SavedAdd your journal

Journals / Gazi University Journal of Science Part A: Engineering and Innovation / 2026 / Volume: 13 Issue: 3

Predicting Bubble Point Pressure and Oil Formation Volume Factor by Explainable and Reproducible Support Vector Regression-Based Models from Multi-Regional PVT Data

Anietie Okon(University of Uyo)0000-0003-1744-3310
Moses Ekpenyong(University of Uyo)0000-0001-6774-5259
Kilaliba Tugwell(University of Uyo)0009-0005-4698-0723
Philip Asuquo(University of Uyo)0000-0001-8084-3427
Pages
—
Publication Date
2026-09-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Thus, the explainable SVR models offer a transparent, accurate, and practical tool for reservoir PVT estimation, combining predictive performance with engineering interpretability.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Accurate estimation of reservoir pressure-volume-temperature (PVT) properties underpins reserves evaluation, reservoir simulation, production forecasting, and surface facility design.
📊
Key Findings & Data:Bubble point pressure (P bp ) and oil formation volume factor (B ob ) are especially critical because they control hydrocarbon phase behaviour, fluid expansion, and depletion performance.
💡
Conclusion & Impact:Thus, the explainable SVR models offer a transparent, accurate, and practical tool for reservoir PVT estimation, combining predictive performance with engineering interpretability.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:PVT Properties · Bubble Point Pressure · Oil Formation Volume Factor

Abstract

Accurate estimation of reservoir pressure-volume-temperature (PVT) properties underpins reserves evaluation, reservoir simulation, production forecasting, and surface facility design. Bubble point pressure (P bp ) and oil formation volume factor (B ob ) are especially critical because they control hydrocarbon phase behaviour, fluid expansion, and depletion performance. Laboratory PVT analysis is the most reliable but often costly, slow, and unavailable. Empirical correlations are more practical; however, they suffer from regional bias, limited calibration ranges, and poor representation of nonlinear fluid behaviour. This study develops explainable, reproducible support vector regression (SVR) models to predict P bp and B ob using four common descriptors: solution gas-oil ratio ( Rs ), gas specific gravity (γ g ), API oil gravity (γ API ), and reservoir temperature (T R ). From 953 global PVT samples, 797 were preprocessed, normalised, and split using hold-out and k-fold cross-validation. Linear-kernel SVR delivered high accuracy: for P bp , (R 2 = 0.9826, R = 0.9913, RMSE = 0.0586, MSE = 0.0034); for B ob , (R 2 = 0.9494, R = 0.9744, RMSE = 0.0882, MSE = 0.0078). To overcome the “black-box” limitation, the SVR models are fully specified using their support vectors, dual coefficients, and bias terms, enabling independent reproduction and implementation. Perturbation-based explainability shows that Rs is the dominant predictor for both properties, accounting for 71.87% of P bp and 76.76% of B ob , consistent with thermodynamic expectations. Compared with widely used empirical correlations, the new models perform better on a multi-regional dataset. Thus, the explainable SVR models offer a transparent, accurate, and practical tool for reservoir PVT estimation, combining predictive performance with engineering interpretability.

🔖

Cite This Article

Okon, A., Ekpenyong, M., Tugwell, K., Asuquo, P. (2026). Predicting Bubble Point Pressure and Oil Formation Volume Factor by Explainable and Reproducible Support Vector Regression-Based Models from Multi-Regional PVT Data. Gazi University Journal of Science Part A: Engineering and Innovation, Volume: 13 Issue: 3. https://doi.org/10.54287/gujsa.1977786

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (71)

