Prediction of Completion Fluid Stability and Productivity Impact in Challenging Reservoir Environments Using Machine Learning Analysis
Keywords:
Completion fluid stability, machine learning, well productivity, reservoir engineering, formation damage, data-driven modelingAbstract
This study aims to develop and validate machine learning models to predict completion fluid stability and quantitatively assess its impact on well productivity in challenging reservoir environments. The study employed a quantitative, applied research design based on historical completion and production data from onshore oil and gas reservoirs in Iran. The dataset integrated reservoir properties, completion fluid physicochemical characteristics, operational parameters, and post-completion productivity indicators. After data preprocessing, feature engineering, and normalization, multiple supervised machine learning algorithms—including linear, kernel-based, and ensemble models—were trained and evaluated. Robust cross-validation and hyperparameter optimization strategies were applied to ensure model generalizability and prevent overfitting. Model interpretability was addressed through feature importance analysis and sensitivity evaluation. Inferential results indicated that nonlinear ensemble models significantly outperformed linear approaches in predicting completion fluid stability, achieving high explanatory power and low prediction error. Reservoir temperature and formation water salinity emerged as the most influential predictors, followed by fluid thermal stability limits and filtration loss characteristics. Predicted stability classes exhibited statistically meaningful differences in productivity outcomes, with high-stability completions associated with substantially higher normalized productivity indices and initial production rates. The relationship between predicted stability and productivity was nonlinear, revealing a threshold beyond which incremental stability improvements yielded diminishing productivity gains. The findings confirm that machine learning provides a robust and interpretable framework for predicting completion fluid stability and its productivity implications under complex reservoir conditions. By linking stability predictions to measurable production outcomes, the proposed approach offers a practical decision-support tool for optimizing completion fluid design, reducing formation damage risk, and enhancing economic performance in challenging reservoirs.
References
M. Derakhshan, "Oil Contracts from the Perspective of Sustainable Production and Enhanced Recovery: The Resistance Economy Approach," Islamic Economic Studies Scientific-Research Biannual, vol. 6, no. 2, 2014.
N. Keshavarz Farajkhah and A. Nadri, "Modern Reservoir Evaluation Using Regional Reservoir Monitoring Techniques," Exploration and Production Journal, no. 91, 2009.
S. Kalam, M. R. Khan, M. Shakeel, M. Mahmoud, and S. A. Abu-Khamsin, "Smart Algorithms for Determination of Interfacial Tension (IFT) Between Injected Gas and Crude Oil – Applicable to EOR Projects," 2023, doi: 10.2118/213375-ms.
S. O. Rab et al., "Machine Learning-Based Estimation of Crude Oil-Nitrogen Interfacial Tension," Scientific Reports, vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-85106-y.
S. A. Thabet, S. Lnu, A. Guezei, O. Ejehu, and R. G. Moghanloo, "Downhole Camera Runs Validate the Capability of Machine Learning Models to Accurately Predict Perforation Entry Hole Diameter," Energies, vol. 17, no. 22, p. 5558, 2024, doi: 10.3390/en17225558.
A. D. Ogbu, K. A. Iwe, W. Ozowe, and A. H. Ikevuje, "Advances in Machine Learning-Driven Pore Pressure Prediction in Complex Geological Settings," Computer Science & It Research Journal, vol. 5, no. 7, pp. 1648-1665, 2024, doi: 10.51594/csitrj.v5i7.1350.
S. Krishna, S. A. Irfan, S. Keshavarz, G. Thonhauser, and S. U. Ilyas, "Smart Predictions of Petrophysical Formation Pore Pressure via Robust Data-Driven Intelligent Models," Multiscale and Multidisciplinary Modeling Experiments and Design, vol. 7, no. 6, pp. 5611-5630, 2024, doi: 10.1007/s41939-024-00542-z.
C. Carpenter, "AI Approach Advances Predictive Precision in CO2 Minimum Miscibility Pressure," Journal of Petroleum Technology, vol. 77, no. 01, pp. 59-62, 2025, doi: 10.2118/0125-0059-jpt.
C. Carpenter, "Physics-Informed ML Improves Forecasting, Connectivity Identification for CO2 EOR," Journal of Petroleum Technology, vol. 77, no. 01, pp. 55-58, 2025, doi: 10.2118/0125-0055-jpt.
K. Al-Azani, A. F. Ibrahim, S. Elkatatny, and D. A. Shehri, "Prediction of Foam Half-Life Time Using Machine Learning Algorithms for Enhanced Oil Recovery and CO2 Sequestration," Energy & Fuels, vol. 39, no. 19, pp. 8989-9007, 2025, doi: 10.1021/acs.energyfuels.5c01054.
W. Wei, P. Lü, C. Zhu, P. Luo, and R. Mesdour, "Advanced Machine Learning Models for CO2 and H2S Solubility in Water and NaCl Brine: Implications for Geoenergy Extraction and Carbon Storage," Energy & Fuels, vol. 38, no. 12, pp. 11119-11136, 2024, doi: 10.1021/acs.energyfuels.4c01423.
P. Vaziri, S. Ahmadi, F. Daneshfar, B. Sedaee, H. Alimohammadi, and M. R. Rasaei, "Machine Learning Techniques in Enhanced Oil Recovery Screening Using Semisupervised Label Propagation," Spe Journal, vol. 29, no. 09, pp. 4557-4578, 2024, doi: 10.2118/221475-pa.
S. Gomaa, "Machine Learning Models for Estimating the Overall Oil Recovery of Waterflooding Operations in Heterogenous Reservoirs," Scientific Reports, vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-97235-5.
