Automation of Gas Lift Opportunity Identification Using Well-Test Trend Analysis

Sadiq Abubakar Garba, Gbenga Godwin Oseke

Abstract


Gas lift is widely applied to sustain oil production from wells experiencing declining natural flow performance; however, identifying suitable gas lift candidates from large volumes of well-test data remains a repetitive and time-consuming engineering task. This study developed an automated gas lift opportunity identification system to process well-test data, capture predefined engineering decision criteria, improve the consistency and speed of candidate identification, and standardize gas lift initiation evaluation. Historical well-test data from 76 wells were analysed using basic sediment and water (BS&W), net oil rate, gas-liquid ratio (GLR), tubing pressure, flowline pressure and choke size. Candidate screening focused on increasing BS&W, declining net oil rate and declining GLR. Mann-Kendall trend analysis and the Theil-Sen slope estimator were used to determine trend direction and trend magnitude. Trend scores were ranked for each parameter, normalized, weighted, and combined to generate a composite score for candidate prioritization. The system identified 69 wells (90.8%) as potential gas lift candidates, while 7 wells (9.2%) exhibited none of the predefined trends and were excluded. Increasing BS&W, declining net oil rate and declining GLR occurred in 49 (64.5%), 47 (61.8%) and 45 (59.2%) wells, respectively. Final composite scores ranged from 0.14 to 0.82, with XY-TD23 ranked highest at 0.82. The results demonstrate that routine well-test data can be transformed into a consistent, quantitative and prioritized candidate list. The developed automation provides a standardized screening framework that can reduce repetitive manual analysis and support faster engineering review of wells requiring further gas lift evaluation. 


Full Text:

PDF

References


Brown, K. E. (1984). The Technology of Artificial Lift Methods. PennWell Publishing.

Darbandi, M., Meqdad, M. N., Hammoud, A. and Nazif, H. (2024). A New Gas Lift Allocation Method in the IoT Environment Using a Hybrid Optimization Algorithm. Scientific Reports.

Economides, M. J., Hill, A. D., Ehlig-Economides, C. and Zhu, D. (2013). Petroleum Production Systems (2nd ed.). Pearson.

Faria, R. R. (2024). Gas-Lift Optimization Using Physics-Informed Deep Reinforcement Learning. Industrial and Engineering Chemistry Research.

Gilbert, W. E. (1954). Flowing and Gas-Lift Well Performance. American Petroleum Institute Drilling and Production Practice.

Lea, J. F. and Nickens, H. V. (1999). Gas Lift. In Petroleum Engineering Handbook. Society of Petroleum Engineers.

Liu, J., Shi, H., Hong, J., Wang, S., Yang, Y., Liu, H., Guo, J. and Liao, R. (2024). Production Prediction and Influencing Factors Analysis of Horizontal Well Plunger Gas Lift Based on Interpretable Machine Learning. Processes.

Mahdi, M. A. A., Amish, M. and Oluyemi, G. (2023). An Artificial Lift Selection Approach Using Machine Learning. Energies.

Nashed, S. and Moghanloo, R. (2025). Hybrid Symbolic Regression and Machine Learning Approaches for Modelling Gas Lift Well Performance. Fluids.

Karimi, M. (2022). Artificial Intelligence in Oil & Gas Upstream: Trends, Challenges and Future Scenarios. Scientific Oil & Gas Exploration & Production, (199), 37-49.

Takács, G. (2005). Gas Lift Manual. PennWell Corporation.

Tariq, Z., Aljawad, M. S., Hasan, A., Murtaza, M., Mohammed, E., El-Husseiny, A., ... & Abdulraheem, A. (2021). A systematic review of data science and machine learning applications to the oil and gas industry. Journal of Petroleum Exploration and Production Technology, 11(12), 4339-4374.

Zanbouri, K., Bastak, M. R., Alizadeh, S. M., Navimipour, N. J. and Yalcin, S. (2022). A New Energy-Aware Method for Gas Lift Allocation in IoT-Based Industries Using a Chemical Reaction-Based Optimization Algorithm. Electronics.


Refbacks

  • There are currently no refbacks.