Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks

Caleb John; Oluwatoyin Akinsete; Abosede A. Fadayomi; Samuel B. Aderemi

doi:doi:10.11648/j.ogce.20261401.11

Research Article |

| Peer-Reviewed

Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks

Caleb John^*

, Oluwatoyin Akinsete

, Abosede A. Fadayomi

, Samuel B. Aderemi

Published in International Journal of Oil, Gas and Coal Engineering (Volume 14, Issue 1)

Received: 1 October 2025 Accepted: 14 October 2025 Published: 2 February 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Modeling fractional flow curves accurately is essential for optimizing reservoir performance and improving hydrocarbon recovery. This study introduces a robust analytical framework utilizing advanced computational techniques to predict fractional flow behavior. The model leverages Gradient Boosted Decision Trees (GBDT) and integrates key physical parameters such as water saturation, viscosity ratios, and relative permeability. The performance of the proposed framework was evaluated using data from reservoir simulations and experiments. The model demonstrated high predictive accuracy, achieving a Root Mean Square Error (RMSE) of 0.005, a Coefficient of Determination (R²) of 0.99, and a Mean Absolute Percentage Error (MAPE) of 1%. Compared to conventional fractional flow models based on Buckley-Leverett theory, which yielded an RMSE of 0.16 and a MAPE of 12.8%, the new approach showed significant improvement. Additionally, it outperformed other computational approaches, including Random Forest (RMSE: 0.02, MAPE: 10.4%) and Artificial Neural Networks (RMSE: 0.016, MAPE: 6.0%), providing both enhanced accuracy and consistency. A sensitivity analysis confirmed the robustness of the model across a range of viscosity ratios, showing strong alignment with physical principles, such as shock front behavior and saturation constraints. The practical utility of this model lies in its ability to accurately predict fractional flow under varying conditions, bridging gaps between analytical methods and data-driven techniques, while remaining computationally efficient. This development enhances the tools available for reservoir engineers, offering new insights for waterflooding strategies, enhanced oil recovery (EOR), and other multi-phase flow applications, with direct relevance to field operations.

Published in	International Journal of Oil, Gas and Coal Engineering (Volume 14, Issue 1)
DOI	10.11648/j.ogce.20261401.11
Page(s)	1-9
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2026. Published by Science Publishing Group

Keywords

Buckley-Leverett Theory, Enhanced Oil Recovery, Fractional Flow Model, Machine Learning, Reservoir Engineering

References

[1]	Buckley, S. E., and Leverett, M. C. (1942). Mechanism of fluid displacement in sands. Transactions of the AIME, 146(1), 107–116. https://doi.org/10.2118/942107-G
[2]	Dake, L. P. (1983). Fundamentals of reservoir engineering. Elsevier.
[3]	Welge, H. J. (1952). A simplified method for computing oil recovery by gas or water drive. Journal of Petroleum Technology, 4(4), 91–98. https://doi.org/10.2118/124-G
[4]	Tarek, A. (2010). Reservoir engineering handbook (4th ed.). Gulf Professional Publishing.
[5]	Fadairo, A., Adeyemi, A., & Falode, O. (2014). A new analytical model for developing fractional flow curve using production data. Journal of Chemical and Petroleum Engineering, 55(1), 45–56. https://doi.org/10.22059/JCHPE.2014.7559
[6]	Nagao, M., Datta-Gupta, A., Onishi, T., & Sankaran, S. (2024). Physics-informed machine learning for reservoir connectivity identification and robust production forecasting. SPE Journal, 29(9), 4527–4541. https://doi.org/10.2118/219773-PA
[7]	Kantzas, A., Bryan, J., & Taheri, S. (2018). Fundamentals of fluid flow in porous media. Perm Inc. Retrieved from https://perminc.com/resources/fundamentals-of-fluid-flow-in-porous-media/
[8]	Ren, X., Li, A., Fu, S., & Wang, S. (2018). Experimental study on the oil-water relative permeability relationship for tight sandstone considering the nonlinear seepage characteristics. Journal of Petroleum Science and Engineering, 163, 655–664. https://doi.org/10.1016/j.petrol.2017.12.003
[9]	Sitorus, J., Sofyan, A., & Abdulfatah, M. Y. (2006). Developing a fractional flow curve from historic production to predict performance of new horizontal wells—Bekasap Field, Indonesia. Society of Petroleum Engineers. https://doi.org/10.2118/101144-MS
[10]	Cao, F., Luo, H., & Lake, L. (2015). Oil rate forecast by inferring fractional flow models from field data. Society of Petroleum Engineers. https://doi.org/10.2118/173315-MS
[11]	Nagoo, A. S. (2018). Insights on pipe fractional flow theory and associated relationships. Retrieved from https://media.licdn.com/dms/document/media/v2/D561FAQGvEGyzCdFNFw/feedshare-document-pdf-analyzed/feedshare-document-pdf-analyzed/0/1721826593406?e=1741219200&v=beta&t=SXxGSsispUaK1eNi0sBzEuPUJTFuADIBcLXCXXEITKw
[12]	Sankaran, S., Matringe, S., Sidahmed, M., Saputelli, L., Wen, X.-H., Popa, A., & Dursun, S. (2020). Data analytics in reservoir engineering. Society of Petroleum Engineers. https://doi.org/10.2118/9781613998205
[13]	Ramalho, L. A. M., Tueros, J. A. R., & Horowitz, B. (2023). Machine learning applied to evaluation of reservoir connectivity. Neural Computing and Applications, 36(2). https://doi.org/10.1007/s00521-023-09056-0
[14]	Gjennestad, M. A., Winkler, M., & Hansen, A. (2019). Pore network modeling of the effects of viscosity ratio and pressure gradient on steady-state incompressible two-phase flow in porous media. https://doi.org/10.1007/s11242-020-01395-z
[15]	Knudsen, H. A., & Hansen, A. (2001). A new relation between pressure and fractional flow in two-phase flow in porous media. https://doi.org/10.1103/PhysRevE.65.056310
[16]	Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. https://doi.org/10.1145/2939672.2939785
[17]	Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
[18]	LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
[19]	Bassir, S. M., Zargar, G., Moghadasi, J., & Roghanian, R. (2016). A comprehensive review of low salinity water-flooding in sandstone/carbonate reservoirs: From theory to practice. The Fourth International Conference on Oil, Gas, Refining & Petrochemical. Retrieved from https://www.researchgate.net/publication/329058576_A_Comprehensive_Review_of_Low_Salinity_Waterflooding_in_SandstoneCarbonate_Reservoirs_From_Theory_to_Practice
[20]	Zhou, W., Liu, C., Liu, Y., Zhang, Z., Chen, P., & Jiang, L. (2024). Machine learning in reservoir engineering: A review. Processes, 12(6), 1219. https://doi.org/10.3390/pr12061219
[21]	Zhang, J., Braga-Neto, U. M., & Gildin, E. (2024). Physics-informed neural networks for multiphase flow in porous media considering dual shocks and interphase solubility. Energy & Fuels, 38(18), 17781–17795. https://doi.org/10.1021/acs.energyfuels.4c02888
[22]	Cao, F., Luo, H., & Lake, L. W. (2015). Oil-rate forecast by inferring fractional-flow models from field data with Koval method combined with the capacitance resistance model. SPE Reservoir Evaluation & Engineering. Society of Petroleum Engineers. https://doi.org/10.2118/173315-PA
[23]	Ertekin, T., Abou-Kassem, J. H., & King, G. R. (2001). Basic applied reservoir simulation (Vol. 7). SPE Textbook Series. https://doi.org/10.2118/9781555630898
[24]	Yousef, A. A., Gentil, P. H., & Jensen, J. L. (2005, October 9–12). A capacitance model to infer interwell connectivity from production and injection rate fluctuations. SPE Annual Technical Conference and Exhibition, Dallas, Texas. Society of Petroleum Engineers. https://doi.org/10.2118/95322-PA
[25]	Temirchev, P., Simonov, M., Kostoev, R., Burnaev, E., Oseledets, I., Akhmetov, A., Margarit, A., Sitnikov, A., & Koroteev, D. (2019). Deep neural networks predicting oil movement in a development unit. arXiv. https://doi.org/10.48550/arXiv.1901.02549
[26]	Ertekin, T., & Sun, Q. (2019). Artificial intelligence applications in reservoir engineering: A status check. Energies, 12(15), 2897. https://doi.org/10.3390/en12152897
[27]	Zhao, C., Zhang, F., Lou, W., Wang, X., & Yang, J. (2024). A comprehensive review of advances in physics-informed neural networks and their applications in complex fluid dynamics. Physics of Fluids, 36(101301). https://doi.org/10.1063/5.0226562
[28]	Gao, M., Liu, Z., Qian, S., Liu, W., Li, W., Yin, H., & Cao, J. (2023). Machine-learning-based approach to optimize CO₂-WAG flooding in low permeability oil reservoirs. Energies, 16(17), 6149. https://doi.org/10.3390/en16176149

Cite This Article

Plain Text BibTeX RIS

APA Style

John, C., Akinsete, O., Fadayomi, A. A., Aderemi, S. B. (2026). Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. International Journal of Oil, Gas and Coal Engineering, 14(1), 1-9. https://doi.org/10.11648/j.ogce.20261401.11

Copy | Download

ACS Style

John, C.; Akinsete, O.; Fadayomi, A. A.; Aderemi, S. B. Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. Int. J. Oil Gas Coal Eng. 2026, 14(1), 1-9. doi: 10.11648/j.ogce.20261401.11

Copy | Download

AMA Style

John C, Akinsete O, Fadayomi AA, Aderemi SB. Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. Int J Oil Gas Coal Eng. 2026;14(1):1-9. doi: 10.11648/j.ogce.20261401.11

Copy | Download

@article{10.11648/j.ogce.20261401.11,
  author = {Caleb John and Oluwatoyin Akinsete and Abosede A. Fadayomi and Samuel B. Aderemi},
  title = {Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks},
  journal = {International Journal of Oil, Gas and Coal Engineering},
  volume = {14},
  number = {1},
  pages = {1-9},
  doi = {10.11648/j.ogce.20261401.11},
  url = {https://doi.org/10.11648/j.ogce.20261401.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ogce.20261401.11},
  abstract = {Modeling fractional flow curves accurately is essential for optimizing reservoir performance and improving hydrocarbon recovery. This study introduces a robust analytical framework utilizing advanced computational techniques to predict fractional flow behavior. The model leverages Gradient Boosted Decision Trees (GBDT) and integrates key physical parameters such as water saturation, viscosity ratios, and relative permeability. The performance of the proposed framework was evaluated using data from reservoir simulations and experiments. The model demonstrated high predictive accuracy, achieving a Root Mean Square Error (RMSE) of 0.005, a Coefficient of Determination (R2) of 0.99, and a Mean Absolute Percentage Error (MAPE) of 1%. Compared to conventional fractional flow models based on Buckley-Leverett theory, which yielded an RMSE of 0.16 and a MAPE of 12.8%, the new approach showed significant improvement. Additionally, it outperformed other computational approaches, including Random Forest (RMSE: 0.02, MAPE: 10.4%) and Artificial Neural Networks (RMSE: 0.016, MAPE: 6.0%), providing both enhanced accuracy and consistency. A sensitivity analysis confirmed the robustness of the model across a range of viscosity ratios, showing strong alignment with physical principles, such as shock front behavior and saturation constraints. The practical utility of this model lies in its ability to accurately predict fractional flow under varying conditions, bridging gaps between analytical methods and data-driven techniques, while remaining computationally efficient. This development enhances the tools available for reservoir engineers, offering new insights for waterflooding strategies, enhanced oil recovery (EOR), and other multi-phase flow applications, with direct relevance to field operations.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks
AU  - Caleb John
AU  - Oluwatoyin Akinsete
AU  - Abosede A. Fadayomi
AU  - Samuel B. Aderemi
Y1  - 2026/02/02
PY  - 2026
N1  - https://doi.org/10.11648/j.ogce.20261401.11
DO  - 10.11648/j.ogce.20261401.11
T2  - International Journal of Oil, Gas and Coal Engineering
JF  - International Journal of Oil, Gas and Coal Engineering
JO  - International Journal of Oil, Gas and Coal Engineering
SP  - 1
EP  - 9
PB  - Science Publishing Group
SN  - 2376-7677
UR  - https://doi.org/10.11648/j.ogce.20261401.11
AB  - Modeling fractional flow curves accurately is essential for optimizing reservoir performance and improving hydrocarbon recovery. This study introduces a robust analytical framework utilizing advanced computational techniques to predict fractional flow behavior. The model leverages Gradient Boosted Decision Trees (GBDT) and integrates key physical parameters such as water saturation, viscosity ratios, and relative permeability. The performance of the proposed framework was evaluated using data from reservoir simulations and experiments. The model demonstrated high predictive accuracy, achieving a Root Mean Square Error (RMSE) of 0.005, a Coefficient of Determination (R2) of 0.99, and a Mean Absolute Percentage Error (MAPE) of 1%. Compared to conventional fractional flow models based on Buckley-Leverett theory, which yielded an RMSE of 0.16 and a MAPE of 12.8%, the new approach showed significant improvement. Additionally, it outperformed other computational approaches, including Random Forest (RMSE: 0.02, MAPE: 10.4%) and Artificial Neural Networks (RMSE: 0.016, MAPE: 6.0%), providing both enhanced accuracy and consistency. A sensitivity analysis confirmed the robustness of the model across a range of viscosity ratios, showing strong alignment with physical principles, such as shock front behavior and saturation constraints. The practical utility of this model lies in its ability to accurately predict fractional flow under varying conditions, bridging gaps between analytical methods and data-driven techniques, while remaining computationally efficient. This development enhances the tools available for reservoir engineers, offering new insights for waterflooding strategies, enhanced oil recovery (EOR), and other multi-phase flow applications, with direct relevance to field operations.
VL  - 14
IS  - 1
ER  -

