Using Machine Learning to Predict Gel Acids' Viscosity in Carbonate Reservoirs: Neural Networks Validation with Laboratory Data

Document Type : Original Article

Authors
Abbas Najafi 1
Ramin Kavousi 2
Seyed Javad Seyedi 3
1 M.Sc. Production Engineering, Department of Production Engineering, National Iranian South Oilfields Companies, Ahwaz, Iran
2 B.Sc. Petroleum Engineering, Department of Production Engineering, National Iranian South Oilfields Companies, Ahwaz, Iran
3 M.Sc. Reservoir Engineering, Department of P‌roduction Engineering, National Iranian South Oilfields Companies, Ahwaz, Iran
20.1001.1/ijge.2024.723137
Abstract
In acidizing operations, gel acids are used as fluid diverters to enhance the efficiency of treatments in heterogeneous carbonate reservoirs. The main challenge in this context is the changes in the viscosity of the gels during and after the operation. The viscosity of these gels is highly influenced by pH changes, and accurately predicting their behavior can contribute to the success of the operation. This study focuses on predicting the apparent viscosity of gel acids as a function of pH using machine learning. In this regard, supervised learning methods and neural network algorithms have been utilized. Two different models were designed and their results compared with laboratory data. Both neural networks consist of 5 layers with 15 neurons each. The results indicate sufficient accuracy of the models, suggesting they can be effectively used as a substitute for laboratory measurements.
Keywords
Gelled acid
Viscosity
Matrix acidizing
Carbonate reservoir
Machine learning
Neural Networks
Supervised Learning
Subjects
  1. Gidley, J., et al., Recent advances in hydraulic fracturing; SPE Monograph Series. Society of Petroleum Engineers: Richardson, TX, 1989.
  2. Zoveidavianpoor, M., A. Samsuri, and S. Shadizadeh, Well stimulation in carbonate reservoirs: The needs and superiority of hydraulic fracturing. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2013. 35(1): p. 92-98.
  3. Clark, J., A hydraulic process for increasing the productivity of wells. Journal of Petroleum Technology, 1949. 1(01): p. 1-8.
  4. Shuai, L., et al. From Acid Treatment to Propped Fracturing: Lesson Learned from the Stimulation of an Ultra-Deep HPHT and Tight Carbonate Reservoir. in SPE International Hydraulic Fracturing Technology Conference and Exhibition. 2023. OnePetro.
  5. Wang, S. and F. Civan. Preventing asphaltene deposition in oil reservoirs by early water injection. in SPE Oklahoma City Oil and Gas Symposium/Production and Operations Symposium. 2005. SPE.
  6. Bennion, D.B., An overview of formation damage mechanisms causing a reduction in the productivity and injectivity of oil and gas producing formations. Journal of Canadian Petroleum Technology, 2002. 41(11).
  7. Fredd, C. and H.S. Fogler, Alternative stimulation fluids and their impact on carbonate acidizing. SPE Journal, 1998. 3(01): p. 34-41.
  8. Williams, B.B., J.L. Gidley, and R.S. Schechter, Acidizing fundamentals. (No Title), 1979.
  9. Abdollahi, R., et al., Conventional diverting techniques and novel fibr-assisted self-diverting system in carbonate reservoir acidizing with successful case studies. Petroleum Research, 2021. 6(3): p. 247-256.
  10. Garrouch, A.A. and A.R. Jennings Jr, A contemporary approach to carbonate matrix acidizing. Journal of Petroleum Science and Engineering, 2017. 158: p. 129-143.
  11. Van Domelen, M.S. A practical guide to modern diversion technology. in SPE Oklahoma City Oil and Gas Symposium/Production and Operations Symposium. 2017. SPE.
  12. Sahu, Q.A., R.E. Arias, and E.A. Alali. Dynamic diverter technology efficiency in acid fracturing applications. in Abu Dhabi International Petroleum Exhibition and Conference. 2019. SPE.
  13. Gomaa, A.M., et al. Experimental investigation of particulate diverter used to enhance fracture complexity. in SPE International Conference and Exhibition on Formation Damage Control. 2016. SPE.
  14. Shah, M., S. Shah, and A. Sircar, A comprehensive overview on recent developments in refracturing technique for shale gas reservoirs. Journal of Natural Gas Science and Engineering, 2017. 46: p. 350-364.
  15. Spurr, N., et al. Far-field diversion agent using a combintion of a soluble particle diverter with specially engineered proppant. in SPE Asia Pacific Hydraulic Fracturing Conference. 2016. SPE.
  16. Gomaa, A.M., et al. Engineering solid particulate diverter to control fracture complexity: experimental study. in SPE Hydraulic Fracturing Technology Conference and Exhibition. 2016. SPE.
  17. Kelland, M.A., Production chemicals for the oil and gas industry. 2016: CRC press.
  18. Arias, R.E., et al. First worldwide application of HP/HT water swellable packers eliminates deployment risks and improves MSF efficiency in tight gas reservoirs. in SPE Middle East Oil and Gas Show and Conference. 2019. SPE.
  19. Sui, Y., et al., Development of gelled acid system in high-temperature carbonate reservoirs. Journal of Petroleum Science and Engineering, 2022. 216: p. 110836.
  20. Rajendra, K., et al., A Non-Damaging Gelled Acid System Based on Surface Modified Nanoparticles. 2021.
  21. Ratnakar, R., N. Kalia, and V. Balakotaiah. Carbonate matrix acidizing with gelled acids: An experiment-based modeling study. in SPE International Production and Operations Conference and Exhibition. 2012. SPE.
  22. Evgenievich Folomeev, A., et al. Gelled acid vs. self-diverting systems for carbonate matrix stimulation: an experimental and field study. in SPE Russian Petroleum Technology Conference? SPE.
  23. Prisching, A., et al., Machine learning-based prediction of malnutrition in hospitalised patients: a validation pilot study. Clinical Nutrition ESPEN, 2024. 63: p. 997.
  24. Corli, S., et al., Quantum machine learning algorithms for anomaly detection: A review. Future Generation Computer Systems, 2024: p. 107632.
  25. Gui, J., et al., A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
  26. Bröker, F., et al., Demystifying unsupervised learning: how it helps and hurts. Trends in Cognitive Sciences, 2024.
  27. Madhuri, A., et al., A new multi-level semi-supervised learning approach for network intrusion detection system based on the ‘goa’. Journal of Interconnection Networks, 2024. 24(supp01): p. 2143047.
  28. Gu, S., et al., A Review of Safe Reinforcement Learning: Methods, Theories and Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
  29. Lawal, A., et al., Machine Learning in Oil and Gas Exploration-A Review. IEEE Access, 2024.
  30. Taylor, K. and H. Nasr-El-Din, Laboratory evaluation of in-situ gelled acids for carbonate reservoirs. Spe Journal, 2003. 8(04): p. 426-434.

  • Receive Date 10 October 2024
  • Revise Date 25 November 2024
  • Accept Date 20 December 2024