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
  20. F. Pedregosa et al., "Scikit-learn: Machine learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
  21. K. J. Bergen, P. A. Johnson, M. V. de Hoop, and G. C. Beroza, "Machine learning for data-driven discovery in solid Earth geoscience," Science, vol. 363, eaau0323, 2019.
  22. J. S. Dramsch, "70 years of machine learning in geoscience in review," Advances in Geophysics, vol. 61, pp. 1–55, 2020.
  23. S. Yu and J. Ma, "Deep learning for geophysics: Current and future trends," Reviews of Geophysics, vol. 59, e2021RG000742, 2021.
  24. M. R. Islam, "System Dynamics of Leadership Influence in Sustainable Supply Chains," World Journal of Advanced Engineering Technology and Sciences, vol. 17, no. 03, pp. 509–514, 2025, doi: 10.30574/wjaets.2025.17.3.1584.
  25. M. R. Islam, "Digital Leadership and Circular Economy Performance in Sustainable Supply Chains," World Journal of Advanced Engineering Technology and Sciences, vol. 17, no. 03, pp. 503–508, 2025, doi: 10.30574/wjaets.2025.17.3.1583.
  26. M. R. Islam, "Circular economy leadership for sustainable industrial transformation: A holistic framework for resilient and resource-efficient growth," World Journal of Advanced Engineering Technology and Sciences, vol. 17, no. 03, pp. 253–262, 2025, doi: 10.30574/wjaets.2025.17.3.1540.
  27. Y. A. Bipasha, M. R. Islam, and M. F. Ahmed, "A blockchain and machine learning framework for secure and transparent digital supply chain management," International Journal of Innovative Science and Research Technology, vol. 11, no. 3, pp. 945–952, Mar. 2026, doi: 10.38124/IJISRT/26MAR767.
  28. M. R. Islam and A. Halim, "Developing a challenge-driven project management framework for sustainable development: An MCDM-based evaluation and prioritization approach," International Journal of Science and Research Archive, vol. 18, no. 01, pp. 177–187, 2026, doi: 10.30574/ijsra.2026.18.1.0027.
  29. M. B. Uddin, M. R. Islam, M. N. Uddin, and A. Halim, "Next-generation plastic recycling: Breakthrough developments and the path toward a circular economy," World Journal of Advanced Engineering Technology and Sciences, vol. 16, no. 01, pp. 513–527, 2025, doi: 10.30574/wjaets.2025.16.1.1237.

Accurate prediction of reservoir porosity and reliable lithofacies classification are fundamental to hydrocarbon exploration and reservoir development because they directly influence reserve estimation, well placement, and production optimization. Conventional seismic interpretation methods often struggle to capture the complex nonlinear relationships between seismic attributes and reservoir properties, particularly in heterogeneous clastic formations. This study presents an integrated machine learning workflow for simultaneous porosity prediction and lithofacies classification using post-stack seismic attributes calibrated with well-log observations. Twenty seismic attributes representing amplitude, frequency, phase, geometric, and textural characteristics were extracted from a three-dimensional seismic volume and screened using a systematic feature-selection strategy. Four supervised machine learning algorithms, namely Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Artificial Neural Networks (ANN), were developed and compared for porosity estimation, while corresponding classification models were evaluated for lithofacies prediction. Model performance was assessed using k-fold cross-validation and blind-well validation to ensure robust generalization. Predictive uncertainty was quantified through ensemble-based confidence estimation and incorporated into the final reservoir property volumes. Illustrative placeholder results indicate that ensemble learning algorithms consistently outperform conventional regression approaches by effectively capturing nonlinear relationships among seismic attributes while providing improved porosity prediction accuracy and more reliable lithofacies discrimination. The proposed workflow integrates feature selection, comparative machine learning evaluation, blind-well validation, and uncertainty assessment into a unified framework that can be readily adapted to other clastic hydrocarbon reservoirs. This study demonstrates the potential of modern machine learning techniques for quantitative seismic reservoir characterization while providing confidence-aware predictions for exploration and field-development decision making.

Keywords : Machine Learning; Seismic Attributes; Reservoir Characterization; Porosity Prediction; Lithofacies Classification; Random Forest; Artificial Neural Network; Gradient Boosting; Support Vector Regression; Uncertainty Assessment.

Paper Submission Last Date
31 - August - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe