Authors : Pronab Chowdhury

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

Google Scholar : https://tinyurl.com/msut32wf

Scribd : https://tinyurl.com/2h69j6ac

DOI : https://doi.org/10.38124/ijisrt/26jul1414

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

Abstract : Artificial intelligence (AI) has significantly improved seismic reservoir characterization by enabling accurate prediction of petrophysical properties from complex seismic attributes. However, many high-performing machine learning algorithms operate as "black-box" models, providing limited insight into how geological features influence prediction outcomes. This lack of interpretability reduces user confidence and restricts the practical adoption of AI-assisted seismic interpretation in hydrocarbon exploration. To address this limitation, this study proposes an Explainable Artificial Intelligence (XAI) framework for quantitative seismic reservoir characterization using SHapley Additive exPlanations (SHAP). The proposed workflow integrates seismic attribute engineering, supervised machine learning, and feature attribution analysis to identify the relative contribution of individual seismic attributes to porosity prediction and lithofacies classification. Multiple machine learning models are trained using calibrated seismic and well-log data, while SHAP is employed to generate both global and local explanations of model predictions. Global feature importance analysis identifies the most influential seismic attributes controlling reservoir quality, whereas local explanations provide sample-specific interpretations that improve geological understanding and decision transparency. Illustrative results indicate that SHAP successfully distinguishes dominant seismic attributes associated with high-quality reservoir zones and reveals nonlinear interactions among amplitude, frequency, and geometric attributes. The proposed framework enhances the interpretability, transparency, and reliability of AI-assisted seismic interpretation while supporting confidence-aware reservoir characterization. This explainable workflow offers an effective decision-support tool for hydrocarbon exploration and provides a practical foundation for integrating trustworthy artificial intelligence into future digital reservoir management systems.

Keywords : Explainable Artificial Intelligence, SHAP, Machine Learning, Seismic Interpretation, Reservoir Characterization, Seismic Attributes, Feature Attribution, Porosity Prediction, Lithofacies Classification.

References :

1. 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.
2. 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.
3. 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.
4. 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.
5. 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.
6. 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.
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, doi: 10.30574/wjaets.2023.9.1.0147.
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, doi: 10.30574/wjaets.2024.11.2.0122.
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, doi: 10.30574/ijsra.2026.18.3.0539.
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, doi: 10.30574/wjaets.2026.18.3.0166.
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, doi: 10.30574/wjaets.2026.20.1.0364.
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, doi: 10.30574/wjaets.2026.20.1.0366.
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, doi: 10.30574/wjaets.2026.20.1.0365.
14. L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
15. J. H. Friedman, "Greedy function approximation: A gradient boosting machine," Annals of Statistics, vol. 29, no. 5, pp. 1189–1232, 2001.
16. 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.
17. S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774.
18. M. T. Ribeiro, S. Singh, and C. Guestrin, "Why should I trust you? Explaining the predictions of any classifier," in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1135–1144.
19. C. Molnar, Interpretable Machine Learning, 2nd ed. 2022.
20. Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.