Copy | Download

Author Information

Caleb John

Department of Petroleum Engineering, University of Ibadan, Ibadan, Nigeria

Contact Email

http://orcid.org/0009-0007-6246-2445
Oluwatoyin Akinsete

Department of Petroleum Engineering, University of Ibadan, Ibadan, Nigeria

Contact Email

http://orcid.org/0000-0003-2950-1581
Abosede A. Fadayomi

Department of Petroleum Engineering, University of Ibadan, Ibadan, Nigeria

Contact Email

http://orcid.org/0009-0001-1351-3679
Samuel B. Aderemi

Department of Petroleum Engineering, University of Ibadan, Ibadan, Nigeria

Contact Email

http://orcid.org/0000-0001-9285-8300

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

John, C., Akinsete, O., Fadayomi, A. A., Aderemi, S. B. (2026). Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. International Journal of Oil, Gas and Coal Engineering, 14(1), 1-9. https://doi.org/10.11648/j.ogce.20261401.11

Copy | Download

ACS Style

John, C.; Akinsete, O.; Fadayomi, A. A.; Aderemi, S. B. Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. Int. J. Oil Gas Coal Eng. 2026, 14(1), 1-9. doi: 10.11648/j.ogce.20261401.11

Copy | Download

AMA Style

John C, Akinsete O, Fadayomi AA, Aderemi SB. Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks. Int J Oil Gas Coal Eng. 2026;14(1):1-9. doi: 10.11648/j.ogce.20261401.11