  1. Abdul-Majeed, G. H., & Salman, N. H. (1988). An empirical correlation for oil FVF prediction. Journal of Canadian Petroleum Technology, 27(06), 118-122. https://doi.org/10.2118/88-06-10
  2. Abuh, F. A., Akpabio, J. U., & Okon, A. N. (2023). Machine learning-based models for basic sediment & water and sand-cut prediction for matured Niger Delta fields. Journal of Energy Research and Reviews, 15(2), 70-93. https://doi.org/10.9734/jenrr/2023/v15i2310
  3. Ahmed, T. (2019). Reservoir engineering handbook (5th Ed.). Gulf Professional Publishing, New York.
  4. Alakbari, F. S., Mohyaldinn, M. E., Ayoub, M. A., Muhsan, A. S., & Hussein, I. A. (2022). An accurate reservoir’s bubble point pressure correlation. ACS Omega, 7(15), 13196-13209. https://doi.org/10.1021/acsomega.2c00651
  5. Alatefi, S., & Almeshal, A. M. (2021). A new model for estimation of bubble point pressure using a Bayesian optimized least square gradient boosting ensemble. Energies, 14(9), 2653. https://doi.org/10.3390/en14092653
  6. Al-Bulushi, N., King, P. R., Blunt, M. J., & Kraaijveld, M. (2009). Development of artificial neural network models for predicting water saturation and fluid distribution. Journal of Petroleum of Science and Engineering, 68(3-4), 197-208. https://doi.org/10.1016/j.petrol.2009.06.017
  7. Al-Marhoun, M. A. (1988). PVT correlations for Middle East crude oils. Journal of Petroleum Technology, 40(05), 650-666. https://doi.org/10.2118/13718-PA
  8. Al-Marhoun, M. A. (1992). New correlations for formation volume factors of oil and gas mixtures. Journal of Canadian Petroleum Technology, 31(3), 22-26. https://doi.org/10.2118/92-03-02
  9. Al-Marhoun, M. A. (2004). Evaluation of empirically derived PVT properties for Middle East crude oils. Journal of Petroleum Science and Engineering, 42(2-4), 209-221. https://doi.org/10.1016/j.petrol.2003.12.012
  10. Al-Marhoun, M. A. (2022). A new derivative-based method for determination of bubble point pressure of hydrocarbon systems. Journal of Petroleum Exploration Production and Technology, 12(4), 949-958. https://doi.org/10.1007/s13202-021-01352-6
  11. Almehaideb, R. A. (1997). Improved PVT correlations for UAE crude oils. In: Society of Petroleum Engineers Middle East Oil Show and Conference, SPE-37691-MS, (15-18 March 1997), Bahrain. https://doi.org/10.2118/37691-MS
  12. Al-Shammasi, A. A. (1999). Bubble point pressure and oil formation volume factor correlations. In: Society of Petroleum Engineers Middle East Oil Show and Conference, SPE-53185-MS, (20-23 February 1999), Bahrain. https://doi.org/10.2118/53185-MS
  13. Al-Shammasi, A. A. (2001). A review of bubble point pressure and oil formation volume factor correlations. Society of Petroleum Engineers Reservoir Evaluation and Engineering, 4(02), 146-160. https://doi.org/10.2118/71302-PA
  14. Arjun, K. S., & Aneesh, K. (2015). Modelling studies by application of artificial neural network using MATLAB. Journal of Engineering Science and Technology, 10(11), 1477-1486.
  15. Awad, M., & Khanna, R. (2015). Support vector regression. In: Efficient Learning Machines. (pp. 67–80), Springer. https://doi.org/10.1007/978-1-4302-5990-9_4
  16. Bagheripour, P., Gholami, A., & Asoodeh, M. (2015). Support vector regression between PVT data and bubble point pressure. Journal of Petroleum Exploration and Production Technology, 5(3), 227-231. https://doi.org/10.1007/s13202-014-0128-8
  17. Balhoff, M. (2022). Review of reservoir rock and fluid properties. In: M. Balhoff (Eds.), Volume 75: An Introduction to Multiphase, Multicomponent Reservoir Simulation (Book Series: Developments in Petroleum Science). (pp. 1-36), Elsevier. https://doi.org/10.1016/B978-0-323-99235-0.00010-5
  18. Bargam, B., Boudhar, A., Kinnard, C., Bouamri, H., Nifa, K., & Chehbouni, A. (2024). Evaluation of the support vector regression (SVR) and the random forest (RF) models accuracy for streamflow prediction under a data-scarce basin in Morocco. Discovery Applied Sciences, 6(6), 306. https://doi.org/10.1007/s42452-024-05994-z
  19. Bello, O. O., Reinicke, K. M., & Patil, P. A. (2008). Comparison of the performance of empirical models used for the predicting of the PVT properties of crude oils of the Niger Delta. Journal of Petroleum Science and Technology, 26(5), 593-609. https://doi.org/10.1080/10916460701204685
  20. Botchkarev, A. (2019). A New Typology Design of Performance Metrics to Measure Errors in Machine Learning Regression Algorithms. Interdisciplinary Journal of Information, Knowledge, and Management, 14, 045–076. https://doi.org/10.28945/4184
  21. Cuevas, E., Díaz, P., & Camarena, O. (2021). ANFIS-Hammerstein model for nonlinear systems identification using GSA. In: Metaheuristic computation: A performance perspective (Book Series: Intelligent Systems Reference Library, 195). (pp. 121–159). Springer, Cham. https://doi.org/10.1007/978-3-030-58100-8_5
  22. Dindoruk, B., Ratnakar, R. R., & He, J. (2020). Review of recent advances in petroleum fluid properties and their representation. Journal of Natural Gas Science and Engineering, 83, 103541. https://doi.org/10.1016/j.jngse.2020.103541
  23. Dokla, M. E., & Osman, M. E. (1992). Correlation of PVT properties for UAE crudes. Society of Petroleum Engineers Formation Evaluation Journal, 7(01), 41-46. https://doi.org/10.2118/20989-PA
  24. El-hoshoudy, A. N., & Desouky, S. M. (2018). Numerical prediction of oil formation volume factor at bubble point for black and volatile oil reservoirs using non-linear regression models. Petroleum & Petrochem Engineering Journal, 2(1), 000145. https://doi.org/10.23880/ppej-16000145
  25. Elkatatny, S., & Mahmoud, M. (2018). Development of new correlations for the oil formation volume factor in oil reservoirs using artificial intelligent white box technique. Petroleum, 4(2), 178-186. https://doi.org/10.1016/j.petlm.2017.09.009
  26. Elkatatny, S., Aloosh, R., Tariq, Z., Mahmoud, M., & Abdulraheem, A. (2017). Development of a new correlation for bubble point pressure in oil reservoirs using artificial intelligence technique. In: Society of Petroleum Engineers Kingdom of Saudi Arabia Technical Symposium and Exhibition, SPE-187977-MS, (24-27 April 2017), Dammam, Saudi Arabia. https://doi.org/10.2118/187977-MS
  27. El-Sebakhy, E. A. (2009). Forecasting PVT properties of crude oil systems based on support vector machines modeling systems. Journal of Petroleum Science and Engineering, 64(1-4), 25-34. https://doi.org/10.1016/j.petrol.2008.12.006
  28. El-Sebakhy, E. A., Sheltami, T., Al-Bokhitan, S., Shaaban, Y., Raharja, I., & Khaeruzzaman, Y. (2007). Support vector machines framework for predicting the PVT properties of crude-oil systems. In: Society of Petroleum Engineers Middle East Oil and Gas Conference, SPE-105698-MS, (11-14 March 2007), Manama, Bahrain. https://doi.org/10.2118/105698-MS
  29. Elsharkawy, A. M., & Alikhan, A. A. (1997). Correlations for predicting solution gas/oil ratio, oil formation volume factor and undersaturated oil compressibility. Journal of Petroleum Science and Engineering, 17(3–4), 291–302. https://doi.org/10.1016/S0920-4105(96)00075-7
  30. Eyo, A. E., Okon, A. N., & Tugwell, K. W. (2024). Machine learning models for reservoir petrophysical properties prediction from well-logs data in the Niger Delta. In: Society of Petroleum Engineers Nigeria Council 48th Nigeria Annual International Conference and Exhibition, SPE-221719-MS, (5-7 August 2024), Lagos, Nigeria. http://doi.org/10.2118/221719-MS
  31. Francis, J., & Ajienka, J. (2019). Bubble point pressure correlation for deep offshore region of Nigeria. International Journal of Petroleum and Gas Exploration Management, 3(1), 1-9.
  32. Ganat, T. A.-A. O. (2020). Estimation of reservoir rock and fluid properties. In: Technical Guidance for Petroleum Exploration and Production Plans. (pp. 29–34). SpringerBriefs in Applied Sciences and Technology. Springer, Cham. https://doi.org/10.1007/978-3-030-45250-6_4
  33. Geng, J., Gan, W., Xu, J., Yang, R., & Wang, S. (2020). Support vector machine regression (SVR)-based nonlinear modeling of radiometric transforming relation for the coarse-resolution data-referenced relative radiometric normalization (RRN). Geo-Spatial Information Science, 23(3), 237–247. https://doi.org/10.1080/10095020.2020.1785958
  34. Gharbi, R. B., & Elsharkawy, A. M. (1997). Network model for estimating the PVT properties of Middle East crude oils. In: Society of Petroleum Engineers Middle East Oil Show and Conference, SPE-37695-MS, (15-18 March 1997), Bahrain. https://doi.org/10.2118/37695-MS
  35. Glaso, O. (1980). Generalized pressure-volume-temperature correlations. Journal of Petroleum Technology, 32(05), 785–795. https://doi.org/10.2118/8016-PA
  36. Gouda, A., & Attia, A. M. (2023). Development of a new approach using an artificial neural network for estimating oil formation volume factor at bubble point pressure of Egyptian crude oil. Journal of King Saud University – Engineering and Science, 36(1), 72-80. https://doi.org/10.1016/j.jksues.2022.08.001
  37. Hadavimoghaddam, F. (2021). A New Correlations Approach for Prediction of PVT Properties of Oil Reservoir. Electrical & Electronic Systems, 10(5).
  38. Hassn, O. F., & Sadiq, D. J. (2009). New correlation for oil formation volume factor at and below bubble point pressure. Journal of Engineering, 15(04): 4347-4355. https://doi.org/10.31026/j.eng.2009.04.16
  39. Hemmati, M. N., & Kharrat, R. (2007). A correlation Approach for prediction of crude oil PVT properties. In: Society of Petroleum Engineers Middle East Oil and Gas Show and Conference, SPE-104543-MS, (11-14 March 2007), Manama, Bahrain. https://doi.org/10.2118/104543-MS
  40. Jarrahian, A., Moghadasi, J., & Heidaryan, E. (2014) Empirical estimating of black oils bubble point (saturation) pressure. Journal of Petroleum Science and Engineering, 126, 69–77. https://doi.org/10.1016/j.petrol.2014.12.004
  41. Karimnezhad, M., Heidarian, M., Kamari, M., & Jalalifar, H. (2014). A new empirical correlation for estimating bubble point oil formation volume factor. Journal of Natural Gas Science and Engineering, 18, 329-335. https://doi.org/10.1016/j.jngse.2014.03.010
  42. Khalil, A. A., Baker, H. A., Naseef, H. A., & AL-Dujaili, A. N. (2025). Effect of residual oil saturation on oil recovery and reservoir performance for Mishrif formation in Southern Iraqi oil field. Improved Oil and Gas Recovery, 9. https://doi.org/10.14800/IOGR.1366
  43. Khamis, M. A., & Fattah, K. A. (2018). Estimating oil-gas ratio for volatile oil and gas condensate reservoirs: artificial network, support vector machines and functional network approach. Journal of Petroleum Exploration Production and Technology, 9(1), 573-582. https://doi.org/10.1007/s13202-018-0501-0
  44. Khashman, M. A., Shirazi, H., & Al-Dujaili, A. N. (2025). Comparative evaluation of productivity indicators in carbonate reservoir modeling by a case study for the Mishrif Formation in the Iraqi Buzurgan Oilfield. Discover Geoscience, 3(1), 17. https://doi.org/10.1007/s44288-025-00118-5
  45. Lasater, J. A. (1958). Bubble Point Pressure Correlation. Journal of Petroleum Technology, 10(05), 65–67. https://doi.org/10.2118/957-G
  46. Mahdavi, E., Suleymani, M., & Rahmanian, N. (2017). Oil and gas properties and correlations. In: Fluid Phase Behavior for Conventional and Unconventional Oil and Gas Reservoirs. (pp. 1-64), Elsevier. https://doi.org/10.1016/B978-0-12-803437-8.00001-4
  47. Mehrizadeh, M. (2020). Estimation of PVT properties using artificial neural networks and comparison of results with experimental data. Khazar Journal of Science and Technology, 4(1), 97-110.
  48. Mwakipunda, G. C., Kouassi, A. K. F., Nadege, M. N., Mgimba, M. M., Ngata, M. R., & Yu, L. (2025). Development of bubble point pressure and oil formation volume factor models using pressure-volume-temperature data. Journal of Rock Mechanics and Geotechnic Engineering, 17(11), 7127-7146. https://doi.org/10.1016/j.jrmge.2025.02.027
  49. Nagi, J., Kiong, T. S., Ahmed, S. K., & Nagi, F. (2009). Prediction of PVT properties in crude oil systems using support vector machines. In: 3rd International Conference on Energy and Environment (ICEE), (7-8 December 2009), Malacca, Malaysia. https://doi.org/10.1109/ICEENVIRON.2009.5398681
  50. Okon, A. N., & Ansa, I. B. (2021). Artificial neural network models for reservoir aquifer dimensionless variables: influx and pressure prediction for water influx calculation. Journal of Petroleum Exploration and Production Technology, 11(4), 1885-1904. https://doi.org/10.1007/s13202-021-01148-8
  51. Okon, A. N., Effiong, A. J., & Daniel, D. D. (2023). Explicit neural network-based models for bubble point pressure and oil formation volume factor prediction. Arabian Journal of Science and Engineering, 48(7), 9221-9257. https://doi.org/10.1007/s13369-022-07240-3
  52. Oloruntoba, F. M., & Onyekonwu, M. O. (2016). Empirical prediction of bubble point pressure and solution gas oil ratio for Niger Delta. International Journal of Science and Engineering Research, 7(6), 520-530.
  53. Omar, M. I., & Todd, A. C. (1993). Development of new modified black oil correlations for Malaysian crudes. In: Society of Petroleum Engineers Asia Pacific Oil and Gas Conference, SPE-25338-MS, (8-10 February 1993), Singapore. https://doi.org/10.2118/25338-MS
  54. Ooi, K. Z., Chen, Z., Poh, P. E., & Cui, J. (2022). BOD5 Prediction using machine learning methods. Water Supply, 22(1), 1168-1183. https://doi.org/10.2166/ws.2021.202
  55. Patil, P. A., Bai, M. X., Teodoriu, C., & Reinicke, K. M. (2014). Development of PVT correlations according to geography. Journal of Petroleum Science and Technology, 32(8), 991-999. https://doi.org/10.1080/10916466.2011.641653
  56. Petrosky, G. E. (1990). PVT correlations for Gulf of Mexico crude oils. MSc. Thesis, University of Southwestern Louisiana, USA.
  57. Petrosky, G. E., & Farshad, F. (1993) Pressure-volume-temperature correlation for the Gulf of Mexico. Society of Petroleum Engineers Reservoir Evaluation Engineering Journal, 1(05), 416-420. https://doi.org/10.2118/51395-PA
  58. Saleem, F., Ali, A., Shaikh, I., & Wasim, M. (2023). Application and comparison of kernel functions for linear parameter varying model approximation of nonlinear systems. Applied Mathematics-A Journal of Chinese University, 38(1), 58-77. https://doi.org/10.1007/s11766-023-3965-8
  59. Salehinia, S., Salehinia, Y., Alimadadi, F., & Sadati, S. H. (2016). Forecasting density, oil formation volume factor and bubble point pressure of crude oil systems based on nonlinear system identification approach. Journal of Petroleum Science and Engineering, 147, 47-55. https://doi.org/10.1016/j.petrol.2016.05.008
  60. Salih, A. M., Raisi-Estabragh, Z., Galazzo, I. B., Radeva, P., Petersen, S. E., Lekadir, K., & Menegaz, G. (2023). A perspective on explainable artificial intelligence methods: SHAP and LIME. Advanced Intelligent Systems, 7(1), 2400304. https://doi.org/10.1002/aisy.202400304
  61. Samuel, S., & Mbachu, I. I. (2021). Modelling approach for Niger Delta oil formation volume factor prediction using support vector machine. American Journal of Engineering Research, 10(12), 80-88.
  62. Satter, A., & Iqbal, G. M. (2016) Reservoir engineering. Gulf Professional Publishing, Elsevier, New York.
  63. Seyyedattar, M., Ghiasi, M. M., Zendehboudi, S., & Butt, S. (2020) Determination of bubble point pressure and oil formation volume factor: Extra trees compared with LSSVM-CSA hybrid and ANFIS models. Fuel, 269, 116834. https://doi.org/10.1016/j.fuel.2019.116834
  64. Sharrad, M., & Abd-Alrahman, H. H. (2019). New derived correlation for Libyan crude oil to estimate bubble-point pressure. Journal of Applied Science, 1(2), 1-13.
  65. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
  66. Soliman, A., Attia, A., & Abdelwahab, M. (2020). Development of new models for predicting crude oil bubble point pressure, oil formation volume factor, and solution gas-oil ratio using genetic algorithm. Journal of Petroleum and Mining Engineering, 22(2), 17-39. https://doi.org/10.21608/jpme.2020.31955.1035
  67. Standing, M. B. (1947). A pressure-volume-temperature correlation for mixtures of California oils and gases. Drilling and Production Practice, 275-287.
  68. Talib, M. Q. A., & Al-Jawad, M. S. (2022). Assessment of the common PVT correlations in Iraqi Oil Fields. Journal of Petroleum Research and Studies, 12(1 (Suppl.)), 68-87. https://doi.org/10.52716/jprs.v12i1(Suppl.).623
  69. Vapnik, V. N. (1995). The Nature of Statistical Learning Theory. Springer, New York. https://doi.org/10.1007/978-1-4757-2440-0
  70. Vasquez, M., & Beggs, H. D. (1980). Correlations for fluid physical property prediction. Journal of Petroleum Technology, 32(06), 968-970. https://doi.org/10.2118/6719-PA
  71. Whitson, C. H., & Brulé, M. R. (2000). Phase behavior. Monograph Series, Society of Petroleum Engineers, Richardson, Texas, USA, 20, 233p.