A. Abdulwarith, M. Ammar, and B. Dindoruk, "Prediction/Assessment of CO2 EOR and Storage Efficiency in Residual Oil Zones Using Machine Learning Techniques," Energies, vol. 18, no. 20, p. 5498, 2025, doi: 10.3390/en18205498.
B. Mepaiyeda, M. Ezeh, O. A. Olafadehan, A. Oladipupo, O. S. Adebayo, and E. Osaro, "Integration of Machine Learning and Feature Analysis for the Optimization of Enhanced Oil Recovery and Carbon Sequestration in Reservoirs," 2025, doi: 10.26434/chemrxiv-2025-5v32t.
A. A. Elhadidy et al., "Smart Matrix Acidizing: Real-Time Skin Factor Prediction With AI," 2025, doi: 10.2118/225024-ms.
S. A. Thabet, A. A. El-Hadydy, and M. A. Gabry, "Machine Learning Models to Predict Pressure at a Coiled Tubing Nozzle's Outlet During Nitrogen Lifting," 2024, doi: 10.2118/218294-ms.
S. Thabet et al., "Prediction of Total Skin Factor in Perforated Wells Using Models Powered by Deep Learning and Machine Learning," 2024, doi: 10.2118/219187-ms.
N. Shokri, "Losing Water Through Evaporation From Water Reservoirs in Water-Stressed Regions: The Case of Iran-Afghanistan," 2025, doi: 10.5194/egusphere-egu24-14853.
M. Maleki, A. Akbari, Y. Kazemzadeh, and A. M. Ranjbar, "Machine Learning Models for the Prediction of Hydrogen Solubility in Aqueous Systems," Scientific Reports, vol. 15, no. 1, 2025, doi: 10.1038/s41598-025-16289-7.
A. Akbari, "Machine Learning and Nanoparticles for Enhancing Condensate Recovery in Gas Condensate Reservoirs," The Canadian Journal of Chemical Engineering, 2025, doi: 10.1002/cjce.70119.
F. Su, J. Zhao, X. Wen, Y. Zhang, J. Han, and Y. Chen, "Machine Learning–Based Prediction of the Mechanical Response of Hydrate-Bearing Sediments Under Multifield Coupling," Spe Journal, pp. 1-18, 2025, doi: 10.2118/230308-pa.
M. N. Assaf, Q. Abdelal, N. M. Hussein, G. Halaweh, and A. Al‐Zubaidi, "Water Quality Monitoring and Management: Integration of Machine Learning Algorithms and Sentinel-2 Images for the Estimation of Chlorophyll-A," Modeling Earth Systems and Environment, vol. 11, no. 5, 2025, doi: 10.1007/s40808-025-02543-4.
M. Nagappan, S. Jayamurugan, and A. Kudiarasumani, "Advanced Prediction of Crop Water Requirements Using Machine Learning Models," International Journal of Innovative Science and Research Techno, pp. 2518-2523, 2025, doi: 10.38124/ijisrt/25feb1206.
H. Jing, H. Pan, J. Liu, and Z. Fang, "Deep-Learning Accelerated Phase Equilibrium Calculations for Compositional Simulation in Shale Reservoir," 2025, doi: 10.2118/223868-ms.
B. Yan and Y. Zhang, "Efficacy Gain From a Deep Neural Network-Based History-Matching Workflow," 2024, doi: 10.2118/220876-ms.
N. Li et al., "Intelligent Method for PDC Bit Selection Based on Graph Neural Network," Applied Sciences, vol. 15, no. 18, p. 9985, 2025, doi: 10.3390/app15189985.
Z. Khursheed et al., "Comparative Study of Machine Learning and Artificial Neural Networks for Porosity and Permeability Prediction in Reservoir Characterization," 2025, doi: 10.2118/224836-ms.
A. Aliyev, S. Kalam, M. Riazi, and P. Pourafshary, "Prediction of Storage and Loss Modules of Preformed Particle Gels Using Machine Learning," 2025, doi: 10.2118/226944-ms.
S. B. Anieto, "Machine Learning Assisted Optimization of Carbon Capture and Storage in Oil and Gas Reservoirs Through Advanced Geomodelling," Harvard International Journal of Engineering Research and Technology, 2025, doi: 10.70382/hijert.v9i5.014.
A. Talapatra, B. Nojabaei, and P. Khodaparast, "A Data-Based Continuous and Predictive Viscosity Model for the Oil-Surfactant-Brine Microemulsion Phase," 2024, doi: 10.2118/218134-ms.
H. Fu, J. Xiu, L. Huang, L. Yi, Y. Ma, and S. Wang, "Evaluation of Oil Displacement by Polysaccharide Fermentation Broth of Athelia Rolfsii Under Extreme Reservoir Conditions," Molecules, vol. 30, no. 13, p. 2861, 2025, doi: 10.3390/molecules30132861.
B. Ahmed, A. Kasha, S. Patil, M. S. Aljawad, and M. S. Kamal, "Extensive Study on the Influencing Parameters of Sc CO2 Foam Viscosity for Enhanced Oil Recovery and Carbon Sequestration: A Machine Learning Approach," 2024, doi: 10.2118/219163-ms.
D. A. Mamykin, "Selection of Flow Diversion Technology for a Carbonate Reservoir Object," Petroleum Engineering, vol. 23, no. 5, pp. 31-42, 2025, doi: 10.17122/ngdelo-2025-5-31-42.
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2025 Parsa Kazemihokmabad (Corresponding author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