Copy | Download

@article{10.11648/j.ogce.20261401.11,
  author = {Caleb John and Oluwatoyin Akinsete and Abosede A. Fadayomi and Samuel B. Aderemi},
  title = {Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks},
  journal = {International Journal of Oil, Gas and Coal Engineering},
  volume = {14},
  number = {1},
  pages = {1-9},
  doi = {10.11648/j.ogce.20261401.11},
  url = {https://doi.org/10.11648/j.ogce.20261401.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ogce.20261401.11},
  abstract = {Modeling fractional flow curves accurately is essential for optimizing reservoir performance and improving hydrocarbon recovery. This study introduces a robust analytical framework utilizing advanced computational techniques to predict fractional flow behavior. The model leverages Gradient Boosted Decision Trees (GBDT) and integrates key physical parameters such as water saturation, viscosity ratios, and relative permeability. The performance of the proposed framework was evaluated using data from reservoir simulations and experiments. The model demonstrated high predictive accuracy, achieving a Root Mean Square Error (RMSE) of 0.005, a Coefficient of Determination (R2) of 0.99, and a Mean Absolute Percentage Error (MAPE) of 1%. Compared to conventional fractional flow models based on Buckley-Leverett theory, which yielded an RMSE of 0.16 and a MAPE of 12.8%, the new approach showed significant improvement. Additionally, it outperformed other computational approaches, including Random Forest (RMSE: 0.02, MAPE: 10.4%) and Artificial Neural Networks (RMSE: 0.016, MAPE: 6.0%), providing both enhanced accuracy and consistency. A sensitivity analysis confirmed the robustness of the model across a range of viscosity ratios, showing strong alignment with physical principles, such as shock front behavior and saturation constraints. The practical utility of this model lies in its ability to accurately predict fractional flow under varying conditions, bridging gaps between analytical methods and data-driven techniques, while remaining computationally efficient. This development enhances the tools available for reservoir engineers, offering new insights for waterflooding strategies, enhanced oil recovery (EOR), and other multi-phase flow applications, with direct relevance to field operations.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Enhancing Fractional Flow Curve Modeling with Advanced Data-driven Techniques: A Comparative Evaluation of Machine Learning Frameworks
AU  - Caleb John
AU  - Oluwatoyin Akinsete
AU  - Abosede A. Fadayomi
AU  - Samuel B. Aderemi
Y1  - 2026/02/02
PY  - 2026
N1  - https://doi.org/10.11648/j.ogce.20261401.11
DO  - 10.11648/j.ogce.20261401.11
T2  - International Journal of Oil, Gas and Coal Engineering
JF  - International Journal of Oil, Gas and Coal Engineering
JO  - International Journal of Oil, Gas and Coal Engineering
SP  - 1
EP  - 9
PB  - Science Publishing Group
SN  - 2376-7677
UR  - https://doi.org/10.11648/j.ogce.20261401.11
AB  - Modeling fractional flow curves accurately is essential for optimizing reservoir performance and improving hydrocarbon recovery. This study introduces a robust analytical framework utilizing advanced computational techniques to predict fractional flow behavior. The model leverages Gradient Boosted Decision Trees (GBDT) and integrates key physical parameters such as water saturation, viscosity ratios, and relative permeability. The performance of the proposed framework was evaluated using data from reservoir simulations and experiments. The model demonstrated high predictive accuracy, achieving a Root Mean Square Error (RMSE) of 0.005, a Coefficient of Determination (R2) of 0.99, and a Mean Absolute Percentage Error (MAPE) of 1%. Compared to conventional fractional flow models based on Buckley-Leverett theory, which yielded an RMSE of 0.16 and a MAPE of 12.8%, the new approach showed significant improvement. Additionally, it outperformed other computational approaches, including Random Forest (RMSE: 0.02, MAPE: 10.4%) and Artificial Neural Networks (RMSE: 0.016, MAPE: 6.0%), providing both enhanced accuracy and consistency. A sensitivity analysis confirmed the robustness of the model across a range of viscosity ratios, showing strong alignment with physical principles, such as shock front behavior and saturation constraints. The practical utility of this model lies in its ability to accurately predict fractional flow under varying conditions, bridging gaps between analytical methods and data-driven techniques, while remaining computationally efficient. This development enhances the tools available for reservoir engineers, offering new insights for waterflooding strategies, enhanced oil recovery (EOR), and other multi-phase flow applications, with direct relevance to field operations.
VL  - 14
IS  - 1
ER  -

Copy | Download